mlsanityData to 7 Oct 2026

FOCUS: Object-Centric World Models for Robotics Manipulation

arXiv 2307.02427 ↗First posted 5 Jul 2023cs.RO cs.AIcited by 17

On the map: World models → Embodied and robot world models

Abstract (arXiv)

Understanding the world in terms of objects and the possible interplays with them is an important cognition ability, especially in robotics manipulation, where many tasks require robot-object interactions. However, learning such a structured world model, which specifically captures entities and relationships, remains a challenging and underexplored problem. To address this, we propose FOCUS, a model-based agent that learns an object-centric world model. Thanks to a novel exploration bonus that stems from the object-centric representation, FOCUS can be deployed on robotics manipulation tasks to explore object interactions more easily. Evaluating our approach on manipulation tasks across different settings, we show that object-centric world models allow the agent to solve tasks more efficiently and enable consistent exploration of robot-object interactions. Using a Franka Emika robot arm, we also showcase how FOCUS could be adopted in real-world settings.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Placed in Embodied and robot world models, one of 11 directions in World models. Builds on 42 of its 61 references that are in the map. First posted on arXiv 5 Jul 2023.

Builds on

42 of 61 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023Multi-View Masked World Models for Visual Robotic Manipulation5 Feb
  2. 2022Masked World Models for Visual Control28 Jun
  3. 2019Solving Rubik's Cube with a Robot Hand16 Oct

Other references · 39

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2023Segment Anythingcited by 8,158
  3. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  4. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,302
  5. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,598
  6. 2016Concrete Problems in AI Safetycited by 1,582
  7. 2018World Modelscited by 1,444
  8. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,327
  9. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
  10. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,221
  11. 2023Mastering Diverse Domains through World Modelscited by 1,193
  12. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,173
27 more
  1. 2020Mastering Atari with Discrete World Modelscited by 990
  2. 2020Object-Centric Learning with Slot Attentioncited by 865
  3. 2015End-to-End Training of Deep Visuomotor Policiescited by 847
  4. 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 730
  5. 2020robosuite: A Modular Simulation Framework and Benchmark for Robot Learningcited by 484
  6. 2019MONet: Unsupervised Scene Decomposition and Representationcited by 388
  7. 2022Temporal Difference Learning for Model Predictive Controlcited by 375
  8. 2022DayDreamer: World Models for Physical Robot Learningcited by 372
  9. 2020Planning to Explore via Self-Supervised World Modelscited by 365
  10. 2019Multi-Object Representation Learning with Iterative Variational Inferencecited by 359
  11. 2018Large-Scale Study of Curiosity-Driven Learningcited by 277
  12. 2019Self-Supervised Exploration via Disagreementcited by 263
  13. 2019Contrastive Learning of Structured World Modelscited by 206
  14. 2023Segment and Track Anythingcited by 193
  15. 2021Behavior From the Void: Unsupervised Active Pre-Trainingcited by 173
  16. 2022SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Modelscited by 146
  17. 2021URLB: Unsupervised Reinforcement Learning Benchmarkcited by 138
  18. 2021State Entropy Maximization with Random Encoders for Efficient Explorationcited by 107
  19. 2021The Distracting Control Suite -- A Challenging Benchmark for Reinforcement Learning from Pixelscited by 97
  20. 2021Generalization and Robustness Implications in Object-Centric Learningcited by 81
  21. 2021DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical Representationscited by 73
  22. 2021Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapescited by 70
  23. 2017Data-efficient Deep Reinforcement Learning for Dexterous Manipulationcited by 61
  24. 2021AW-Opt: Learning Robotic Skills with Imitation and Reinforcement at Scalecited by 43
  25. 2021Curiosity-Driven Exploration via Latent Bayesian Surprisecited by 22
  26. 2022Mastering the Unsupervised Reinforcement Learning Benchmark from Pixelscited by 20
  27. 2021Touch-based Curiosity for Sparse-Reward Taskscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 10; 2025: 4; 2026: 2.

17 papers.

Sort:

By area:

  1. 2023MUVO: A Multimodal Generative World Model for Autonomous Driving with Geometric Representationscited by 33
  2. 2024Entity-Centric Reinforcement Learning for Object Manipulation from Pixelscited by 27
  3. 2026OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulationcited by 25
  4. 2024World Model-based Perception for Visual Legged Locomotioncited by 17
  5. 2024Composing Pre-Trained Object-Centric Representations for Robotics From "What" and "Where" Foundation Modelscited by 16
  6. 2025PlaySlot: Learning Inverse Latent Dynamics for Controllable Object-Centric Video Prediction and Planningcited by 13
  7. 2025Dyn-O: Building Structured World Models with Object-Centric Representationscited by 12
  8. 2024EC-Diffuser: Multi-Object Manipulation via Entity-Centric Behavior Generationcited by 8
  9. 2024Recasting Generic Pretrained Vision Transformers As Object-Centric Scene Encoders For Manipulation Policiescited by 6
  10. 2025Focusing on What Matters: Object-Agent-centric Tokenization for Vision Language Action modelscited by 6
  11. 2024Object-Centric Temporal Consistency via Conditional Autoregressive Inductive Biasescited by 5
  12. 2024Make the Pertinent Salient: Task-Relevant Reconstruction for Visual Control with Distractionscited by 4
5 more
  1. 2024Zero-Shot Generalization of Vision-Based RL Without Data Augmentationcited by 3
  2. 2024Physically Interpretable World Models via Weakly Supervised Representation Learningcited by 3
  3. 2026A Definition and Roadmap for World Modelscited by 3
  4. 2024Grouped Discrete Representation Guides Object-Centric Learningcited by 2
  5. 2025Learning to Grasp Anything by Playing with Random Toyscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Representing Positional Information in Generative World Models for Object Manipulation
  2. 2025Object-Centric World Model for Language-Guided Manipulation
  3. 2025A Step Toward World Models: A Survey on Robotic Manipulation
  4. 2022Binding Actions to Objects in World Models
  5. 2026World Models for Robotic Manipulation: A Survey
  6. 2022Factored World Models for Zero-Shot Generalization in Robotic Manipulation
  7. 2025OmniManip: Towards General Robotic Manipulation via Object-Centric Interaction Primitives as Spatial Constraints
  8. 2026Unifying Object-Centric World Models and Diffusion Policy: A Hierarchical Framework for Multi-Stage Robotic Tasks