Parallelized and Randomized Adversarial Imitation Learning for Safety-Critical Self-Driving Vehicles

TL;DR

This paper introduces RAIL, a novel derivative-free adversarial imitation learning algorithm designed for safe autonomous driving, effectively coordinating multiple ADAS functions in complex highway environments.

Contribution

It presents RAIL, a new randomized adversarial imitation learning method that improves autonomous driving decision-making with multi-ADAS coordination.

Findings

Successfully trains decision makers using LIDAR data in complex highway scenarios.

Achieves desired performance in simulation-based evaluations.

Demonstrates effectiveness of derivative-free adversarial imitation learning.

Abstract

Self-driving cars and autonomous driving research has been receiving considerable attention as major promising prospects in modern artificial intelligence applications. According to the evolution of advanced driver assistance system (ADAS), the design of self-driving vehicle and autonomous driving systems becomes complicated and safety-critical. In general, the intelligent system simultaneously and efficiently activates ADAS functions. Therefore, it is essential to consider reliable ADAS function coordination to control the driving system, safely. In order to deal with this issue, this paper proposes a randomized adversarial imitation learning (RAIL) algorithm. The RAIL is a novel derivative-free imitation learning method for autonomous driving with various ADAS functions coordination; and thus it imitates the operation of decision maker that controls autonomous driving with various ADAS functions. The proposed method is able to train the decision maker that deals with the LIDAR data and controls the autonomous driving in multi-lane complex highway environments. The simulation-based evaluation verifies that the proposed method achieves desired performance.