Browse Topic: Steering systems

Items (2,222)
Due to the inherent characteristics of large dimensions, complex curved surfaces, and densely distributed protrusions present in aerospace products, conventional offline programming and trajectory planning techniques for robots primarily prioritize the facilitation of uninterrupted grinding processes and the generation of points along trajectories on surfaces characterized by smoothness. However, these methods encounter challenges in identifying and proactively avoiding surface protrusions during the planning phase. The present paper puts forth a proposal for an automated robot trajectory planning method for grinding operations. This method is predicated on the integration of region partitioning and deformation correction. Specifically, this method first identifies protrusions based on curvature features and rule matching, followed by an analysis of the feasible workspace of a six-axis industrial robot equipped with an external axis. The product surface is discretized into multiple regional units according to the distribution characteristics of protrusions and the constraints of the feasible workspace. Subsequently, a parameter-optimized parallel sectioning method is employed to independently plan trajectories for each unit. The utilization of on-site measured point cloud data facilitates the analysis of contour deviations. In addition, grinding trajectories are dynamically corrected to meet high-precision process requirements. This approach effectively overcomes the challenge that trajectory planning for large-scale, complex-shaped products is easily affected by protrusions. According to the established methodology, the development of an offline programming software system for robotic automatic grinding was initiated. To this end, experiments were conducted on aircraft wall panels to plan and modify grinding trajectories using the proposed method. This process was undertaken to validate the effectiveness and engineering practicability of the proposed method.
Fan, ChanghaoWang, MingyangLv, RuiqiangZhou, Peng
To address the high failure rate of rollers in coal mine belt conveyors, the inefficiency of manual replacement, and the operational disruptions caused by maintenance shutdowns, this study proposes a robotic arm system capable of replacing rollers without halting conveyor operations. The research focuses on the kinematic performance and path planning strategy of the robotic arm. A kinematic model is established using the Denavit–Hartenberg (DH) parameters, and the workspace distribution is analyzed via the Monte Carlo method. The results show that the horizontal reach exceeds 2020 mm and the vertical reach extends up to 2000 mm, which fully satisfies the spatial requirements for roller replacement across the entire conveyor system. In the path planning phase, an obstacle expansion model is constructed, and an improved Informed RRT* algorithm is implemented to generate collision-free trajectories, ensuring effective obstacle avoidance. To improve trajectory smoothness, path pruning and cubic B-spline interpolation are applied to refine the initial paths. For trajectory planning in joint space, quintic polynomial interpolation is employed, with boundary conditions set to ensure zero velocity and zero acceleration at both the start and end points, thereby guaranteeing smooth and stable motion of the robotic arm. Simulation results indicate that joint angles, angular velocities, and angular accelerations vary smoothly throughout the roller grasping process, without abrupt changes, and converge to zero at the beginning and end of the trajectory. End-effector trajectory tracking error analysis reveals positioning errors within 0.8 mm for side rollers and 3 mm for central rollers, well within acceptable engineering accuracy thresholds. This work provides a theoretical foundation and a practical implementation framework for advancing automation and intelligent operation in roller replacement tasks within coal mine belt conveyor systems.
Pu, CongyuanQian, Ke
Given the braking deviation of commercial vehicles, this paper discusses the influencing factors and uses Adams simulation software to accurately model the vehicle model due to the unreasonable match between the suspension system and the steering system. Through K&C analysis and dynamics analysis of the model, the root cause of braking deviation is identified, and the simulation method is used to quickly realize optimization and verification.
Yan, TangWang, JingxianSun, HongyangWu, Zhen
The implementation of the ground deceleration function in civil aircraft represents a critically complex process that deeply relies on the seamless collaboration of multiple onboard systems, including but not limited to braking, thrust reversal, spoiler, and steering systems. The operational logic governing these systems is highly intricate, characterized by tightly coupled interactions, stringent safety requirements, and a vast array of diverse physical and logical interfaces. This inherent complexity makes it exceptionally difficult to gain a thorough, system-level understanding of the implementation mechanisms and collaborative principles solely through traditional means of examining extensive, yet often fragmented, design documentation. The limitations of document-based analysis frequently lead to unforeseen integration conflicts, which are typically discovered late in the development cycle, resulting in substantial rework costs and project delays. To address this pervasive industry challenge, this paper selects the aircraft ground deceleration function as a representative case study and proposes an innovative, simulation-based validation methodology. This approach systematically utilizes model state machines to create a dynamic digital representation of the system-of-systems, enabling rigorous validation of aircraft deceleration requirements under various operational scenarios. By adopting this model-based systems engineering (MBSE) paradigm for mechanism representation, our approach effectively captures the nuanced coordination, timing dependencies, and dynamic interactions within the multi-system operational logic. It thereby facilitates the intuitive identification, analysis, and resolution of potential design flaws, including logical conflicts, deadlocks, race conditions, and uncovered or ambiguous requirements. Consequently, the method not only provides a robust framework for validating the aircraft’s function-related design requirements with greater confidence but also offers crucial, data-driven support for the iterative optimization and evolution of the overall functional architecture. The fundamental value proposition of this research lies in its transformative capability to convert implicit design knowledge and assumptions—originally scattered across voluminous documents, specifications, and expert minds—into an integrated set of executable, observable, and analyzable formal models. This digital thread enables systems engineers and designers to identify deep-seated integration and coordination issues proactively during the early conceptual and detailed design stages, rather than relying on discovery during the late, costly integration and testing phases. By shifting validation left in the development V-cycle, this approach significantly reduces the risk of major design changes and associated cost overruns later in the project lifecycle. Ultimately, it effectively enhances the overall maturity, safety, certifiability, and operational reliability of complex aircraft function development, paving the way for more efficient and predictable engineering processes.
Wang, MingqianYu, QiaoYu, MiaoTang, Chao
This SAE Information Report establishes a uniform procedure for assuring the manufactured quality, installed utility, and performance of automotive remote steering controls other than those provided by the vehicle manufacturer (OEM). These products are intended to provide driving capability to persons with physical disabilities. The adaptive modifications seek to compensate for lost or reduced function in the extremities of the driver with a disability. Remote steering controls are designed to provide a steering input device alternative to the OEM steering wheel that either reduces the required input force, changes the required range of motion or changes the location of the steering control, or any combination of the above. These controls supplement by power, other than by the driver’s own muscular efforts, the force output of the driver with a disability. Because this is an Information Report, the numerical values for performance measurements presented in this report and in the accompanying Test Procedure, while based upon the best knowledge available at the time, have not been validated by a testing of the Test Procedure.
Adaptive Devices Standards Committee
Quadrotors (UAVs) are widely used in intelligent inspection, environmental monitoring, and logistics due to their simple structure, strong maneuverability, and vertical take-off and landing capabilities. However, their highly nonlinear, strongly coupled, and highly constrained dynamic characteristics make trajectory tracking control a challenging task. To improve trajectory tracking accuracy and control robustness, this paper proposes a quadrotor trajectory tracking method based on model predictive control (MPC). First, a six-degree-of-freedom dynamic model of the quadrotor is established and linearized with small disturbances to transform it into a state-space model suitable for MPC design. An MPC optimization controller is then constructed, with an objective function that minimizes state error and imposes an input energy penalty, while explicitly considering the system's input and state constraints. Simulation results demonstrate that this method exhibits good tracking accuracy and control smoothness for typical trajectory tracking tasks (such as circular and spiral trajectory tracking). Compared with traditional PID and LQR controllers, the proposed method significantly improves maximum error, mean square error, and interference rejection. This study provides an engineering-feasible optimization control framework for UAV trajectory control.
Peng, FeiTao, ZhongGao, QiangJia, Bobo
This paper, for the first time, applies the Divine Religions Algorithm (DRA) to three-dimensional UAV path planning. Targeting the complex terrain of urban-mountain mixed environments, we propose a novel method that incorporates multiple enhancements, including A* initialization, single-point disturbance mutation, and adaptive weighting. First, the A* algorithm is employed to generate high-quality initial paths, serving as the skeleton of the population. Innovative mechanisms such as terrain-adaptive disturbances and dynamic weight adjustment are integrated to achieve both efficiency and robustness in path optimization. Comparative experiments with Genetic Algorithm (GA) and Crowned Porcupine Optimization (CPO) show that the improved DRA algorithm exhibits significant advantages in terms of path length, safety margin, average altitude variation, average turning angle, and overall cost function. It consistently obtains superior paths and achieves faster convergence. The results demonstrate that the proposed approach provides an efficient, adaptive, and practical intelligent optimization tool for UAV path planning in urban-mountain mixed or similarly complex environments, offering promising prospects for engineering applications.
Fang, LianyuYi, Wenjun
This work aims to investigate how disturbance-aware, robustness-embedding reference trajectories translate into actual driving performance when executed by professional drivers in a dynamic driving simulator. The study compares three planned reference trajectories against a free-driving baseline (NO-REF) to assess the trade-offs between lap time (LT) performance and steering effort: NOM, the nominal time-optimal trajectory; TLC, a track-limit-robust, time-optimal trajectory obtained by tightening margins to the track edges; and FLC, a friction-limit-robust, time-optimal trajectory obtained by tightening against axle/tire saturation. All reference trajectories share the same minimum LT objective with a small steering-smoothness regularizer, and are evaluated with two professional drivers driving a high-performance car on a virtual track. The reference trajectories stem from a disturbance-aware minimum-LT framework recently proposed by some of the authors, where worst-case disturbance growth is propagated over a finite horizon and used to tighten tire-friction and track-limit constraints, preserving performance while delivering probabilistic safety margins. LT and steering energy (SE) are evaluated as indicators of driving performance and steering effort, respectively, while RMS values of lateral deviation, speed error, and drift angle are used to characterize driving style. The results reveal a Pareto-like trade-off between LT and SE: NOM achieves the shortest LT, but with the highest SE, TLC minimizes SE at the expense of longer LT, while FLC lies near the efficient frontier, markedly reducing SE relative to NOM with only a minor LT increase. Removing reference trajectories (NO-REF) leads to both higher SE and longer LT, confirming that trajectory guidance improves pace and control efficiency. Overall, the findings highlight reference-based and disturbance-aware planning, particularly the FLC variant, as effective tools for training and for achieving fast yet stable trajectories.
Masoni, MatteoPalermo, VincenzoGabiccini, MarcoGulisano, MartinoPreviati, GiorgioGobbi, MassimilianoComolli, FrancescoMastinu, GianpieroGuiggiani, Massimo
To address the limitations of the traditional A* algorithm in lane-level navigation, we propose an autonomous vehicle path planning algorithm based on high-precision maps and an improved A* algorithm to ensure effective application in complex traffic environments. We construct a hierarchical high-precision map based on the Lanelet2 framework to achieve structured modeling of complex road environments. To address the adaptability issues of the A* algorithm in lane-level navigation, we propose optimization schemes, including heuristic function improvements, path segment division, and target point validity verification, to ensure that vehicles can autonomously change lanes on multi-lane roads. By combining dynamic programming (DP) and quadratic programming (QP), we ensure the safety and smoothness of the path. Simulation results demonstrate that the optimized algorithm enables smooth stopping and starting at traffic lights in structured road environments and autonomous lane changes on multi-lane roads. Compared to using DP alone, QP provides smoother and safer driving paths and exhibits superior obstacle avoidance performance in speed planning. This method effectively ensures the rationality of path planning in complex road environments while strictly adhering to traffic rules, thereby enhancing the safety and reliability of path planning.
Wang, SiyuZhou, RongShi, TianXu, ZhenZhao, Zhiguo
In recent years, with the low-altitude economy developing rapidly, the operation and management of low-altitude airspace has gradually become a hot topic. Unmanned aerial vehicles (UAVs) constitute a fundamental component of the low-altitude airspace ecosystem, significantly influencing its structure and functionality. The technological advancement of UAVs has fundamentally transformed the operational paradigm for low-altitude airspace management. This paper presents a comprehensive review of UAV-supported technologies in the context of low-altitude airspace operations and management. It systematically analyzes key technologies and applications of UAVs in areas such as airspace capacity and safety assessment, trajectory planning, and standardized flight management. Drawing from kinematic analysis and traffic flow theory, UAV density control and collision risk prediction offer quantitative insights into airspace capacity evaluation. Additionally, probabilistic analysis and simulation techniques enhance the accuracy and efficiency of safety assessments. In trajectory planning, multi-objective optimization algorithms tailored to operational scenarios—such as logistics delivery and agricultural operations—have significantly improved the utilization of airspace resources. Concurrently, collision avoidance techniques leveraging graph search, numerical optimization, and machine learning ensure flight safety in complex environments. Standardized flight management relies on pilot qualification review, airworthiness certification, and planning standardization, while discussing airspace segmentation strategies based on geofencing and intelligent control systems. Future developments in UAV-supported technologies are expected to trend toward higher precision, intelligence, and regulatory integration. By incorporating cutting-edge fields such as deep reinforcement learning and digital integration, these technologies are poised to further enhance the efficiency and safety of low-altitude airspace management, thereby providing robust technical support for the sustainable growth of the low-altitude economy.
Gong, LeiMa, ZhenxiaoLuo, Qin
With the rapid development of the low-altitude economy—represented by drone logistics, aerial inspections, and air taxis—air traffic has exhibited new characteristics including diverse forms, high density, and significant speed differences. To address these changes, the traditional air traffic control system requires upgrades, particularly in dynamic aircraft scheduling. This study proposes an air traffic control model (DS-ATM) tailored to this domain, built on the Deepseek large model. By integrating spatiotemporal graph neural networks with multi-objective reinforcement learning algorithms, the model achieves real-time path planning and conflict resolution in complex airspace environments. Validated using public datasets such as OpenSky Network, NASA UTM Dataset, and METAR meteorological data, experimental results demonstrate its significant advantages in reducing conflict rates and scheduling delays.
Li, RuiZhao, FangyuShe, YueLi, Wujie
The Active Wheel-Corner (AWC) integrates driving, braking, steering, and suspension systems into the wheel end, forming a fully drive-by-wire, four-wheel independent steering and four-wheel independent driving (4WIS&4WID) vehicle platform. While improving vehicle control performance, the full by-wire architecture also places higher demands on system reliability and fault tolerance. The steer-by-wire system has electrical, communication, and software failure risks, which may cause the vehicle to lose steering capability and trigger severe traffic accidents. This article proposes a hierarchical active fault-tolerant control strategy based on fault information reconstruction (FAST-FTC), enabling fault diagnosis and active fault-tolerant control when the steer-by-wire system fails, effectively ensuring the steering maneuverability and lateral stability of the vehicle under fault conditions. First, the strategy designs an adaptive observer combined with the Dugoff tire model to estimate nonlinear tire forces, while introducing a fault factor to achieve quantitative grading of steering system faults. Second, a hierarchical controller is designed for steering system faults. The upper-level controller, based on Adaptive Super-Twisting Sliding Mode Control (AST-SMC), determines the generalized forces required to track the desired trajectory under different fault conditions. The lower-level controller, based on the Fault-Aware Model Predictive Control (FA-MPC) strategy, dynamically adjusts weight matrices according to the fault factor and tire reconstructed stiffness, coordinating the allocation of four-wheel driving and the steering of healthy wheels to ensure lateral stability. Finally, the effectiveness of the proposed active fault-tolerant control strategy is validated through Hardware-in-the-Loop (HIL) simulation and real-vehicle tests.
Xiao, FengJiang, YueyongCheng, RuiXu, ChangheTang, XiangjiaoGao, FenglingLi, Jianhua
Safety of Automated Driving Systems (ADSs) is arguably one of the main remaining barriers before widespread market deployment. While there exists a plethora of methods for planning a trajectory that fulfils certain constraints, what those constraints should look like, to enable effective planning of safe trajectories, is still being discussed. In this article, we generalize the concept of Precautionary Safety (PCS) and present a framework providing constraints on the tactical and operational decisions of the ADS. Such constraints consider the ADS’ capabilities, the external conditions, knowledge of statistically relevant events and behaviors of other traffic actors, as well as the controllability of these events. The proposed framework enables assessment of the statistical fulfilment of quantitative risk acceptance criteria (QRACs), including requirements on accident, injury, and fatality rates. The framework further provides a means to dynamically adapt the constraints used for trajectory planning, i.e., to adapt the driving to the situation at hand. A case study, considering a possible collision scenario with a jaywalking pedestrian and a rear-end collision with a trailing vehicle, is provided to showcase the applicability and usefulness of the presented framework. The simulation-based case study displays the safety benefits from considering QRACs with multiple injury risk levels and further shows how the proposed PCS framework can be applied in practice.
Gyllenhammar, Magnusde Campos, Gabriel RodriguesSandblom, FredrikTörngren, MartinFredriksson, Jonas
Electrical/Electronic Architectures (EEAs) are continuously evolving to meet newly emerging demands. In recent years, major drivers of this evolution have been the increasing software-defined nature of vehicles and the push toward automated driving. Key technologies such as edge-enhanced functions, vehicle-to-vehicle communication, and service-oriented architectures are therefore the focus of current research efforts. This paper presents a vision of how these technologies can be used to enable cooperation between vehicles, illustrated by using parked vehicles as edge nodes. These are typically seen as obstructions, as they significantly increase the risk of missing or misinterpreting vulnerable road users such as pedestrians or cyclists. Our proposed approach to counteract this problem is the use of the parked vehicles themselves as edge nodes that support object detection or even trajectory planning. Current research primarily considers smart traffic infrastructure, roadside units, and other vehicles as potential edge nodes. Including parked vehicles as edge nodes means that, instead of acting solely as obstacles, we leverage their built-in sensors to contribute to cooperative awareness. While such cooperation will enhance the safety of automated vehicles in urban areas, several challenges arise. In this paper, we discuss how data traceability, decision-making in the presence of conflicting information, and incentive mechanisms for owners of parked vehicles can be addressed. Based on these challenges, the paper outlines requirements for future cooperative architecture and highlights the role of edge-enhanced functions, Vehicle-to-Vehicle (V2V) communication, and service-oriented architectures in enabling fully automated driving.
Lüntzel, VitusLukezic, NikolaKraus, DavidSeidel, LucaBeck, MaximilianSchindewolf, MarcSax, Eric
As automation advances and occupants transition from active drivers to passive passengers, understanding how automated driving behavior is evaluated becomes increasingly important. While longitudinal and lateral vehicle dynamics are known to influence perceived comfort and safety, it remains unclear to what extent motion–perception relationships remain stable across urban traffic contexts. This study compares two real-world investigations of automated driving: a left-turn maneuver at a signalized intersection on a test track and a roundabout maneuver with a shuttle in public traffic. Both datasets include high-resolution vehicle dynamics and structured subjective ratings. A consistent objectification approach was applied to examine the transferability of motion–perception relationships across contexts. However, differences in vehicle platform, automation level, trajectory characteristics, and study design limit direct comparability and require cautious interpretation. Despite partially overlapping ranges in selected peak-based dynamic parameters, such as longitudinal acceleration, subjective comfort and safety ratings were consistently higher in the roundabout scenario. Furthermore, strong associations were observed between motion parameters and subjective evaluations in the intersection context (adj. R2 up to 0.891), whereas objective parameters showed only limited explanatory power in the roundabout scenario (adj. R2 ≤ 0.06). The results indicate that motion–perception relationships derived within a specific context may not be directly transferable across different traffic scenarios. The findings highlight limitations of globally derived motion-based evaluation models and underline the importance of validating objectification approaches across diverse operational environments.
Panzer, AnnaStrenge, EmmaIatropoulos, JannesHenze, Roman
This article presents a cross-layer framework that integrates realistic vehicle-to-network-to-vehicle (V2N2V) delay characterization with a rigorous stability analysis of automated vehicle steering control. Both constant and network-induced time-varying delays modeled via deterministic bounds are addressed. For constant delays, delay-independent stability regions within the controller gain space are analytically derived. For time-varying delays with stochastic network origins, modeled using deterministic bounds, a refined Lyapunov–Krasovskii functional (LKF) incorporating augmented single- and double-integral terms is constructed. To establish delay-dependent linear matrix inequality (LMI) conditions, a reciprocally convex combination approach is employed to handle the delay interval partitioning, and the second-order Bessel–Legendre inequality is applied to tighten the integral quadratic bounds. The resulting LMI conditions explicitly capture the coupled effects of delay magnitude, delay variation rate, and control gains on closed-loop stability. Simulations of a lane-keeping scenario confirm that the predicted stability boundaries accurately match the closed-loop system behavior. Notably, incorporating a realistic time-varying V2N2V delay profile into the controller design reduces the lateral-state root-mean-square error (RMSE) by over 54% and decreases the settling time by a factor of 10 compared to designs relying on an average-delay assumption. However, high packet loss rates are shown to still induce residual oscillations due to information scarcity. Ultimately, these results elucidate delay-induced instability mechanisms and provide practical guidelines for designing delay-robust steering controllers for connected and automated vehicles.
Li, JialinLu, JianweiWei, HengAo, Di
Vehicle electrification and accelerated development cycles create a need for virtual Noise, Vibration and Harshness (NVH) development tools which are fast, precise and, seamlessly interchangeable between development sites, suppliers and OEMs. Component-based Transfer Path Analysis (C-TPA), standardized in ISO 20270:2019, enables independent component characterization and integration with virtual models to predict sound and vibration in new assemblies, referred to as Virtual Prototype Assemblies (VPA). However, conventional measurements are labor-intensive, typically restricted to a small number of samples, and overlook production variability. This paper introduces a fully automated, ISO 20270-compliant C-TPA system for non-rigid test benches, featuring a pre-instrumented test fixture with multiple vibration shakers and sensors automatically linked to a data acquisition system for immediate processing. Components can be characterized within minutes, with blocked forces directly integrated into a VPA workflow, replacing time-intensive in-vehicle testing with a repeatable, operator-independent bench procedure. A case study on an automotive steering system demonstrates the method’s accuracy, repeatability, and efficiency, along with its ability to predict realistic interior sound pressure levels and capture production variability, enabling robust virtual NVH evaluation early in the development cycle.
Sturm, MichaelWienen, KevinBrandstetter, MarkusSorber, EricCorbeels, PatrickVerrecas, BartGonçalves, Vinícius
In recent years, the automotive industry has actively explored the application of various AI-based models such as Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM) networks, Autoencoders, and Transformers to improve defect detection rates at the End-of-Line (EOL) stage. However, implementing these approaches in the Noise, Vibration, and Harshness (NVH) area face several practical challenges: ① extended evaluation times compared to other data types, which limit the quantity of training data and lead to overfitting; ② label imbalance caused by the relatively small amount of defect data; ③ reduced labeling accuracy due to human error; ④ decreased robustness under domain shifts such as changes in jig fixtures, test environments, and signal-to-noise ratio (SNR); ⑤ diminished model reliability when new defect arise during development; and ⑥ constraints imposed by compatibility requirements with existing test equipment. This study proposes a Convolutional Autoencoder (CAE) based framework trained on NVH datasets collected from normal and defective Column-type Electric Power Steering (C-EPS) systems. Latent variables at the bottleneck layer are used for dimension reduction, enabling visualization and unsupervised classification using a clustering algorithm. A classification model derived from the encoder is fine-tuned with clustered data, and Gradient-weighted Class Activation Mapping (Grad-CAM), an eXplainable AI (XAI) technique, is applied to extract Feature Frequency Maps (FFM) highlighting defect-related noise and vibration characteristics. The proposed approach does not rely on the deep learning model to directly classify defect. Instead, it utilizes extracted FFM as weights(mask) to detect defect. This method enables quantitative data representation and ensures high applicability with existing EOL equipment. Post-processing within the FFM enables root cause analysis, reducing issue resolution time and supporting integration with conventional signal analysis techniques.
Park, Jun-SeoJo, Hyeon-ChoelCho, In-JeSeo, Jae-YongYoo, Seong-Sik
Opposed-piston free-piston engine generators (OFPEGs) are emerging as a promising technology for next-generation hybrid and electrified transportation systems due to their high efficiency, reduced mechanical complexity, and improved noise, vibration, and harshness (NVH) characteristics. However, due to eliminating the conventional crankshaft mechanism and directly coupling a free-piston engine with linear generators, performance of OFPEG systems is governed by a strong coupling between piston dynamics, in-cylinder combustion processes, and electrical loading conditions. This coupling presents substantial challenges for system design, control, and optimization, limiting the further development and application of OFPEGs. Existing researches lack a comprehensive numerical model that integrates detailed in-cylinder thermodynamic process with control system of linear generator, and quantitative analysis of the effect of piston motion trajectory on system performance remains insufficiently explored. In this study, a novel one-dimensional OFPEG model is developed in Gasdyn and coupled with a linear motor model and a control strategy in MATLAB/Simulink, thus forming a complete numerical model for OFPEG. The model is validated against experimental measurements, demonstrating effective prediction of thermodynamic and dynamic performance with acceptable errors. Based on the validated model, the effects of varying piston motion trajectory on system performance are analyzed. Lower Rt and higher Ωcom and Ωexp are recommended for higher performance. When Rt is reduced to 2.5:1, thermal efficiency and indicated power improve to 36.3% and 3.4 kW, respectively. When Ωcom is increased to 0.6, thermal efficiency and indicated power improve to 35.5% and 3.22 kW, respectively. When Ωexp is increased to 0.6, thermal efficiency and indicated power improve to 36.0% and 3.41 kW, respectively. These improvements are primarily attributed to reduced heat transfer losses and enhanced scavenging efficiency under the modified trajectories. The results provide valuable insights into the optimization of piston motion trajectory to achieve higher performance. Furthermore, the proposed numerical model provides an effective tool for OFPEG design, optimization, and control strategy development, supporting the advancement of high-efficiency, low-carbon OFPEG systems for future transportation applications.
Wang, JiayuMorandi, NicolaLucchini, TommasoFENG, HUIHUAJia, BoruRen, Peirong
Automated aircraft parking systems enhance airport ground operations by enabling precise and autonomous docking of aircraft at gates. These systems reduce turnaround time, minimize human error, and optimize apron space through real-time object detection, obstacle avoidance, and dynamic path planning. Unlike fixed guided-path methods, the proposed system adapts to congestion and environmental conditions such as low visibility, ensuring safety and efficient maneuvering. Validation through simulation demonstrates the system’s potential to improve operational resilience and support scalable automation in future airport infrastructure.
Penugonda, Navya SunainaEdiga, Venkatadiwakar Goud
Trajectory optimization for reusable launch vehicles is a critical challenge in space mission design, aiming to determine fuel-efficient paths for spacecraft during ascent, hover, and descent phases. Minimizing fuel consumption not only enhances cost-effectiveness but also improves mission sustainability. The optimization process is governed by nonlinear orbital mechanics, gravitational perturbations, atmospheric drag, and operational constraints such as thrust limits and collision avoidance. These factors make the problem highly non-convex and discontinuous, posing significant difficulties for classical gradient-based approaches, which often fail to identify global optima. In this work, we formulate the trajectory optimization problem for a reusable rocket executing an ascent–hover–descent cycle. The vehicle must ascend to a specified target altitude, maintain a stable hover for a given duration, and then return to the launch site. The primary decision variable is the throttle control profile, which is represented as a vector of throttle settings over a discretized time horizon and governs thrust levels throughout all flight phases. The objective is to minimize total fuel consumption while satisfying all physical and operational constraints. To address the problem’s complexity, we employ the BQPhy platform, which implements Quantum-Inspired Evolutionary Optimization (QIEO). This metaheuristic approach efficiently explores the search space, overcoming the limitations of traditional methods. Comparative analysis with a classical Genetic Algorithm (GA) shows that the QIEO-based method delivers solutions 5–10 times faster while achieving superior fuel-optimal trajectories. The proposed approach highlights the potential of quantum-inspired optimization for high-dimensional, nonlinear aerospace trajectory design problems, offering a promising solution for enhancing the efficiency of reusable spaceflight operations.
Eswara Sai Kumar, KandulaSingh, UtkarshPohankar, PritamA, AnoopMaharana, PriyabrataLineswala, Rut
In response to the problems of urban traffic congestion and the limited expansion of infrastructure, this paper conducts two core research focusing on the intelligent chassis system of split-type flying vehicle. Firstly, an autonomous navigation strategy for the intelligent chassis module is proposed based on chassis module Navigation 2 architecture, which fuses LIDAR and IMU positioning to plan paths using the A* global planning algorithm on a global cost map, and update the local cost map in real time with sensor data. It is orchestrated by the BT Navigator using a behavior tree, with failures handled by the Recovery Server, to achieve autonomous driving across multiple waypoints. In simulation and closed-field experiments, the system can stably reach the preset target points. The positioning accuracy and trajectory tracking performance can meet the design requirements. Secondly, a mechanical slide rail-type docking structure adapted to the split flying vehicle architecture is designed. Deformation analysis under the representative working conditions are evaluated through finite element software. The test results show that the maximum deformation of this docking structure under typical load is significantly lower than the docking tolerance and positioning repeatability requirements. The structural stiffness and stability meet the design indicators. The above work indicates that the proposed autonomous navigation strategy and the docking structure for the intelligent chassis can effectively support the modular operation of “air trunk & ground terminal” mode, providing a scientific basis for the functional integration and system reliability research of split-type flying vehicles.
Zhao, WenyuShi, QinJiang, CongHe, Zejia
Robot Arm Tracking Control refers to the control of robot end effectors following a prescribed trajectory as their movement in robotic systems. The work presents a combination of Kalman Filter Based Dynamic System Tracking with Reinforcement Learning Based Trajectory Planning. These two aspects of tracking and planning help the robotic manipulator dynamically track a target that is located on an arbitrary moving path. In particular, by using Kalman filtering to estimate the position of a moving target and to compensate for sensor noise and sparse sampling, we take high-precision estimation values of each point’s coordinates along the target trajectory as a reliable basis to build a policy network using reinforcement learning. Based on it, the robot manipulator could produce effective motion planning under its own dynamic capabilities and physical constraint limit. Comprehensive simulation results illustrate advantages of the new algorithm against the classical control method, confirm that the novel technique achieves better performance both in accuracy and computation efficiency. Also, this mixed control system can deal with complex moving path for track target object. Even when meet different obstacle and not sure measurement, it still works well with other moving obstacle in many conditions. This can be strong to face other dynamic obstacle even if have different situation with changing obstacle and uncertain data. It shows that this paper works as an attempt toward optimal solution to combine the model-based technique together with data-driven approach aiming to support real-time, highly accurate, adaptive prediction is based control technique, promising applications into industry and promoting more improved works related.
Yu, JingzeWang, YujiaLi, JunshenChen, CongXu, Peng
In this paper, the design and process research of uniform filling linear trajectory for filament wound hydrogen storage tank with unequal polar holes are carried out. Firstly, by optimizing the slip coefficient, the winding angles of the left and right heads are smoothly and continuously transitioned to the cylindrical section. We study the necessary conditions for achieving the central angle of uniform filling, and calculate the tangent points of the trajectory line based on the continuous fraction principle. Meanwhile, the slip coefficients at the left and right ends that satisfy stable winding and uniform covering are determined. Based on the equal contour constraint conditions, we analyze the motion trajectory equation of the four-axis winding machine and convert it into the corresponding machine code for actual winding operations. Experimental results show that stable winding of fibers on the surface of the unequal-polar-hole mandrel is achieved, and uniform filling and winding effects are obtained after a certain number of winding cycles. Simulation results show that the proposed design parameters and optimization algorithm are feasible and effective.
Chen, BaosenFu, JianhuiCao, XuewenYu, Libin
The rapid development of autonomous driving technology has brought emerging opportunities to optimize the omnidirectional vehicle driving performance. However, its compliance with driving habits directly determines its social acceptance. Therefore, how to balance consistency between performance improvement and driving habits has become an important bottleneck restricting the rapid promotion of autonomous driving technology. Manual driving vehicles mostly focus on the safety of both longitudinal and lateral movements, and cannot cope with the vertical movement, let alone the performance of economy, comfort, and efficiency. In this context, this paper proposes an anthropomorphic trajectory optimization method incorporating vehicle omnidirectional dynamic characteristics and corresponding driving habits. Firstly, this paper explores vehicle dynamic characteristics in longitudinal, lateral, and vertical directions, and reveals the coupling effect of motion states during driving. Furthermore, the featured function of anthropomorphic driving is constructed by the driving habit patterns related to the accelerator pedal, deceleration pedal, and steering wheel. Then, a comprehensive trajectory optimization method that considers safety, economy, comfort, and efficiency is constructed to improve the driving performance while ensuring social acceptance. Finally, the sensitivity of method weights and the adaptability toward the real world are verified by the case studies and discussions. The results indicate that the proposed method can fully utilize the optimization potential of autonomous driving technology in the omnidirectional performance, and effectively assist the intelligent and automated development of road traffic systems.
Liao, PengZhang, DefengNing, DonghongLi, SijiaWang, Tao
To improve the handling stability of four-wheel steering/drive vehicles under complex high-speed maneuvers, this study proposes a coordinated control strategy that incorporates Active Rear Steering (ARS) and Direct Yaw Moment Control (DYC) based on a dynamic stability region. Firstly, a four-wheel steering vehicle dynamics model including lateral motion and yaw motion is established, and the ideal values of the control variables are determined. Secondly, combined with the fuzzy control theory and double-line method, the boundary of the dynamic stability region is obtained in the sideslip angle-sideslip angle rate β−β̇ phase plane, and the vehicle state is categorized into stable, unstable, and critical stable region. Then, A hierarchical control architecture is designed based on the stability boundary. The upper controller comprehensively solves the target rear wheel angle and additional yaw moment through feedforward feedback control; the coordinated control layer allocates control weights according to the stable state of the vehicle; the lower controller optimizes torque distribution through quadratic programming. Finally, the control strategy is validated by MATLAB/Simulink and CarSim co-simulation platform. The results show that the proposed control strategy reduces the RMS values of yaw rate and sideslip angle by 23.1% and 28.5% respectively, significantly improving the handling stability of the vehicle.
Nie, KeheChen, JinWang, FalongLi, RenBai, Xianxu
Autonomous vehicles exhibit extremely strong nonlinearity during drift. However, existing autonomous drift algorithms often neglect previewed path curvature and offer only limited consideration of road surface uncertainty because of the influence of vehicle nonlinear dynamics, which can affect tracking accuracy and robustness of drift control. To solve these problems, this study proposes a robust optimal drift control framework based on curvature preview. First, a preview vehicle kinematic model is constructed, and a preview model predictive control path-tracking controller that considers the forthcoming curvature is designed. Through the analysis of equilibrium points with additional yaw moment, a robust optimal drift controller is developed, which employs a three-degrees-of-freedom vehicle model with an additional yaw moment. This controller adopts integral sliding mode control with a super-twisting algorithm (STA) and exhibits good stability, which is verified through Lyapunov analysis. The proposed control algorithm is validated through hardware-in-the-loop experiments. The experimental results demonstrate that the proposed method significantly improves path-tracking accuracy and robustness under uncertain road surface conditions, thereby providing an effective control solution for drift-based path-tracking maneuvers.
Gan, YurunSong, ZiyuGu, TongtongDing, HaitaoXu, NanZhang, Jianwei
Atmospheric turbulence is a major source of uncertainty for unmanned rotorcraft operating in confined or disturbed environments, where robust trajectory planning requires reliable bounds on vehicle response. High-fidelity turbulence models are typically too computationally demanding for onboard use and difficult to integrate into planning frameworks. This paper presents a Control Equivalent Turbulence Input (CETI)–based approach to characterize turbulence effects on the inner-loop dynamics of a small unmanned helicopter and to derive disturbance-induced state deviation bounds suitable for robust planning. CETI models are identified from manually piloted hover flight tests of the unmanned research helicopter midiARTIS using a linear bare-airframe model and a Kalman filter for disturbance estimation. CETI transfer functions are fitted to averaged power spectral densities of the extracted disturbance inputs. The resulting model is validated by reproducing the identified transfer functions and by comparing open-loop simulation results to flight-test data in both time and frequency domain. Based on simulations with CETI inputs, probabilistic bounds on state deviations are derived and related to measured flight-test responses. The results demonstrate that the proposed CETI workflow provides a compact and computationally efficient turbulence surrogate that captures the dominant effects of atmospheric gusts on rotorcraft dynamics and is well suited for inner-loop performance assessment and as an input to robust model predictive control algorithms.
Ehlert, TobiasSchitz, PhilippDux, Rafael
The safe integration of Unmanned Aerial Vehicles (UAVs) into shared airspace necessitates robust conflict detection and avoid (DAA) methods that scale effectively with multiple dynamic intruders. Geometric methods, such as those in the DO-365 standard, are provably safe for pairwise encounters but become intractable in dense environments. Conversely, applying kinodynamic motion planners designed for static obstacles to dynamic scenarios leads to unstable behavior, characterized by excessive re-planning and oscillatory motion, as they lack a predictive model of intruder trajectories. This paper introduces a closed-loop planning framework based on the Closed-Loop Rapidly-exploring Random Tree* (CL-RRT*) algorithm to prevent Loss of Well-Clear (LoWC) in multi-intruder scenarios. Our approach integrates a closed-loop dynamics model to guarantee dynamically feasible trajectories and incorporates a spatiotemporal planning strategy. A time-to-come metric is propagated from the tree root to all nodes, enabling prediction of the state and time at future trajectory points. Predicted states are continuously evaluated against known intruder trajectories (from ADS-B or perception system) using the formal DO-365 well-clear criteria, checking each point against the Hazard Area Zone (HAZ) via Horizontal Miss Distance (HMD) and Distance-Modification-for-Tau (DMOD) metrics. Simulations demonstrate that the proposed planner successfully generates safe and feasible trajectories that prevent LoWC in complex multi-intruder scenarios.
Dadkhah Tehrani, NavidCarlson, SeanCherepinsky, IgorMooney, David
This paper presents the development, optimization, and flight test validation of a Trajectory Control System (TCS)-based flight control system for a tiltwing unmanned aerial vehicle. The TCS is a configuration-independent middle-loop longitudinal controller for vertical takeoff and landing aircraft and is integrated here with explicit model following inner-loop controllers, inverse propulsor models, and a tiltwing-specific control allocation scheme. The resulting flight control system provides coordinated control across vertical flight mode, hybrid flight mode, transition flight mode, and forward flight mode while relying on a concise feedback set and requiring only airspeed from the air data system. The control laws are obtained using a formal constrained optimization framework and transferred directly from simulation to flight without additional on-site retuning. Flight test results from piloted, semi-autonomous, and fully autonomous operations demonstrate stable and predictable behavior throughout the flight envelope, including tight hover performance, simultaneous climb rate and speed tracking in hybrid flight, and successful departure and arrival transitions at multiple speeds. Selected simulation-versus-flight comparisons further show that the nonlinear model captures the dominant trends in the measured response while also identifying specific aerodynamic and transition regime effects that warrant further refinement. Overall, the results demonstrate that the TCS + EMF architecture provides a practical and effective control solution for tiltwing VTOL aircraft.
Comer, AnthonyChakraborty, ImonKunwar, BikashSchmidt, Peter
This work describes the flight control system architecture of the VSDDL VT-03-s Shadow, a cost-effective subscale aircraft used as a testbed for novel flight control schemes. The highlight is the Maneuver Control System comprising the Trajectory Control System, which facilitates Simplified Vehicle Operations, and the Tactical Maneuvering System, which permits more aggressive maneuvering. The control laws permit the selection of both vertical takeoff and landing and conventional takeoff and landing modes of operation. Flight test results shown include transitions between vertical and forward flight modes performed using both Trajectory Control System and Tactical Maneuvering System, limited aerobatic maneuvering performed using the Tactical Maneuvering System, and demonstration of some of the automatic flight functions and capabilities.
Chakraborty, ImonMcCormick, ColeKunwar, BikashBhandari, RajanPutra, Stefanus Harris
This paper presents the design and simulation-based evaluation of a configuration-independent Trajectory Control System (TCS) for multiple vertical takeoff and landing (VTOL) vehicles. The TCS provides a unified, middle-loop longitudinal control system applicable to lift-plus-cruise, tiltwing, and vectored-thrust configurations. Developed under the Simplified Vehicle Operations (SVO) paradigm, the TCS computes thrust-to-weight commands from normalized vertical and horizontal acceleration using inertial frame force-balance relationships and allocates the resulting trajectory requirements across the available propulsors. The governing TCS equations, propulsor-share framework, and mode structure remain common across configurations, while configuration-specific effects enter only through mode thresholds, inverse propulsor models, and control allocation. The control laws require only attitude, angular rate, fore-aft acceleration, and vertical velocity feedback. Subscale simulation comparisons across three dissimilar VTOL vehicles demonstrate closely grouped longitudinal response characteristics together with broadly comparable departure and arrival transition behavior, supporting the predicted configuration-independent formulation and its suitability for pilot-intuitive operation. These results establish a scalable longitudinal control approach for next-generation VTOL vehicles. The simulation-based findings are further supported by the broader flight test progression of the three configurations reported in prior work.
Comer, Anthony
This study aims to explore and evaluate the effect of various foot positions on the kinematic and kinetic response of the lower extremity during frontal crashes using a realistic vehicle interior. Frontal impact sled tests were performed with the Test Device for Human Occupant Restraint, 50th-percentile Male (THOR-50M) and Test Device for Human Occupant Restraint, 5th-percentile Female (THOR-05F) anthropometric test device (ATD) in the driver’s seat of a midsize SUV testing buck (with realistic interior components including an instrument panel with steering wheel and steering wheel airbag, seat, three-point seat belt with pretensioner and force-limiter, accelerator pedal, brake pedal, knee airbag, and seat belt retractor pretensioner). Six sled tests were performed in two principal directions of force (PDOF) [three each in frontal (0°) and oblique (−20°) configurations]. The right foot was positioned on the accelerator pedal, fully on the brake, and half on the brake. A single test was conducted with the THOR-05F in an oblique configuration with the foot on the accelerator. Ankle response was analyzed from internal ATD instrumentation. Restraint engagement was found to be consistent across all testing cases. Ankle moment and angle varied based on PDOF and the tested foot condition. Right ankle moment ranged from 70 to −70 Nm in inversion/eversion. Right ankle angles ranged from 37° inversion to 28° eversion. Left ankle moment ranged from 10 to −41 Nm in inversion/eversion. Left ankle angles ranged from 10° eversion to 23° inversion. Differences in lower extremity motion and loading were observed for each testing condition. Placing the foot on the accelerator pedal produced greater ankle moment than either brake pedal condition. Placing the foot on the brake pedal resulted in the highest dorsiflexion angle response. Obliquity increased ankle moment and rotation for both ankles. The United States New Car Assessment Program (US-NCAP) foot position with an oblique PDOF created the highest ankle moment while the in-line brake position in oblique created the highest dorsiflexion rotation. By combining these findings with other efforts focused on naturalistic driving and foot positioning, these results might aid in development of additional testing practices that might enhance our understanding of the lower extremity in nonstandard initial positions.
Noss, JuniorDonlon, John-PaulMorris, AnnaSamier, GermainPark, JosephForman, Jason
The objective of this research was to understand the impact of transition window duration on success and performance during nominal transitions from conditional driving automation (SAE level 3). Because the driver can be disengaged from driving when conditional driving automation is engaged, the central challenge is how to safely transition from automated control to human control. Past research from the literature on Level 3 Automated Driving Systems (L3 ADS) has focused on safety-critical event responses (e.g., responding to a hazard) and on automation that operates at high speeds, which is not representative of the systems currently deployed that operate in lower-speed traffic jam situations [4, 5]. This article presents an analysis of data from several transition-of-control studies with conditional driving automation in a high-fidelity driving simulator. A range of transition window durations were compared, and different transition-of-control behaviors were coded from video data. Transition windows for 4, 6, 8, and 10 s conditions resulted in failures by the drivers to resume control. Success rates by condition were lowest with 4 s transition windows, but also lower with 10 s windows, compared to 6 s, 8 s, or 15 s windows (potential explanations appear in the discussion). Time to first glance back at the forward road and time to first-hand on the steering wheel were predictors of transition of control success across all transition windows. Survival analyses showed that drivers needed to begin the transition process within a few seconds to make successful transitions, even with longer transition windows. The results demonstrate the impact of different transition window durations on transition of control and provide unique insights into the factors influencing transition success in situations representative of those happening on the road now. These results help shape understanding of the requisite time needed for safe transition from automated to manual control and speak to the design recommendations for human–automation interactions.
Gaspar, JohnAhmad, OmarSchwarz, ChrisFincannon, ThomasJerome, Christian
To address the performance testing requirements of autonomous vehicles (AVs), this study proposes a model predictive control (MPC) algorithm specifically designed for low-ground-clearance test target vehicles (TTVs) to achieve trajectory tracking control. First, the kinematic model of the TTV is established, and its state-space equations are derived. An objective optimization function incorporating both error weighting and control weighting is designed. Simulation analysis reveals the influence of the control error weighting ratio (CEWR) on both straight-line and curved trajectory tracking performance: For straight-line tracking, increasing the CEWR from 10 to 25 reduces the overshoot, but increases the distance required to reach the target trajectory by 4.7%. A similar pattern is observed in curved trajectory tracking. To overcome the limitations of the fixed CEWR, an improved MPC algorithm integrating fuzzy control is proposed. This algorithm dynamically adjusts the CEWR in real time based on deviations from the target trajectory to achieve adaptive optimization. Simulation results demonstrate that for straight-line tracking, the MPC-Fuzzy eliminates overshoot entirely and reduces the stabilization time on the target trajectory by approximately 12.68%, 14.90%, and 15.73% compared to three MPCs with fixed CEWR, respectively. For curved trajectory tracking, the MPC-Fuzzy algorithm achieves faster trajectory convergence while simultaneously reducing overshoot to some extent, demonstrating effective compromise control performance.
Ji, ShaoboLu, YueqiLiao, GuoliangChen, ZhongyanLi, MengLyu, ChengjuZhang, Zhipeng
Precision control in Level 4 Automated Vehicles is essential for enhancing operational efficiency, accuracy, and safety. This work, conducted as part of ARPA-E’s NEXTCAR program, focuses on developing a robust hardware and software control solution to enable drive-by-wire functionality. A previous publication by the authors presented the hardware solutions for overtaking stock vehicle controls. This paper focuses on a model-based and data-driven control algorithm to enable drive-by-wire functionality for longitudinal and lateral motion control for a 2021 Honda Clarity Plug-In Hybrid Electric Vehicle. This vehicle was equipped with a set of sensors and an onboard processing unit to enable Level 4 automation. For lateral controls, an algorithm was developed to command steering torque to the electronic power steering module, ensuring the vehicle could attain the desired steering angle position at varying speeds. The system leveraged feedforward and feedback mechanisms. Feedback controller gains were identified through frequency response analysis of the steering torque assist electric motor and were further refined during track testing. To optimize the controller’s response time, a feedforward function was developed using a physics-aware model of the vehicle's steering system. The independent feature selection for the model was guided by using the physics of the system. For longitudinal control, the control inputs included the positions of the brake and accelerator pedals sent to the stock ECU, with the desired speed as the setpoint. The setup used a combination of feedforward and feedback control to achieve the target acceleration or deceleration. These algorithms underwent extensive dynamometer and track testing to perform various maneuvers in conjunction with the automated driving system.
Adsule, KartikBhagdikar, PiyushDrallmeier, JosephAlden, JoshuaGankov, Stanislav
Advanced autonomous driving is a critical component in the intelligent development of new-generation electric vehicles. Research on reliable chassis control algorithms ensures the safety and stability of autonomous vehicles during operation. To enhance the control performance of autonomous vehicles and improve the accuracy of trajectory tracking, this paper proposes a data-driven feedforward compensation trajectory tracking control approach. By optimizing the design of the feedforward compensation loop, systematic errors and latency in the vehicle’s steering system are mitigated, thereby enhancing the precision and robustness of the control algorithm. Initially, the paper analyzes the control errors present when the vehicle responds to controller commands. Subsequently, the paper focuses on the steering angle errors in trajectory tracking, identifying and analyzing the most relevant factors. A time-delay neural network (TDNN) based on data-driven principles is designed to model and predict these errors. This network captures the temporal characteristics of steering angle errors, enabling accurate predictions. Finally, the feedforward controller compensates for prediction errors by integrating feedforward compensation with the Model Predictive Control (MPC) controller’s predictions. This approach enables high-precision trajectory tracking by delivering precise control inputs. Experimental results demonstrate that the data-driven feedforward compensation control algorithm reduced trajectory tracking error by approximately 19% in co-simulations using Matlab/Simulink and Carsim, and by 56% in real-vehicle tests, thereby validating the effectiveness of the proposed approach.
Yang, YijinYuan, YinWang, ZhenfengSu, AilinZhang, ZhijieLu, Yukun
Object detection and distance prediction have advanced significantly in recent years. The YOLO toolbox has released its 11th version, along with numerous variants that have been applied across various fields. Meanwhile, the Detection Transformer (DETRs) has repeatedly set new state-of-the-art (SOTA) records in the field of object detection. Depth Anything also released its second version last year, further pushing the boundaries of distance detection. Although these models achieve impressive performance, they often require substantial computational resources. However, for the algorithms intended for real-world applications and deployment on onboard devices, computational efficiency are extremely critical. Inference time per frame is a critical factor in ensuring an algorithm’s reliability and feasibility. Designing a model that operates in real time without sacrificing accuracy remains an extremely challenging problem, and extensive research is ongoing in this area. To address this challenge, we present a model called the Fast Detection model, which runs in real time on a comma 3X device equipped with a Qualcomm Snapdragon 845 processor. We deployed the comma 3X device on a 2025 Nissan Leaf electric vehicle for autonomous driving purposes. Furthermore, experimental results of comparing our model to the state-of-the-art one-stage object detection models of the YOLO series indicate that our model demonstrates comparable performance but with faster speed on our collected real-world dataset. Additionally, we have incorporated an extra module into our Fast Detection model that enables it to predict the distance between our vehicle and detected objects, providing valuable information for downstream tasks such as path planning.
Li, TaozheWang, HanchenHajnorouzali, YasamanXu, Bin
In order to achieve fully autonomous driving, point to point autonomous navigation is the most important task. Most existing end-to-end models output a short-horizon path which makes the decision process hard to interpret and unreliable at intersections and complex driving scenarios. In this research, we build a navigation-integrated end-to-end path planner on top of an openpilot open source model. We created a navigation branch that encodes route polyline geometry, distance-to-next-maneuver, and high-level instructions and combines with path plan branch using residual blocks and feed-forward layers. By adding minimal parameters, new model keeps the original openpilot tasks unchanged and have the path output based on the navigation information. The model is trained on diverse urban scenes’ intersections, and it shows improved route performance in vehicle testing. The proposed model is validated in a Comma 3x device installed on a 2025 Nissan Leaf test vehicle. The road test results show the proposed algorithm shows less path planning error than the stock openpilot end to end model when evaluated against the human driver. This proposed path planning model can be adapted to different type of vehicles for the point to point navigation task.
Wang, HanchenLi, TaozheHajnorouzali, YasamanBurch, Collinli, VictoriaTan, LinArjmanzdadeh, ZibaXu, Bin
Drivers often interact with partial automation (SAE Level 2) systems, initiating transfer of control (TOC) either by handing control over to the automation or by taking it back. Accurately predicting these interactions may inform the design of future automation systems that adapt proactively to the operating context, enhance comfort, and ultimately may improve safety. We present a context-aware framework that generates a unified driver–vehicle–environment representation by fusing data from in-cabin video of the driver and of the forward roadway with vehicle kinematics, driver glance, and hands-on-wheel behaviors. This representation was encoded in a hierarchical Graph Neural Network that classified driver-initiated TOCs to: (i) Manual-to-automation and (ii) Automation-to-manual transitions and predicted time-to-TOC. Shapley-based explainable AI was used to quantify how the importance of behavioral, contextual, and kinematic cues evolved in the seconds preceding a TOC. Analysis of a naturalistic dataset of 1,565 driver-initiated TOCs from 16 experienced drivers revealed distinct patterns. Manual-to-automation transitions were preceded by lane count increases, acceleration, and spikes in glances to the instrument-cluster. In contrast, Automation-to-manual transitions were associated with lane count reductions, higher surrounding-vehicle density, deceleration, reduction in secondary-task engagement, and higher steering wheel control. Together, these patterns highlight key cues for predicting the TOC type and time-to-TOC. Using environment-only features, the classifier achieved 78% accuracy; adding vehicle kinematics increased accuracy to 84%, and incorporating driver behavior features further improved prediction to 90%. Across prediction horizons, the Manual-to-automation TOC was consistently predicted more accurately than the automation-to-manual TOC. Shapley analyses underscore that driver behavior provided the strongest cues for predicting TOCs, highlighting the value of fusing driving context with information obtained from monitoring the driver behavior to anticipate the type of driver-automation interaction and its timing.
Zhao, ZhouqiaoGershon, Pnina
Parking assist systems are among the most widely adopted driver-assistance features in modern vehicles. A key component of these systems is the path planning module, which ensures accurate vehicle alignment within a parking slot while satisfying various constraints such as maintaining slot centering, avoiding collisions in confined spaces, minimizing maneuver count, and achieving the shortest feasible path. Multiple path generation techniques—such as geometric, polynomial-based, and search-based methods—have been developed to enable safe and efficient parking maneuvers. However, most of these approaches rely on the simplifying assumption that the vehicle’s instantaneous center of rotation (ICR) is fixed, typically located on the non-steering axle. In practice, the ICR is not constant and can vary significantly across vehicles due to several physical and kinematic factors, including steering geometry, tire slip characteristics, suspension configuration, and weight distribution. Neglecting these variations can introduce trajectory inaccuracies, reducing the precision and reliability of automated parking systems. Although prior studies have explored estimation methods for the instantaneous center of rotation (ICR), limited research has examined how variations in the ICR influence overall parking performance. This paper addresses this gap by investigating the impact of ICR variation on path generation and motion control accuracy in parking assist systems. A simulation-based study using an SUV-class vehicle model is conducted to evaluate system behavior across diverse parking scenarios. The results demonstrate how ICR assumptions affect path precision and overall parking accuracy, providing insights to enhance path planning and control algorithms for real-world applications.
Awathe, ArpitPatanwala, AbizerJain, ArihantVarunjikar, Tejas
Autonomous vehicle navigation requires accurate prediction of driving path curvature to ensure smooth and safe trajectory planning. This paper presents a novel approach to curvature prediction using deep neural networks trained on GPS-derived ground truth data, rather than model predictions, providing a more accurate training signal that reflects actual vehicle motion. We develop a multi-modal neural network architecture with temporal GRU encoders that processes vision features, driver intent signals, historical curvature, and vehicle state parameters to predict curvature. A key innovation is the use of GPS-based actual curvature measurements computed from vehicle motion data (κ = ωz/v) as training supervision, enabling the model to learn from real-world driving patterns. The model is trained on 5,322 samples from real-world driving data collected on The University of Oklahoma’s Norman Campus using a Comma 3X device and a 2025 Nissan Leaf electric vehicle. Experimental results demonstrate high steering curvature prediction accuracy with a Pearson correlation coefficient of 0.805, Mean Absolute Error of 0.027654, and Root Mean Squared Error of 0.034402 on the validation set. The model achieves stable convergence within 10 epochs and maintains consistent performance across diverse driving scenarios, from straight highway segments to complex turning maneuvers. This work contributes to autonomous driving technology by demonstrating the effectiveness of GPS-supervised learning for curvature prediction, successfully deployed in OpenPilot’s production system with real-time inference at 5 Hz.
Hajnorouzali, YasamanWang, HanchenLi, TaozheBurch, CollinLee, VictoriaTan, LinArjmandzadeh, ZibaXu, Bin
Accurately predicting the future trajectories of surrounding vehicles is one of the core tasks in autonomous driving, and its precision is directly related to the safety and reliability of decision-making, path planning, and control execution. However, challenges such as the complexity of traffic participants’ behaviors, the variability of interactions, and the highly dynamic nature of traffic environments make it difficult for existing methods to effectively model spatiotemporal dependencies and achieve accurate long-term prediction in dynamic scenarios, thus limiting their applicability in real-world settings. In this paper, we propose a Transformer-based trajectory prediction model with a spatiotemporal attention mechanism to extract and effectively model vehicle motion and spatial interactions. Specifically, the temporal attention module captures the motion patterns of the target vehicle across the time dimension, while the spatial attention module constructs vehicle interactions through an adjacency graph, characterizing local interaction features such as relative positions and lane relationships. In addition, a GRU structure is incorporated as a complementary temporal component to enhance the model’s ability to capture continuous trajectory evolution trends. We evaluate the proposed model on the public NGSIM dataset, and the results demonstrate that our approach significantly outperforms a variety of existing trajectory prediction methods. In particular, the integration of spatiotemporal interaction feature extraction plays a crucial role in improving prediction accuracy, especially for long-term trajectory prediction, where it substantially enhances the model’s ability to represent complex and dynamic traffic scenarios and generates more accurate trajectories. Finally, ablation studies are conducted to analyze the importance of each module, verifying the key roles of the spatiotemporal attention mechanism and the GRU structure in modeling complex interactive behaviors and improving predictive performance.
Zhang, LijunHu, XingyuMeng, DejianZhu, Zhehui
This paper presents an approach utilizing Nonlinear Model Predictive Control (NMPC) and Unscented Kalman Filter (UKF) to predict system state and control the trajectory of the vehicle with dual trailers in an intersection turn scenario. The UKF estimates vehicle and trailers’ lateral traversal velocity states and the NMPC controls the vehicle acceleration and steering to maintain the vehicle’s desired heading through the turn. The vehicle’s lateral traversal velocity function is formulated using Lyapunov based method which is used as a propagation function in the UKF to improve the estimation accuracy. The lateral traversal velocity is then used as one of the constraints in the NMPC problem. The overall estimation and the control scheme are formulated and assessed in the simulation environment. The simulation results show good tracking and curb avoidance performance.
Malla, Rijan
Tuned Mass Dampers (TMDs) are widely used in the automotive industry to mitigate Noise, Vibration, and Harshness (NVH) issues across various vehicle systems. These passive devices are particularly effective in reducing structural vibrations in components subjected to resonant excitation. However, real-world applications often face challenges due to manufacturing variability and system-level build differences, which can cause deviations in both the TMD’s tuned frequency (up to ±15%) and the vibration characteristics of the host structure. These uncertainties—in both the TMD properties and the vehicle subsystem dynamics—can be modeled using statistical distributions. This paper presents a generalized methodology for vibration analysis and design under uncertainty, combining reliability engineering with dynamic vibration modeling. The approach formulates a unified mathematical framework that incorporates probabilistic and stochastic modeling to assess TMD performance under a range of build and environmental conditions. As a case study, the method is applied to assess steering column vibrations, with a focus on quantifying the probability that system performance meets specified NVH targets. Multiple statistical distribution models are considered to predict the likelihood that vibrations exceed customer acceptance thresholds, potentially leading to unfavorable subjective and objective ratings. The results are validated using population-level vehicle data. While demonstrated on the steering system, the proposed methodology is applicable to any vehicle subsystem equipped with a TMD, provided that the relevant random variables—such as modal properties, excitation inputs, and build tolerances—are properly characterized. This enables robust TMD design across vehicle domains, ensuring performance consistency despite system variability.
Abbas, AhmadHaider, Syedd'Souza, Suneel
Despite advances in crash avoidance, occupant restraint systems remain crucial in protecting the motoring public. Following decades of improvement in occupant protection, including several supplemental restraint systems for front seat occupants, the safety of rear seat occupants has recently undergone scrutiny. Studies evaluating rear seat occupant injury risk via field crash data have reported reduced relative safety in rear seating positions and alluded to advanced rear seat restraints, such as pretensioners and load limiters, as potential solutions. While the pursuit of novel technologies has historically improved occupant outcomes, evaluation of new systems in both controlled laboratory environments and field crashes is necessary to understand potential consequences of widespread introduction. This study analyzed the prevalence of advanced seat belts (load limiters and pretensioners) in the rear seating positions in the U.S. fleet. Additionally, occupant injury risk was compared across vehicles equipped with conventional and advanced seat belts in the rear seat, as well as between rear and front seat occupants, using data from state crash databases. The proportion of vehicles equipped with advanced rear seat restraints has steadily increased over the past couple of decades, but, as of 2023, remained below 10% of registered vehicles on US roadways. Evaluation of police-reported field crash data indicated that lap-shoulder belted rear seat occupants sustained fatal or incapacitating injury at a lesser rate than front seat occupants. Rear seat occupants have historically been and remain well-protected. Current field data do not consistently demonstrate a statistically significant reduction in rear seat occupant injury or fatality risk attributable to advanced seat belts. However, the relatively low number of crashes involving serious injury or fatality for rear-seated occupants in vehicles equipped with these systems underscores the need for additional data to fully evaluate their effectiveness in real-world crashes.
Rapp van Roden, Elizabeth AnnMiller, BrucePearson, JosephWilliamson, JamesBrown, Thomas
High-precision estimation of key vehicle–road state parameters is crucial for ensuring the accurate and safe control of mining trucks (MT), as well as for reliable trajectory tracking. Among these parameters, the vehicle sideslip angle is particularly critical for assessing and predicting lateral stability. However, its direct measurement is challenging, and its estimation typically depends on an accurate characterization of tire cornering stiffness. For MT, large variations in loading conditions (from empty to fully loaded) pose significant challenges to sideslip angle estimation due to the resulting nonlinearity and variability of tire cornering stiffness. To address this issue, a novel joint estimation framework integrating the Moving Horizon Estimation (MHE) and Square-Root Cubature Kalman Filter (SCKF) is proposed to simultaneously achieve high-precision estimation of both tire cornering stiffness for each tire and vehicle sideslip angle. In this framework, the cornering stiffness of the front, middle, and rear axles is identified and updated in real time using MHE through a forgetting-factor least squares method based on yaw rate and lateral acceleration data within a fixed-length time window. The updated stiffness is then incorporated into the SCKF for accurate estimation of the sideslip angle. This sequential process effectively establishes a coupling between the estimation of the two parameters, forming an integrated joint estimation mechanism. The proposed framework is validated on the TruckSim–Simulink co-simulation platform, and the results confirm its superior accuracy and robustness, demonstrating its potential to improve the safety and control performance of MT.
Xia, XueShen, PeihongJiao, LeqiLi, TaoChen, HuiyongZhao, KunJiao, LeqiZhao, Zhiguo
Occupant body size in vehicles varies significantly, encompassing differences in height, mass, and overall body composition. Adaptive restraint systems, featuring adjustable parameters such as belt load limiters, steering column load limiters and stroke, seat pan stiffness, and airbag pressure, can offer more equitable protection tailored to individual body sizes. In this study, a test rig modeled after the Volvo XC90 (2016) was used to collect data from 46 participants who were dressed in typical summer clothing and seated upright, without slouching or leaning sideways. Stepwise adjustments of the seat pan and seatback were performed. The collected measurements include seat pan movements (front-back and up-down), seatback recline, and key seatbelt-related parameters, such as belt payout length, D-ring angle, lap belt length, and buckle tension. The collected data was then used to train machine learning models to predict individual occupant characteristics: standing height, mass, and seated height. This study shows the challenges and opportunities for occupant body size estimation from seatbelt and seat location inputs. The prediction’s root mean square error across validation dataset was as follows: standing height 8.76cm, mass 11.33kg, and seated height 5.61cm. The prediction of mass fulfilled the defined criterion, while the prediction accuracy for standing height and seated height require further improvement. Our analysis reveals that a key improvement could be achieved by implementing an upgraded lap belt position sensor, given that lap belt length was identified as a dominant feature across models. Furthermore, the analysis suggests that D-ring angle, buckle tension, and seatback recline can be excluded from the input feature set.
Wang, DaAhmed, JawwadRowe, MikeBrase, Dan
Autonomous mobile robots are becoming a key part of everyday operations in industries like manufacturing, logistics, healthcare, and even home assistance. A core requirement for these robots is the ability to navigate efficiently and reliably within their operating environments. To do this automation, the robot needs to understand its surroundings, figure out where it is on a map, and find a safe path from where it is to where it needs to go without bumping into anything. This paper presents an effective grid-based path planning solution for autonomous indoor navigation with a mobile robot. Achieving reliable and collision-free navigation in changing environments is a major challenge for mobile robotics. This is especially true when obstacles can appear unexpectedly, requiring quick re-planning. To tackle this issue, an improved A* algorithm was implemented to work closely with LiDAR for environmental awareness. The improved algorithm was added to the robot’s navigation system, and LiDAR data were used for simultaneous localization and mapping (SLAM) with Gmapping. A key improvement was integrating with ROS move_base control instead of using direct velocity control, enabling smoother motion and better path tracking. Additionally, the improved A* path is further simplified into a series of crucial waypoints, which are followed by move_base while the system watches LiDAR data in real time to spot obstacles. When a moving obstacle is detected, the planner recalculates the path and updates waypoints, enabling the robot to go around the obstruction and continue toward its goal safely. Tests in real indoor environments showed that the proposed system performs reliably at avoiding dynamic obstacles, navigating smoothly, and achieving goals. By combining heuristic planning, LiDAR perception, and ROS navigation tools, the proposed system offers a practical solution for autonomous mobile robot navigation.
Devaraj, Sriram SanjeevPark, Jungme
Accurate perception of the surrounding environment is fundamental and essential to safe and reliable autonomous driving. This work presents an integrated vision-based framework that com bines object detection, 3D spatial localization, and lane segmentation to construct a unified bird’s-eye-view (BEV) representation of the driving scene. The pipeline provides geometric information on object position and orientation by employing Omni3D to infer 3D bounding boxes of objects from monocular camera frames. Detections are subsequently projected onto a 2D BEV canvas, where object instances are represented with respect to the ground plane for enhanced interpretability. To complement the object-level perception, we utilized YOLOPv2 to perform lane segmentation, producing both lane masks and lane line masks in the image domain for future coordinate transformation. By adopting a pinhole camera model, the coordinate transformation of these masks from the perspective image plane into the BEV canvas can be performed. The fusion of 3D object detections and geometrically transformed lane representations yields a coherent and structured spatial map of the vehicle’s surroundings. In addition, the BEV space is integrated into a local 2D map generated from Mapbox tool. This unified environment model enables explicit reasoning about drivable space and surrounding obstacles, facilitating its integration into downstream modules such as path planning and trajectory prediction. The framework demonstrates the feasibility of leveraging recent advances in monocular 3D perception and deep learning-based lane segmentation to construct a computationally efficient and semantically rich BEV representation, which is a potential core perception component in real-time autonomous driving systems.
Tan, LinArjmanzdadeh, ZibaWang, HanchenLi, TaozheHajnorouzali, YasamanBurch, CollinLee, VictoriaXu, Bin
Items per page:
1 – 50 of 2222