Hybrid Data-Driven Predictive Control for Robust and Reactive Exoskeleton Locomotion Synthesis

TL;DR

This paper presents a hybrid data-driven predictive control framework for exoskeletons that enables robust, reactive, and adaptable bipedal locomotion through real-time planning of foot contact and trajectories.

Contribution

It introduces a novel hybrid control framework combining contact scheduling and trajectory planning using Hankel matrix-based system modeling for exoskeleton locomotion.

Findings

Improved robustness in exoskeleton walking.

Enhanced adaptability to environmental changes.

Effective online replanning demonstrated on Atalante exoskeleton.

Abstract

Robust bipedal locomotion in exoskeletons requires the ability to dynamically react to changes in the environment in real time. This paper introduces the hybrid data-driven predictive control (HDDPC) framework, an extension of the data-enabled predictive control, that addresses these challenges by simultaneously planning foot contact schedules and continuous domain trajectories. The proposed framework utilizes a Hankel matrix-based representation to model system dynamics, incorporating step-to-step (S2S) transitions to enhance adaptability in dynamic environments. By integrating contact scheduling with trajectory planning, the framework offers an efficient, unified solution for locomotion motion synthesis that enables robust and reactive walking through online replanning. We validate the approach on the Atalante exoskeleton, demonstrating improved robustness and adaptability.