Diffusion models create personalized gait paths for wearable robots
Diffusion-Based Generation of Gait Trajectories
Artificial IntelligenceMachine LearningRobotics
Summary
Helping people walk better with wearable devices like robotic legs needs movement patterns that match each person. The authors show new computer models that can generate walking paths based on a person’s step size and other traits. These models create realistic and smooth joint movements unlike older methods that are rigid or slow. Their work tested thousands of walking cycles to see how well the models perform. This approach could lead to better, personalized support from robotic exoskeletons in rehab or daily use.
What this means in practice
- •For exoskeleton developers: Generate adaptive walking joint-angle patterns tailored to individual users to improve exoskeleton movement precision and comfort.$Commercial implications: Enables development of personalized exoskeleton control software that can be sold to manufacturers for better patient outcomes.
- •For rehabilitation device engineers: Create realistic simulated gait data reflecting various patient-specific walking parameters to design and test therapies more efficiently.
Authors
Damian Benasco, Juan Carballeira-Lopez, Jaime Ramos-Rojas, Julio S. Lora-Millan, Antonio J. Del-Ama, David Rodriguez-Cianca, Pablo Lanillos
Abstract
Generation of musculoskeletal gait trajectories conditioned on patient-specific parameters remains a key challenge for wearable robotics and rehabilitation. Assistive systems such as lower-limb exoskeletons require reference trajectories that adapt to individual morphology and therapeutic goals while preserving biomechanical realism. Traditional approaches rely on hand-crafted gait templates or optimization procedures that scale poorly across subjects and walking conditions. In this work, we explore conditional diffusion models for generating lower-limb joint-angle trajectories conditioned on gait parameters such as step length. We compare a baseline transformer diffusion model with a controllable diffusion transformer variant incorporating adaptive normalization and classifier-free guidance. Experiments on a dataset of 4,590 gait cycles show that diffusion models can generate realistic periodic gait trajectories while enabling some controllability variation in gait characteristics, highlighting their potential for personalized gait synthesis in assistive robotics.