Reinforcement Learning-Based Model Matching in COBRA, a Slithering Snake Robot

TL;DR

This paper introduces a reinforcement learning-based method to improve the dynamic model accuracy of the COBRA snake robot, reducing the sim-to-real gap through iterative parameter refinement validated on hardware.

Contribution

It presents a novel reinforcement learning approach for model identification that enhances the fidelity of snake robot dynamics models.

Findings

Improved model accuracy through RL-based parameter tuning

Successful validation on COBRA hardware platform

Potential to reduce sim-to-real gap in snake robot control

Abstract

This work 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.