A Champion-Level Vision-Based Reinforcement Learning Agent for Competitive Racing in Gran Turismo 7
- 14 April 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (6) , 5545-5552
Abstract
Deep reinforcement learning has achieved superhuman racing performance in high-fidelity simulators like Gran Turismo 7 (GT7). It typically utilizes global features that require instrumentation external to a car, such as precise localization of agents and opponents, limiting real-world applicability. To address this limitation, we introduce a vision-based autonomous racing agent that relies solely on ego-centric camera views and onboard sensor data, eliminating the need for precise localization during inference. This agent employs an asymmetric actor-critic framework: the actor uses a recurrent neural network with the sensor data local to the car to retain track layouts and opponent positions, while the critic accesses the global features during training. Evaluated in GT7, our agent consistently outperforms GT7's built-drivers. To our knowledge, this work presents the first vision-based autonomous racing agent to demonstrate champion-level performance in competitive racing scenarios.Keywords
All Related Versions
This publication has 26 references indexed in Scilit:
- Learning Model Predictive Control with Error Dynamics Regression for Autonomous Racing2024
- Adaptive Planning and Control with Time-Varying Tire Models for Autonomous Racing Using Extreme Learning Machine2024
- Outracing champion Gran Turismo drivers with deep reinforcement learningNature, 2022
- Learn-to-Race: A Multimodal Control Environment for Autonomous Racing2021
- Autonomous Overtaking in Gran Turismo Sport Using Curriculum Reinforcement Learning2021
- Vehicle Odometry with Camera-Lidar-IMU Information Fusion and Factor-Graph OptimizationJournal of Intelligent & Robotic Systems, 2021
- End-to-End Race Driving with Deep Reinforcement Learning2018
- MuJoCo: A physics engine for model-based control2012
- Wiley Series in Probability and Statistics2008
- Backpropagation through time: what it does and how to do itProceedings of the IEEE, 1990