mlsanityData to 7 Oct 2026

Generative Skill Chaining: Long-Horizon Skill Planning with Diffusion Models

arXiv 2401.03360 ↗First posted 13 Oct 2023cs.ROcited by 87

On the map: Diffusion models → Diffusion and flow policies for robotics

Abstract (arXiv)

Long-horizon tasks, usually characterized by complex subtask dependencies, present a significant challenge in manipulation planning. Skill chaining is a practical approach to solving unseen tasks by combining learned skill priors. However, such methods are myopic if sequenced greedily and face scalability issues with search-based planning strategy. To address these challenges, we introduce Generative Skill Chaining~(GSC), a probabilistic framework that learns skill-centric diffusion models and composes their learned distributions to generate long-horizon plans during inference. GSC samples from all skill models in parallel to efficiently solve unseen tasks while enforcing geometric constraints. We evaluate the method on various long-horizon tasks and demonstrate its capability in reasoning about action dependencies, constraint handling, and generalization, along with its ability to replan in the face of perturbations. We show results in simulation and on real robot to validate the efficiency and scalability of GSC, highlighting its potential for advancing long-horizon task planning. More details are available at: https://generative-skill-chaining.github.io/

Key facts. Cited by 87 papers in the map (data through 7 Oct 2026). Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models. Builds on 41 of its 65 references that are in the map. First posted on arXiv 13 Oct 2023.

Builds on

41 of 65 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusion7 Mar
  2. 2023Imitating Human Behaviour with Diffusion Models25 Jan
  3. 2022Is Conditional Generative Modeling all you need for Decision-Making?28 Nov
  4. 2022DALL-E-Bot: Introducing Web-Scale Diffusion Models to Robotics5 Oct

Other references · 37

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2020Denoising Diffusion Implicit Modelscited by 9,655
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  5. 2022Scalable Diffusion Models with Transformerscited by 5,931
  6. 2022Classifier-Free Diffusion Guidancecited by 5,717
  7. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  8. 2016Generative Adversarial Imitation Learningcited by 1,576
  9. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
  10. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,023
  11. 2019When to Trust Your Model: Model-Based Policy Optimizationcited by 753
  12. 2018Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Modelscited by 748
25 more
  1. 2022Compositional Visual Generation with Composable Diffusion Modelscited by 619
  2. 2022Fast Sampling of Diffusion Models with Exponential Integratorcited by 526
  3. 2023Learning Universal Policies via Text-Guided Video Generationcited by 506
  4. 2018Data-Efficient Hierarchical Reinforcement Learningcited by 436
  5. 2016The Option-Critic Architecturecited by 433
  6. 2016Deep Visual Foresight for Planning Robot Motioncited by 276
  7. 2023Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMCcited by 216
  8. 2023Scaling Robot Learning with Semantically Imagined Experiencecited by 175
  9. 2022gDDIM: Generalized denoising diffusion implicit modelscited by 125
  10. 2023DiffCollage: Parallel Generation of Large Content with Diffusion Modelscited by 100
  11. 2021Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Taskscited by 75
  12. 2015Reinforcement Learning with Parameterized Actionscited by 61
  13. 2018Learning Plannable Representations with Causal InfoGANcited by 56
  14. 2018CEM-RL: Combining evolutionary and gradient-based methods for policy searchcited by 53
  15. 2020Learning compositional models of robot skills for task and motion planningcited by 47
  16. 2019Neural Empirical Bayescited by 46
  17. 2019Efficient Bimanual Manipulation Using Learned Task Schemascited by 44
  18. 2021Adversarial Skill Chaining for Long-Horizon Robot Manipulation via Terminal State Regularizationcited by 44
  19. 2020Deep Affordance Foresight: Planning Through What Can Be Done in the Futurecited by 41
  20. 2018Active model learning and diverse action sampling for task and motion planningcited by 28
  21. 2021Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoningcited by 25
  22. 2021Search-Based Task Planning with Learned Skill Effect Models for Lifelong Robotic Manipulationcited by 20
  23. 2018Learning sparse relational transition modelscited by 11
  24. 2022Symbolic State Estimation with Predicates for Contact-Rich Manipulation Taskscited by 8
  25. 2020Learning Sequences of Manipulation Primitives for Robotic Assemblycited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 28; 2025: 34; 2026: 22.

87 papers.

Sort:

By area:

  1. 2023Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Actioncited by 301
  2. 2023Diffusion Models for Reinforcement Learning: A Surveycited by 84
  3. 2024Towards Long-Horizon Vision-Language Navigation: Platform, Benchmark and Methodcited by 66
  4. 2025Long-VLA: Unleashing Long-Horizon Capability of Vision Language Action Model for Robot Manipulationcited by 48
  5. 2024PoCo: Policy Composition from and for Heterogeneous Robot Learningcited by 42
  6. 2024Compositional Generative Modeling: A Single Model is Not All You Needcited by 41
  7. 2024Towards Generalist Robot Learning from Internet Video: A Surveycited by 40
  8. 2025Diffusion Models for Robotic Manipulation: A Surveycited by 39
  9. 2025DynaGuide: Steering Diffusion Polices with Active Dynamic Guidancecited by 39
  10. 2025Generative Trajectory Stitching through Diffusion Compositioncited by 38
  11. 2024Multi-Robot Motion Planning with Diffusion Modelscited by 37
  12. 2024VisualPredicator: Learning Abstract World Models with Neuro-Symbolic Predicates for Robot Planningcited by 37
38 more
  1. 2024Deep Generative Models in Robotics: A Survey on Learning from Multimodal Demonstrationscited by 35
  2. 2024Inference-Time Policy Steering through Human Interactionscited by 35
  3. 2024TacDiffusion: Force-domain Diffusion Policy for Precise Tactile Manipulationcited by 23
  4. 2024Practice Makes Perfect: Planning to Learn Skill Parameter Policiescited by 22
  5. 2024Mamba Policy: Towards Efficient 3D Diffusion Policy with Hybrid Selective State Modelscited by 22
  6. 2024Don't Start from Scratch: Behavioral Refinement via Interpolant-based Policy Diffusioncited by 21
  7. 2024DiffuSolve: Diffusion-based Solver for Non-convex Trajectory Optimizationcited by 19
  8. 2024A Survey of Optimization-based Task and Motion Planning: From Classical To Learning Approachescited by 19
  9. 2024Generative Image as Action Modelscited by 18
  10. 2024Diffusion Policy Attacker: Crafting Adversarial Attacks for Diffusion-based Policiescited by 17
  11. 2024Diffusion Model for Planning: A Systematic Literature Reviewcited by 17
  12. 2024Language-Driven 6-DoF Grasp Detection Using Negative Prompt Guidancecited by 16
  13. 2024Diffusion Imitation from Observationcited by 12
  14. 2025Decoupled Diffusion Sparks Adaptive Scene Generationcited by 12
  15. 2026LiLo-VLA: Compositional Long-Horizon Manipulation via Linked Object-Centric Policiescited by 12
  16. 2025State-Covering Trajectory Stitching for Diffusion Plannerscited by 11
  17. 2025From Screens to Scenes: A Survey of Embodied AI in Healthcarecited by 10
  18. 2025Robotic Compliant Object Prying Using Diffusion Policy Guided by Vision and Force Observationscited by 9
  19. 2025TeLoGraF: Temporal Logic Planning via Graph-encoded Flow Matchingcited by 9
  20. 2025Latent Theory of Mind: A Decentralized Diffusion Architecture for Cooperative Manipulationcited by 9
  21. 2025Multi-Modal Manipulation via Multi-Modal Policy Consensuscited by 9
  22. 2025Local Manifold Approximation and Projection for Manifold-Aware Diffusion Planningcited by 8
  23. 2025ExoPredicator: Learning Abstract Models of Dynamic Worlds for Robot Planningcited by 8
  24. 2023C3DM: Constrained-Context Conditional Diffusion Models for Imitation Learningcited by 7
  25. 2024Generative AI Agents in Autonomous Machines: A Safety Perspectivecited by 7
  26. 2025Hybrid Diffusion for Simultaneous Symbolic and Continuous Planningcited by 6
  27. 2024RAIL: Reachability-Aided Imitation Learning for Safe Policy Executioncited by 5
  28. 2025JointDiff: Bridging Continuous and Discrete in Multi-Agent Trajectory Generationcited by 5
  29. 2024DIDI: Diffusion-Guided Diversity for Offline Behavioral Generationcited by 4
  30. 2025Flow-based Domain Randomization for Learning and Sequencing Robotic Skillscited by 4
  31. 2025Cascaded Diffusion Models for Neural Motion Planningcited by 4
  32. 2025Compose by Focus: Scene Graph-based Atomic Skillscited by 4
  33. 2025Generative View Stitchingcited by 4
  34. 2026Compositional Planning with Jumpy World Modelscited by 4
  35. 2026Diffusion ReRoll: Revisable Denoising for Robotic Sequential Predictioncited by 4
  36. 2024Scaling Value Iteration Networks to 5000 Layers for Extreme Long-Term Planningcited by 3
  37. 2024WARPD: World model Assisted Reactive Policy Diffusioncited by 3
  38. 2025Real-Time Verification of Embodied Reasoning for Generative Skill Acquisitioncited by 3

50 most cited of 87 All 87 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Generative Factor Chaining: Coordinated Manipulation with Diffusion-based Factor Graph
  2. 2025RoboHiMan: A Hierarchical Evaluation Paradigm for Compositional Generalization in Long-Horizon Manipulation
  3. 2026Skill-Aware Diffusion for Generalizable Robotic Manipulation
  4. 2026Uni-Skill: Building Self-Evolving Skill Repository for Generalizable Robotic Manipulation
  5. 2023Offline Skill Generalization via Task and Motion Planning
  6. 2023SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstractions in Diffusion-Based Task Execution
  7. 2026Flow Policies as Actions of Skill-Level World Models: Learned and Symbolic Abstractions for Long-Horizon Planning
  8. 2021Bottom-Up Skill Discovery from Unsegmented Demonstrations for Long-Horizon Robot Manipulation