mlsanityData to 14 Oct 2026

ET-SEED: Efficient Trajectory-Level SE(3) Equivariant Diffusion Policy

arXiv 2411.03990 ↗First posted 6 Nov 2024cs.RO cs.CV cs.LGcited by 26

On the map: Diffusion models → Diffusion and flow policies for robotics

also in 1 more
Abstract (arXiv)

Imitation learning, e.g., diffusion policy, has been proven effective in various robotic manipulation tasks. However, extensive demonstrations are required for policy robustness and generalization. To reduce the demonstration reliance, we leverage spatial symmetry and propose ET-SEED, an efficient trajectory-level SE(3) equivariant diffusion model for generating action sequences in complex robot manipulation tasks. Further, previous equivariant diffusion models require the per-step equivariance in the Markov process, making it difficult to learn policy under such strong constraints. We theoretically extend equivariant Markov kernels and simplify the condition of equivariant diffusion process, thereby significantly improving training efficiency for trajectory-level SE(3) equivariant diffusion policy in an end-to-end manner. We evaluate ET-SEED on representative robotic manipulation tasks, involving rigid body, articulated and deformable object. Experiments demonstrate superior data efficiency and manipulation proficiency of our proposed method, as well as its ability to generalize to unseen configurations with only a few demonstrations. Website: https://et-seed.github.io/

Key facts. Cited by 26 papers in the map (data through 14 Oct 2026). Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models. Builds on 31 of its 37 references that are in the map. First posted on arXiv 6 Nov 2024.

Builds on

31 of 37 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024EquiBot: SIM(3)-Equivariant Diffusion Policy for Generalizable and Data Efficient Learning1 Jul
  2. 2023Diffusion-EDFs: Bi-equivariant Denoising Generative Modeling on SE(3) for Visual Robotic Manipulation6 Sep
  3. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusion7 Mar
  4. 2022SE(3)-DiffusionFields: Learning smooth cost functions for joint grasp and motion optimization through diffusion8 Sep

Other references · 27

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  3. 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
  4. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
  5. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,410
  6. 2021What Matters in Learning from Offline Human Demonstrations for Robot Manipulationcited by 725
  7. 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 607
  8. 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generationcited by 516
  9. 2024Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperationcited by 391
  10. 2021Vector Neurons: A General Framework for SO(3)-Equivariant Networkscited by 305
  11. 2022Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphscited by 264
  12. 2022Structure-based Drug Design with Equivariant Diffusion Modelscited by 217
15 more
  1. 2021Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulationcited by 209
  2. 2023Scaling Robot Learning with Semantically Imagined Experiencecited by 177
  3. 20233D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Predictioncited by 177
  4. 2022VIOLA: Imitation Learning for Vision-Based Manipulation with Object Proposal Priorscited by 136
  5. 2023EquivAct: SIM(3)-Equivariant Visuomotor Policies beyond Rigid Object Manipulationcited by 37
  6. 2023SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimationcited by 33
  7. 2024DiffAssemble: A Unified Graph-Diffusion Model for 2D and 3D Reassemblycited by 33
  8. 2023Leveraging SE(3) Equivariance for Learning 3D Geometric Shape Assemblycited by 28
  9. 2022USEEK: Unsupervised SE(3)-Equivariant 3D Keypoints for Generalizable Manipulationcited by 27
  10. 2024UniGarmentManip: A Unified Framework for Category-Level Garment Manipulation via Dense Visual Correspondencecited by 23
  11. 2024GarmentLab: A Unified Simulation and Benchmark for Garment Manipulationcited by 22
  12. 2024OrbitGrasp: SE(3)-Equivariant Grasp Learningcited by 16
  13. 2024Contrastive Imitation Learning for Language-guided Multi-Task Robotic Manipulationcited by 15
  14. 2024RiEMann: Near Real-Time SE(3)-Equivariant Robot Manipulation without Point Cloud Segmentationcited by 12
  15. 2024EqvAfford: SE(3) Equivariance for Point-Level Affordance Learningcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 9; 2026: 17.

26 papers.

Sort:

By area:

  1. 2026OAT: Ordered Action Tokenizationcited by 15
  2. 2025AdaManip: Adaptive Articulated Object Manipulation Environments and Policy Learningcited by 12
  3. 2026AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understandingcited by 12
  4. 2025VGGT-DP: Generalizable Robot Control via Vision Foundation Modelscited by 11
  5. 2025SE(3)-Equivariant Robot Learning and Control: A Tutorial Surveycited by 10
  6. 2025SE(3)-Equivariant Diffusion Policy in Spherical Fourier Spacecited by 8
  7. 2025A Practical Guide for Incorporating Symmetry in Diffusion Policycited by 5
  8. 20253D Equivariant Visuomotor Policy Learning via Spherical Projectioncited by 5
  9. 2026Learning Part-Aware Dense 3D Feature Field for Generalizable Articulated Object Manipulationcited by 5
  10. 2025Partially Equivariant Reinforcement Learning in Symmetry-Breaking Environmentscited by 3
  11. 2026A3D: Adaptive Affordance Assembly with Dual-Arm Manipulationcited by 3
  12. 2025Eq.Bot: Enhance Robotic Manipulation Learning via Group Equivariant Canonicalizationcited by 2
14 more
  1. 2026Efficient Hybrid SE(3)-Equivariant Visuomotor Flow Policy via Spherical Harmonics for Robot Manipulationcited by 1
  2. 2026EquiVLA: A General Framework for Rotationally Equivariant Vision-Language-Action Modelscited by 1
  3. 2026SAVLA: Symmetry-Aware Vision-Language-Action Models for Robotic Manipulationcited by 1
  4. 2025ReSeFlow: Rectifying SE(3)-Equivariant Policy Learning Flowscited by 0
  5. 2026GraspLDP: Towards Generalizable Grasping Policy via Latent Diffusioncited by 0
  6. 2026Morphologically Equivariant Flow Matching for Bimanual Mobile Manipulationcited by 0
  7. 2026The Lie We Tell: Correcting the Euclidean Fallacy in Vision Language Action Policies via Score Matching on Tangent Spacecited by 0
  8. 2026Factor-Aware Mixture-of-Experts with Pretrained Encoder for Combinatorial Generalizationcited by 0
  9. 2026BridgeFlow: Fast and Robust SE(2)-Equivariant Motion Planning with Flow Matchingcited by 0
  10. 2026Terminal Symmetry as a Carrier of Asymmetric Process Knowledge: Statewise Refinement for Anytime Verified Constructioncited by 0
  11. 2026LieSpline-DP: Lie-Group B-Spline Diffusion Policy for Smooth Robot Manipulationcited by 0
  12. 2026Manifold-Stable Flow Matchingcited by 0
  13. 2026Equivariant Visual-Tactile Diffusion Policy for Contact-Rich Manipulationcited by 0
  14. 2026Phase-Conditioned Affordance Fields for SE(3)-Equivariant Visuomotor Policiescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022SEIL: Simulation-augmented Equivariant Imitation Learning
  2. 2025Canonical Policy: Learning Canonical 3D Representation for SE(3)-Equivariant Policy
  3. 2026SegDiff: Segmented Trajectory Diffusion for Consistent and Adaptive Robot Manipulation
  4. 2024WARPD: World model Assisted Reactive Policy Diffusion
  5. 2026EquiBim: Learning Symmetry-Equivariant Policy for Bimanual Manipulation
  6. 2026SeedPolicy: Horizon Scaling via Self-Evolving Diffusion Policy for Robot Manipulation
  7. 2024Equivariant Diffusion Policy
  8. 2025Time-Unified Diffusion Policy with Action Discrimination for Robotic Manipulation