mlsanityData to 14 Oct 2026

On Robot Grasp Learning Using Equivariant Models

arXiv 2306.06489 ↗First posted 10 Jun 2023cs.RO cs.AIcited by 12

Not on the map. Why?

Abstract (arXiv)

Real-world grasp detection is challenging due to the stochasticity in grasp dynamics and the noise in hardware. Ideally, the system would adapt to the real world by training directly on physical systems. However, this is generally difficult due to the large amount of training data required by most grasp learning models. In this paper, we note that the planar grasp function is SE(2)-equivariant and demonstrate that this structure can be used to constrain the neural network used during learning. This creates an inductive bias that can significantly improve the sample efficiency of grasp learning and enable end-to-end training from scratch on a physical robot with as few as 600 grasp attempts. We call this method Symmetric Grasp learning (SymGrasp) and show that it can learn to grasp ``from scratch'' in less that 1.5 hours of physical robot time.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 45 of its 56 references that are in the map. First posted on arXiv 10 Jun 2023.

Builds on

45 of 56 references.

References · 45

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  5. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  6. 2016Group Equivariant Convolutional Networkscited by 1,165
  7. 2020CURL: Contrastive Unsupervised Representations for Reinforcement Learningcited by 760
  8. 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 743
  9. 2020Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixelscited by 585
  10. 2020VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representationcited by 530
  11. 2020Reinforcement Learning with Augmented Datacited by 468
  12. 2019General E(2)-Equivariant Steerable CNNscited by 446
33 more
  1. 2016Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collectioncited by 316
  2. 2016Steerable CNNscited by 305
  3. 2017Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metricscited by 264
  4. 20196-DOF GraspNet: Variational Grasp Generation for Object Manipulationcited by 242
  5. 2018A General Theory of Equivariant CNNs on Homogeneous Spacescited by 228
  6. 2021Contact-GraspNet: Efficient 6-DoF Grasp Generation in Cluttered Scenescited by 218
  7. 2015Supersizing Self-supervision: Learning to Grasp from 50K Tries and 700 Robot Hourscited by 209
  8. 2018Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networkscited by 174
  9. 2020MDP Homomorphic Networks: Group Symmetries in Reinforcement Learningcited by 142
  10. 2018Learning Synergies between Pushing and Grasping with Self-supervised Deep Reinforcement Learningcited by 128
  11. 2020Incorporating Symmetry into Deep Dynamics Models for Improved Generalizationcited by 126
  12. 2019ClearGrasp: 3D Shape Estimation of Transparent Objects for Manipulationcited by 124
  13. 2018Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approachcited by 120
  14. 2021Dex-NeRF: Using a Neural Radiance Field to Grasp Transparent Objectscited by 119
  15. 2017Grasp Pose Detection in Point Cloudscited by 111
  16. 2021Synergies Between Affordance and Geometry: 6-DoF Grasp Detection via Implicit Representationscited by 108
  17. 2019Grasping in the Wild:Learning 6DoF Closed-Loop Grasping from Low-Cost Demonstrationscited by 107
  18. 2021Volumetric Grasping Network: Real-time 6 DOF Grasp Detection in Cluttercited by 95
  19. 2018Jacquard: A Large Scale Dataset for Robotic Grasp Detectioncited by 87
  20. 2022SO(2)-Equivariant Reinforcement Learningcited by 84
  21. 2021Equivariant Q Learning in Spatial Action Spacescited by 62
  22. 2019Antipodal Robotic Grasping using Generative Residual Convolutional Neural Networkcited by 59
  23. 2022Edge Grasp Network: A Graph-Based SE(3)-invariant Approach to Grasp Detectioncited by 35
  24. 2018Fully Convolutional Grasp Detection Network with Oriented Anchor Boxcited by 27
  25. 2020Trajectory Prediction using Equivariant Continuous Convolutioncited by 26
  26. 2020Group Equivariant Deep Reinforcement Learningcited by 24
  27. 2021Roto-translated Local Coordinate Frames For Interacting Dynamical Systemscited by 24
  28. 2017Learning to Factor Policies and Action-Value Functions: Factored Action Space Representations for Deep Reinforcement learningcited by 15
  29. 2020Policy learning in SE(3) action spacescited by 14
  30. 2020Multi-modal Transfer Learning for Grasping Transparent and Specular Objectscited by 13
  31. 2020Exploratory Grasping: Asymptotically Optimal Algorithms for Grasping Challenging Polyhedral Objectscited by 9
  32. 2022Grasp Learning: Models, Methods, and Performancecited by 8
  33. 2021Robot Learning of 6 DoF Grasping using Model-based Adaptive Primitivescited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 8; 2026: 2.

12 papers.

  1. 2024Equivariant Diffusion Policycited by 66
  2. 2025Two by Two: Learning Multi-Task Pairwise Objects Assembly for Generalizable Robot Manipulationcited by 13
  3. 2025SE(3)-Equivariant Diffusion Policy in Spherical Fourier Spacecited by 8
  4. 2024MATCH POLICY: A Simple Pipeline from Point Cloud Registration to Manipulation Policiescited by 6
  5. 2025Constraint-Preserving Data Generation for Visuomotor Policy Learningcited by 6
  6. 2025A Practical Guide for Incorporating Symmetry in Diffusion Policycited by 5
  7. 2025EfficientFlow: Efficient Equivariant Flow Policy Learning for Embodied AIcited by 4
  8. 2025Coarse-to-Fine 3D Keyframe Transportercited by 2
  9. 2025Equivariant Volumetric Graspingcited by 1
  10. 2026Efficient Hybrid SE(3)-Equivariant Visuomotor Flow Policy via Spherical Harmonics for Robot Manipulationcited by 1
  11. 2025Reinforcement Learning Using known Invariancescited by 0
  12. 2026Pix2Act: Image-Space Manipulation Policies with Equivariant Augmentationcited by 0