RBE PhD Dissertation Proposal: Xuan Liu | Intelligent Control of Soft Snake Robot Locomotion with Biomimic Vertebrate System

Friday, September 1, 2023
2:00 p.m. to 4:00 p.m.
Preview

RBE Robot Lineup

RBE PhD Dissertation Proposal

Xuan Liu

Intelligent Control of Soft Snake Robot Locomotion with Biomimic Vertebrate System

September 1st, 2023

2:00 PM - 4:00 PM

Zoom Link: https://us06web.zoom.us/j/3823211640

Abstract: RIntelligent control of soft robots is challenging due to the nonlinear and difficult-to-model dynamics. One promising model-free approach for soft robot control is reinforcement learning (RL). However, model-free RL methods tend to be computationally expensive and data-inefficient and may not yield natural and smooth locomotion patterns for soft robots. In this dissertation proposal, I will present a bioinspired design of a learning-based goal-tracking controller for a soft snake robot. The controller is composed of two modules: An RL module for learning goal-tracking behaviors given the unmodeled and stochastic dynamics of the robot, and a central pattern generator (CPG) with the Matsuoka oscillators for generating stable and diverse locomotion patterns. To show the advantage of the controller, I will present our theoretical investigation on the maneuverability of Matsuoka CPG’s oscillation bias, frequency, and amplitude for steering control, velocity control, and sim-to-real adaptation of the soft snake robot respectively. Based on this analysis, this work proposed a composition of RL and CPG modules such that the RL module regulates the tonic inputs to the CPG system given state feedback from the robot, and the output of the CPG module is then transformed into pressure inputs to pneumatic actuators of the soft snake robot. This design allows the RL agent to naturally learn to entrain the desired locomotion patterns determined by the CPG maneuverability. The optimality and robustness of the control design in both simulation and reality are thoroughly validated. Furthermore, the generality of the proposed work is addressed by testing the controller on different robots’ locomotion tasks and running extensive comparisons with state-of-art RL methods on the soft snake robot locomotion task. At the end of this presentation, the ongoing progress for the contact-aware soft snake robot locomotion will also be briefly presented.

Advisor:

Professor Jie Fu, University of Florida

Committee: 

Professor Cagdas Onal, Worcester Polytechnic Institute (WPI)

Professor  Carlo Pinciroli, Worcester Polytechnic Institute (WPI)

Professor Ming Luo, Washington State University (WSU)