aiqbench analysis
This research advances robotic dexterous manipulation by learning object-centric motion priors from human-object interaction datasets to improve generalization and reduce reliance on task-specific reward engineering. The method demonstrates superior performance across simulation and real-world scenarios, successfully transferring skills between different robot hands without fine-tuning.
Learning Object-Centric Motion Priors from Human for Robotic Dexterous Manipulation
arXiv:2611.05979v1 Announce Type: new Abstract: Manipulating diverse objects with multi-fingered dexterous hands is challenging due to the high dimensionality and complex dynamics. Human-Object Interaction (HOI) datasets provide rich knowledge about task information and embodied interactions. Instead of solely imitating the human demonstrations, our method learns to holistically predict future hand-object states by leveraging these datasets. The predicted future states of the object can serve as a general-purpose reward term for reinforcement learning, reducing reliance on task-specific reward engineering and enhancing generalization across tasks. We conduct extensive experiments on three manipulation tasks in simulation and the real world. Our approach outperforms existing SOTA methods in both success rate and generalizability on novel objects. Furthermore, we validate the cross-embodiment compatibility of our methods by successfully deploying the skills on different robot hands.
Abstract:Manipulating diverse objects with multi-fingered dexterous hands is challenging due to the high dimensionality and complex dynamics. Human-Object Interaction (HOI) datasets provide rich knowledge about task information and embodied interactions. Instead of solely imitating the human demonstrations, our method learns to holistically predict future hand-object states by leveraging these datasets. The predicted future states of the object can serve as a general-purpose reward term for reinforcement learning, reducing reliance on task-specific reward engineering and enhancing generalization across tasks. We conduct extensive experiments on three manipulation tasks in simulation and the real world. Our approach outperforms existing SOTA methods in both success rate and generalizability on novel objects. Furthermore, we validate the cross-embodiment compatibility of our methods by successfully deploying the skills on different robot hands.
Robotics (cs.RO)
arXiv:2611.05979 [cs.RO]
(or arXiv:2611.05979v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2611.05979 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
https://doi.org/10.1609/aaai.v40i22.38892 Focus to learn more DOI(s) linking to related resources
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 · 228 words