Using Simulation to Design Path Following and Obstacle Avoidance Policies for Autonomous Robots

EasyChair Preprint 13296

Abstract

This study explores the development of neural network-based control policies for autonomous robots, focusing on path following and obstacle avoidance. Utilizing the Autonomy Research Testbed (ART) and the Chrono simulation engine, we crafted two control strategies: an end-to-end imitation learning policy and a hybrid policy combining path following with a value function-based obstacle controller. Preliminary simulations validate both approaches, highlighting their respective efficiencies in managing complex navigation tasks. Future efforts will address transferring these policies to real vehicles, emphasizing the reduction of the sim-to-real performance gap.

Keyphrases: Autonomy Policy Design, Autonomy Simulator, Sim2Real

@booklet{EasyChair:13296,
  author    = {Harry Zhang and Stefan Caldararu and Alexis Ruiz and Huzaifa Unjhawala and Nevindu Batagoda and Ishaan Mahajan and Sriram Ashokkumar and Jason Zhou and Aaron Young and Dan Negrut},
  title     = {Using Simulation to Design Path Following and Obstacle Avoidance Policies for Autonomous Robots},
  howpublished = {EasyChair Preprint 13296},
  year      = {EasyChair, 2024}}