mlsanityData to 14 Oct 2026

JUICER: Data-Efficient Imitation Learning for Robotic Assembly

arXiv 2404.03729 ↗First posted 4 Apr 2024cs.RO cs.LGcited by 38

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

Abstract (arXiv)

While learning from demonstrations is powerful for acquiring visuomotor policies, high-performance imitation without large demonstration datasets remains challenging for tasks requiring precise, long-horizon manipulation. This paper proposes a pipeline for improving imitation learning performance with a small human demonstration budget. We apply our approach to assembly tasks that require precisely grasping, reorienting, and inserting multiple parts over long horizons and multiple task phases. Our pipeline combines expressive policy architectures and various techniques for dataset expansion and simulation-based data augmentation. These help expand dataset support and supervise the model with locally corrective actions near bottleneck regions requiring high precision. We demonstrate our pipeline on four furniture assembly tasks in simulation, enabling a manipulator to assemble up to five parts over nearly 2500 time steps directly from RGB images, outperforming imitation and data augmentation baselines. Project website: https://imitation-juicer.github.io/.

Key facts. Cited by 38 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 58 of its 66 references that are in the map. First posted on arXiv 4 Apr 2024.

Builds on

58 of 66 references.

Closest ancestors · 5

Same direction, newest first

  1. 2023FurnitureBench: Reproducible Real-World Benchmark for Long-Horizon Complex Manipulation22 May
  2. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware23 Apr
  3. 2023NeRF in the Palm of Your Hand: Corrective Augmentation for Robotics via Novel-View Synthesis18 Jan
  4. 2022VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training30 Sep
  5. 2020Grasping with Chopsticks: Combating Covariate Shift in Model-free Imitation Learning for Fine Manipulation13 Nov

Other references · 53

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2020Denoising Diffusion Implicit Modelscited by 9,781
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  6. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  7. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  8. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  9. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  10. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 3,080
  11. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  12. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,979
38 more
  1. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,556
  2. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
  3. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,061
  4. 2021What Matters in Learning from Offline Human Demonstrations for Robot Manipulationcited by 725
  5. 2017Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrationscited by 715
  6. 2022R3M: A Universal Visual Representation for Robot Manipulationcited by 694
  7. 2022Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulationcited by 551
  8. 2022Is Conditional Generative Modeling all you need for Decision-Making?cited by 516
  9. 2020Reinforcement Learning with Augmented Datacited by 468
  10. 2023Imitating Human Behaviour with Diffusion Modelscited by 263
  11. 2023Goal-Conditioned Imitation Learning using Score-based Diffusion Policiescited by 236
  12. 2017DART: Noise Injection for Robust Imitation Learningcited by 191
  13. 2015Deep Spatial Autoencoders for Visuomotor Learningcited by 153
  14. 2023RoboCat: A Self-Improving Generalist Agent for Robotic Manipulationcited by 111
  15. 2018Interactive Supercomputing on 40,000 Cores for Machine Learning and Data Analysiscited by 110
  16. 2021Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Interventioncited by 95
  17. 2023Compositional Foundation Models for Hierarchical Planningcited by 95
  18. 2020An Analysis of SVD for Deep Rotation Estimationcited by 86
  19. 2021Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapescited by 71
  20. 2022Factory: Fast Contact for Robotic Assemblycited by 54
  21. 2023IndustReal: Transferring Contact-Rich Assembly Tasks from Simulation to Realitycited by 53
  22. 2019Form2Fit: Learning Shape Priors for Generalizable Assembly from Disassemblycited by 51
  23. 2022Vision-Based Manipulators Need to Also See from Their Handscited by 47
  24. 2020Meta-Reinforcement Learning for Robotic Industrial Insertion Taskscited by 34
  25. 2023Provable Guarantees for Generative Behavior Cloning: Bridging Low-Level Stability and High-Level Behaviorcited by 33
  26. 2020Variable Compliance Control for Robotic Peg-in-Hole Assembly: A Deep Reinforcement Learning Approachcited by 29
  27. 2023CCIL: Continuity-based Data Augmentation for Corrective Imitation Learningcited by 29
  28. 2020Residual Learning from Demonstration: Adapting DMPs for Contact-rich Manipulationcited by 28
  29. 2018Learning Robotic Assembly from CADcited by 21
  30. 2022TaSIL: Taylor Series Imitation Learningcited by 21
  31. 2021Learning Insertion Primitives with Discrete-Continuous Hybrid Action Space for Robotic Assembly Taskscited by 20
  32. 2023ASAP: Automated Sequence Planning for Complex Robotic Assembly with Physical Feasibilitycited by 18
  33. 2021Collect & Infer -- a fresh look at data-efficient Reinforcement Learningcited by 17
  34. 2021InsertionNet -- A Scalable Solution for Insertioncited by 16
  35. 2023Mastering Stacking of Diverse Shapes with Large-Scale Iterative Reinforcement Learning on Real Robotscited by 13
  36. 2022Visual Backtracking Teleoperation: A Data Collection Protocol for Offline Image-Based Reinforcement Learningcited by 11
  37. 2022InsertionNet 2.0: Minimal Contact Multi-Step Insertion Using Multimodal Multiview Sensory Inputcited by 9
  38. 2020Dynamic Experience Replaycited by 7

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 7; 2025: 19; 2026: 12.

38 papers.

Sort:

By area:

  1. 2024Diffusion Policy Policy Optimizationcited by 280
  2. 2025Steering Your Diffusion Policy with Latent Space Reinforcement Learningcited by 169
  3. 2024From Imitation to Refinement -- Residual RL for Precise Assemblycited by 90
  4. 2024TRANSIC: Sim-to-Real Policy Transfer by Learning from Online Correctioncited by 59
  5. 2025Residual Off-Policy RL for Finetuning Behavior Cloning Policiescited by 55
  6. 2025RaC: Robot Learning for Long-Horizon Tasks by Scaling Recovery and Correctioncited by 39
  7. 2025A Survey on Imitation Learning for Contact-Rich Tasks in Roboticscited by 14
  8. 2025VT-Refine: Learning Bimanual Assembly with Visuo-Tactile Feedback via Simulation Fine-Tuningcited by 11
  9. 2026Emergent Dexterity via Diverse Resets and Large-Scale Reinforcement Learningcited by 10
  10. 2025Uncertainty Comes for Free: Human-in-the-Loop Policies with Diffusion Modelscited by 8
  11. 2025Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL Finetuningcited by 8
  12. 2025Fine-tuning Diffusion Policies with Backpropagation Through Diffusion Timestepscited by 7
26 more
  1. 2026UniIntervene: Agentic Intervention for Efficient Real-World Reinforcement Learningcited by 6
  2. 2025Bi-LAT: Bilateral Control-Based Imitation Learning via Natural Language and Action Chunking with Transformerscited by 5
  3. 2025BiAssemble: Learning Collaborative Affordance for Bimanual Geometric Assemblycited by 5
  4. 2024Imagine-2-Drive: Leveraging High-Fidelity World Models via Multi-Modal Diffusion Policiescited by 4
  5. 2026Lagrangian Perturbation Diffusion Steering: Latent Reinforcement Learning for Generative Policiescited by 4
  6. 2025FM-IRL: Flow-Matching for Reward Modeling and Policy Regularization in Reinforcement Learningcited by 3
  7. 2024Good Data Is All Imitation Learning Needscited by 2
  8. 2024AugInsert: Learning Robust Visual-Force Policies via Data Augmentation for Object Assembly Taskscited by 2
  9. 2025Sample-Efficient Behavior Cloning Using General Domain Knowledgecited by 2
  10. 2025Self-Augmented Robot Trajectory: Efficient Imitation Learning via Safe Self-augmentation with Demonstrator-annotated Precisioncited by 2
  11. 2025Uncertainty Quantification and Data Efficiency in AI: An Information-Theoretic Perspectivecited by 2
  12. 2026HDFlow: Hierarchical Diffusion-Flow Planning for Long-horizon Taskscited by 2
  13. 2025Exploiting Policy Idling for Dexterous Manipulationcited by 1
  14. 2025Vision-Language-Action Models for Selective Robotic Disassembly: A Case Study on Critical Component Extraction from Desktopscited by 1
  15. 2025Distributionally Robust Imitation Learning: Layered Control Architecture for Certifiable Autonomycited by 1
  16. 2026Set-Supervised Diffusion Policy: Learning Action-Chunking Diffusion through Correctionscited by 1
  17. 2026Play2Perfect: What Matters in Dexterous Play Pretraining for Precise Assembly?cited by 1
  18. 2026FurnitureVLA: Learning Long-Horizon Bimanual Furniture Assembly with Vision-Language-Action Modelcited by 1
  19. 2024Learning from Demonstration with Implicit Nonlinear Dynamics Modelscited by 0
  20. 2025Modality Selection and Skill Segmentation via Cross-Modality Attentioncited by 0
  21. 2025RAMAC: Multimodal Risk-Aware Offline Reinforcement Learning and the Role of Behavior Regularizationcited by 0
  22. 2026Online Conformal Prediction with Corrupted Feedbackcited by 0
  23. 2026Adversarial Dual On-Policy Distillation from Expressive Teachercited by 0
  24. 2026ReGuide: From Test-Time Guidance to Self-Improving Diffusion Policiescited by 0
  25. 2026Beyond Conservatism: Recoverability-Conditioned Exploration for Model-Based Imitation Learningcited by 0
  26. 2026Task-Space Imitation Guidance for Efficient Reinforcement Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024VITAL: Interactive Few-Shot Imitation Learning via Visual Human-in-the-Loop Corrections
  2. 2026Improving Imitation Learning Efficiency for Manipulation through Geometric Prior Pretraining
  3. 2025Bootstrapping Imitation Learning for Long-horizon Manipulation via Hierarchical Data Collection Space
  4. 2025RoboManipBaselines: A Unified Framework for Imitation Learning in Robotic Manipulation across Real and Simulation Environments
  5. 2025Imitation Learning with Precisely Labeled Human Demonstrations
  6. 2020Visual Imitation Made Easy
  7. 2024Data Scaling Laws in Imitation Learning for Robotic Manipulation
  8. 2026MinInter: Minimizing Trajectory Interpolation During Data Augmentation for Imitation Learning