Continual Learning from Simulated Interactions via Multitask Prospective Rehearsal for Bionic Limb Behavior Modeling

TL;DR

This paper presents a continual learning model for bionic limb behavior prediction that uses multitask prospective rehearsal to adaptively improve movement synthesis across diverse locomotion tasks, validated on real-world gait data.

Contribution

It introduces a novel multitask prospective rehearsal technique within an evolving architecture for adaptive bionic limb control, addressing challenges of distributional shifts and noise.

Findings

Outperforms baseline models in real-world gait datasets

Effective in scenarios with distributional shifts and adversarial noise

Demonstrates scalable, task-specific adaptation for bionic prosthesis control

Abstract

Lower limb amputations and neuromuscular impairments severely restrict mobility, necessitating advancements beyond conventional prosthetics. While motorized bionic limbs show promise, their effectiveness depends on replicating the dynamic coordination of human movement across diverse environments. In this paper, we introduce a model for human behavior in the context of bionic prosthesis control. Our approach leverages human locomotion demonstrations to learn the synergistic coupling of the lower limbs, enabling the prediction of the kinematic behavior of a missing limb during tasks such as walking, climbing inclines, and stairs. We propose a multitasking, continually adaptive model that anticipates and refines movements over time. At the core of our method is a technique called multitask prospective rehearsal, that anticipates and synthesizes future movements based on the previous prediction and employs a corrective mechanism for subsequent predictions. Our evolving architecture merges lightweight, task-specific modules on a shared backbone, ensuring both specificity and scalability. We validate our model through experiments on real-world human gait datasets, including transtibial amputees, across a wide range of locomotion tasks. Results demonstrate that our approach consistently outperforms baseline models, particularly in scenarios with distributional shifts, adversarial perturbations, and noise.