Imitation learning for agile autonomous driving. (March 2020)

• Record Type: Journal Article
• Authors: Pan, Yunpeng; Cheng, Ching-An; Saigol, Kamil; Lee, Keuntaek; Yan, Xinyan; Theodorou, Evangelos A; Boots, Byron
• Is Part Of: International journal of robotics research. Volume 39:Number 2/3(2020)
• Page Start: 286
• Page End: 302
• Publication Date: 2020-03
• Subjects: Imitation learning -- autonomous driving -- control; Robots -- Periodicals; Robots, Industrial -- Periodicals; 629.89205
• DOI: 10.1177/0278364919880273
• Languages: English
• ISSNs: 0278-3649

Abstract

We present an end-to-end imitation learning system for agile, off-road autonomous driving using only low-cost on-board sensors. By imitating a model predictive controller equipped with advanced sensors, we train a deep neural network control policy to map raw, high-dimensional observations to continuous steering and throttle commands. Compared with recent approaches to similar tasks, our method requires neither state estimation nor on-the-fly planning to navigate the vehicle. Our approach relies on, and experimentally validates, recent imitation learning theory. Empirically, we show that policies trained with online imitation learning overcome well-known challenges related to covariate shift and generalize better than policies trained with batch imitation learning. Built on these insights, our autonomous driving system demonstrates successful high-speed off-road driving, matching the state-of-the-art performance.