mlsanityData to 7 Oct 2026

Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapes

arXiv 2110.06192 ↗First posted 12 Oct 2021cs.RO cs.LGcited by 70

Not on the map. Why?

Abstract (arXiv)

We study the problem of robotic stacking with objects of complex geometry. We propose a challenging and diverse set of such objects that was carefully designed to require strategies beyond a simple "pick-and-place" solution. Our method is a reinforcement learning (RL) approach combined with vision-based interactive policy distillation and simulation-to-reality transfer. Our learned policies can efficiently handle multiple object combinations in the real world and exhibit a large variety of stacking skills. In a large experimental study, we investigate what choices matter for learning such general vision-based agents in simulation, and what affects optimal transfer to the real robot. We then leverage data collected by such policies and improve upon them with offline RL. A video and a blog post of our work are provided as supplementary material.

Key facts. Cited by 70 papers in the map (data through 7 Oct 2026). Builds on 47 of its 71 references that are in the map. First posted on arXiv 12 Oct 2021.

Builds on

47 of 71 references.

References · 47

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  5. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,830
  6. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
  7. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  8. 2018Off-Policy Deep Reinforcement Learning without Explorationcited by 1,227
  9. 2017A Distributional Perspective on Reinforcement Learningcited by 743
  10. 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 730
  11. 2020AWAC: Accelerating Online Reinforcement Learning with Offline Datasetscited by 647
  12. 2018Learning Dexterous In-Hand Manipulationcited by 643
35 more
  1. 2017Sim-to-Real Transfer of Robotic Control with Dynamics Randomizationcited by 616
  2. 2015Policy Distillationcited by 414
  3. 2018Maximum a Posteriori Policy Optimisationcited by 318
  4. 2016Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collectioncited by 312
  5. 2020Critic Regularized Regressioncited by 269
  6. 2016Safe and Efficient Off-Policy Reinforcement Learningcited by 260
  7. 2017Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metricscited by 259
  8. 2017One-Shot Imitation Learningcited by 232
  9. 2016CAD2RL: Real Single-Image Flight without a Single Real Imagecited by 227
  10. 2015Supersizing Self-supervision: Learning to Grasp from 50K Tries and 700 Robot Hourscited by 208
  11. 2017Asymmetric Actor Critic for Image-Based Robot Learningcited by 202
  12. 2019Deep Dynamics Models for Learning Dexterous Manipulationcited by 200
  13. 2018Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networkscited by 171
  14. 2018Learning by Playing - Solving Sparse Reward Tasks from Scratchcited by 164
  15. 2017OSQP: An Operator Splitting Solver for Quadratic Programscited by 156
  16. 2017Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Graspingcited by 138
  17. 2017Robotic Pick-and-Place of Novel Objects in Clutter with Multi-Affordance Grasping and Cross-Domain Image Matchingcited by 124
  18. 2018Reinforcement and Imitation Learning for Diverse Visuomotor Skillscited by 124
  19. 2015Benchmarking in Manipulation Research: The YCB Object and Model Set and Benchmarking Protocolscited by 98
  20. 2020RL-CycleGAN: Reinforcement Learning Aware Simulation-To-Realcited by 89
  21. 2019ROBEL: Robotics Benchmarks for Learning with Low-Cost Robotscited by 70
  22. 2020RetinaGAN: An Object-aware Approach to Sim-to-Real Transfercited by 68
  23. 2016Learning Physical Intuition of Block Towers by Examplecited by 66
  24. 2017Transferring End-to-End Visuomotor Control from Simulation to Real World for a Multi-Stage Taskcited by 66
  25. 2018ShapeStacks: Learning Vision-Based Physical Intuition for Generalised Object Stackingcited by 55
  26. 2019Towards Practical Multi-Object Manipulation using Relational Reinforcement Learningcited by 54
  27. 2016Analysis and Observations from the First Amazon Picking Challengecited by 41
  28. 2018Relational inductive bias for physical construction in humans and machinescited by 41
  29. 2017Domain Randomization and Generative Models for Robotic Graspingcited by 34
  30. 2018Relative Entropy Regularized Policy Iterationcited by 32
  31. 2020Learning Dexterous Manipulation from Suboptimal Expertscited by 23
  32. 2019Self-Supervised Sim-to-Real Adaptation for Visual Robotic Manipulationcited by 19
  33. 2019Scaling data-driven robotics with reward sketching and batch reinforcement learningcited by 18
  34. 2021Active Learning of Abstract Plan Feasibilitycited by 11
  35. 2019Adaptive Curriculum Generation from Demonstrations for Sim-to-Real Visuomotor Controlcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 12; 2023: 22; 2024: 18; 2025: 12; 2026: 4.

70 papers.

Sort:

By area:

  1. 2022A Generalist Agentcited by 802
  2. 2023PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Trackingcited by 274
  3. 2022TAP-Vid: A Benchmark for Tracking Any Point in a Videocited by 258
  4. 2023Tracking Everything Everywhere All at Oncecited by 190
  5. 2024SpatialTracker: Tracking Any 2D Pixels in 3D Spacecited by 178
  6. 2023Scaling Robot Learning with Semantically Imagined Experiencecited by 175
  7. 2024Deep Reinforcement Learning for Robotics: A Survey of Real-World Successescited by 153
  8. 2023FurnitureBench: Reproducible Real-World Benchmark for Long-Horizon Complex Manipulationcited by 132
  9. 2023Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functionscited by 129
  10. 2023RoboCat: A Self-Improving Generalist Agent for Robotic Manipulationcited by 108
  11. 2023Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysiscited by 99
  12. 2023Bootstrap Your Own Skills: Learning to Solve New Tasks with Large Language Model Guidancecited by 85
38 more
  1. 2024Local All-Pair Correspondence for Point Trackingcited by 77
  2. 2024DELTA: Dense Efficient Long-range 3D Tracking for any videocited by 62
  3. 2022When to Trust Your Simulator: Dynamics-Aware Hybrid Offline-and-Online Reinforcement Learningcited by 59
  4. 2023Dense Optical Tracking: Connecting the Dotscited by 58
  5. 2025AllTracker: Efficient Dense Point Tracking at High Resolutioncited by 54
  6. 2023Towards A Unified Agent with Foundation Modelscited by 46
  7. 2022NeRF2Real: Sim2real Transfer of Vision-guided Bipedal Motion Skills using Neural Radiance Fieldscited by 41
  8. 2024JUICER: Data-Efficient Imitation Learning for Robotic Assemblycited by 36
  9. 2024Offline Actor-Critic Reinforcement Learning Scales to Large Modelscited by 30
  10. 2022Offline Reinforcement Learning for Visual Navigationcited by 28
  11. 2023Lossless Adaptation of Pretrained Vision Models For Robotic Manipulationcited by 28
  12. 2021Learning Transferable Motor Skills with Hierarchical Latent Mixture Policiescited by 26
  13. 2022Hyperbolic Deep Reinforcement Learningcited by 25
  14. 2022Learning to Grasp the Ungraspable with Emergent Extrinsic Dexteritycited by 25
  15. 2022Generalization with Lossy Affordances: Leveraging Broad Offline Data for Learning Visuomotor Taskscited by 24
  16. 2023DriveTrack: A Benchmark for Long-Range Point Tracking in Real-World Videoscited by 24
  17. 2022Compositional Multi-Object Reinforcement Learning with Linear Relation Networkscited by 19
  18. 2023FOCUS: Object-Centric World Models for Robotics Manipulationcited by 17
  19. 2024A Comprehensive Survey of Cross-Domain Policy Transfer for Embodied Agentscited by 16
  20. 2025Exploring Temporally-Aware Features for Point Trackingcited by 15
  21. 2024Track Everything Everywhere Fast and Robustlycited by 13
  22. 2024Learning from negative feedback, or positive feedback or bothcited by 13
  23. 2023Replay across Experiments: A Natural Extension of Off-Policy RLcited by 10
  24. 2025OXE-AugE: A Large-Scale Robot Augmentation of OXE for Scaling Cross-Embodiment Policy Learningcited by 10
  25. 2026Track4World: Feedforward World-centric Dense 3D Tracking of All Pixelscited by 10
  26. 2022How to Spend Your Robot Time: Bridging Kickstarting and Offline Reinforcement Learning for Vision-based Robotic Manipulationcited by 9
  27. 2021Distilling Motion Planner Augmented Policies into Visual Control Policies for Robot Manipulationcited by 8
  28. 20226D Robotic Assembly Based on RGB-only Object Pose Estimationcited by 8
  29. 2023Visual-Policy Learning through Multi-Camera View to Single-Camera View Knowledge Distillation for Robot Manipulation Taskscited by 7
  30. 2023Leveraging Jumpy Models for Planning and Fast Learning in Robotic Domainscited by 6
  31. 2025Dynamic Rank Adjustment in Diffusion Policies for Efficient and Flexible Trainingcited by 6
  32. 2023Robust Visual Sim-to-Real Transfer for Robotic Manipulationcited by 5
  33. 2024MResT: Multi-Resolution Sensing for Real-Time Control with Vision-Language Modelscited by 5
  34. 2024Diffusion Augmented Agents: A Framework for Efficient Exploration and Transfer Learningcited by 5
  35. 2025PRISM-DP: Spatial Pose-based Observations for Diffusion-Policies via Segmentation, Mesh Generation, and Pose Trackingcited by 5
  36. 2024Fourier Controller Networks for Real-Time Decision-Making in Embodied Learningcited by 3
  37. 2024Representing Positional Information in Generative World Models for Object Manipulationcited by 3
  38. 2024Optimizing Active Perception for Learning Simultaneous Viewpoint Selection and Manipulation with Diffusion Policycited by 3

50 most cited of 70 All 70 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024StackGen: Generating Stable Structures from Silhouettes via Diffusion
  2. 2025Robot Control Stack: A Lean Ecosystem for Robot Learning at Scale
  3. 2024Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning
  4. 2025Zero-Shot Visual Generalization in Robot Manipulation
  5. 2025Empirical Analysis of Sim-and-Real Cotraining of Diffusion Policies for Planar Pushing from Pixels
  6. 2021Seeing All the Angles: Learning Multiview Manipulation Policies for Contact-Rich Tasks from Demonstrations
  7. 2025PRISM: Projection-based Reward Integration for Scene-Aware Real-to-Sim-to-Real Transfer with Few Demonstrations
  8. 2022Transporters with Visual Foresight for Solving Unseen Rearrangement Tasks