Pith. sign in

REVIEW 1 cited by

PartManip: Learning Cross-Category Generalizable Part Manipulation Policy from Point Cloud Observations

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 2303.16958 v1 pith:72WTZXCA submitted 2023-03-29 cs.CV cs.RO

classification cs.CVcs.RO
keywords objectmanipulationpolicycross-categorylearningobjectscategorieswork
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Learning a generalizable object manipulation policy is vital for an embodied agent to work in complex real-world scenes. Parts, as the shared components in different object categories, have the potential to increase the generalization ability of the manipulation policy and achieve cross-category object manipulation. In this work, we build the first large-scale, part-based cross-category object manipulation benchmark, PartManip, which is composed of 11 object categories, 494 objects, and 1432 tasks in 6 task classes. Compared to previous work, our benchmark is also more diverse and realistic, i.e., having more objects and using sparse-view point cloud as input without oracle information like part segmentation. To tackle the difficulties of vision-based policy learning, we first train a state-based expert with our proposed part-based canonicalization and part-aware rewards, and then distill the knowledge to a vision-based student. We also find an expressive backbone is essential to overcome the large diversity of different objects. For cross-category generalization, we introduce domain adversarial learning for domain-invariant feature extraction. Extensive experiments in simulation show that our learned policy can outperform other methods by a large margin, especially on unseen object categories. We also demonstrate our method can successfully manipulate novel objects in the real world.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. RoboGSim: A Real2Sim2Real Robotic Gaussian Splatting Simulator

    cs.RO 2024-11 conditional novelty 5.0 of 10

    A real2sim2real robot simulator that combines 3D Gaussian Splatting with a physics engine to generate photorealistic training data and run closed-loop policy evaluation.

Pith tools