mlsanityData to 7 Oct 2026

Learning Symbolic Operators for Task and Motion Planning

arXiv 2103.00589 ↗First posted 28 Feb 2021cs.RO cs.AI cs.LGcited by 57

Not on the map. Why?

Abstract (arXiv)

Robotic planning problems in hybrid state and action spaces can be solved by integrated task and motion planners (TAMP) that handle the complex interaction between motion-level decisions and task-level plan feasibility. TAMP approaches rely on domain-specific symbolic operators to guide the task-level search, making planning efficient. In this work, we formalize and study the problem of operator learning for TAMP. Central to this study is the view that operators define a lossy abstraction of the transition model of a domain. We then propose a bottom-up relational learning method for operator learning and show how the learned operators can be used for planning in a TAMP system. Experimentally, we provide results in three domains, including long-horizon robotic planning tasks. We find our approach to substantially outperform several baselines, including three graph neural network-based model-free approaches from the recent literature. Video: https://youtu.be/iVfpX9BpBRo Code: https://git.io/JCT0g

Key facts. Cited by 57 papers in the map (data through 7 Oct 2026). Builds on 12 of its 32 references that are in the map. First posted on arXiv 28 Feb 2021.

Builds on

12 of 32 references.

References · 12

  1. 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
  2. 2020Integrated Task and Motion Planningcited by 281
  3. 2018PDDLStream: Integrating Symbolic Planners and Blackbox Samplers via Optimistic Adaptive Planningcited by 147
  4. 2020Inductive logic programming at 30: a new introductioncited by 83
  5. 2020Hierarchical Planning for Long-Horizon Manipulation with Geometric and Symbolic Scene Graphscited by 83
  6. 2020Deep Visual Reasoning: Learning to Predict Action Sequences for Task and Motion Planning from an Initial Scene Imagecited by 45
  7. 2018Active model learning and diverse action sampling for task and motion planningcited by 28
  8. 2018Learning to guide task and motion planning using score-space representationcited by 27
  9. 2020SPOTTER: Extending Symbolic Planning Operators through Targeted Reinforcement Learningcited by 23
  10. 2018Learning Quickly to Plan Quickly Using Modular Meta-Learningcited by 15
  11. 2019Learning STRIPS Action Models with Classical Planningcited by 13
  12. 2018Learning sparse relational transition modelscited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 9; 2023: 12; 2024: 10; 2025: 13; 2026: 11.

57 papers.

Sort:

By area:

  1. 2024ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulationcited by 305
  2. 2023Text2Motion: From Natural Language Instructions to Feasible Planscited by 223
  3. 2022Learning Neuro-Symbolic Skills for Bilevel Planningcited by 55
  4. 2022Predicate Invention for Bilevel Planningcited by 49
  5. 2021Learning Neuro-Symbolic Relational Transition Models for Bilevel Planningcited by 43
  6. 2026World Model for Robot Learning: A Comprehensive Surveycited by 42
  7. 2024VisualPredicator: Learning Abstract World Models with Neuro-Symbolic Predicates for Robot Planningcited by 37
  8. 2023Learning adaptive planning representations with natural language guidancecited by 36
  9. 2022LEAGUE: Guided Skill Learning and Abstraction for Long-Horizon Manipulationcited by 32
  10. 2023Vision-Language Interpreter for Robot Task Planningcited by 29
  11. 2023Human-in-the-Loop Task and Motion Planning for Imitation Learningcited by 28
  12. 2025PoE-World: Compositional World Modeling with Products of Programmatic Expertscited by 25
38 more
  1. 2024Practice Makes Perfect: Planning to Learn Skill Parameter Policiescited by 22
  2. 2024A Survey of Optimization-based Task and Motion Planning: From Classical To Learning Approachescited by 19
  3. 2022Learning Efficient Abstract Planning Models that Choose What to Predictcited by 17
  4. 2023Embodied Lifelong Learning for Task and Motion Planningcited by 17
  5. 2024Partially Observable Task and Motion Planning with Uncertainty and Risk Awarenesscited by 17
  6. 2024Composable Part-Based Manipulationcited by 17
  7. 2022DANLI: Deliberative Agent for Following Natural Language Instructionscited by 15
  8. 2025Synthesizing world models for bilevel planningcited by 13
  9. 2026LiLo-VLA: Compositional Long-Horizon Manipulation via Linked Object-Centric Policiescited by 12
  10. 2024From Pixels to Predicates: Learning Symbolic World Models via Pretrained Vision-Language Modelscited by 11
  11. 2022Accelerating Integrated Task and Motion Planning with Neural Feasibility Checkingcited by 10
  12. 2021Learning to Search in Task and Motion Planning with Streamscited by 9
  13. 2023Embodied Active Learning of Relational State Abstractions for Bilevel Planningcited by 8
  14. 2023NOD-TAMP: Generalizable Long-Horizon Planning with Neural Object Descriptorscited by 8
  15. 2025ExoPredicator: Learning Abstract Models of Dynamic Worlds for Robot Planningcited by 8
  16. 2022Meta-Learning Parameterized Skillscited by 7
  17. 2023PDSketch: Integrated Planning Domain Programming and Learningcited by 7
  18. 2022Creative Problem Solving in Artificially Intelligent Agents: A Survey and Frameworkcited by 4
  19. 2025Prime the search: Using large language models for guiding geometric task and motion planning by warm-starting tree searchcited by 4
  20. 2025Compose by Focus: Scene Graph-based Atomic Skillscited by 4
  21. 2025A Systematic Study of Large Language Models for Task and Motion Planning With PDDLStreamcited by 4
  22. 2023Discovering Predictive Relational Object Symbols with Symbolic Attentive Layerscited by 3
  23. 2024Learning Planning Abstractions from Languagecited by 3
  24. 2025Curiosity-Driven Imagination: Discovering Plan Operators and Learning Associated Policies for Open-World Adaptationcited by 3
  25. 2025Learning from Less: Guiding Deep Reinforcement Learning with Differentiable Symbolic Planningcited by 3
  26. 2025SLAP: Shortcut Learning for Abstract Planningcited by 3
  27. 2026Kintsugi: Learning Policies by Repairing Executable Knowledge Basescited by 3
  28. 2023Learning Type-Generalized Actions for Symbolic Planningcited by 2
  29. 2023Learning Concept-Based Causal Transition and Symbolic Reasoning for Visual Planningcited by 2
  30. 2025Few-Shot Neuro-Symbolic Imitation Learning for Long-Horizon Planning and Actingcited by 2
  31. 2025Symbolic Planning and Multi-Agent Path Finding in Extremely Dense Environments with Unassigned Agentscited by 2
  32. 2022Policy-Guided Lazy Search with Feedback for Task and Motion Planningcited by 1
  33. 2023Learning a Hierarchical Planner from Humans in Multiple Generationscited by 1
  34. 2024Learning to Bridge the Gap: Efficient Novelty Recovery with Planning and Reinforcement Learningcited by 1
  35. 2024Learning for Long-Horizon Planning via Neuro-Symbolic Abductive Imitationcited by 1
  36. 2025Learning Hierarchical Domain Models Through Environment-Grounded Interactioncited by 1
  37. 2026Toward Learning POMDPs Beyond Full-Rank Actions and State Observabilitycited by 1
  38. 2025Grounded Vision-Language Interpreter for Long-Horizon Bimanual Task and Motion Planningcited by 0

50 most cited of 57 All 57 (JSON)