End-to-end Lidar-Driven Reinforcement Learning for Autonomous Racing
It addresses autonomous racing for robotics applications, but is incremental as it applies existing RL methods to a specific domain with simulation-to-real transfer.
This study tackled the problem of autonomous car racing in dynamic environments by developing a reinforcement learning agent that uses raw lidar and velocity data without prior maps, achieving successful experimental evaluation in real-world scenarios.
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.