DeepRacer: Educational Autonomous Racing Platform for Experimentation with Sim2Real Reinforcement Learning

Abstract

DeepRacer is a platform for end-to-end experimentation with RL and can be used to systematically investigate the key challenges in developing intelligent control systems. Using the platform, we demonstrate how a 1/18th scale car can learn to drive autonomously using RL with a monocular camera. It is trained in simulation with no additional tuning in physical world and demonstrates: 1) formulation and solution of a robust reinforcement learning algorithm, 2) narrowing the reality gap through joint perception and dynamics, 3) distributed on-demand compute architecture for training optimal policies, and 4) a robust evaluation method to identify when to stop training. It is the first successful large-scale deployment of deep reinforcement learning on a robotic control agent that uses only raw camera images as observations and a model-free learning method to perform robust path planning. We open source our code and video demo on GitHub: https://git.io/fjxoJ.

References in corpus (15)

• End to End Learning for Self-Driving Cars
• Trust Region Policy Optimization
• Learning agile and dynamic motor skills for legged robots
• DeepMind Control Suite
• PRIMAL: Pathfinding via Reinforcement and Imitation Multi-Agent Learning
• Robust Adversarial Reinforcement Learning
• Deep Reinforcement Learning that Matters
• Hindsight Experience Replay
• Deep Drone Racing: From Simulation to Reality with Domain Randomization
• Learning Dexterous In-Hand Manipulation
• EPOpt: Learning Robust Neural Network Policies Using Model Ensembles
• Sim-to-Real Robot Learning from Pixels with Progressive Nets
• F1/10: An Open-Source Autonomous Cyber-Physical Platform
• MuSHR: A Low-Cost, Open-Source Robotic Racecar for Education and Research
• Self-driving scale car trained by Deep reinforcement learning

Cited by in corpus (6)

• BayesRace: Learning to race autonomously using prior experience
• Enhancing State Estimator for Autonomous Racing : Leveraging Multi-modal System and Managing Computing Resources
• Sim-To-Real Transfer for Miniature Autonomous Car Racing
• REPAINT: Knowledge Transfer in Deep Reinforcement Learning
• Towards Closing the Sim-to-Real Gap in Collaborative Multi-Robot Deep Reinforcement Learning
• Ubiquitous Distributed Deep Reinforcement Learning at the Edge: Analyzing Byzantine Agents in Discrete Action Spaces