Simulation of Adaptive Running with Flexible Sports Prosthesis using Reinforcement Learning of Hybrid-link System

2026-04-10

AI Summary

This study addresses the limitations of trial-and-error–based prosthetic design for transtibial amputees and the lack of personalized dynamic simulation by proposing a whole-body dynamics simulation framework that integrates a hybrid linkage system with a piecewise-constant strain model. This approach enables, for the first time, coupled modeling of compliant prostheses and human locomotion. Leveraging motion-capture–driven imitation learning and reinforcement learning, the method supports adaptive running simulations tailored to individual users’ preferred prosthetic stiffness and incorporates metabolic cost of transport as a performance metric. Experiments successfully replicated amputee running behaviors across varying stiffness levels, revealing the impact of prosthetic stiffness on locomotor efficiency and demonstrating the framework’s feasibility for personalized prosthetic evaluation and optimization in virtual environments.

Technology Category

Cognitive Modeling & Cognitive Systems: Simulating Human BehaviorSearch and Optimization: Sampling/Simulation-based SearchIntelligent Robots: Manipulation

Application Category

User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systemsEconomics, Online Markets and Human Computation: Cost models of using LLMs in production systemsWeb Mining and Content Analysis: Web data generation and simulation

Abstract

This study proposes a reinforcement learning-based adaptive running motion simulation for a unilateral transtibial amputee with the flexibility of a leaf-spring-type sports prosthesis using hybrid-link system. The design and selection of sports prostheses often rely on trial and error. A comprehensive whole-body dynamics analysis that considers the interaction between human motion and prosthetic deformation could provide valuable insights for user-specific design and selection. The hybrid-link system facilitates whole-body dynamics analysis by incorporating the Piece-wise Constant Strain model to represent the flexible deformation of the prosthesis. Based on this system, the simulation methodology generates whole-body dynamic motions of a unilateral transtibial amputee through a reinforcement learning-based approach, which combines imitation learning from motion capture data with accurate prosthetic dynamics computation. We simulated running motions under different virtual prosthetic stiffness conditions and analyzed the metabolic cost of transport obtained from the simulations, suggesting that variations in stiffness influence running performance. Our findings demonstrate the potential of this approach for simulation and analysis under virtual conditions that differ from real conditions.

Problem

• adaptive running
• flexible prosthesis
• whole-body dynamics
• prosthetic stiffness
• transtibial amputee

Innovation

• reinforcement learning
• hybrid-link system
• flexible prosthesis
• whole-body dynamics
• metabolic cost of transport