Research/ PLANETARY ROBOTICS
Behavioral Repertoires for Soft Tensegrity Robots
Kyle Doney, Aikaterini Petridou, Jacob Karaul, Ali Khan, Geoffrey Liu, John Rieffel
Learning-based MethodsOpenAlex topic: Reinforcement Learning in Robotics · Design, Mechanisms & HardwareOpenAlex topic: Soft Robotics and Applications · Surface Mobility & TerramechanicsOpenAlex topic: Robotic Locomotion and Control
arXivcs.RO · cs.AIOpenAlexSoft Robotics and Applications · Robotic Locomotion and Control · Reinforcement Learning in Robotics
Mobile soft robots offer compelling applications in fields ranging from urban search and rescue to planetary exploration. A critical challenge of soft robotic control is that the nonlinear dynamics imposed by soft materials often result in complex behaviors that are counterintuitive and hard to model or predict. As a consequence, most behaviors for mobile soft robots are discovered through empirical trial and error and hand-tuning. A second challenge is that soft materials are difficult to simulate with high fidelity -- leading to a significant reality gap when trying to discover or optimize new behaviors. In this work we employ a Quality Diversity Algorithm running model-free on a physical soft tensegrity robot that autonomously generates a behavioral repertoire with no a priori knowledge of the robot dynamics, and minimal human intervention. The resulting behavior repertoire displays a diversity of unique locomotive gaits useful for a variety of tasks. These results help provide a road map for increasing the behavioral capabilities of mobile soft robots through real-world automation.
Comments: 7 pages, 6 figures, accepted, IEEE SSCI2020