In order to improve trajectory tracking accuracy, a reinforcement learning method was employed to address the trajectory tracking task in autonomous driving. There are many conveniences and advantages in theories, methods and tools utilizing reinforcement learning to solve trajectory tracking control problems. To teach an intelligent agent effective driving skills, the structured road information in the urban environment was extracted to generate an accurate reference trajectory. Then real-world scenarios were modeled to build a simulation environment for training. To effectively train the intelligent driving agent, Imitation Learning was firstly employed to teach the agent primary driving skills. Afterwards, Reinforcement Learning was adopted to optimize the agent’s driving policy. After the intelligent driving agent was well trained in the simulator, the tracking experiments were conducted in the simulator and the real-world scenarios. The proposed method was compared with base-line methods of geometric tracking, optimization-based tracking and learning-based tracking. The experimental results demonstrated that Reinforcement-Tracking can achieve accurate trajectory tracking performance and even exceed the accuracy of most baseline methods.
Reinforcement-Tracking: An Effective Trajectory Tracking and Navigation Method for Autonomous Urban Driving
IEEE Transactions on Intelligent Transportation Systems ; 23 , 7 ; 6991-7007
2022-07-01
4154440 byte
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Complex Trajectory Tracking Using PID Control for Autonomous Driving
Springer Verlag | 2020
|Autonomous driving vehicle trajectory planning and tracking control method considering active safety
Europäisches Patentamt | 2023
|British Library Conference Proceedings | 2015
|Autonomous automobile guidance and trajectory-tracking
Europäisches Patentamt | 2022
|Trajectory-Tracking Control for Autonomous Driving Considering Its Stability with ESP
SAE Technical Papers | 2018
|