Preference-Based Learning for Exoskeleton Gait Optimization

This paper presents a personalized gait optimization framework for lower-body exoskeletons. Rather than optimizing numerical objectives such as the mechanical cost of transport, our approach directly learns from user prefer-ences, e. g. , for comfort. Building upon work in preference-based interactive learning, we present the CoSpar algorithm. CoSpar prompts the user to give pairwise preferences between trials and suggest improvements; as exoskeleton walking is a non-intuitive behavior, users can provide preferences more easily and reliably than numerical feedback. We show that CoSpar performs competitively in simulation and demonstrate a prototype implementation of CoSpar on a lower-body exoskeleton to optimize human walking trajectory features. In the experiments, CoSpar consistently found user-preferred parameters of the exoskeleton’s walking gait, which suggests that it is a promising starting point for adapting and personalizing exoskeletons (or other assistive devices) to individual users.

Authors

• Maegan Tucker
• Ellen R. Novoseller
• Claudia Kann
• Yanan Sui
• Yisong Yue
• Joel W. Burdick
• Aaron D. Ames

Keywords

• Exoskeletons
• Legged locomotion
• Optimization
• Bayes methods
• Reliability
• Trajectory
• Exoskeleton Gait
• Gait Optimization
• Preference-based Learning
• Transportation Costs
• Assistive Technology
• User Preferences
• Walking Gait
• Objective Function
• Human Experience
• Feature Space
• Gaussian Process
• Step Length
• Physical Constraints
• Posterior Mean
• Utility Value
• Numerical Score
• User Feedback
• Dueling
• Laplace Approximation
• Step Width
• Shorter Step Length
• User Comfort
• Metabolic Expenditure
• Synthetic Function
• Dynamic Walking