Diffusion-Based Generation of Gait Trajectories

The paper presents a method for generating lower‑limb joint‑angle gait trajectories using conditional diffusion models. It compares a baseline transformer diffusion model with a controllable diffusion transformer that includes adaptive normalization and classifier‑free guidance. Experiments on 4,590 gait cycles demonstrate that these diffusion models can produce realistic, periodic gait patterns while allowing some control over gait characteristics such as step length.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• diffusion
• robotics