Hierarchical Reinforcement Learning Framework for Adaptive Walking Control Using General Value Functions of Lower-Limb Sensor Signals

TL;DR

This paper presents a hierarchical reinforcement learning approach using general value functions to improve adaptive control in lower-limb exoskeletons, enhancing terrain recognition and decision-making during walking.

Contribution

It introduces a novel HRL framework with GVFs for sensor signal prediction, improving exoskeleton control across varied terrains.

Findings

Adding GVF predictions increased network accuracy.

Terrain-specific performance improved with predictive signals.

Predictive information aids decision-making under uncertainty.

Abstract

Rehabilitation technology is a natural setting to study the shared learning and decision-making of human and machine agents. In this work, we explore the use of Hierarchical Reinforcement Learning (HRL) to develop adaptive control strategies for lower-limb exoskeletons, aiming to enhance mobility and autonomy for individuals with motor impairments. Inspired by prominent models of biological sensorimotor processing, our investigated HRL approach breaks down the complex task of exoskeleton control adaptation into a higher-level framework for terrain strategy adaptation and a lower-level framework for providing predictive information; this latter element is implemented via the continual learning of general value functions (GVFs). GVFs generated temporal abstractions of future signal values from multiple wearable lower-limb sensors, including electromyography, pressure insoles, and goniometers. We investigated two methods for incorporating actual and predicted sensor signals into a policy network with the intent to improve the decision-making capacity of the control system of a lower-limb exoskeleton during ambulation across varied terrains. As a key result, we found that the addition of predictions made from GVFs increased overall network accuracy. Terrain-specific performance increases were seen while walking on even ground, uneven ground, up and down ramps, and turns, terrains that are often misclassified without predictive information. This suggests that predictive information can aid decision-making during uncertainty, e.g., on terrains that have a high chance of being misclassified. This work, therefore, contributes new insights into the nuances of HRL and the future development of exoskeletons to facilitate safe transitioning and traversing across different walking environments.