{"ID":6497631,"CreatedAt":"2026-07-13T01:19:40.13847098Z","UpdatedAt":"2026-07-14T01:36:59.12045529Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.09519","arxiv_id":"2607.09519","title":"DemoBridge: A Simulation-in-the-Loop Toolkit for Single-View Human Demonstration Retargeting","abstract":"We present DemoBridge, an toolkit that turns a single-view RGB stereo recording of a human hand demonstration into an executable, physics-validated robot-arm trajectory. Retargeting across the embodiment gap is hard. A robot arm reaches a target with a long, articulated body whose links carry far more collision volume than a hand. Solving inverse kinematics for the mapped end-effector pose often yields no collision-free solution, and a trajectory imposes this at every waypoint. A single view adds noise, leaving the demonstrated reference inaccurate. At the core of DemoBridge is a single collision-aware planner. It optimizes the whole joint trajectory at once, reasoning jointly over alternative grasp poses, whole-arm and grasped-object collision, and fidelity to the demonstrated path. A physics simulator runs in the loop. It validates each phase as it is produced and backtracks on failure, so a demonstration that cannot be reproduced as given is re-planned rather than discarded. The resulting action sequence is dynamically stable and faithful to the demonstrated manipulation. It also doubles as a ready-to-use simulation rollout for policy learning. Grasp timing is inferred automatically, and the perception backends, robot, and pipeline stages are swappable from configuration. We evaluate whole-pipeline retargeting on three real-demonstration tasks and the planner on a controlled synthetic benchmark. Our code is available at https://gitlab.kuleuven.be/u0123974/demo-bridge/ .","short_abstract":"We present DemoBridge, an toolkit that turns a single-view RGB stereo recording of a human hand demonstration into an executable, physics-validated robot-arm trajectory. Retargeting across the embodiment gap is hard. A robot arm reaches a target with a long, articulated body whose links carry far more collision volume...","url_abs":"https://arxiv.org/abs/2607.09519","url_pdf":"https://arxiv.org/pdf/2607.09519v1","authors":"[\"Zehao Wang\",\"Fabien Despinoy\",\"Sergey Zakharov\",\"Tinne Tuytelaars\",\"Rahaf Aljundi\"]","published":"2026-07-10T15:31:04Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[]","project_urls":"[\"https://gitlab.kuleuven.be/u0123974/demo-bridge/\"]","has_code":false,"code_links":[{"ID":614102,"CreatedAt":"2026-07-13T01:19:40.13847098Z","UpdatedAt":"2026-07-13T01:19:40.13847098Z","DeletedAt":null,"paper_id":6497631,"paper_url":"https://arxiv.org/abs/2607.09519","paper_title":"DemoBridge: A Simulation-in-the-Loop Toolkit for Single-View Human Demonstration Retargeting","repo_url":"https://github.com/whatwg/fetch","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}