Elastica: A Compliant Mechanics Environment for Soft Robotic Control

• Published in: IEEE robotics and automation letters Vol. 6; no. 2; pp. 3389 - 3396
• Main Authors: Naughton, Noel, Sun, Jiarui, Tekinalp, Arman, Parthasarathy, Tejaswin, Chowdhary, Girish, Gazzola, Mattia
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.04.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; And learning for soft robots; Computational modeling; Context modeling; Continuum mechanics; control; Control methods; Dynamic control; Elastica; Environment models; Flight simulators; Machine learning; Manipulators; Mathematical model; modeling; Modulus of elasticity; reinforcement learning; Robot arms; Robot control; Robot kinematics; Robots; Simulation; simulation and animation; Soft robotics
• ISSN: 2377-3766; 2377-3766
• DOI: 10.1109/LRA.2021.3063698

Soft robots are notoriously hard to control. This is partly due to the scarcity of models and simulators able to capture their complex continuum mechanics, resulting in a lack of control methodologies that take full advantage of body compliance. Currently available methods are either too computational demanding or overly simplistic in their physical assumptions, leading to a paucity of available simulation resources for developing such control schemes. To address this, we introduce Elastica, an open-source simulation environment modeling the dynamics of soft, slender rods that can bend, twist, shear, and stretch. We couple Elastica with five state-of-the-art reinforcement learning (RL) algorithms (TRPO, PPO, DDPG, TD3, and SAC). We successfully demonstrate distributed, dynamic control of a soft robotic arm in four scenarios with both large action spaces, where RL learning is difficult, and small action spaces, where the RL actor must learn to interact with its environment. Training converges in 10 million policy evaluations with near real-time evaluation of learned policies.