Bayesian Preference Elicitation: Human-In-The-Loop Optimization of An Active Prosthesis

2026-02-26

AI Summary

This study addresses the limitations of conventional prosthetic tuning, which is time-consuming and relies on metrics that often fail to capture users’ true needs. To overcome this, the authors propose a human-in-the-loop, preference-driven optimization framework that efficiently personalizes a four-parameter prosthetic controller through direct user feedback. The core innovation lies in a novel acquisition function tailored for preference-based multi-objective Bayesian optimization, accompanied by two algorithmic variants: a discrete version (EUBO-LineCoSpar) and a continuous one (BPE4Prost). Experimental results demonstrate that the proposed approach rapidly converges in both simulation and real-world settings, accurately captures user preferences, and significantly enhances biomechanical performance.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Intelligent Robots: Learning & Optimization for ROB
• Humans and AI: Learning Human Values and Preferences

Application Category

• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

Tuning active prostheses for people with amputation is time-consuming and relies on metrics that may not fully reflect user needs. We introduce a human-in-the-loop optimization (HILO) approach that leverages direct user preferences to personalize a standard four-parameter prosthesis controller efficiently. Our method employs preference-based Multiobjective Bayesian Optimization that uses a state-or-the-art acquisition function especially designed for preference learning, and includes two algorithmic variants: a discrete version (\textit{EUBO-LineCoSpar}), and a continuous version (\textit{BPE4Prost}). Simulation results on benchmark functions and real-application trials demonstrate efficient convergence, robust preference elicitation, and measurable biomechanical improvements, illustrating the potential of preference-driven tuning for user-centered prosthesis control.

Problem

• prosthesis tuning
• user preferences
• human-in-the-loop
• preference elicitation
• personalization

Innovation

• Bayesian Preference Elicitation
• Human-in-the-Loop Optimization
• Preference-Based Multiobjective Bayesian Optimization
• Active Prosthesis Tuning
• User-Centered Control