Dexterous Point Policy: Learning Point-based Dexterous Hand Policies from Human Demonstrations

• URL: http://arxiv.org/abs/2606.10614v1
• Date: Tue, 09 Jun 2026 09:13:36 GMT
• Title: Dexterous Point Policy: Learning Point-based Dexterous Hand Policies from Human Demonstrations
• Abstract summary: Dexterous Point Policy learns dexterous manipulation policies directly from human videos and requires no robot demonstrations.<n>We extract 3D keypoints of task-relevant objects and human hands from raw videos, and train an autoregressive transformer over these keypoints.<n>On a suite of real-robot tasks spanning pick-and-place and tool use, Dexterous Point Policy attains 75.0% success, whereas a state-of-the-art VLA baseline reaches only 1.0%.
• Score: 47.549615826832856
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Robotic foundation models pre-trained on human demonstration videos have shown promise, but a significant embodiment gap remains when the resulting policies are deployed on real robots. A common remedy is to fine-tune these models on robot-specific demonstrations. However, robot data collection can be prohibitively expensive and time-consuming, which is particularly acute in dexterous manipulation, e.g., teleoperating a multi-fingered hand for even a single atomic task can take days. To address this, we introduce Dexterous Point Policy, a framework that learns dexterous manipulation policies directly from human videos and requires no robot demonstrations. Our core insight is that a unified 3D keypoint representation can bridge human and robot embodiments when used for both observations and actions. Specifically, we extract 3D keypoints of task-relevant objects and human hands from raw videos, and train an autoregressive transformer over these keypoints. We observe that at the keypoint level, specifically the wrist and fingertips, human and robot behaviors closely align, enabling direct policy transfer. On a suite of real-robot tasks spanning pick-and-place and tool use, Dexterous Point Policy attains 75.0% success, whereas a state-of-the-art VLA baseline reaches only 1.0%. Furthermore, our method generalizes strongly to unseen scenarios, including multi-object environments and novel object categories.

Related papers

• Dexterity from Smart Lenses: Multi-Fingered Robot Manipulation with In-the-Wild Human Demonstrations [52.29884993824894]
  Learning multi-fingered robot policies from humans performing daily tasks in natural environments has long been a grand goal in the robotics community.<n>AINA enables learning multi-fingered policies from data collected by anyone, anywhere, and in any environment using Aria Gen 2 glasses.
  arXiv  Detail & Related papers  (2025-11-20T18:59:02Z)
• ZeroMimic: Distilling Robotic Manipulation Skills from Web Videos [15.809468471562537]
  ZeroMimic generates image goal-conditioned skill policies for several common manipulation tasks.<n>We evaluate ZeroMimic's out-of-the-box performance in varied real-world and simulated kitchen settings.<n>To enable plug-and-play reuse of ZeroMimic policies on other task setups and robots, we release software and policy checkpoints.
  arXiv  Detail & Related papers  (2025-03-31T09:27:00Z)
• Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation [65.46610405509338]
  We seek to learn a generalizable goal-conditioned policy that enables zero-shot robot manipulation. Our framework,Track2Act predicts tracks of how points in an image should move in future time-steps based on a goal. We show that this approach of combining scalably learned track prediction with a residual policy enables diverse generalizable robot manipulation.
  arXiv  Detail & Related papers  (2024-05-02T17:56:55Z)
• Giving Robots a Hand: Learning Generalizable Manipulation with Eye-in-Hand Human Video Demonstrations [66.47064743686953]
  Eye-in-hand cameras have shown promise in enabling greater sample efficiency and generalization in vision-based robotic manipulation. Videos of humans performing tasks, on the other hand, are much cheaper to collect since they eliminate the need for expertise in robotic teleoperation. In this work, we augment narrow robotic imitation datasets with broad unlabeled human video demonstrations to greatly enhance the generalization of eye-in-hand visuomotor policies.
  arXiv  Detail & Related papers  (2023-07-12T07:04:53Z)
• Learning Video-Conditioned Policies for Unseen Manipulation Tasks [83.2240629060453]
  Video-conditioned Policy learning maps human demonstrations of previously unseen tasks to robot manipulation skills. We learn our policy to generate appropriate actions given current scene observations and a video of the target task. We validate our approach on a set of challenging multi-task robot manipulation environments and outperform state of the art.
  arXiv  Detail & Related papers  (2023-05-10T16:25:42Z)
• Zero-Shot Robot Manipulation from Passive Human Videos [59.193076151832145]
  We develop a framework for extracting agent-agnostic action representations from human videos. Our framework is based on predicting plausible human hand trajectories. We deploy the trained model zero-shot for physical robot manipulation tasks.
  arXiv  Detail & Related papers  (2023-02-03T21:39:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.