Application of Reinforcement Learning in the Autonomous Driving Platform of the DeepRacer

• Published in: Chinese Control Conference pp. 5345 - 5352
• Main Authors: Zhu, Wenjie, Du, Haikuo, Zhu, Moyan, Liu, Yanbo, Lin, Chaoting, Wang, Shaobo, Sun, Weiqi, Yan, Huaming
• Format: Conference Proceeding
• Language: English
• Published: Technical Committee on Control Theory, Chinese Association of Automation 25.07.2022
• Subjects: Action space; Amazon's cloud platform; Analytical models; Autonomous driving; Cloud computing; Data models; Path planning; Reinforcement learning; Sarsa; Training; Web services
• ISSN: 1934-1768
• DOI: 10.23919/CCC55666.2022.9902325

This article revolves around autonomous driving, mainly introducing the autonomous driving cloud platform based on the reinforcement learning to improve the autonomous driving of the car on the Deep Racer using the AWS (Amazon Web Service). Applying the sample codes provided by the DeepRacer platform, the training and completion of the car requires a long time. Therefore, we applied path planning into DeepRacer based on reinforcement learning. Several breakthroughs have been shown as follows: The formulation and solution of RL are completed on DeepRacer. The model of vehicle is simplified as the bicycle and thus reality gap between perception and joints was narrowed. A novel system framework VNARM(Vehicle Network Autonomous Racing Model) is introduced. Reward functions were set properly for tracing in RL. The vehicle's performance of finishing one lap is increased from nearly 30 seconds to less than 9 seconds, while maintaining a high percentage of completion.