Adaptive and Resilient Soft Tensegrity Robots
This work addresses the problem of gait design for soft robots, which has relied on hand-designed trial-and-error, offering a more efficient approach for researchers and engineers in robotics.
The paper tackles the challenge of designing and controlling soft robots by introducing an easy-to-assemble tensegrity-based robot that achieves highly dynamic locomotive gaits and resilience to physical damage, using a machine learning algorithm to discover effective gaits with minimal physical trials.
Living organisms intertwine soft (e.g., muscle) and hard (e.g., bones) materials, giving them an intrinsic flexibility and resiliency often lacking in conventional rigid robots. The emerging field of soft robotics seeks to harness these same properties in order to create resilient machines. The nature of soft materials, however, presents considerable challenges to aspects of design, construction, and control -- and up until now, the vast majority of gaits for soft robots have been hand-designed through empirical trial-and-error. This manuscript describes an easy-to-assemble tensegrity-based soft robot capable of highly dynamic locomotive gaits and demonstrating structural and behavioral resilience in the face of physical damage. Enabling this is the use of a machine learning algorithm able to discover effective gaits with a minimal number of physical trials. These results lend further credence to soft-robotic approaches that seek to harness the interaction of complex material dynamics in order to generate a wealth of dynamical behaviors.