Browse Topic: Trajectory control
Unmanned Underwater Vehicles (UUVs) operate in complex and uncertain environments, which require a suitable controller. While traditional PID controllers are widely used, they often have slow response speed and inadequate disturbance rejection, particularly under complex and uncertain conditions. To overcome these shortcomings, this paper introduces the DDPG-DLPID, an adaptive motion controller, including a Deep Deterministic Policy Gradient (DDPG) reinforcement learning that can acquire the parameters of PID controllers. In this paper, we design two loops: the inner loop handles velocity regulation, and the outer loop handles position and attitude. By using DDPG, the system can efficiently adjust the PID parameters of both loops in real time, allowing it to effectively adapt to environmental changes and achieve optimized requirements. To evaluate the controller, we design the following scenarios, including straight-line and complex path-following tasks. Compared with single-loop PID and dual-loop PID controllers, the proposed DDPGDLPID approach achieves faster response and higher tracking accuracy, while substantially reducing tracking errors under interference conditions. Physical experiments under three conditions-straight-line voyage, attitude maintaining, and depth control-were further carried out to validate the strategy’s real-world applicability. Experimental data confirm that DDPG-DLPID has better performance when compared with both traditional PID and dual-loop PID controllers across all test scenarios.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
This paper presents the design and implementation of a Semi-Autonomous Light Commercial Vehicle (LCV) capable of following a person while performing obstacle avoidance in urban and controlled environments. The LCV leverages its onboard 360-degree view camera, RTK-GNSS, Ultrasonic sensors, and algorithms to independently navigate the environment, avoiding obstacles and maintaining a safe distance from the person it is following. The path planning algorithm described here generates a secondary lateral path originating from the primary driving path to navigate around static obstacles. A Behavior Planner is utilized to decide when to generate the path and avoid obstacles. The primary objective is to ensure safe navigation in environments where static obstacles are prevalent. The LCV's path tracking is achieved using a combination of Pure Pursuit and Proportional-Integral (PI) controllers. The Pure Pursuit controller is utilized as lateral control to follow the generated path, ensuring smooth and accurate path tracking. Additionally, a PI controller is utilized for speed control, maintaining a consistent and safe speed. Multiple tests were conducted in various urban and controlled environments, especially densely-parked city roads, ramps, residential streets to evaluate the LCV's performance. The results demonstrate the LCV's ability to safely avoid parked vehicles showing human-like decision making and motion control, also maintaining a consistent following distance with the lead-person. The solution focuses on slow-speed applications where precision is of utmost priority. Additionally, the application of ultrasonic sensors helped in achieving immediate stops in close proximity scenarios. This system has significant potential for applications in last-mile delivery, logistics, waste management, and urban mobility, offering a versatile solution for safe and efficient navigation in complex environments and narrow roads.
Items per page:
50
1 – 50 of 350