Lasse Peters
Lasse Peters

About Me

I am a postdoctoral researcher at the ICON Lab at UC Berkeley, where I work with Negar Mehr. I obtained my PhD from TU Delft, where I was advised by Javier Alonso-Mora and Laura Ferranti. Beyond Berkeley and Delft, I worked with Cyrill Stachniss at the University of Bonn and as a visiting researcher with Andrea Bajcsy at Carnegie Mellon University.

I develop algorithms that let robots handle complex interaction with the real world. That complexity may come from challenging dynamics, as in agile flight or contact-rich manipulation, or from other agents, humans and robots alike, whose behavior the robot must anticipate. My work builds on tools from reinforcement learning, imitation learning, and game theory to make such interaction tractable: learning policies and interaction models from limited data and keeping robots safe when their models are uncertain. I care about methods that work on real hardware, so I validate them on manipulators, mobile robots, and quadrotors.

My dissertation focused on the multi-agent side of this picture: using dynamic game theory to capture how a robot’s decisions and those of the agents around it shape each other. My RSS Pioneers research statement provides a more detailed overview of my past work and future directions.

Contact

For coordinating meetings, this calendar shows times when I will be busy.
Email: lasse.peters@berkeley.edu

Selected Publications

  1. Coordinated Diffusion: Generating Multi-Agent Behavior Without Multi-Agent Demonstrations Lasse Peters, Laura Ferranti†, Andrea Bajcsy†, Javier Alonso-Mora† arXiv preprint arXiv:2605.11485, 2026 Hardware · Franka
    paperwebsite
    bib 
    @article{peters2026codi,
    title   = {Coordinated Diffusion: Generating Multi-Agent Behavior Without Multi-Agent Demonstrations},
    author  = {Peters, Lasse and Ferranti, Laura and Bajcsy, Andrea and Alonso-Mora, Javier},
    journal = {arXiv preprint arXiv:2605.11485},
    year    = {2026},
    url     = {https://arxiv.org/abs/2605.11485}
}
  2. Strategizing at Speed: A Learned Model Predictive Game for Multi-Agent Drone Racing Andrei-Carlo Papuc, Lasse Peters, Sihao Sun, Laura Ferranti, Javier Alonso-Mora IEEE Robotics and Automation Letters (RA-L), 2026 Hardware · Agilicious quadrotor
    paper
    bib 
    @article{papuc2026strategizing,
    title   = {Strategizing at Speed: A Learned Model Predictive Game for Multi-Agent Drone Racing},
    author  = {Papuc, Andrei-Carlo and Peters, Lasse and Sun, Sihao and Ferranti, Laura and Alonso-Mora, Javier},
    journal = {IEEE Robotics and Automation Letters (RA-L)},
    volume  = {11},
    number  = {8},
    pages   = {9056--9063},
    year    = {2026},
    doi     = {10.1109/LRA.2026.3701568}
}
  3. Bayesian Inverse Games with High-Dimensional Multi-Modal Observations Yash Jain*, Xinjie Liu*, Lasse Peters*, David Fridovich-Keil, Ufuk Topcu arXiv preprint arXiv:2601.00696, 2026
    paper
    bib 
    @article{jain2026bayesian,
    title   = {Bayesian Inverse Games with High-Dimensional Multi-Modal Observations},
    author  = {Jain, Yash and Liu, Xinjie and Peters, Lasse and Fridovich-Keil, David and Topcu, Ufuk},
    journal = {arXiv preprint arXiv:2601.00696},
    year    = {2026},
    url     = {https://arxiv.org/abs/2601.00696}
}
  4. Generalizing Safety Beyond Collision-Avoidance via Latent-Space Reachability Analysis Kensuke Nakamura, Lasse Peters, Andrea Bajcsy Robotics: Science and Systems (RSS), 2025 Hardware · Franka
    paperwebsite
    bib 
    @inproceedings{nakamura2025latent,
    title     = {Generalizing Safety Beyond Collision-Avoidance via Latent-Space Reachability Analysis},
    author    = {Nakamura, Kensuke and Peters, Lasse and Bajcsy, Andrea},
    booktitle = {Proc.~of Robotics: Science and Systems (RSS)},
    year      = {2025},
    doi       = {10.15607/RSS.2025.XXI.113}
}
  5. Contingency Games for Multi-Agent Interaction Lasse Peters, Andrea Bajcsy, Chih-Yuan Chiu, David Fridovich-Keil, Forrest Laine, Laura Ferranti, Javier Alonso-Mora IEEE Robotics and Automation Letters (RA-L), 2024 · Best Paper Finalist, IEEE RAS TC on Robot Control
    paperwebsitecodevideo
    bib 
    @article{peters2024ral,
  title={Contingency Games for Multi-Agent Interaction},
  author={Peters, Lasse and Bajcsy, Andrea and Chiu, Chih-Yuan and Fridovich-Keil, David and Laine, Forrest and Ferranti, Laura and Alonso-Mora, Javier},
  journal={IEEE Robotics and Automation Letters (RA-L)},
  year={2024},
  volume={9},
  number={3},
  pages={2208--2215},
  doi={10.1109/lra.2024.3354548},
}
  6. Learning Mixed Strategies in Trajectory Games Lasse Peters, David Fridovich-Keil, Laura Ferranti, Cyrill Stachniss, Javier Alonso-Mora, Forrest Laine Robotics: Science and Systems (RSS), 2022
    paperwebsitecodevideo
    bib 
    @inproceedings{peters2022rss,
    title     = {Learning Mixed Strategies in Trajectory Games},
    author    = {Peters, Lasse and Fridovich-Keil, David and Ferranti, Laura and Stachniss, Cyrill and Alonso-Mora, Javier and Laine, Forrest},
    booktitle = {Proc.~of Robotics: Science and Systems (RSS)},
    year      = {2022},
    url       = {https://arxiv.org/abs/2205.00291},
    doi       = {10.15607/rss.2022.xviii.051},
}

* Equal contribution† Equal advising

All publications →