Skip to content
DraconiticResearch
Search Sources API
197,768 studies31 sourcesUpdated 23 min ago
PreprintCC BY 4.0arXiv

Notes on Generative Modeling for Feedback Control and Planning

  • Karthik Elamvazhuthi
Open at sourcePDFDOICite

Abstract

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.

Related

  1. Amortized Feedback Planning: Turning Model-Based Rollouts into Executable Policies
    Jeonggyu Huh
    arXivPreprintarXiv licenceFull textOptimisation & controlarXiv
  2. LyapuFlow: Controlling Generative Flows with Lyapunov Feedback for Inverse Problems
    Minseon Gwak, Hans Hao-Hsun Hsu, Danielle C. Maddix +1
    arXivPreprintarXiv licenceFull textStatisticsarXiv
  3. Generative Deep Learning for CSI Feedback in Massive MIMO via Channel Distribution Prediction
    Liujia Yao, Changsheng You, Chao Zhou +2
    arXivPreprintarXiv licenceFull textGeneral mathematicsarXiv
  4. Generative modeling via hierarchical tensor sketching
    Yifan Peng, Yi-An Chen, Edwin Miles Stoudenmire +1
    Journal of Computational and Applied MathematicsPeer-reviewedLicence not statedFull text23 citedNumerical analysis & scientific computingOpenAlex
  5. CleanRM: Reward Modeling from Noisy Feedback with a Few Clean Feedback for RLHF
    Licheng Pan, Haocheng Yang, Yuzhou Chen +7
    arXivPreprintarXiv licenceFull textStatisticsarXiv

Cite

BibTeXRIS
BibTeX
@misc{elamvazhuthi2026notes,
  title = {{Notes on Generative Modeling for Feedback Control and Planning}},
  author = {Karthik Elamvazhuthi},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2609.33164},
  eprint = {2609.33164},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.33164},
  note = {CC BY 4.0},
}
RIS
TY  - UNPB
TI  - Notes on Generative Modeling for Feedback Control and Planning
AU  - Karthik Elamvazhuthi
PY  - 2026
DA  - 2026/09/27
PB  - arXiv
DO  - 10.48550/arxiv.2609.33164
UR  - https://arxiv.org/abs/2609.33164
AB  - 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.
ER  -