mlsanityData to 7 Oct 2026

Deep Object-Centric Representations for Generalizable Robot Learning

arXiv 1708.04225 ↗First posted 14 Aug 2017cs.RO cs.AI cs.CVcited by 50

Not on the map. Why?

Abstract (arXiv)

Robotic manipulation in complex open-world scenarios requires both reliable physical manipulation skills and effective and generalizable perception. In this paper, we propose a method where general purpose pretrained visual models serve as an object-centric prior for the perception system of a learned policy. We devise an object-level attentional mechanism that can be used to determine relevant objects from a few trajectories or demonstrations, and then immediately incorporate those objects into a learned policy. A task-independent meta-attention locates possible objects in the scene, and a task-specific attention identifies which objects are predictive of the trajectories. The scope of the task-specific attention is easily adjusted by showing demonstrations with distractor objects or with diverse relevant objects. Our results indicate that this approach exhibits good generalization across object instances using very few samples, and can be used to learn a variety of manipulation tasks using reinforcement learning.

Key facts. Cited by 50 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Aug 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 7; 2023: 6; 2024: 14; 2025: 10; 2026: 6.

50 papers.

Sort:

By area:

  1. 2022VIOLA: Imitation Learning for Vision-Based Manipulation with Object Proposal Priorscited by 135
  2. 2021GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinementcited by 109
  3. 2023Learning Generalizable Manipulation Policies with Object-Centric 3D Representationscited by 60
  4. 2024Robot See Robot Do: Imitating Articulated Object Manipulation with Monocular 4D Reconstructioncited by 51
  5. 2024Vision-based Manipulation from Single Human Video with Open-World Object Graphscited by 46
  6. 2023Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstractioncited by 45
  7. 2025ControlVLA: Few-shot Object-centric Adaptation for Pre-trained Vision-Language-Action Modelscited by 43
  8. 2024Learning Manipulation by Predicting Interactioncited by 36
  9. 2024Deep Generative Models in Robotics: A Survey on Learning from Multimodal Demonstrationscited by 35
  10. 2024AffordDP: Generalizable Diffusion Policy with Transferable Affordancecited by 35
  11. 2022Compositional Scene Representation Learning via Reconstruction: A Surveycited by 27
  12. 2021Look Wide and Interpret Twice: Improving Performance on Interactive Instruction-following Taskscited by 25
38 more
  1. 2022Is an Object-Centric Video Representation Beneficial for Transfer?cited by 24
  2. 2021Structured World Belief for Reinforcement Learning in POMDPcited by 21
  3. 2022Visuomotor Control in Multi-Object Scenes Using Object-Aware Representationscited by 21
  4. 2023Slot-VAE: Object-Centric Scene Generation with Slot Attentioncited by 20
  5. 2025Rethinking Progression of Memory State in Robotic Manipulation: An Object-Centric Perspectivecited by 20
  6. 2021Semantic Tracklets: An Object-Centric Representation for Visual Multi-Agent Reinforcement Learningcited by 18
  7. 2024Keypoint Abstraction using Large Models for Object-Relative Imitation Learningcited by 18
  8. 2021Self-supervised Reinforcement Learning with Independently Controllable Subgoalscited by 16
  9. 2024Composing Pre-Trained Object-Centric Representations for Robotics From "What" and "Where" Foundation Modelscited by 16
  10. 2024P3-PO: Prescriptive Point Priors for Visuo-Spatial Generalization of Robot Policiescited by 16
  11. 2022Learning Category-Level Generalizable Object Manipulation Policy via Generative Adversarial Self-Imitation Learning from Demonstrationscited by 15
  12. 2024Language-Guided Object-Centric Diffusion Policy for Generalizable and Collision-Aware Robotic Manipulationcited by 14
  13. 2025Object-Centric World Models from Few-Shot Annotations for Sample-Efficient Reinforcement Learningcited by 9
  14. 2025SlotVLA: Towards Modeling of Object-Relation Representations in Robotic Manipulationcited by 9
  15. 2025Subtask-Aware Visual Reward Learning from Segmented Demonstrationscited by 7
  16. 2021Agent-Centric Representations for Multi-Agent Reinforcement Learningcited by 6
  17. 2023GRID: A Platform for General Robot Intelligence Developmentcited by 6
  18. 2024Out-of-Distribution Recovery with Object-Centric Keypoint Inverse Policy for Visuomotor Imitation Learningcited by 6
  19. 2026OCRA: Object-Centric Learning with 3D and Tactile Priors for Human-to-Robot Action Transfercited by 5
  20. 2025PosA-VLA: Enhancing Action Generation via Pose-Conditioned Anchor Attentioncited by 4
  21. 2022Dance of SNN and ANN: Solving binding problem by combining spike timing and reconstructive attentioncited by 3
  22. 2023Generalizable Imitation Learning Through Pre-Trained Representationscited by 3
  23. 2021A Bayesian Approach to Identifying Representational Errorscited by 2
  24. 2023Unified Task and Motion Planning using Object-centric Abstractions of Motion Constraintscited by 2
  25. 2024Relevance for Human Robot Collaborationcited by 2
  26. 2025Similarity as Reward Alignment: Robust and Versatile Preference-based Reinforcement Learningcited by 2
  27. 2026Tether: Autonomous Functional Play with Correspondence-Driven Trajectory Warpingcited by 2
  28. 2022Training and Evaluation of Deep Policies using Reinforcement Learning and Generative Modelscited by 1
  29. 2024Relevance-driven Decision Making for Safer and More Efficient Human Robot Collaborationcited by 1
  30. 2025Disentangled Object-Centric Image Representation for Robotic Manipulationcited by 1
  31. 2026Object-Centric World Models Meet Monte Carlo Tree Searchcited by 1
  32. 2026See Less, Specify More: Visual Evidence Budgets for Generalizable VLAscited by 1
  33. 2024The Indoor-Training Effect: unexpected gains from distribution shifts in the transition functioncited by 0
  34. 2024Learning the Generalizable Manipulation Skills on Soft-body Tasks via Guided Self-attention Behavior Cloning Policycited by 0
  35. 2025GLUE: Global-Local Unified Encoding for Imitation Learning via Key-Patch Trackingcited by 0
  36. 2025Learning to Grasp Anything by Playing with Random Toyscited by 0
  37. 2026Beyond World-Frame Action Heads: Motion-Centric Action Frames for Vision-Language-Action Modelscited by 0
  38. 2026Enabling a Unified Cross-Domain Representation for Two-Finger Gripper Manipulation via Interaction-Centric Modelingcited by 0