End-to-end Lidar-Driven Reinforcement Learning for Autonomous Racing

TL;DR

This paper presents an end-to-end reinforcement learning approach that uses raw lidar and velocity data to train an autonomous racing agent in simulation, which is then tested in real-world scenarios, demonstrating feasibility and benefits.

Contribution

It introduces a novel RL framework that directly utilizes raw lidar data for autonomous racing, bridging simulation and real-world application without relying on prior maps.

Findings

RL agent successfully navigates real-world racing environment

Raw lidar data suffices for effective autonomous racing decisions

Simulation-trained model generalizes well to real-world scenarios

Abstract

Reinforcement Learning (RL) has emerged as a transformative approach in the domains of automation and robotics, offering powerful solutions to complex problems that conventional methods struggle to address. In scenarios where the problem definitions are elusive and challenging to quantify, learning-based solutions such as RL become particularly valuable. One instance of such complexity can be found in the realm of car racing, a dynamic and unpredictable environment that demands sophisticated decision-making algorithms. This study focuses on developing and training an RL agent to navigate a racing environment solely using feedforward raw lidar and velocity data in a simulated context. The agent's performance, trained in the simulation environment, is then experimentally evaluated in a real-world racing scenario. This exploration underlines the feasibility and potential benefits of RL algorithm enhancing autonomous racing performance, especially in the environments where prior map information is not available.