mlsanityData to 14 Oct 2026

SEIL: Simulation-augmented Equivariant Imitation Learning

arXiv 2211.00194 ↗First posted 31 Oct 2022cs.ROcited by 23

On the map: Offline RL and imitation learning from data → Robot manipulation imitation learning

Abstract (arXiv)

In robotic manipulation, acquiring samples is extremely expensive because it often requires interacting with the real world. Traditional image-level data augmentation has shown the potential to improve sample efficiency in various machine learning tasks. However, image-level data augmentation is insufficient for an imitation learning agent to learn good manipulation policies in a reasonable amount of demonstrations. We propose Simulation-augmented Equivariant Imitation Learning (SEIL), a method that combines a novel data augmentation strategy of supplementing expert trajectories with simulated transitions and an equivariant model that exploits the O(2) symmetry in robotic manipulation. Experimental evaluations demonstrate that our method can learn non-trivial manipulation tasks within ten demonstrations and outperforms the baselines with a significant margin.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Placed in Robot manipulation imitation learning, one of 13 directions in Offline RL and imitation learning from data. Builds on 31 of its 38 references that are in the map. First posted on arXiv 31 Oct 2022.

Builds on

31 of 38 references.

Closest ancestors · 2

Same direction, newest first

  1. 2021Towards More Generalizable One-shot Visual Imitation Learning26 Oct
  2. 2020Human-in-the-Loop Imitation Learning using Remote Teleoperation12 Dec

Other references · 29

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  3. 2017Random Erasing Data Augmentationcited by 1,239
  4. 2016End to End Learning for Self-Driving Carscited by 1,009
  5. 2020Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixelscited by 585
  6. 2020Reinforcement Learning with Augmented Datacited by 468
  7. 2017Time-Contrastive Networks: Self-Supervised Learning from Videocited by 459
  8. 2021Implicit Behavioral Cloningcited by 452
  9. 2019General E(2)-Equivariant Steerable CNNscited by 446
  10. 2020Transporter Networks: Rearranging the Visual World for Robotic Manipulationcited by 344
  11. 2016Steerable CNNscited by 305
  12. 2017Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperationcited by 289
17 more
  1. 2018Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Taskscited by 154
  2. 2021Coarse-to-Fine Q-attention: Efficient Learning for Visual Robotic Manipulation via Discretisationcited by 122
  3. 20213D Neural Scene Representations for Visuomotor Controlcited by 111
  4. 2019Grasping in the Wild:Learning 6DoF Closed-Loop Grasping from Low-Cost Demonstrationscited by 107
  5. 2021Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulationcited by 85
  6. 2022SO(2)-Equivariant Reinforcement Learningcited by 84
  7. 2016Understanding data augmentation for classification: when to warp?cited by 74
  8. 2021Equivariant Q Learning in Spatial Action Spacescited by 62
  9. 2022Sample Efficient Grasp Learning Using Equivariant Modelscited by 53
  10. 2021Offline Reinforcement Learning with Reverse Model-based Imaginationcited by 47
  11. 2022Equivariant Transporter Networkcited by 46
  12. 2022On-Robot Learning With Equivariant Modelscited by 42
  13. 2022Data Augmentation for Manipulationcited by 16
  14. 2020Policy learning in SE(3) action spacescited by 14
  15. 2019Reinforcement Learning for Robotic Manipulation using Simulated Locomotion Demonstrationscited by 11
  16. 2022BulletArm: An Open-Source Robotic Manipulation Benchmark and Learning Frameworkcited by 9
  17. 2020Learning visual servo policies via planner cloningcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 7; 2025: 6; 2026: 5.

23 papers.

Sort:

By area:

  1. 2024EquiBot: SIM(3)-Equivariant Diffusion Policy for Generalizable and Data Efficient Learningcited by 75
  2. 2024Equivariant Diffusion Policycited by 66
  3. 2023Waypoint-Based Imitation Learning for Robotic Manipulationcited by 61
  4. 2023Diffusion-EDFs: Bi-equivariant Denoising Generative Modeling on SE(3) for Visual Robotic Manipulationcited by 52
  5. 2023EquivAct: SIM(3)-Equivariant Visuomotor Policies beyond Rigid Object Manipulationcited by 37
  6. 2024Fourier Transporter: Bi-Equivariant Robotic Manipulation in 3Dcited by 33
  7. 2023A General Theory of Correct, Incorrect, and Extrinsic Equivariancecited by 19
  8. 2023Leveraging Symmetries in Pick and Placecited by 19
  9. 2024MILES: Making Imitation Learning Easy with Self-Supervisioncited by 10
  10. 2024MATCH POLICY: A Simple Pipeline from Point Cloud Registration to Manipulation Policiescited by 6
  11. 2025Constraint-Preserving Data Generation for Visuomotor Policy Learningcited by 6
  12. 2024Equivariant Offline Reinforcement Learningcited by 5
11 more
  1. 2025A Practical Guide for Incorporating Symmetry in Diffusion Policycited by 5
  2. 20253D Equivariant Visuomotor Policy Learning via Spherical Projectioncited by 5
  3. 2025EfficientFlow: Efficient Equivariant Flow Policy Learning for Embodied AIcited by 4
  4. 2026Combined Constrained Sampling and Reinforcement Learning for Robotic Manipulationcited by 3
  5. 2024AugInsert: Learning Robust Visual-Force Policies via Data Augmentation for Object Assembly Taskscited by 2
  6. 2025Coarse-to-Fine 3D Keyframe Transportercited by 2
  7. 2026EquiVLA: A General Framework for Rotationally Equivariant Vision-Language-Action Modelscited by 1
  8. 2025Generalization Bounds for Equivariant Networks on Markov Datacited by 0
  9. 2026Morphologically Equivariant Flow Matching for Bimanual Mobile Manipulationcited by 0
  10. 2026ReGuide: From Test-Time Guidance to Self-Improving Diffusion Policiescited by 0
  11. 2026Pix2Act: Image-Space Manipulation Policies with Equivariant Augmentationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024ET-SEED: Efficient Trajectory-Level SE(3) Equivariant Diffusion Policy
  2. 2026EquiBim: Learning Symmetry-Equivariant Policy for Bimanual Manipulation
  3. 2024RoCoDA: Counterfactual Data Augmentation for Data-Efficient Robot Learning from Demonstrations
  4. 2025Multi-Group Equivariant Augmentation for Reinforcement Learning in Robot Manipulation
  5. 2026MinInter: Minimizing Trajectory Interpolation During Data Augmentation for Imitation Learning
  6. 2025Self-evolved Imitation Learning in Simulated World
  7. 2025Canonical Policy: Learning Canonical 3D Representation for SE(3)-Equivariant Policy
  8. 2025RoboManipBaselines: A Unified Framework for Imitation Learning in Robotic Manipulation across Real and Simulation Environments