mlsanityData to 7 Oct 2026

Leveraging Locality to Boost Sample Efficiency in Robotic Manipulation

arXiv 2406.10615 ↗First posted 15 Jun 2024cs.RO cs.AI cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

Given the high cost of collecting robotic data in the real world, sample efficiency is a consistently compelling pursuit in robotics. In this paper, we introduce SGRv2, an imitation learning framework that enhances sample efficiency through improved visual and action representations. Central to the design of SGRv2 is the incorporation of a critical inductive bias-action locality, which posits that robot's actions are predominantly influenced by the target object and its interactions with the local environment. Extensive experiments in both simulated and real-world settings demonstrate that action locality is essential for boosting sample efficiency. SGRv2 excels in RLBench tasks with keyframe control using merely 5 demonstrations and surpasses the RVT baseline in 23 of 26 tasks. Furthermore, when evaluated on ManiSkill2 and MimicGen using dense control, SGRv2's success rate is 2.54 times that of SGR. In real-world environments, with only eight demonstrations, SGRv2 can perform a variety of tasks at a markedly higher success rate compared to baseline models. Project website: http://sgrv2-robot.github.io

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 56 of its 64 references that are in the map. First posted on arXiv 15 Jun 2024.

Builds on

56 of 64 references.

References · 56

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2022A ConvNet for the 2020scited by 3,545
  5. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  6. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,598
  7. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,490
  8. 2020CURL: Contrastive Unsupervised Representations for Reinforcement Learningcited by 745
  9. 2021What Matters in Learning from Offline Human Demonstrations for Robot Manipulationcited by 699
  10. 2022R3M: A Universal Visual Representation for Robot Manipulationcited by 678
  11. 2019RLBench: The Robot Learning Benchmark & Learning Environmentcited by 669
  12. 2021Perceiver IO: A General Architecture for Structured Inputs & Outputscited by 616
38 more
  1. 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 602
  2. 2020Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixelscited by 573
  3. 2022Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulationcited by 545
  4. 2020robosuite: A Modular Simulation Framework and Benchmark for Robot Learningcited by 484
  5. 2023TD-MPC2: Scalable, Robust World Models for Continuous Controlcited by 482
  6. 2020Reinforcement Learning with Augmented Datacited by 452
  7. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
  8. 2020Learning Invariant Representations for Reinforcement Learning without Reconstructioncited by 424
  9. 2022VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Trainingcited by 384
  10. 2020Transporter Networks: Rearranging the Visual World for Robotic Manipulationcited by 342
  11. 2023ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skillscited by 313
  12. 2023MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrationscited by 308
  13. 20243D Diffuser Actor: Policy Diffusion with 3D Scene Representationscited by 278
  14. 2022Masked Visual Pre-training for Motor Controlcited by 246
  15. 2022Real-World Robot Learning with Masked Visual Pre-trainingcited by 241
  16. 2023RVT: Robotic View Transformer for 3D Object Manipulationcited by 224
  17. 2023Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?cited by 215
  18. 2021Contact-GraspNet: Efficient 6-DoF Grasp Generation in Cluttered Scenescited by 213
  19. 2023Any-point Trajectory Modeling for Policy Learningcited by 207
  20. 2019DeepMDP: Learning Continuous Latent Space Models for Representation Learningcited by 204
  21. 2021Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulationcited by 204
  22. 2022The Unsurprising Effectiveness of Pre-Trained Vision Models for Controlcited by 155
  23. 2023Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulationcited by 135
  24. 2021Coarse-to-Fine Q-attention: Efficient Learning for Visual Robotic Manipulation via Discretisationcited by 120
  25. 20243D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representationscited by 115
  26. 2023GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fieldscited by 99
  27. 2022Instruction-driven history-aware policies for robotic manipulationscited by 93
  28. 2021RRL: Resnet as representation for Reinforcement Learningcited by 89
  29. 2022DexPoint: Generalizable Point Cloud Reinforcement Learning for Sim-to-Real Dexterous Manipulationcited by 78
  30. 2023Multi-View Masked World Models for Visual Robotic Manipulationcited by 78
  31. 2023Waypoint-Based Imitation Learning for Robotic Manipulationcited by 59
  32. 2022Pre-Trained Image Encoder for Generalizable Visual Reinforcement Learningcited by 58
  33. 2022Equivariant Descriptor Fields: SE(3)-Equivariant Energy-Based Models for End-to-End Visual Robotic Manipulation Learningcited by 54
  34. 2022SE(3)-Equivariant Relational Rearrangement with Neural Descriptor Fieldscited by 51
  35. 2021Generalization in Dexterous Manipulation via Geometry-Aware Multi-Task Learningcited by 49
  36. 2022Learning Generalizable Dexterous Manipulation from Human Grasp Affordancecited by 46
  37. 2023EquivAct: SIM(3)-Equivariant Visuomotor Policies beyond Rigid Object Manipulationcited by 37
  38. 2022Frame Mining: a Free Lunch for Learning Robotic Manipulation from 3D Point Cloudscited by 31

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 5; 2026: 5.

13 papers.

Sort:

By area:

  1. 2024Lift3D Foundation Policy: Lifting 2D Large-Scale Pretrained Models for Robust 3D Robotic Manipulationcited by 45
  2. 2025FP3: A 3D Foundation Policy for Robotic Manipulationcited by 31
  3. 2025SKIL: Semantic Keypoint Imitation Learning for Generalizable Data-efficient Manipulationcited by 21
  4. 2025AirExo-2: Scaling up Generalizable Robotic Imitation Learning with Low-Cost Exoskeletonscited by 17
  5. 2024What's the Move? Hybrid Imitation Learning via Salient Pointscited by 9
  6. 2025HybridGen: VLM-Guided Hybrid Planning for Scalable Data Generation of Imitation Learningcited by 3
  7. 2026Learning Part-Aware Dense 3D Feature Field for Generalizable Articulated Object Manipulationcited by 3
  8. 2026See Less, Specify More: Visual Evidence Budgets for Generalizable VLAscited by 1
  9. 2026Lift3D-VLA: Lifting VLA Models to 3D Geometry and Dynamics-Aware Manipulationcited by 1
  10. 2024Problem Space Transformations for Out-of-Distribution Generalisation in Behavioural Cloningcited by 0
  11. 2025No Need for Real 3D: Fusing 2D Vision with Pseudo 3D Representations for Robotic Manipulation Learningcited by 0
  12. 2026Flow-Enabled Generalization to Human Demonstrations in Few-Shot Imitation Learningcited by 0
1 more
  1. 2026HeteroGenManip: Generalizable Manipulation For Heterogeneous Object Interactionscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025MOVE: A Simple Motion-Based Data Collection Paradigm for Spatial Generalization in Robotic Manipulation
  2. 2024Learning from 10 Demos: Generalisable and Sample-Efficient Policy Learning with Oriented Affordance Frames
  3. 2026Beyond the Majority: Long-tail Imitation Learning for Robotic Manipulation
  4. 2024Data Scaling Laws in Imitation Learning for Robotic Manipulation
  5. 2025Bootstrapping Imitation Learning for Long-horizon Manipulation via Hierarchical Data Collection Space
  6. 2022Sample Efficient Robot Learning with Structured World Models
  7. 2024RoCoDA: Counterfactual Data Augmentation for Data-Efficient Robot Learning from Demonstrations
  8. 2026ATHENA: Accelerated Multi-Task Heterogeneous Influence Functions for Robot Data Curation