Damage Adaptation in Seconds for Architected Materials

2026-06-15

AI Summary

This work addresses the challenge of rapid autonomous adaptation in soft robots following sudden physical damage—such as cuts or burns—by introducing a real-time, simulation-free self-adaptation method. Leveraging the progressive failure characteristics of structured materials and a low-dimensional discrete damage representation, the approach integrates proprioceptive feedback with a robust ensemble learning algorithm (LEAP), reducing the sample complexity of damage adaptation from exponential to linear for the first time. Validated on a six-degree-of-freedom soft wrist based on Handed Shearing Auxetic (HSA) actuators, the method enables sub-second adaptation in real-world environments, successfully maintaining trajectory tracking performance under diverse unforeseen damages—including cutting, burning, and actuator repair—demonstrating real-time robustness suitable for practical deployment.

Abstract

Adaptation to damages and in-situ physical repairs is essential for long-term robot autonomy, yet challenging outside of narrowly defined and well-anticipated bounds. In this work we proprioceptively adapt to catastrophic damage in soft-actuated systems in under one minute. Architected materials are well equipped for adaptation: actuator failure occurs gradually rather than acutely, and damage can be described in a low-dimensional, discrete coordinate space. Surprisingly, latent damage representations plus a simple yet robust ensemble method is sufficient for adapting to unseen damage in real-time. Moreover, we identify conditions under which exponential sample complexity collapses to linear sample complexity for learned representations of architected materials, a concrete advantage over rigid components or continuum soft mechanisms. We demonstrate LEAP, our method for adaptive proprioception, via a tracing task for a 6DoF soft wrist based on Handed Shearing Auxetic (HSA) actuators. Our algorithm is able to adapt to cuts, burns, and actuator repairs, enabling simulation-free real-time adaptation that is critical for realizing the promise of soft robots outside the lab. Videos and more information are available at https://murpheylab.github.io/leap.

Problem

• damage adaptation
• soft robotics
• architected materials
• proprioception
• real-time adaptation

Innovation

• architected materials
• damage adaptation
• proprioceptive learning
• sample complexity reduction
• soft robotics