Notes on Generative Modeling for Feedback Control and Planning
On the map: Diffusion models → Diffusion and flow policies for robotics
Abstract (arXiv)
In these notes, we view control as a dynamically constrained sampling problem on the state-space of a control system. With this viewpoint, we extend methods from generative modeling, such as flow matching, normalizing flows and denoising diffusions to control problems. Concepts such as controllability, optimal control and trajectory planning play an important role in guiding the extension and understanding well-posedeness of the corresponding algorithms, with application to steering systems to target states or distributions and sampling from reachable sets. The notes are intended as an accessible introduction for readers with a background in control theory and robotics.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models. Builds on 8 of its 51 references that are in the map. First posted on arXiv 27 Sep 2026.
Builds on
8 of 51 references.
References · 8
- 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
- 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,061
- 2018Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Reviewcited by 482
- 2024Benamou-Brenier Formulation of Optimal Transport for Nonlinear Control Systems on Rdcited by 5
- 2024Flow matching for stochastic linear control systemscited by 4
- 2025Flow Matching for Measure Transport and Feedback Stabilization of Control-Affine Systemscited by 3
- 2025Score Matching Diffusion Based Feedback Control and Planning of Nonlinear Systemscited by 2
- 2016Optimal transport over nonlinear systems via infinitesimal generators on graphscited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Dynamics-aware Diffusion Models for Planning and Control
- 2025Generative Predictive Control: Flow Matching Policies for Dynamic and Difficult-to-Demonstrate Tasks
- 2024Denoising Diffusion-Based Control of Nonlinear Systems
- 2025Much Ado About Noising: Dispelling the Myths of Generative Robotic Control
- 2025HardFlow: Hard-Constrained Sampling for Flow-Matching Models via Trajectory Optimization
- 2026Grounding Generative Policies in Physics: Optimization-Guided Diffusion for Robot Control
- 2026Generative Control as Optimization: Time Unconditional Flow Matching for Adaptive and Robust Robotic Control
- 2025Offline Reinforcement Learning with Generative Trajectory Policies