analiza aiqbench
This study applies conditional diffusion models to generate realistic, patient-specific gait trajectories for lower-limb exoskeletons, addressing scalability issues inherent in traditional optimization methods. By leveraging adaptive normalization and classifier-free guidance, the approach successfully synthesizes periodic joint-angle movements that adapt to individual morphology and therapeutic goals. The results demonstrate significant potential for personalized assistive robotics, marking a practical advancement in applying generative AI to complex biomechanical control problems.
Diffusion-Based Generation of Gait Trajectories
arXiv:2609.14642v1 Announce Type: new 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.
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.
Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Robotics (cs.RO)
arXiv:2609.14642 [cs.AI]
(or arXiv:2609.14642v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.14642 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 232 cuvinte
Subiecte conexe
Bionic Human-Motion Style Transfer for Physically Executable Whole-Body Control of Humanoid Robots
arXiv · 3 iun. 2026
ResDiffFRG: Residual Diffusion for Multiple Appropriate Facial Reaction Generation
arXiv · 30 sept. 2026
Planner-Conditioned Diffusion for Coordinated Multi-Agent Exploration
arXiv · 18 aug. 2026
Training-Free Diffusion Planning with Analytical Local Scores
arXiv · 2 oct. 2026