WROOM: An Autonomous Driving Approach for Off-Road Navigation

Dvij Rajesh Kalaria, Shreya Sharma, Sarthak Bhagat, Haoru Xue, John Dolan

Keywords: Off-road mobility, Control Barrier Functions, Reinforcement Learning, Sim-to-Real

TL;DR: Reinforcement learning framework for offroad driving

Abstract: Off-road navigation is a challenging problem both at the planning level to get a smooth trajectory and at the control level to avoid flipping over, hitting obstacles, or getting stuck at a rough patch. There have been several recent works using classical approaches involving depth map prediction followed by smooth trajectory planning and using a controller to track it. We design an end-to-end reinforcement learning (RL) system for an autonomous vehicle in off-road environments using a custom-designed simulator in the Unity game engine. We warm start the agent by imitating a rule-based controller and utilize Proximal Policy Optimization (PPO) to improve the policy based on a reward that incorporates Control Barrier Functions (CBF), facilitating the agent's ability to generalize effectively to real-world scenarios. The training involves agents concurrently undergoing domain-randomized trials in various environments. We also propose a novel simulation environment to replicate off-road driving scenarios and deploy our proposed approach on a real buggy RC car.

Submission Number: 16