mlsanityData to 7 Oct 2026

Generative Models From and For Sampling-Based MPC: A Bootstrapped Approach For Adaptive Contact-Rich Manipulation

arXiv 2510.14643 ↗First posted 16 Oct 2025cs.ROcited by 2

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

Abstract (arXiv)

We present a generative predictive control (GPC) framework that amortizes sampling-based Model Predictive Control (SPC) by bootstrapping it with conditional flow-matching models trained on SPC control sequences collected in simulation. Unlike prior work relying on iterative refinement or gradient-based solvers, we show that meaningful proposal distributions can be learned directly from noisy SPC data, enabling more efficient and informed sampling during online planning. We further demonstrate, for the first time, the application of this approach to real-world contact-rich loco-manipulation with a quadruped robot. Extensive experiments in simulation and on hardware show that our method improves sample efficiency, reduces planning horizon requirements, and generalizes robustly across task variations.

Key facts. Cited by 2 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 37 of its 68 references that are in the map. First posted on arXiv 16 Oct 2025.

Builds on

37 of 68 references.

Closest ancestors · 7

Same direction, newest first

  1. 2025Diffusion-Based Approximate MPC: Fast and Consistent Imitation of Multi-Modal Action Distributions6 Apr
  2. 2025Generative Predictive Control: Flow Matching Policies for Dynamic and Difficult-to-Demonstrate Tasks19 Feb
  3. 2024Diffusion Model Predictive Control7 Oct
  4. 2024Model-Based Diffusion for Trajectory Optimization28 May
  5. 2024DiffuSolve: Diffusion-based Solver for Non-convex Trajectory Optimization22 Feb
  6. 2023Motion Planning Diffusion: Learning and Planning of Robot Motions with Diffusion Models3 Aug
  7. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusion7 Mar

Other references · 30

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2022Flow Matching for Generative Modelingcited by 5,426
  3. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  4. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,490
  5. 2023Improving and generalizing flow-based generative models with minibatch optimal transportcited by 835
  6. 2023TD-MPC2: Scalable, Robust World Models for Continuous Controlcited by 482
  7. 2017Thinking Fast and Slow with Deep Learning and Tree Searchcited by 245
  8. 2018Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Controlcited by 104
  9. 2017Learning Sampling Distributions for Robot Motion Planningcited by 79
  10. 2022Motion Policy Networkscited by 53
  11. 2021STORM: An Integrated Framework for Fast Joint-Space Model-Predictive Control for Reactive Manipulationcited by 46
  12. 2022Predictive Sampling: Real-time Behaviour Synthesis with MuJoCocited by 39
18 more
  1. 2021On the Limitations of Multimodal VAEscited by 37
  2. 2019MPC-Net: A First Principles Guided Policy Searchcited by 28
  3. 2022Learning Implicit Priors for Motion Optimizationcited by 20
  4. 2024Full-Order Sampling-Based MPC for Torque-Level Locomotion Control via Diffusion-Style Annealingcited by 20
  5. 2024Neural MP: A Generalist Neural Motion Plannercited by 18
  6. 2025A Smooth Sea Never Made a Skilled SAILOR: Robust Imitation via Learning to Searchcited by 16
  7. 2019Deep Value Model Predictive Controlcited by 14
  8. 2025Bootstrapped Model Predictive Controlcited by 13
  9. 2024DROP: Dexterous Reorientation via Online Planningcited by 11
  10. 2022Learning Sampling Distributions for Model Predictive Controlcited by 10
  11. 2023Neural Networks for Fast Optimisation in Model Predictive Control: A Reviewcited by 10
  12. 2022VP-STO: Via-point-based Stochastic Trajectory Optimization for Reactive Robot Behaviorcited by 9
  13. 2021The Value of Planning for Infinite-Horizon Model Predictive Controlcited by 8
  14. 2024Toward Near-Globally Optimal Nonlinear Model Predictive Control via Diffusion Modelscited by 8
  15. 2025Versatile Loco-Manipulation through Flexible Interlimb Coordinationcited by 4
  16. 2025Dynamic object goal pushing with mobile manipulators through model-free constrained reinforcement learningcited by 3
  17. 2025Infinite-Horizon Value Function Approximation for Model Predictive Controlcited by 3
  18. 2025Judo: A User-Friendly Open-Source Package for Sampling-Based Model Predictive Controlcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Learning Loco-Manipulation From SMPC Demonstrations With Sparse Offline-to-Online RLcited by 0
  2. 2026Think Fast, Plan Selectively: Adaptive Deliberation for Efficient Data-Driven MPCcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Inference-Time Enhancement of Generative Robot Policies via Predictive World Modeling
  2. 2026Generative Control as Optimization: Time Unconditional Flow Matching for Adaptive and Robust Robotic Control
  3. 2024Should We Learn Contact-Rich Manipulation Policies from Sampling-Based Planners?
  4. 2022Learning to Optimize in Model Predictive Control
  5. 2025Flexible Locomotion Learning with Diffusion Model Predictive Control
  6. 2024Diffusion-based learning of contact plans for agile locomotion ↗
  7. 2024Learning Diffusion Policies from Demonstrations For Compliant Contact-rich Manipulation
  8. 2025Improving Generative Behavior Cloning via Self-Guidance and Adaptive Chunking