ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2506.00589
25
0

Constrained Stein Variational Gradient Descent for Robot Perception, Planning, and Identification

31 May 2025
Griffin Tabor
Tucker Hermans
ArXiv (abs)PDFHTML
Main:8 Pages
6 Figures
Bibliography:2 Pages
Abstract

Many core problems in robotics can be framed as constrained optimization problems. Often on these problems, the robotic system has uncertainty, or it would be advantageous to identify multiple high quality feasible solutions. To enable this, we present two novel frameworks for applying principles of constrained optimization to the new variational inference algorithm Stein variational gradient descent. Our general framework supports multiple types of constrained optimizers and can handle arbitrary constraints. We demonstrate on a variety of problems that we are able to learn to approximate distributions without violating constraints. Specifically, we show that we can build distributions of: robot motion plans that exactly avoid collisions, robot arm joint angles on the SE(3) manifold with exact table placement constraints, and object poses from point clouds with table placement constraints.

View on arXiv
@article{tabor2025_2506.00589,
  title={ Constrained Stein Variational Gradient Descent for Robot Perception, Planning, and Identification },
  author={ Griffin Tabor and Tucker Hermans },
  journal={arXiv preprint arXiv:2506.00589},
  year={ 2025 }
}
Comments on this paper