Towards Data-Driven Adaptive Exoskeleton Assistance for Post-stroke Gait

Recent work has shown that exoskeletons controlled through data-driven methods can dynamically adapt assistance to various tasks for healthy young adults. However, applying these methods to populations with neuromotor gait deficits, such as post-stroke hemiparesis, is challenging. This is due not only to high population heterogeneity and gait variability but also to a lack of post-stroke gait datasets to train accurate models. Despite these challenges, data-driven methods offer a promising avenue for control, potentially allowing exoskeletons to function safely and effectively in unstructured community settings. This work presents a first step towards enabling adaptive plantarflexion and dorsiflexion assistance from data-driven torque estimation during post-stroke walking. We trained a multi-task Temporal Convolutional Network (TCN) using collected data from four post-stroke participants walking on a treadmill ($R^2$ of $0.74 \pm 0.13$). The model uses data from three inertial measurement units (IMU) and was pretrained on healthy walking data from 6 participants. We implemented a wearable prototype for our ankle torque estimation approach for exoskeleton control and demonstrated the viability of real-time sensing, estimation, and actuation with one post-stroke participant.

Point Cloud Context Analysis for Rehabilitation Grasping Assistance

Controlling hand exoskeletons for assisting impaired patients in grasping tasks is challenging because it is difficult to infer user intent. We hypothesize that majority of daily grasping tasks fall into a small set of categories or modes which can be inferred through real-time analysis of environmental geometry from 3D point clouds. This paper presents a low-cost, real-time system for semantic image labeling of household scenes with the objective to inform and assist activities of daily living. The system consists of a miniature depth camera, an inertial measurement unit and a microprocessor. It is able to achieve 85% or higher accuracy at classification of predefined modes while processing complex 3D scenes at over 30 frames per second. Within each mode it can detect and localize graspable objects. Grasping points can be correctly estimated on average within 1 cm for simple object geometries. The system has potential applications in robotic-assisted rehabilitation as well as manual task assistance.

Explaining Bayesian Optimization by Shapley Values Facilitates Human-AI Collaboration

Bayesian optimization (BO) with Gaussian processes (GP) has become an indispensable algorithm for black box optimization problems. Not without a dash of irony, BO is often considered a black box itself, lacking ways to provide reasons as to why certain parameters are proposed to be evaluated. This is particularly relevant in human-in-the-loop applications of BO, such as in robotics. We address this issue by proposing ShapleyBO, a framework for interpreting BO's proposals by game-theoretic Shapley values.They quantify each parameter's contribution to BO's acquisition function. Exploiting the linearity of Shapley values, we are further able to identify how strongly each parameter drives BO's exploration and exploitation for additive acquisition functions like the confidence bound. We also show that ShapleyBO can disentangle the contributions to exploration into those that explore aleatoric and epistemic uncertainty. Moreover, our method gives rise to a ShapleyBO-assisted human machine interface (HMI), allowing users to interfere with BO in case proposals do not align with human reasoning. We demonstrate this HMI's benefits for the use case of personalizing wearable robotic devices (assistive back exosuits) by human-in-the-loop BO. Results suggest human-BO teams with access to ShapleyBO can achieve lower regret than teams without.