Pith. sign in

REVIEW 5 cited by

Sample Efficient Grasp Learning Using Equivariant Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2202.09468 v1 pith:FWQTQ2P6 submitted 2022-02-18 cs.RO

Xupeng Zhu , Dian Wang , Ondrej Biza , Guanang Su , Robin Walters , Robert Platt This is my paper · ORCID
classification cs.RO
keywords graspequivariantfunctionlearnlearningmathrmsampleable
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

In planar grasp detection, the goal is to learn a function from an image of a scene onto a set of feasible grasp poses in $\mathrm{SE}(2)$. In this paper, we recognize that the optimal grasp function is $\mathrm{SE}(2)$-equivariant and can be modeled using an equivariant convolutional neural network. As a result, we are able to significantly improve the sample efficiency of grasp learning, obtaining a good approximation of the grasp function after only 600 grasp attempts. This is few enough that we can learn to grasp completely on a physical robot in about 1.5 hours.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

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

  1. Expected Return Symmetries

    cs.MA 2025-02 conditional novelty 7.0 of 10

    Expected return symmetries, transformations that preserve the expected return of optimal policies, contain environment symmetries as a subgroup and improve zero-shot coordination in Hanabi and Overcooked V2.

  2. Robot Tactile Gesture Recognition Based on Full-body Modular E-skin

    cs.RO 2025-06 conditional novelty 6.0 of 10

    A full-body modular e-skin with an equivariant graph neural network classifies tactile gestures on a robot arm with 91.1% held-out test accuracy.

  3. Symmetries-enhanced Multi-Agent Reinforcement Learning

    cs.RO 2025-01 conditional novelty 5.0 of 10

    A canonicalization-based equivariant graph transformer with a learned symmetry-breaking head improves collision rates and zero-shot scalability in simulated quadrotor swarm MARL.

  4. Equivariant Action Sampling for Reinforcement Learning and Planning

    cs.RO 2024-12 conditional novelty 5.0 of 10

    Augmenting each sampled action with its full symmetry orbit makes finite-sample planning exactly equivariant and speeds up learning on several rotationally symmetric control tasks.

  5. MTF-Grasp: A Multi-tier Federated Learning Approach for Robotic Grasping

    cs.LG 2025-07 reject novelty 4.0 of 10

    MTF-Grasp, a two-tier federated learning method that seeds low-data robots with models pre-trained by high-quality clients, reports up to 8% higher grasp accuracy than vanilla FedAvg under data quantity skew.

Pith tools