Liangliang Xiang: Data-Driven Gait Biomechanics for Precision Rehabilitation

3 February 2025 – 2 February 2027

Objective
This research aims to develop data-driven models for gait biomechanics to improve precision rehabilitation. By integrating statistical shape modeling, musculoskeletal simulations, and deep reinforcement learning, the project enables personalized gait impairment assessments and optimizes rehabilitation interventions for individuals with neurological and musculoskeletal disorders.

Background
Human gait is a complex biomechanical process influenced by neuromuscular control, skeletal structure, and external factors. Understanding gait abnormalities is essential for designing effective rehabilitation strategies. Traditional gait analysis, relying on motion capture and inverse dynamics, has limitations in scalability, personalization, and real-time applicability.

Recent advancements in artificial intelligence, musculoskeletal modeling, and wearable technology offer new opportunities for precision rehabilitation. Statistical shape modeling enables personalized bone and muscle geometry reconstruction, while deep reinforcement learning facilitates adaptive gait retraining strategies. This research integrates these approaches to develop predictive models that bridge the gap between clinical gait analysis and real-world rehabilitation applications.

About the Digital Futures Postdoc Fellow
Liangliang Xiang is a researcher in biomechanics and computational modeling. He holds a PhD in Bioengineering from the Auckland Bioengineering Institute, University of Auckland. His research focuses on gait biomechanics, musculoskeletal modeling, and explainable AI for movement analysis. He has developed predictive models for bone stress in running, integrated wearable sensors into biomechanical simulations, and applied deep learning for human movement analysis. He focuses on translating computational biomechanics into practical applications for gait rehabilitation.

Main supervisor
Elena Gutierrez Farewik, Professor, Department of Engineering Mechanics, KTH

Co-supervisor
Ruoli Wang, Assistant Professor, Department of Engineering Mechanics, KTH

Host