Neural reservoir control of a soft bio-hybrid arm

2025-03-12

AI Summary

Soft-bodied robots present significant challenges for dynamic control due to their highly nonlinear, heterogeneous, anisotropic, and distributed dynamics. To address this, we propose a biologically hybrid arm equipped with tendon-driven actuation and an elastic spinal structure—exhibiting both biomechanical complexity and structural compliance—and introduce a real-time cooperative controller based on spiking neural reservoir computing (RC). Our method is the first to employ spiking neural reservoirs for online self-modeling and task-driven control of such systems, implemented on neuromorphic hardware (e.g., Intel Loihi) for brain-inspired acceleration. Experimental results demonstrate superior performance over conventional artificial neural networks (ANNs) across multiple dynamic manipulation tasks. Moreover, the neuromorphic hardware implementation achieves approximately 100× higher energy efficiency than CPU-based execution, enabling cable-free, miniaturized, and embedded deployment.

Technology Category

• Intelligent Robots: Manipulation
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Bio-inspired Learning

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
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

A long-standing engineering problem, the control of soft robots is difficult because of their highly non-linear, heterogeneous, anisotropic, and distributed nature. Here, bridging engineering and biology, a neural reservoir is employed for the dynamic control of a bio-hybrid model arm made of multiple muscle-tendon groups enveloping an elastic spine. We show how the use of reservoirs facilitates simultaneous control and self-modeling across a set of challenging tasks, outperforming classic neural network approaches. Further, by implementing a spiking reservoir on neuromorphic hardware, energy efficiency is achieved, with nearly two-orders of magnitude improvement relative to standard CPUs, with implications for the on-board control of untethered, small-scale soft robots.

Problem

• Control of soft robots due to non-linear, heterogeneous, anisotropic nature
• Dynamic control of bio-hybrid arm using neural reservoir
• Energy-efficient spiking reservoir for untethered soft robots

Innovation

• Neural reservoir controls soft bio-hybrid arm
• Spiking reservoir enhances energy efficiency
• Outperforms classic neural network approaches