publications

2025

1. 

   Diffusion-Informed Probabilistic Contact Search for Multi-Finger Manipulation

   *Abhinav Kumar , *Thomas Power , Fan Yang , and 4 more authors

   In International Conference on Robotics and Automation (ICRA) , 2025

   Bib HTML Video

   @inproceedings{dips,
     author = {Kumar, *Abhinav and Power, *Thomas and Yang, Fan and Aguilera Marinovic, Sergio and Iba, Soshi and Soltani Zarrin, Rana and Berenson, Dmitry},
     booktitle = {International Conference on Robotics and Automation (ICRA)},
     title = {Diffusion-Informed Probabilistic Contact Search for Multi-Finger Manipulation},
     year = {2025},
     doi = {10.1109/ICRA55743.2025.11127844},
   }

2. Multi-finger manipulation via trajectory optimization with differentiable rolling and geometric constraints

   Fan Yang , Thomas Power, Sergio Aguilera Marinovic , and 3 more authors

   IEEE Robotics and Automation Letters, 2025

   Bib HTML Video

   @article{fantrajopt,
     author = {Yang, Fan and Power, Thomas and Aguilera Marinovic, Sergio and Iba, Soshi and Soltani Zarrin, Rana and Berenson, Dmitry},
     journal = {IEEE Robotics and Automation Letters},
     title = {Multi-finger manipulation via trajectory optimization with differentiable rolling and geometric constraints},
     year = {2025},
     volume = {10},
     issue = {5},
     pages = {5170-5177},
     doi = {10.1109/LRA.2025.3557752},
   }

2024

1. Probabilistic Contact Mode Planning for Multi-Finger Manipulation Using Diffusion Models

   *Thomas Power , *Abhinav Kumar , Fan Yang , and 4 more authors

   In CoRL 2025 Workshop on Learning Robot Fine and Dexterous Manipulation: Perception and Control , 2024

   Bib

   @inproceedings{dips_workshop,
     author = {Power, *Thomas and Kumar, *Abhinav and Yang, Fan and Aguilera Marinovic, Sergio and Iba, Soshi and Soltani Zarrin, Rana and Berenson, Dmitry},
     booktitle = {CoRL 2025 Workshop on Learning Robot Fine and Dexterous Manipulation:
     Perception and Control},
     title = {Probabilistic Contact Mode Planning for Multi-Finger Manipulation Using Diffusion Models},
     year = {2024},
   }

2. 

   Learning a Generalizable Trajectory Sampling Distribution for Model Predictive Control

   Thomas Power, and Dmitry Berenson

   IEEE Transactions on Robotics, 2024

   Bib HTML Video

   @article{10449376,
     author = {Power, Thomas and Berenson, Dmitry},
     journal = {IEEE Transactions on Robotics},
     title = {Learning a Generalizable Trajectory Sampling Distribution for Model Predictive Control},
     year = {2024},
     volume = {40},
     pages = {2111-2127},
     doi = {10.1109/TRO.2024.3370026},
   }

3. 

   Constrained Stein Variational Trajectory Optimization

   Thomas Power, and Dmitry Berenson

   IEEE Transactions on Robotics, 2024

   arXiv Bib HTML

   @article{power2023constrained,
     title = {Constrained Stein Variational Trajectory Optimization},
     author = {Power, Thomas and Berenson, Dmitry},
     journal = {IEEE Transactions on Robotics},
     year = {2024},
     volume = {40},
     number = {},
     pages = {3602-3619},
     doi = {10.1109/TRO.2024.3428428}
   }

2023

1. Task-space Kernels for Diverse Stein Variational MPC

   Madhav Shekhar Sharma , Thomas Power, and Dmitry Berenson

   In IROS 2023 Workshop on Differentiable Probabilistic Robotics: Emerging Perspectives on Robot Learning , 2023

   Bib HTML

   @inproceedings{sharma2023task,
     title = {Task-space Kernels for Diverse Stein Variational MPC},
     author = {Sharma, Madhav Shekhar and Power, Thomas and Berenson, Dmitry},
     booktitle = {IROS 2023 Workshop on Differentiable Probabilistic Robotics: Emerging Perspectives on Robot Learning},
     year = {2023},
   }

2. Sampling Constrained Trajectories Using Composable Diffusion Models

   Thomas Power, Rana Soltani-Zarrin , Soshi Iba , and 1 more author

   In IROS 2023 Workshop on Differentiable Probabilistic Robotics: Emerging Perspectives on Robot Learning , 2023

   Bib HTML

   @inproceedings{power2023sampling,
     title = {Sampling Constrained Trajectories Using Composable Diffusion Models},
     author = {Power, Thomas and Soltani-Zarrin, Rana and Iba, Soshi and Berenson, Dmitry},
     booktitle = {IROS 2023 Workshop on Differentiable Probabilistic Robotics: Emerging Perspectives on Robot Learning},
     year = {2023},
   }

2022

1. 

   Variational Inference MPC using Normalizing Flows and Out-of-Distribution Projection

   Thomas Power, and Dmitry Berenson

   In Robotics: Science and Systems , 2022

   arXiv Bib Video

   @inproceedings{power2022flowmpc,
     title = {Variational Inference MPC using Normalizing Flows and Out-of-Distribution Projection},
     author = {Power, Thomas and Berenson, Dmitry},
     booktitle = {Robotics: Science and Systems},
     year = {2022},
   }

2. Improving Sample-based MPC with Normalizing Flows & Out-of-distribution Projection

   Thomas Power, and Dmitry Berenson

   In Planning with Implicit Neural Representations of Geometry Workshop, ICRA , 2022

2021

1. 

   Keep It Simple: Data-Efficient Learning for Controlling Complex Systems With Simple Models

   Thomas Power, and Dmitry Berenson

   IEEE Robotics and Automation Letters, 2021

   Bib HTML Video

   @article{power2021lvspc,
     author = {Power, Thomas and Berenson, Dmitry},
     journal = {IEEE Robotics and Automation Letters},
     title = {Keep It Simple: Data-Efficient Learning for Controlling Complex Systems With Simple Models},
     year = {2021},
     volume = {6},
     number = {2},
     pages = {1184-1191},
   }

2. Variational Inference MPC for Robot Motion with Normalizing Flows

   Thomas Power, and Dmitry Berenson

   In Robot Learning Workshop, NeurIPS , 2021

2020

1. 

   Learning When to Trust a Dynamics Model for Planning in Reduced State Spaces

   Dale McConachie , Thomas Power, Peter Mitrano , and 1 more author

   IEEE Robotics and Automation Letters, 2020

   Bib HTML Video

   @article{8988145,
     author = {McConachie, Dale and Power, Thomas and Mitrano, Peter and Berenson, Dmitry},
     journal = {IEEE Robotics and Automation Letters},
     title = {Learning When to Trust a Dynamics Model for Planning in Reduced State Spaces},
     year = {2020},
     volume = {5},
     number = {2},
     pages = {3540-3547},
     doi = {10.1109/LRA.2020.2972858},
   }

2. Data-efficient Control from Images by Learning How to Use a Simple Model

   Thomas Power, and Dmitry Berenson

   In Machine Learning for Planning in Planning and Control of Robot Motion Workshop, ICRA , 2020