Advancing physical intelligence for autonomous soft robots

Abstract

Achieving lifelike autonomy remains a long-term aspiration, yet soft robots so far have mostly demonstrated rudimentary physical intelligence that relies on manipulation of external stimuli to generate continuous motion. To realize autonomous physical intelligence (API) capable of self-regulated sensing, decision-making, and actuation, a promising approach is creating nonlinear time-lag feedback embedded within materials, where a constant stimulus elicits delayed responses to enable autonomous motion. This Review explores such feedback mechanisms, traces the evolution of physically intelligent robots, outlines strategies for embedding API in soft robots under diverse environments, and further discusses challenges and future directions beyond simple locomotion.