Agile Off-Road Autonomous Driving Using End-to-End Deep Imitation Learning

By Yunpeng Pan, Ching-An Cheng, Kamil Saigol, Keuntaek Lee, Xinyan Yan, Evangelos A. Theodorou, Byron Boots. 2017

54 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Automotive Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Sergey Levine
2. Byron Boots
3. Pieter Abbeel
4. J. Bagnell
5. Chelsea Finn
6. Ching-An Cheng
7. Jan Peters
8. Wen Sun

In Automotive Engineering

1. Byron Boots
2. Keuntaek Lee
3. Ching-An Cheng
4. Kamil Saigol
5. Dieter Fox
6. Evangelos A. Theodorou
7. J. Bagnell

Citations in the corpus

• Agile Autonomous Driving using End-to-End Deep Imitation Learning (2017, background): “in which cpos favors the vehicle to stay in the middle of the track, cspd drives the vehicle to reach the desired speed, cslip stabilizes the car from slipping, and cact inhibits large control commands (see [21] for details).”
• Truncated Horizon Policy Search: Combining Reinforcement Learning & Imitation Learning (2018, background): “, 2016) or via access to a simulator using Dynamic Programming (DP) techniques (Choudhury et al., 2017; Pan et al., 2017).”
• Neural Autonomous Navigation with Riemannian Motion Policy (2019, background): “An alternative scheme is to train an end-to-end network [16], [17], [18] that directly outputs the control commands.”
• A survey of deep learning techniques for autonomous driving (2019, methodology): “…2017; Z. Yang, Zhou, Li, & Wang, 2017b) and model predictive control (MPC; Drews, Williams, Goldfain, Theodorou, & Rehg, 2017; Lefevre, Carvalho, & Borrelli, 2015; Lefèvre, Carvalho, & Borrelli, 2016; Ostafew et al., 2015, 2016; Pan et al., 2018, 2017; Rosolia, Carvalho, & Borrelli, 2017).”
• Combining Optimal Control and Learning for Visual Navigation in Novel Environments (2019, unknown): “Other works such as that from Levine et al. [26] and Pan et al. [34] combine optimal control and end-to-end learning, by training neural network policies to mimic the output control values based on the raw images.”
• Convergence of Value Aggregation for Imitation Learning (2018, background): “In this case, it can be shown that CR(x) F (x, x) for some C > 0 (usually C > 1) (Pan et al., 2017).”
• Fast Policy Learning through Imitation and Reinforcement (2018, background): “This can lead to prohibitive cost and slow convergence when applied to real-world problems, such as those found in robotics (Pan et al., 2017).”