mlsanityData to 7 Oct 2026

SafeDiffuser: Safe Planning with Diffusion Probabilistic Models

arXiv 2306.00148 ↗First posted 31 May 2023cs.LG cs.RO cs.SYcited by 69

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

Abstract (arXiv)

Diffusion model-based approaches have shown promise in data-driven planning, but there are no safety guarantees, thus making it hard to be applied for safety-critical applications. To address these challenges, we propose a new method, called SafeDiffuser, to ensure diffusion probabilistic models satisfy specifications by using a class of control barrier functions. The key idea of our approach is to embed the proposed finite-time diffusion invariance into the denoising diffusion procedure, which enables trustworthy diffusion data generation. Moreover, we demonstrate that our finite-time diffusion invariance method through generative models not only maintains generalization performance but also creates robustness in safe data generation. We test our method on a series of safe planning tasks, including maze path generation, legged robot locomotion, and 3D space manipulation, with results showing the advantages of robustness and guarantees over vanilla diffusion models.

Key facts. Cited by 69 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 29 of its 50 references that are in the map. First posted on arXiv 31 May 2023.

Builds on

29 of 50 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022Is Conditional Generative Modeling all you need for Decision-Making?28 Nov

Other references · 28

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  3. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  5. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  6. 2021Convex optimizationcited by 2,479
  7. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,221
  8. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,023
  9. 2021Offline Reinforcement Learning as One Big Sequence Modeling Problemcited by 636
  10. 2023AudioLDM: Text-to-Audio Generation with Latent Diffusion Modelscited by 592
  11. 2017OptNet: Differentiable Optimization as a Layer in Neural Networkscited by 588
  12. 2019Model-Based Reinforcement Learning for Ataricited by 495
16 more
  1. 2022PhysDiff: Physics-Guided Human Motion Diffusion Modelcited by 365
  2. 2016Control Barrier Function Based Quadratic Programs for Safety Critical Systemscited by 261
  3. 2018Differentiable MPC for End-to-end Planning and Controlcited by 178
  4. 2022TransDreamer: Reinforcement Learning with Transformer World Modelscited by 143
  5. 20213D Neural Scene Representations for Visuomotor Controlcited by 110
  6. 2020Learning Control Barrier Functions from Expert Demonstrationscited by 88
  7. 2023Constrained Decision Transformer for Offline Safe Reinforcement Learningcited by 65
  8. 2021Vector Quantized Models for Planningcited by 47
  9. 2021Mismatched No More: Joint Model-Policy Optimization for Model-Based RLcited by 35
  10. 2020Model-based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEscited by 32
  11. 2019Control Barrier Functions for Systems with High Relative Degreecited by 30
  12. 2020Safe Optimal Control Using Stochastic Barrier Functions and Deep Forward-Backward SDEscited by 22
  13. 2020Learning Accurate Long-term Dynamics for Model-based Reinforcement Learningcited by 21
  14. 2020ShieldNN: A Provably Safe NN Filter for Unsafe NN Controllerscited by 17
  15. 2020Learning Safe Neural Network Controllers with Barrier Certificatescited by 16
  16. 2022On the Forward Invariance of Neural ODEscited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 16; 2025: 25; 2026: 26.

69 papers.

Sort:

By area:

  1. 2023Diffusion Models for Reinforcement Learning: A Surveycited by 84
  2. 2025What Makes a Good Diffusion Planner for Decision Making?cited by 37
  3. 2024Motion Planning Diffusion: Learning and Adapting Robot Motion Planning with Diffusion Modelscited by 32
  4. 2024Model-Based Diffusion for Trajectory Optimizationcited by 30
  5. 2024CGD: Constraint-Guided Diffusion Policies for UAV Trajectory Planningcited by 21
  6. 2024Deep Generative Models for Offline Policy Learning: Tutorial, Survey, and Perspectives on Future Directionscited by 20
  7. 2024DiffuSolve: Diffusion-based Solver for Non-convex Trajectory Optimizationcited by 19
  8. 2025Dexterous Manipulation through Imitation Learning: A Surveycited by 18
  9. 2024Diffusion Model for Planning: A Systematic Literature Reviewcited by 17
  10. 2024LTLDoG: Satisfying Temporally-Extended Symbolic Constraints for Safe Diffusion-based Planningcited by 15
  11. 2025FlowMP: Learning Motion Fields for Robot Planning with Conditional Flow Matchingcited by 15
  12. 2025DDAT: Diffusion Policies Enforcing Dynamically Admissible Robot Trajectoriescited by 14
38 more
  1. 2025Generative Models in Decision Making: A Surveycited by 14
  2. 2025SafeFlowMatcher: Safe and Fast Planning using Flow Matching with Control Barrier Functionscited by 11
  3. 2024OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learningcited by 10
  4. 2025HardFlow: Hard-Constrained Sampling for Flow-Matching Models via Trajectory Optimizationcited by 10
  5. 2025Constraint-Aware Diffusion Guidance for Robotics: Real-Time Obstacle Avoidance for Autonomous Racingcited by 9
  6. 2025Constrained Diffusers for Safe Planning and Controlcited by 9
  7. 2023Denoising Heat-inspired Diffusion with Insulators for Collision Free Motion Planningcited by 8
  8. 2024Learning from Random Demonstrations: Offline Reinforcement Learning with Importance-Sampled Diffusion Modelscited by 8
  9. 2024BiRoDiff: Diffusion policies for bipedal robot locomotion on unseen terrainscited by 6
  10. 2024Stable Continual Reinforcement Learning via Diffusion-based Trajectory Replaycited by 6
  11. 2025Zero-Shot Trajectory Planning for Signal Temporal Logic Taskscited by 6
  12. 2025CHD: Coupled Hierarchical Diffusion for Long-Horizon Taskscited by 6
  13. 2024RAIL: Reachability-Aided Imitation Learning for Safe Policy Executioncited by 5
  14. 2024The Duality of Generative AI and Reinforcement Learning in Robotics: A Reviewcited by 5
  15. 2026Safe-Night VLA: Seeing the Unseen via Thermal-Perceptive Vision-Language-Action Models for Safety-Critical Manipulationcited by 5
  16. 2024Dynamic High-Order Control Barrier Functions with Diffuser for Safety-Critical Trajectory Planning at Signal-Free Intersectionscited by 4
  17. 2025DiffusionRL: Efficient Training of Diffusion Policies for Robotic Grasping Using RL-Adapted Large-Scale Datasetscited by 4
  18. 2025UniConFlow: A Unified Constrained Flow-Matching Framework for Certified Motion Planningcited by 4
  19. 2025From Demonstrations to Safe Deployment: Path-Consistent Safety Filtering for Diffusion Policiescited by 4
  20. 2026How Does the Lagrangian Guide Safe Reinforcement Learning through Diffusion Models?cited by 4
  21. 2026Safety-Guided Flow (SGF): A Unified Framework for Negative Guidance in Safe Generationcited by 4
  22. 2025Generative AI for Autonomous Driving: A Reviewcited by 3
  23. 2025Risk-Guided Diffusion: Toward Deploying Robot Foundation Models in Space, Where Failure Is Not An Optioncited by 3
  24. 2025RODS: Robust Optimization Inspired Diffusion Sampling for Detecting and Reducing Hallucination in Generative Modelscited by 3
  25. 2026Implicit Maximum Likelihood Estimation for Real-time Generative Model Predictive Controlcited by 3
  26. 2024Dynamic Obstacle Avoidance through Uncertainty-Based Adaptive Planning with Diffusioncited by 2
  27. 2024Denoising Diffusion Planner: Learning Complex Paths from Low-Quality Demonstrationscited by 2
  28. 2025Formal Safety Verification and Refinement for Generative Motion Planners via Certified Local Stabilizationcited by 2
  29. 2025SAD-Flower: Flow Matching for Safe, Admissible, and Dynamically Consistent Planningcited by 2
  30. 2025Model-Based Diffusion Sampling for Predictive Control in Offline Decision Makingcited by 2
  31. 2025Masked Generative Policy for Robotic Controlcited by 2
  32. 2026Safe Vision Language Action Models via Barrier Enhanced Flow Matchingcited by 2
  33. 2026Contractive Diffusion Policies: Robust Action Diffusion via Contractive Score-Based Sampling with Differential Equationscited by 1
  34. 2026Guiding Vector Field Generation via Score-based Diffusion Modelcited by 1
  35. 2026DriveAnchor: Progressive Anchor-based Flow Learning for Autonomous Driving Planningcited by 1
  36. 2026PolyFlow: Safe and Efficient Polytope-Constrained Flow Matching with Constraint Embedding and Projection-free Updatecited by 1
  37. 2026Motion Planning with Model-Based Diffusion via Constraint Optimization and Adaptive Schedulingcited by 1
  38. 2026Steering Generative Robot Policies with Lexicographic Preferencescited by 1

50 most cited of 69 All 69 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Graph-Guided Safe Diffuser: Topological Graph Guidance for Safe Diffusion Planning ↗
  2. 2025Joint Model-based Model-free Diffusion for Planning with Constraints
  3. 2026DiRecT: Safe Diffusion-Based Planning via Receding-Horizon Denoising
  4. 2026RS-Diffuser: Risk-Sensitive Diffusion Planning with Distributional Value Guidance
  5. 2023Motion Planning Diffusion: Learning and Planning of Robot Motions with Diffusion Models
  6. 2024CoBL-Diffusion: Diffusion-Based Conditional Robot Planning in Dynamic Environments Using Control Barrier and Lyapunov Functions
  7. 2025Diffusion-SAFE: Diffusion-Native Human-to-Robot Driving Handover for Shared Autonomy
  8. 2025Diffusion-based Planning with Learned Viability Filters