FastRLAP: A System for Learning High-Speed Driving via Deep RL and Autonomous Practicing

TL;DR

FastRLAP is a system enabling an autonomous RC car to learn aggressive driving from visual observations using reinforcement learning, without simulation or expert demonstrations, achieving human-like performance in under 20 minutes.

Contribution

The paper introduces FastRLAP, a novel RL system that learns high-speed driving directly in the real world with minimal training time and no reliance on simulation or expert data.

Findings

Learns to drive in various racing courses in less than 20 minutes

Achieves aggressive driving behaviors like braking and acceleration timing

Performs comparably to human drivers in first-person driving tasks

Abstract

We present a system that enables an autonomous small-scale RC car to drive aggressively from visual observations using reinforcement learning (RL). Our system, FastRLAP (faster lap), trains autonomously in the real world, without human interventions, and without requiring any simulation or expert demonstrations. Our system integrates a number of important components to make this possible: we initialize the representations for the RL policy and value function from a large prior dataset of other robots navigating in other environments (at low speed), which provides a navigation-relevant representation. From here, a sample-efficient online RL method uses a single low-speed user-provided demonstration to determine the desired driving course, extracts a set of navigational checkpoints, and autonomously practices driving through these checkpoints, resetting automatically on collision or failure. Perhaps surprisingly, we find that with appropriate initialization and choice of algorithm, our system can learn to drive over a variety of racing courses with less than 20 minutes of online training. The resulting policies exhibit emergent aggressive driving skills, such as timing braking and acceleration around turns and avoiding areas which impede the robot's motion, approaching the performance of a human driver using a similar first-person interface over the course of training.