Field-programmable dynamics in a soft magnetic actuator enabling true random number generation and reservoir computing

2025-11-28

AI Summary

Conventional soft robot design avoids complex or chaotic dynamics to prevent wear and loss of control. Method: This work introduces a programmable soft magnetic actuator that leverages external magnetic fields to modulate the dynamic response of elastomer composites, enabling, for the first time, stable exploitation of chaos and stochastic dynamics in soft systems. The actuator exhibits exceptional durability (>10⁵ cycles without fatigue) and supports physical-layer stochastic computing and temporal signal processing. Contribution/Results: We establish a physical reservoir computing framework based on this actuator, demonstrating true random number generation, Mackey–Glass time-series prediction, and real-world intelligent interaction tasks—including biomimetic blinking and speech stochastic modulation. This work breaks the longstanding reliance of soft robotics on deterministic, ordered motion, opening a new paradigm for harnessing complex dynamics to enable non-von Neumann computing architectures and life-like behavioral autonomy.

Technology Category

• Intelligent Robots: Cognitive Robotics
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

Complex and even chaotic dynamics, though prevalent in many natural and engineered systems, has been largely avoided in the design of electromechanical systems due to concerns about wear and controlability. Here, we demonstrate that complex dynamics might be particularly advantageous in soft robotics, offering new functionalities beyond motion not easily achievable with traditional actuation methods. We designed and realized resilient magnetic soft actuators capable of operating in a tunable dynamic regime for tens of thousands cycles without fatigue. We experimentally demonstrated the application of these actuators for true random number generation and stochastic computing. {W}e validate soft robots as physical reservoirs capable of performing Mackey--Glass time series prediction. These findings show that exploring the complex dynamics in soft robotics would extend the application scenarios in soft computing, human-robot interaction and collaborative robots as we demonstrate with biomimetic blinking and randomized voice modulation.

Problem

• Exploring complex dynamics in soft magnetic actuators for new functionalities
• Enabling true random number generation and reservoir computing capabilities
• Extending soft robotics applications to computing and human-robot interaction

Innovation

• Soft magnetic actuators with tunable dynamic regime
• True random number generation using chaotic dynamics
• Physical reservoir computing for time series prediction