Evaluating the Sim-to-Real Transferability of End-to-End Control Policies for Autonomous Vehicles Operating on Deformable Terrains

EasyChair Preprint no. 13294

Abstract

We report on the transfer of an end-to-end control policy synthesized in simulation to a real-world set-ting. The policy guides a 1/6th scale vehicle, named ART-B, to a target location while navigating aroundobstacles with the aid of a 2D Lidar and GPS sensor. We utilize Gym-Chrono, a ReinforcementLearning (RL) environment based on the Project Chrono simulator, and the Open AI Gymnasium frame-work to synthesize this control policy trained using the Proximal Policy Optimization (PPO) algorithm.The approach involves training three versions of the policy: one for guiding ART-B across flat-rigid ter-rain, another for hilly-rigid terrain, and a third for hilly-deformable terrain. Subsequently, each policy will be tested in a real-world scenario with deformable terrain to answer the underlying research question– Does training an end-to-end control policy in a simulated setting with deformable terrain enhance itseffectiveness in real-world applications?

Keyphrases: autonomous vehicles, Reinforcement Learning, Robotics, Sim-to-Real gap, Terrain modelling

@Booklet{EasyChair:13294,
  author = {Huzaifa Unjhawala and Zhenhao Zhou and Ishaan Mahajan and Harry Zhang and Alexis Ruiz and Radu Serban and Dan Negrut},
  title = {Evaluating the Sim-to-Real Transferability of End-to-End Control Policies for Autonomous Vehicles Operating on Deformable Terrains},
  howpublished = {EasyChair Preprint no. 13294},

  year = {EasyChair, 2024}}