Data-Driven Predictive Control for Robust Exoskeleton Locomotion

TL;DR

This paper presents a data-driven predictive control framework for exoskeletons that improves robustness and adaptability in walking gait generation, validated through simulations and hardware experiments with payload variations.

Contribution

It introduces a multi-layer DDPC approach using Hankel matrices and a state transition matrix for adaptive gait planning in exoskeletons, outperforming traditional MPC methods.

Findings

Enables robust walking at various velocities.

Adapts to different users and payloads effectively.

Outperforms model predictive control in tests.

Abstract

Exoskeleton locomotion must be robust while being adaptive to different users with and without payloads. To address these challenges, this work introduces a data-driven predictive control (DDPC) framework to synthesize walking gaits for lower-body exoskeletons, employing Hankel matrices and a state transition matrix for its data-driven model. The proposed approach leverages DDPC through a multi-layer architecture. At the top layer, DDPC serves as a planner employing Hankel matrices and a state transition matrix to generate a data-driven model that can learn and adapt to varying users and payloads. At the lower layer, our method incorporates inverse kinematics and passivity-based control to map the planned trajectory from DDPC into the full-order states of the lower-body exoskeleton. We validate the effectiveness of this approach through numerical simulations and hardware experiments conducted on the Atalante lower-body exoskeleton with different payloads. Moreover, we conducted a comparative analysis against the model predictive control (MPC) framework based on the reduced-order linear inverted pendulum (LIP) model. Through this comparison, the paper demonstrates that DDPC enables robust bipedal walking at various velocities while accounting for model uncertainties and unknown perturbations.