Browse Topic: Chassis

Items (14,648)
Regenerative braking has a strong influence on the energy efficiency and drivability of battery-electric vehicles. This study establishes an empirical baseline analysis under controlled conditions of the regenerative braking behavior of the 2020 Tesla Model 3 to support the interpretation of on-road performance and serve as a reference for subsequent testing and analysis. The tests were performed on a four-wheel-drive chassis dynamometer at Argonne National Laboratory, combining Multi Cycle Testing (MCT) to simulate real world driving patterns (city, highway) with coast-down tests to isolate periods where the motor is operating in regen mode and compare the behavior across different parameters. Vehicle data was collected from the vehicle using taps in the Controller Area Network (CAN) bus as well as a high-resolution power analyzer. The vehicle displayed the highest efficiency during simulated city driving conditions (3.62 miles/kWh followed by highway (3.40 miles/kWh) and aggressive
Pierce, Benjamin BranchDi Russo, MiriamDas, DebashisZhan, LuStutenberg, Kevin
Accurate flux linkage characterization is essential for the design, control, performance and efficiency optimization of permanent magnet (PM) traction motors in automotive applications. Precise knowledge of flux linkage across varying load, speed, and temperature conditions directly impacts torque production, field-weakening capability, overall drive system efficiency and torque security. This paper presents a critical review and classification of flux-linkage characterization methods, encompassing offline laboratory mapping, standstill signal injection, self-commissioning inverter-only routines, and online real-time estimation. Each method exhibits distinct trade-offs in terms of accuracy, robustness to inverter nonlinearities, temperature adaptability, cost, and scalability for production and in-vehicle use. With the increasing complexity of automotive traction systems, understanding these trade-offs is crucial for optimal motor design and control. To enable systematic comparison, a
Khan, Ahmad ArshanHaddad, ReemonKim, JayHermann, JustinMohamadian, Mustafa
Active suspension systems play a crucial role in improving vehicle ride comfort and handling stability. However, most existing studies focus on the low-frequency range below 20 Hz, leaving the suppression of high-frequency vibrations within 50–500 Hz largely unexplored, even though these vibrations strongly affect in-cabin noise and ride quality. To address this gap, this study introduces a quarter-car suspension model incorporating both bushing dynamics and a rigid-ring tire within a reinforcement learning (RL) framework. A major challenge for RL-based suspension control is its degradation in high-frequency performance. To overcome this issue, we design an innovative training framework that integrates multiple synergistic strategies. First, frequency-domain rewards are incorporated as auxiliary signals to explicitly guide policy optimization in the high-frequency band. Second, long short-term memory (LSTM) networks are embedded in both the Actor and Critic to capture the sequential
zhu, ZhehuiZhang, LijunMeng, DejianHu, Xingyu
As electric intelligent vehicles advance, drive-by-wire systems are increasingly adopted, and the thermal reliability of electromechanical brake (EMB) motors—the key actuators—remains safety-critical. Under stalled-rotor operation, unequal DC currents are typically applied to the three phases, producing nonuniform winding heating. Conventional thermal models can miss the associated tangential heat-transfer effects, increasing the risk of phase-wise end-winding hot spot. This paper analyzes EMB motor thermal behavior under stalled-rotor conditions using a modular 3-D lumped-parameter thermal network (LPTN). First, a standardized tooth module with external interfaces is developed. Its internal parameters are informed by experiments and computational fluid dynamics (CFD) and identified via particle swarm optimization (PSO), allowing the module to be encapsulated for reuse. Next, based on the machine topology, a minimal motor is derived and multiple tooth modules are interconnected through
Duan, YanlongXiong, LuWang, XinjianZhuo, GuirongZeng, Jie
Flat tires represent a common yet serious issue in vehicle safety, leading to compromised control, increased braking distance, and potential rim or structural damage when undetected. Conventional tire pressure monitoring systems (TPMS) rely on embedded sensors that can fail, incur high replacement costs, and are not always equipped in older or low-cost vehicles. To address these limitations, this study presents a comprehensive visual dataset for flat-tire classification using computer vision and machine learning techniques. The dataset comprises 600 labeled images—300 flat-tire and 300 non-flat-tire samples—collected from diverse vehicle types, lighting conditions, and viewpoints. This dataset is designed to support the training and benchmarking of lightweight edge-AI models suitable for real-time deployment on embedded platforms. A set of supervised learning models were evaluated. Results demonstrate that visual-based classification provides a cost-effective and scalable pathway
Gunasekaran, AswinGovilesh, VidarshanaChalla, KarthikeyaMaxim, BruceShen, Jie
High thermal loads on brake systems during extended descents followed by vehicle soak pose significant safety and durability risks. Excessive rotor or fluid temperatures can cause loss of braking efficacy, fluid degradation or evaporation, thermal fade, and accelerated component wear. This study uses time-history data of brake-disc and fluid temperatures which were collected during controlled hill-descent events with subsequent soak periods, where the vehicle is parked in a wind protected area. Besides the rotor and brake fluid temperatures, environmental conditions were recorded (ambient temperature, humidity, wind speed and direction) and the vehicle and brake specifications are known (rotor/caliper geometry, pad material, vehicle aerodynamic configuration and mass). 126 test runs from a dedicated vehicle program are used, each providing time-history records that form the basis of our analysis. From these records we extract phase-specific samples (descent and soak phase) and engineer
Poojari, Uday KumarWestphalen, JanVenugopal, Narayana
Helical compression springs have been used widely in various industries from automotive, aerospace and construction to electronics and medical devices. In the automotive industry, they appear in many places such as suspension, valvetrain, etc., as well in the discharge check valve of Gasoline Direct Injection (GDI) pump, which is the subject of study due to a recent fracture in lab testing. A theoretical study is conducted first to establish the equation governing spring dynamic motion under impact velocity, which can be in high magnitude with surging shock wave along spring axis. A new spring shock wave equation is developed for spring axial motion coupled with coil torsional effect. This newly derived shock wave equation has a broader term than the classic spring formula found in most engineering books. In this paper, it shows that the classic spring shock wave equation is only a special case for the general wave equation newly discovered. Then, a theoretical formula on spring shock
Pang, Michael L.Gunturu, SrinuNorkin, Eugene
As the adoption of electric vehicles continues to accelerate, the demand for their development and testing using chassis dynamometers has also increased significantly. Compared with internal combustion engine vehicles, chassis dynamometer testing for electric vehicles typically requires test durations several to several dozen times longer, resulting in substantially increased labor requirements. In addition, low-temperature testing is often required, further intensifying the workload associated with vehicle testing. To address these challenges, this study developed and evaluated a pedal robot designed to enable unmanned and automated testing. The pedal robot developed in this study weighs only 12 kg and can be installed within a few minutes. It is, to the authors’ knowledge, the world’s first pedal robot that mimics human driving behavior by using a single foot to operate both the accelerator and brake pedals. Unlike conventional driving robots, the actuators of the proposed system do
Lee, DaeyupKang, Ji MyeongJo, YechanChoi, SeongUnShin, JaesikKim, JongminKang, Keonwoo
Off-road autonomous vehicle systems must be able to operate across unstructured and variable terrain while avoiding obstacles. This presents significant challenges in vehicle and control system design, especially for less conventional platforms such as 6×4 vehicles. While forward driving autonomy has developed and matured in recent years, effective reverse navigation remains an under-explored area of vehicle co-design. Reversing 6×4 vehicles have limited rear steering authority, an extended wheelbase, and asymmetric traction, which introduce complex dynamics into any control system that is used. To address this need, a robust and experimentally validated fuzzy logic control architecture for 6×4 reverse navigation was developed during the course of this project. This architecture incorporates both near-field and long-range path data with adaptive outputs controlling steering and velocity based on a rule base that covers the whole vehicle state space. This method has low computational
Dekhterman, Samuel R.Sreenivas, Ramavarapu S.Norris, William R.Patterson, Albert E.Soylemezoglu, AhmetNottage, Dustin
This paper investigates the performance of a computational radial passenger car tire over winter road sand at different operating conditions. This study seeks to address gaps in literature by using both an experimental direct shear-strength test and then validating the same test in a Finite Element Analysis (FEA) software called Virtual Performance Solution (VPS) using a Smoothed-Particle Hydrodynamic (SPH) technique to model a winter road sand. The simulated sand was measured against physical sand data ensuring validation of the density, internal friction angle and cohesion. Once the sand was validated against physical testing data the sand was layered atop an icy road surface to understand the influence sand has on tractive effort and rolling resistance performance. With modelled and validated winter road sand and a Continental CrossContact LX Sport tire size 235/55R19 testing conditions were set up. The tire-sand interaction was simulated using a node-to-segment contact algorithm
Fenton, ErinEl-Sayegh, Zeinab
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
Awathe, ArpitPatanwala, AbizerJain, ArihantVarunjikar, Tejas
For off-road driving, particularly on steep grades and over barriers, the engine torque is a key design criterion of off-road vehicles. In conventional powertrains with combustion engines, mechanical all-wheel-drive systems combined with differential locks are used to distribute the torque demand between the front and the rear axle based on wheel-specific traction. With the growing market share of electric powertrains, off-road applications are becoming increasingly relevant for electric passenger cars. In comparison to conventional powertrains, electric all-wheel-drive configurations do not have a mechanical torque transfer between the two axles. If one axle experiences low traction, the second axle can rely on its own torque capability only. Transfer of unused torque of the slipping axle to the other one is not possible. The challenge, therefore, is to specify the right torque requirements for each axle for off-road driving while avoiding over-dimensioning and high powertrain costs
Martin, MichaelWinkelheide, JonasHartmann, LukasSturm, AxelHenze, Roman
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
Adsule, KartikBhagdikar, PiyushDrallmeier, JosephAlden, JoshuaGankov, Stanislav
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
Hajnorouzali, YasamanWang, HanchenLi, TaozheBurch, CollinLee, VictoriaTan, LinArjmandzadeh, ZibaXu, Bin
Vehicles may enter highly unstable dynamic states due to lateral collisions, sudden loss of grip, or extreme steering disturbances. When such instability arises in congested road sections where obstacle avoidance is required, the safety risk to both the ego vehicle and surrounding traffic escalates significantly. In such scenarios, the vehicle must not only regain stability but also navigate the roadway in the shortest feasible time to prevent secondary collisions. This paper investigates the minimum-time maneuver of a vehicle starting from an unstable dynamic condition and constrained to travel within prescribed road boundaries. A single-track vehicle model with combined-slip nonlinear tire model is employed to capture the vehicle dynamics under high slip conditions. Phase-plane analysis is conducted to reveal how control inputs reshape the system’s vector field and influence the possibility and speed of stability recovery. An optimal control problem is formulated to compute the
Leng, JiatongYu, LiangyaoWang, YongxinYou, WeijieLi, ZiangJin, Zhipeng
Brake pulsation noise caused by fluid-borne vibration, which is generated by pressure pulsations from the pump in the Electronic Stability Control (ESC) modulator, occurs when the control brake function is activated under various driving conditions, such as Adaptive Cruise Control (ACC) and regenerative-friction brake coordination. This noise is particularly noticeable in Battery Electric Vehicles (BEVs), where the background noise from the power source is lower than that of internal combustion engine vehicles. The simulation of pressure pulsations in the brake system requires the excitation force of the pump built into the ESC modulator, the characteristics of valves, and the characteristics of the flexible hose; however, it is extremely difficult to determine these parameters with high accuracy from the design specifications. For this reason, in this study, the pump and valves were experimentally identified, while the flexible hose was represented by a three-element Voigt model to
Koike, YoheiKomada, MasashiYano, MasahiroYoshioka, Nobuhiko
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
Zhang, LijunHu, XingyuMeng, DejianZhu, Zhehui
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
Tan, LinArjmanzdadeh, ZibaWang, HanchenLi, TaozheHajnorouzali, YasamanBurch, CollinLee, VictoriaXu, Bin
This article deals with the development of a real-time capable, three-dimensional model of the Mercedes-Benz G-Class with flexible ladder frame that considers nonlinear suspension kinematics and force elements. The shift to new drivetrain technologies often results in a significant increase in vehicle weight and requires corresponding design modifications – also applying to off-road vehicles. These modifications result in changed stiffness of elements such as the ladder frame or anti-roll bar, which significantly affect vehicle dynamics and off-road performance. Therefore, strategic, efficient assessments must be made in early development stages, where no detailed information about individual systems and components is available yet, to detect and avoid potential massive, costly changes in later stages. This requires a “handmade” vehicle simulation model specifically tailored to this particular application, since the use of commercial multi-purpose simulation packages is not effective
Riebler, SandroPernsteiner, SamuelGranitz, ChristinaSchabauer, Martin
Electrification is rapidly entering all vehicle classes, including light- and heavy-duty trucks designed for heavy towing capabilities. Still, the quantitative impact of towing on battery-electric vehicle (BEV) energy use and range remains under-characterized. We conducted controlled towing tests with a Ford F-150 Lightning using two trailers of different sizes and varying payloads to isolate aerodynamic and mass effects and to span the full range of towable payloads within the vehicle’s rated capacity. The vehicle was instrumented at the CAN bus level, capturing motor power, torque, speed, and related internal signals from different control modules. On-road testing consisted of repeated back-and-forth passes on level, straight road segments at set speeds focusing on highway operation, where aerodynamic drag is stronger and real-world towing use cases occur. From these data, we extracted road load equations and dynamometer coefficients for each trailer combination, then reproduced
Timermans Ladero, Inigo
With the rapid development of automated driving and the increasing adoption of “zero-gravity” seats, the crash safety of highly reclined occupants has become a critical issue. The current THOR dummy, designed for frontal impacts in the standard upright posture, exhibits limitations when directly applied to reclined seating configurations, including insufficient spinal flexion capability and excessive posterior pelvic rotation. In this study, the thoracolumbar spine kinematics of the THUMS human body model, reconstructed against post-mortem human subject (PMHS) tests, were analyzed. A two-segment linear fitting was employed to characterize a “dummy-like” spinal flexion response, yielding a virtual rotational hinge located near the thoracolumbar joint of the original THOR model. The characteristic rotation angle obtained from THUMS showed a strong linear correlation with the flexion moment of the T12–L1 vertebrae. Based on this relationship, the rotational joint of the THOR dummy was
Guo, WenchengKuang, GaoyuanShen, WenxuanTan, PuyuanZhou, Qing
Tires are critical to vehicle dynamics, transmitting traction, braking, and cornering forces to the road. A tire blowout, the sudden and rapid loss of inflation pressure due to puncture or structural failure, can cause severe instability, rollover, or collisions. Understanding vehicle response during blowout events is essential for developing robust safety systems and control strategies. Earlier developed simulation models are used to study and understand vehicle behavior during blowouts, but there is a lack of on-road testing platforms to validate these models experimentally. In this paper, an experimental platform integrating a tire blowout device and an instrumentation system has been developed to address this gap. The blowout device consists of multiple solenoid valves mounted on the wheel surface and powered by a 12V power supply. All valves can be triggered at the same time using an RF remote, producing rapid and synchronized deflation. As an extension of this implementation, an
Kanthala, Maha Vishnu Vardhan ReddyKrishnakumar, AshwinLin, Wen-ChiaoChen, Yan
Software-defined vehicles offer customers a greater degree of customization of vehicle controls and driving experience. One such feature is user-adjustable tuning of vehicle ride and handling, where customers can vary ride height, damper stiffness, front-rear torque balance, and other aspects of vehicle dynamics. While promising a great customer experience, such a feature can expose the vehicle to a wider range of structural loads than those in the nominal design condition, particularly when such tuning is extended to cover spirited “sport” mode driving, off-road driving, etc. In this paper we present a novel methodology combining Road Load Data Acquisition (RLDA) data and real-world telemetry data to estimate the impact of user-adjustable vehicle-dynamics tuning on structural durability. In doing so, the method combines the physics of damage accumulation (from RLDA data) with user behavior (from telemetry data) to present an accurate assessment of the impact on durability, moving
Demiri, AlbionRamakrishnan, SankaranKhapane, PrashantBorton, ZackeryRamakrishnan, SankaranKhapane, PrashantBorton, Zackery
When a vehicle performs planar motion, the tire side force induces a jacking-up effect determined by the suspension roll center height governed by suspension geometry. These jacking forces also excite pitching motion. In this study, the pitching degree of freedom, along with roll degree of freedom, was incorporated in the bicycle model of the vehicle motion, hence it becomes four-degree-of-freedom model, and a new analytical method that applies modal analysis method to the model decomposes the motion of the sprung mass of the vehicle into mutually independent vibration modes. Since the superposition of these vibration modes can reproduce vehicle motion, these vibration modes are the fundamental factors governing sprung-mass behavior. Therefore, understanding how these vibration modes respond to design parameters provides a theoretical foundation to design desired vehicle dynamics from the early stage of car development. This report presents, by conducting modal analysis of the four
Kusaka, KaoruYuhara, TakahiroKoakutsu, Shingo
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
Abbas, AhmadHaider, Syedd'Souza, Suneel
Towing imposes substantial efficiency penalties on both battery-electric vehicles (BEVs) and internal combustion engine (ICE) vehicles, reducing range by 30-50%. This paper presents a proof-of-concept embedded control architecture for distributed trailer propulsion that actively regulates drawbar force to reduce towing loads. Unlike proprietary e-trailer systems requiring specialized hardware, the proposed implementation demonstrates feasibility using commercial off-the-shelf (COTS) components and open-source software. The distributed architecture employs dual Raspberry Pi 4B single-board computers communicating via ROS 2 at 20 Hz. The trailer-mounted controller executes a Simulink-generated control node coordinating load cell acquisition (HX711 ADC), motor CAN bus telemetry, and throttle commands to a 5 kW BLDC traction motor powered by a 5 kWh LiFePO4 battery pack. A vehicle-mounted controller logs OBD-II/CAN validation data. The control pipeline implements cascaded EWMA/Hampel
Joshi, GauravAdelman, IanLiu, JunDonnaway, Ruthie
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
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
Zhao, ZhouqiaoGershon, Pnina
The increasing need to decarbonize the transport sector is accelerating the adoption of renewable and low-carbon fuels such as Hydrotreated Vegetable Oil (HVO) and biodiesel as sustainable substitutes for fossil diesel. These fuels are evaluated as drop-in solutions requiring no engine recalibration, enabling immediate GHG emission reduction in existing diesel fleets. This study experimentally investigates the combustion, performance, and emission characteristics of a turbocharged common-rail two-cylinder diesel engine (Kohler LWD 442 CRS) operated with conventional fossil Diesel, pure HVO (Hydrotreated Vegetable Oil), and an HVOB20 blend (80% HVO and 20% biodiesel produced from waste cooking oil and animal fats). Tests were carried out under steady-state conditions at the DIIEM Engine Laboratory of Roma Tre University. The analysis focused on in-cylinder pressure evolution, brake power, brake specific fuel consumption (BSFC), and both regulated and unregulated emissions. Regulated
Zaccai, MartinaChiavola, OrnellaPalmieri, FulvioVerdoliva, Francesco
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
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
Wang, HanchenLi, TaozheHajnorouzali, YasamanBurch, Collinli, VictoriaTan, LinArjmanzdadeh, ZibaXu, Bin
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
Yang, YijinYuan, YinWang, ZhenfengSu, AilinZhang, ZhijieLu, Yukun
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
Devaraj, Sriram SanjeevPark, Jungme
Roller bearings are used in many rotating power transmission systems in the automotive industry. During the assembly process of the power transmission system, some types of roller bearings (e.g., tapered roller bearings) require a compressive preload force. Those bearings' rolling resistance and lifespan strongly depend on the preload set during the installation process. Therefore, accurate setting of the preload can improve bearing efficiency, increase bearing lifespan and reduce maintenance costs over the life of the vehicle. A new method for bearing preload measurement has shown potential for both high accuracy and fast cycle time using the frequency response characteristics of the power transmission system. An open problem is experimental validation of the multi-row tapered roller bearing analytical model. After validation, the analytical model can be used to predict the assembled system damped natural frequency for a desired bearing preload. This work presents the experimental
Gruzwalski, DavidMynderse, James
Items per page:
1 – 50 of 14648