mlsanityData to 14 Oct 2026

RISE: 3D Perception Makes Real-World Robot Imitation Simple and Effective

arXiv 2404.12281 ↗First posted 18 Apr 2024cs.ROcited by 41

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

Abstract (arXiv)

Precise robot manipulations require rich spatial information in imitation learning. Image-based policies model object positions from fixed cameras, which are sensitive to camera view changes. Policies utilizing 3D point clouds usually predict keyframes rather than continuous actions, posing difficulty in dynamic and contact-rich scenarios. To utilize 3D perception efficiently, we present RISE, an end-to-end baseline for real-world imitation learning, which predicts continuous actions directly from single-view point clouds. It compresses the point cloud to tokens with a sparse 3D encoder. After adding sparse positional encoding, the tokens are featurized using a transformer. Finally, the features are decoded into robot actions by a diffusion head. Trained with 50 demonstrations for each real-world task, RISE surpasses currently representative 2D and 3D policies by a large margin, showcasing significant advantages in both accuracy and efficiency. Experiments also demonstrate that RISE is more general and robust to environmental change compared with previous baselines. Project website: rise-policy.github.io.

Key facts. Cited by 41 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. First posted on arXiv 18 Apr 2024.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 6; 2025: 21; 2026: 14.

41 papers.

Sort:

By area:

  1. 2025RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulationcited by 518
  2. 2025PointVLA: Injecting the 3D World into Vision-Language-Action Modelscited by 105
  3. 2024FlowPolicy: Enabling Fast and Robust 3D Flow-based Policy via Consistency Flow Matching for Robot Manipulationcited by 104
  4. 2024Generalizable Humanoid Manipulation with 3D Diffusion Policiescited by 52
  5. 2024Lift3D Foundation Policy: Lifting 2D Large-Scale Pretrained Models for Robust 3D Robotic Manipulationcited by 46
  6. 2025DeepVerse: 4D Autoregressive Video Generation as a World Modelcited by 40
  7. 2024ForceMimic: Force-Centric Imitation Learning with Force-Motion Capture System for Contact-Rich Manipulationcited by 36
  8. 2025FP3: A 3D Foundation Policy for Robotic Manipulationcited by 32
  9. 2024SPA: 3D Spatial-Awareness Enables Effective Embodied Representationcited by 28
  10. 2025SKIL: Semantic Keypoint Imitation Learning for Generalizable Data-efficient Manipulationcited by 21
  11. 2025Dense Policy: Bidirectional Autoregressive Learning of Actionscited by 19
  12. 2025CordViP: Correspondence-based Visuomotor Policy for Dexterous Manipulation in Real-Worldcited by 18
29 more
  1. 2025AirExo-2: Scaling up Generalizable Robotic Imitation Learning with Low-Cost Exoskeletonscited by 18
  2. 2026LaMP: Learning Vision-Language-Action Policy with 3D Scene Flow as Latent Motion Priorcited by 11
  3. 2025FreqPolicy: Frequency Autoregressive Visuomotor Policy with Continuous Tokenscited by 9
  4. 20253D Flow Diffusion Policy: Visuomotor Policy Learning via Generating Flow in 3D Spacecited by 9
  5. 2025Benchmarking Generalizable Bimanual Manipulation: RoboTwin Dual-Arm Collaboration Challenge at CVPR 2025 MEIS Workshopcited by 8
  6. 2025SE(3)-Equivariant Diffusion Policy in Spherical Fourier Spacecited by 8
  7. 20254D Visual Pre-training for Robot Learningcited by 8
  8. 2025SIME: Enhancing Policy Self-Improvement with Modal-level Explorationcited by 7
  9. 2025TwinAligner: Visual-Dynamic Alignment Empowers Physics-aware Real2Sim2Real for Robotic Manipulationcited by 7
  10. 2024MATCH POLICY: A Simple Pipeline from Point Cloud Registration to Manipulation Policiescited by 6
  11. 2025SOE: Sample-Efficient Robot Policy Self-Improvement via On-Manifold Explorationcited by 6
  12. 2026RoboRouter: Training-Free Policy Routing for Robotic Manipulationcited by 6
  13. 2025Toward Embodiment Equivariant Vision-Language-Action Policycited by 5
  14. 2025LodeStar: Long-horizon Dexterity via Synthetic Data Augmentation from Human Demonstrationscited by 4
  15. 2025Knowledge-Driven Imitation Learning: Enabling Generalization Across Diverse Conditionscited by 2
  16. 2026Lift3D-VLA: Lifting VLA Models to 3D Geometry and Dynamics-Aware Manipulationcited by 2
  17. 2026Advances and Innovations in the Multi-Agent Robotic System (MARS) Challengecited by 1
  18. 2026Efficient Hybrid SE(3)-Equivariant Visuomotor Flow Policy via Spherical Harmonics for Robot Manipulationcited by 1
  19. 2026RoboWits: Unexpected Challenges for Robotic Creative Problem Solvingcited by 1
  20. 2026Revisiting Articulated Parts Perception in Robot Manipulationcited by 1
  21. 2026Asynchronous Multimodal Diffusion Policy Composition via Latency-Aware Guidance Fusioncited by 1
  22. 2026Self-Adaptive VLA for Robust Robot Deploymentcited by 1
  23. 2025No Need for Real 3D: Fusing 2D Vision with Pseudo 3D Representations for Robotic Manipulation Learningcited by 0
  24. 2025ISS Policy : Scalable Diffusion Policy with Implicit Scene Supervisioncited by 0
  25. 2026KAN We Flow? Advancing Robotic Manipulation with 3D Flow Matching via KAN & RWKVcited by 0
  26. 2026Flow-Enabled Generalization to Human Demonstrations in Few-Shot Imitation Learningcited by 0
  27. 2026TransDex: Pre-training Visuo-Tactile Policy with Point Cloud Reconstruction for Dexterous Manipulation of Transparent Objectscited by 0
  28. 2026HeteroGenManip: Generalizable Manipulation For Heterogeneous Object Interactionscited by 0
  29. 2026Spatially Conditioned Diffusion Policy: Learning Precise and Robust Manipulation with a Single RGB Cameracited by 0

Similar, not cited

Close in wording, no citation either way

  1. 20243D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations
  2. 2025RISE: Robust Imitation through Stochastic Encoding
  3. 2026R3D: Revisiting 3D Policy Learning
  4. 2026Learning to See While Learning to Act: Diffusion Models for Active Perception in Robot Imitation
  5. 2025Canonical Policy: Learning Canonical 3D Representation for SE(3)-Equivariant Policy
  6. 2025PRISM: Pointcloud Reintegrated Inference via Segmentation and Cross-attention for Manipulation
  7. 2026PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation
  8. 2025Adapt3R: Adaptive 3D Scene Representation for Domain Transfer in Imitation Learning