Collaborative Physics-Informed Neural Dynamics Approach for Autonomous Vehicles With Nonconvex Safety-Critical Constraints
- 2 June 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (10) , 16887-16898
Abstract
Increasing complex driving scenarios inevitably expose autonomous vehicles to intricate nonconvex challenges, which are usually simplified or even ignored by current research, leading to accuracy compromises. In this regard, this paper newly constructs a collaborative physics-informed neural dynamics (CPIND) approach to simultaneously tackle the trajectory tracking and safety-critical control problems in autonomous vehicles. Specifically, the proposed CPIND approach consists of a linear quadratic regulator to provide global control inputs for the trajectory tracking task and a safety-critical optimization control scheme with newly established control barrier functions. The constructed optimization control scheme is essentially nonconvex with respect to decision variables to update the local control inputs for the obstacle avoidance task with the highest priority. A theorem is provided to substantiate the convergence of the proposed CPIND approach. At last, a comparative example, an example on the CarSim-Simulink co-simulation platform, and an experiment on the AgileX autonomous driving platform are conducted to verify the effectiveness and preponderance of the proposed CPIND approach. Overall, the proposed CPIND approach enables autonomous vehicles to follow a collision-free trajectory effectively and accurately, offering a promising solution for enhancing the safety and reliability of autonomous vehicles.Keywords
Funding Information
- National Natural Science Foundation of China (62476115, 624B2060)
- Fundamental Research Funds for the Central Universities (lzujbky-2023-ct05, lzujbky-2023-it01)
- Natural Science Foundation of Gansu Province (24JRRA483)
- Gansu Provincial Department of Education: Outstanding Graduate Student "Star of Innovation" Project (2025CXZX-051)
- Supercomputing Center of Lanzhou University
This publication has 46 references indexed in Scilit:
- Improved RRT*-Smart Algorithm for UGV Path Planning in Emergency Rescue Scenarios2024
- LiDAR-Based Online Control Barrier Function Synthesis for Safe Navigation in Unknown EnvironmentsIEEE Robotics and Automation Letters, 2023
- Formation Reconfiguration Control With Collision Avoidance of Nonholonomic Mobile RobotsIEEE Robotics and Automation Letters, 2023
- Global Path Planning of UGVs in Large-Scale Off-Road Environment Based on Improved A-star Algorithm and Quadratic Programming2023
- A Survey on the Control Lyapunov Function and Control Barrier Function for Nonlinear-Affine Control SystemsIEEE/CAA Journal of Automatica Sinica, 2023
- RRT* and Goal-Driven Variable Admittance Control for Obstacle Avoidance in Manual Guidance ApplicationsIEEE Robotics and Automation Letters, 2022
- Convergence-Guaranteed Trajectory Planning for a Class of Nonlinear Systems With Nonconvex State ConstraintsIEEE Transactions on Aerospace and Electronic Systems, 2021
- Comparative Analysis of Control Barrier Functions and Artificial Potential Fields for Obstacle Avoidance2021
- Control Barrier Function Based Quadratic Programs for Safety Critical SystemsIEEE Transactions on Automatic Control, 2016
- An External Active-Set Strategy for Solving Optimal Control ProblemsIEEE Transactions on Automatic Control, 2009