Learn to Make Decision with Small Data for Autonomous Driving: Deep Gaussian Process and Feedback Control. (28th August 2020)

• Record Type: Journal Article
• Authors: Fang, Wenqi; Zhang, Shitian; Huang, Hui; Dang, Shaobo; Huang, Zhejun; Li, Wenfei; Wang, Zheng; Sun, Tianfu; Li, Huiyun
• Other Names: Du Yuchuan Academic Editor.
• Is Part Of: Journal of advanced transportation. Volume 2020(2020)
• Publication Date: 2020-08-28
• Subjects: Transportation -- Periodicals; 388.05
• DOI: 10.1155/2020/8495264
• Languages: English
• ISSNs: 0197-6729

Abstract

Abstract : Autonomous driving is a popular and promising field in artificial intelligence. Rapid decision of the next action according to the latest few actions and status, such as acceleration, brake, and steering angle, is a major concern for autonomous driving. There are some learning methods, such as reinforcement learning which automatically learns the decision. However, it usually requires large volume of samples. In this paper, to reduce the sample size, we exploit the deep Gaussian process, where a regression model is trained on small sample datasets and captures the most significant features correctly. Besides, to realize the real-time and close-loop control, we combine the feedback control into the process. Experimental results on the Torcs simulation engine illustrate smooth driving on virtual road which can be achieved. Compared with the amount of training data in deep reinforcement learning, our method uses only 0.34% of its size and obtains similar simulation results. It may be useful for real road tests in the future.