Hitting the Gym: Reinforcement Learning Control of Exercise-Strengthened Biohybrid Robots in Simulation

TL;DR

This paper demonstrates how reinforcement learning can control and optimize biohybrid robots with adaptable muscle actuators, enabling improved task performance and design insights in simulation.

Contribution

It introduces a reinforcement learning framework for controlling and co-designing adaptive muscle-based biohybrid robots, addressing the challenge of changing muscle force output over time.

Findings

Adaptive agents outperform non-adaptive agents in reward and training time.

Reinforcement learning effectively coordinates multiple muscles for target reaching.

The approach aids in understanding muscle importance for specific tasks.

Abstract

Animals can accomplish many incredible behavioral feats across a wide range of operational environments and scales that current robots struggle to match. One explanation for this performance gap is the extraordinary properties of the biological materials that comprise animals, such as muscle tissue. Using living muscle tissue as an actuator can endow robotic systems with highly desirable properties such as self-healing, compliance, and biocompatibility. Unlike traditional soft robotic actuators, living muscle biohybrid actuators exhibit unique adaptability, growing stronger with use. The dependency of a muscle's force output on its use history endows muscular organisms the ability to dynamically adapt to their environment, getting better at tasks over time. While muscle adaptability is a benefit to muscular organisms, it currently presents a challenge for biohybrid researchers: how does one design and control a robot whose actuators' force output changes over time? Here, we incorporate muscle adaptability into a many-muscle biohybrid robot design and modeling tool, leveraging reinforcement learning as both a co-design partner and system controller. As a controller, our learning agents coordinated the independent contraction of 42 muscles distributed on a lattice worm structure to successfully steer it towards eight distinct targets while incorporating muscle adaptability. As a co-design tool, our agents enable users to identify which muscles are important to accomplishing a given task. Our results show that adaptive agents outperform non-adaptive agents in terms of maximum rewards and training time. Together, these contributions can both enable the elucidation of muscle actuator adaptation and inform the design and modeling of adaptive, performant, many-muscle robots.