Predictive safety filter enhanced curriculum learning control for efficient vehicle dynamics controller
2026-08-10 • Robotics
RoboticsArtificial Intelligence
AI summaryⓘ
The authors focus on improving vehicle control by combining learning-based methods with physics-based safety checks to make driving safer and more reliable. They use a step-by-step learning approach, called curriculum learning, along with a safety filter that predicts and prevents risky moves. Tested on a simulation platform, their method showed better performance and could handle different driving situations more effectively than previous approaches. This means their controller can manage vehicle stability and agility with less manual tuning. Overall, the authors aim to balance safety and performance in vehicle control using both learning and physics insights.
learning-based controlcurriculum learningphysics-based safety filtervehicle dynamicsmotion controlPython-CarSimstabilityagilitystate-based controlparameter calibration
Authors
Baocong Zhang, Siliang Lu, Chenyang Li
Abstract
Recent advances in learning-based control have enabled impressive achievements in solving complex control problems in various domains. However, since learning-based control may not be able to realize safety-guaranties, it is of great importance to enhance safety and robustness while maintaining good performances. Take vehicle motion \& dynamics control as an example, in order to overcome the pain points of traditional methods such as heavy parameter calibration effort and learning-based control to bring better performance and efficiency in stability \& agility over prior work for state-based vehicle control tasks, in this work, our method aims to develop a curriculum learning controller enhanced with physics-based predictive safety filter. The validation is conducted with the Python-CarSim platform, demonstrating better improvements and scalability under various maneuvers.