Reinforcement Learning-Based Model Matching to Reduce the Sim-Real Gap in COBRA

TL;DR

This paper introduces a reinforcement learning-based method to improve the accuracy of a snake robot’s dynamic model, reducing the sim-to-real gap through iterative optimization and experimental validation.

Contribution

It presents a novel reinforcement learning approach for model identification that enhances simulation accuracy for snake robots, addressing the sim-to-real gap.

Findings

Improved model accuracy demonstrated on COBRA robot

Effective reduction of sim-to-real gap in experiments

Reinforcement learning enhances dynamical parameter estimation

Abstract

This paper employs a reinforcement learning-based model identification method aimed at enhancing the accuracy of the dynamics for our snake robot, called COBRA. Leveraging gradient information and iterative optimization, the proposed approach refines the parameters of COBRA's dynamical model such as coefficient of friction and actuator parameters using experimental and simulated data. Experimental validation on the hardware platform demonstrates the efficacy of the proposed approach, highlighting its potential to address sim-to-real gap in robot implementation.