aiqbench analysis
SPIDER addresses the embodiment gap by using physics-based solvers to convert human motion data into dynamically feasible robot trajectories, significantly accelerating policy learning for both humanoid locomotion and dexterous manipulation. By bypassing direct policy optimization, this framework achieves state-of-the-art performance while enabling efficient data augmentation through simulated perturbations and payloads. The release of a large-scale dataset further supports the transition from kinematic demonstrations to robust, real-world robotic execution.
SPIDER: Scalable Physics-Informed Dexterous Retargeting
arXiv:2511.09484v3 Announce Type: replace Abstract: Learning agile robotic policies requires large-scale demonstrations, but translating abundant human motion data to robots is bottlenecked by the embodiment gap and missing dynamic information. To bridge this gap, we propose Scalable Physics-Informed DExterous Retargeting (SPIDER), a physics-based retargeting framework to transform and augment kinematic-only human demonstrations into dynamically feasible robot trajectories at scale. Our key insight is that human demonstrations should provide global task structure and objective, while a sampling-based solver can be used to find the feasible solution given the physics constraints. As a general framework, SPIDER is an efficient physics-based retargeting method that can be applied to both humanoid whole-body loco-manipulation and dexterous manipulation across 9 humanoid/dexterous hand embodiments, 6 datasets and 3 simulators. By bypassing the need for policy optimization, it achieves state-of-the-art performance while being 10x faster than reinforcement learning (RL) baselines. Furthermore, SPIDER enables physics-based data augmentation, such as imposing external payloads, perturbations, and new contact patterns, to generate diverse data. We demonstrate that the retargeted motion can be executed on the robot directly open-loop or serve as feasible reference motion for efficient RL policy learning. Our pipeline enables large-scale generation of robot trajectories from human motion, and we release a dataset of 6,520 simulated demonstrations across four hands and 191 dataset-specific object identities to support future research.
Abstract:Learning agile robotic policies requires large-scale demonstrations, but translating abundant human motion data to robots is bottlenecked by the embodiment gap and missing dynamic information. To bridge this gap, we propose Scalable Physics-Informed DExterous Retargeting (SPIDER), a physics-based retargeting framework to transform and augment kinematic-only human demonstrations into dynamically feasible robot trajectories at scale. Our key insight is that human demonstrations should provide global task structure and objective, while a sampling-based solver can be used to find the feasible solution given the physics constraints. As a general framework, SPIDER is an efficient physics-based retargeting method that can be applied to both humanoid whole-body loco-manipulation and dexterous manipulation across 9 humanoid/dexterous hand embodiments, 6 datasets and 3 simulators. By bypassing the need for policy optimization, it achieves state-of-the-art performance while being 10x faster than reinforcement learning (RL) baselines. Furthermore, SPIDER enables physics-based data augmentation, such as imposing external payloads, perturbations, and new contact patterns, to generate diverse data. We demonstrate that the retargeted motion can be executed on the robot directly open-loop or serve as feasible reference motion for efficient RL policy learning. Our pipeline enables large-scale generation of robot trajectories from human motion, and we release a dataset of 6,520 simulated demonstrations across four hands and 191 dataset-specific object identities to support future research.
Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
arXiv:2511.09484 [cs.RO]
(or arXiv:2511.09484v3 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2511.09484 Focus to learn more arXiv-issued DOI via DataCite
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.
Full text under the publisher's open licence · 311 words
Related coverage
SLAC Quantum Dots Aim for Mass-Producible Qubits
Quantum Zeitgeist · Jul 14, 2026
Dexterous Robot Manipulation from Human Demonstrations via Contact-Anchored Retargeting and Residual Policy Learning
arXiv · Sep 22, 2026
Dex-X: Learning Visual-Tactile Dexterous Manipulation From Human Videos with Simulated Interaction
arXiv · Sep 9, 2026
DexDirect: Direct Kinesthetic Arm Guidance for Efficient Dexterous Demonstration Collection
arXiv · Jul 31, 2026