Pith. sign in

REVIEW 14 cited by

Point Policy: Unifying Observations and Actions with Key Points for Robot Manipulation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2502.20391 v1 pith:GSBFVVHX submitted 2025-02-27 cs.RO

Point Policy: Unifying Observations and Actions with Key Points for Robot Manipulation

classification cs.RO
keywords policydatapointrobotlearningobjectacrosshuman
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Building robotic agents capable of operating across diverse environments and object types remains a significant challenge, often requiring extensive data collection. This is particularly restrictive in robotics, where each data point must be physically executed in the real world. Consequently, there is a critical need for alternative data sources for robotics and frameworks that enable learning from such data. In this work, we present Point Policy, a new method for learning robot policies exclusively from offline human demonstration videos and without any teleoperation data. Point Policy leverages state-of-the-art vision models and policy architectures to translate human hand poses into robot poses while capturing object states through semantically meaningful key points. This approach yields a morphology-agnostic representation that facilitates effective policy learning. Our experiments on 8 real-world tasks demonstrate an overall 75% absolute improvement over prior works when evaluated in identical settings as training. Further, Point Policy exhibits a 74% gain across tasks for novel object instances and is robust to significant background clutter. Videos of the robot are best viewed at https://point-policy.github.io/.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 14 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Human Universal Grasping

    cs.RO 2026-06 unverdicted novelty 7.0

    HUG trains a flow-matching model on a new 1M-frame egocentric human grasp dataset to generate retargetable grasps from single RGB-D images, beating baselines by 23-34% on a new 90-object benchmark.

  2. EgoWAM: World Action Models Beyond Pixels with In-the-Wild Egocentric Human Data

    cs.RO 2026-07 accept novelty 6.5

    World Action Model co-training with DINO or 3D-flow targets scales human-to-robot transfer on bimanual tasks far better than behavior cloning, while pixel prediction transfers weakly.

  3. MaskWAM: Unifying Mask Prompting and Prediction for World-Action Models

    cs.CV 2026-06 unverdicted novelty 6.0

    MaskWAM unifies mask prompting and prediction in world-action models via Mixture of Transformers to improve robotic policy generalization on language-ambiguous tasks.

  4. Hand-centric Human-to-Robot Trajectory Transfer from Video Demonstrations via Open-World Contact Localization

    cs.RO 2026-06 unverdicted novelty 6.0

    HOWTransfer recovers 3D hand motion from video, localizes contact intervals via hand-object cues, generates multi-modal grasp hypotheses, and edits trajectories to produce diverse robot-executable motions achieving 86...

  5. GHOST: Hierarchical Sub-Goal Policies for Generalizing Robot Manipulation

    cs.RO 2026-06 unverdicted novelty 6.0

    GHOST improves generalization in robot manipulation via hierarchical factorization into 3D sub-goal prediction from RGB-D views and a goal-conditioned low-level controller, enabling human video integration without act...

  6. KPGrasp: Scalable Keypoint Flow Matching for Dexterous Grasp Generation

    cs.RO 2026-06 unverdicted novelty 6.0

    KPGrasp is a scalable Transformer flow-matching model using 3D hand keypoints that achieves 76.3% success on Dexonomy (47.4% improvement) and best average on DexGrasp Anything without contact losses or test-time refinement.

  7. LACE: Latent Visual Representation for Cross-Embodiment Learning

    cs.RO 2026-05 unverdicted novelty 6.0

    LACE aligns human-robot visual features via semantic distribution matching on corresponding body parts plus Gram loss, yielding 65% better zero-shot policy transfer than baseline DINO.

  8. GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization

    cs.RO 2026-05 unverdicted novelty 6.0

    GuidedVLA improves VLA generalization by supervising individual attention heads with manually defined auxiliary signals for three task-relevant factors.

  9. GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization

    cs.RO 2026-05 unverdicted novelty 6.0

    GuidedVLA improves VLA success rates by manually supervising separate attention heads in the action decoder with auxiliary signals for task-relevant factors.

  10. WARPED: Wrist-Aligned Rendering for Robot Policy Learning from Egocentric Human Demonstrations

    cs.RO 2026-04 unverdicted novelty 6.0

    WARPED synthesizes realistic wrist-view observations from monocular egocentric human videos via foundation models, hand-object tracking, retargeting, and Gaussian Splatting to train visuomotor policies that match tele...

  11. X-Diffusion: Training Diffusion Policies on Cross-Embodiment Human Demonstrations

    cs.RO 2025-11 unverdicted novelty 6.0

    X-Diffusion adapts Ambient Diffusion to selectively train on noised human actions for cross-embodiment robot policies, yielding 16% higher average success rates than naive co-training or manual filtering across five r...

  12. KITE: Decoupling Kinematics and Interaction for Zero-Shot Cross-Embodiment Manipulation

    cs.RO 2026-06 unverdicted novelty 5.0

    KITE decouples task reasoning from embodiment-specific control via learned latent interaction intents to enable zero-shot transfer across structurally different robots.

  13. LUCID: Learning Embodiment-Agnostic Intent Models from Unstructured Human Videos for Scalable Dexterous Robot Skill Acquisition

    cs.RO 2026-06 unverdicted novelty 5.0

    LUCID learns embodiment-agnostic intent models from unstructured human videos to train dexterous robot policies in simulation, enabling zero-shot transfer on real-world tasks like stirring and wiping.

  14. On the Generalization Capabilities, Design Choices and Limitations of Keypoint Imitation Learning

    cs.RO 2026-05 conditional novelty 5.0

    KIL using foundation model keypoints reaches 75% success on five manipulation tasks, beating RGB (47%) but matching S2-diffusion (73%), with generalization tests on unseen objects via over 2000 real-world rollouts.