Rohan Sinha

rhnsinha [at] stanford [dot] edu

prof_pic.jpg

PhD Candidate

Autonomous Systems Lab

Stanford University

I am a PhD candidate in the department of Aeronautics and Astronautics at Stanford University, where I am a member of the Autonomous Systems Lab advised by Prof. Marco Pavone. I currently am also a student researcher at Google Deepmind Robotics, working with Sumeet Singh and Vikas Sindhwani

My research focuses on developing methodologies that improve the reliability of ML-enabled robotic systems, particularly when these systems encounter out-of-distribution conditions with respect to their training data. My work on this topic was recognized with the best paper award at RSS 2024. Broadly, my research interests lie at the intersection of control theory, machine learning, and applied robotics.

Previously, I received bachelor’s degrees in Mechanical Engineering and Computer Science from the University of California, Berkeley with honors and a distinction in general scholarship. As an undergraduate, I worked on data-driven predictive control under Prof. Francesco Borrelli in the Model Predictive Control Lab and on learning control algorithms that rely on vision systems under Prof. Benjamin Recht in the Berkeley Artificial Intelligence Lab. I have also interned as an autonomous driving engineer at Delphi (now Motional) and as a software engineer at Amazon.

news

Sep 1, 2023 Thrilled to organize the first workshop on Out-of-Distribution Generalization in Robotics: Towards Reliable Learning-based Autonomy! 📅 Short paper submissions open 09/01/2023, due 10/06/23
Jul 31, 2023 Our paper, titled Semantic Anomaly Detection with Large Language Models, was accepted to the Autonomous Robots’ special issue on large language models in robotics!
Jul 21, 2023 I presented a tutorial Avoiding failures in ML-enabled systems: Tutorial on Runtime Monitoring and Contingency Planning at the Center for Automotive Research at Stanford (CARS). I overviewed recent literature for runtime monitoring and presented some of our recent results. Thanks for the invitation!
Jul 18, 2023 It was an honor to give an invited talk “Towards reliable learning-enabled autonomy throughout its operational lifecycle” at the 2023 IEEE Space Mission Challenges for Information Technology - IEEE Space Computing Conference!
Jul 11, 2023 Our paper Closing the loop on runtime monitors with fallback-safe MPC was accepted to the 2023 IEEE CDC! Looking forwards to Singapore!

selected publications

2023

  1. FSMPC.gif
    Closing the Loop on Runtime Monitors with Fallback-Safe MPC
    R. Sinha, E. Schmerling, and M. Pavone
    In Proc. IEEE Conf. on Decision and Control, 2023
    (in press)
  2. anomaly_stop_sign.gif
    Semantic Anomaly Detection with Large Language Models
    A. Elhafsi, R. Sinha, C. Agia, E. Schmerling, I. A. D Nesnas, and M. Pavone
    Autonomous Robots, 2023
    Special Issue on Large Language Models in Robotics (in press)
  3. FF.gif
    Online Distribution Shift Detection via Recency Prediction
    R. Luo, R. Sinha, A. Hindy, S. Zhao, S. Savarese, E. Schmerling, and M. Pavone
    arxiv preprint, arxiv:2211.09916, 2023

2022

  1. timescales.png
    A System-Level View on Out-of-Distribution Data in Robotics
    R. Sinha, S. Sharma, S. Banerjee, T. Lew, R. Luo, S. M. Richards, Y. Sun, E. Schmerling, and M. Pavone
    arXiv preprint arXiv:2212.14020, 2022
  2. ACC-v2.png
    Adaptive Robust Model Predictive Control with Matched and Unmatched Uncertainty
    R. Sinha, J. Harrison, S. M. Richards, and M. Pavone
    In American Control Conference, 2022
  3. DroneWind.png
    Adaptive Robust Model Predictive Control via Uncertainty Cancellation
    R. Sinha, J. Harrison, S. M. Richards, and M. Pavone
    IEEE Transactions on Automatic Control, 2022
    (under review).
  4. CORL_4WAY.gif
    Cautious Markov Games for Interaction Aware Robotics
    R. Sinha, and S. Lall
    In Conference on Robot Learning: Workshop on Strategic Multi-Agent Interactions, 2022