Rohan Sinha

Contacts:

Personal Webpage

Rohan Sinha


Rohan is a graduate student in the department of Aeronautics and Astronautics. Rohan’s research interests lie at the intersection of control theory, machine learning, and applied robotics. Currently, his research focuses on developing learning-based control algorithms with safety guarantees.

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

In his free time, Rohan enjoys playing a variety of sports including sailing, tennis, soccer, and snowboarding.


ASL Publications

  1. R. Sinha, J. Harrison, S. M. Richards, and M. Pavone, “Adaptive Robust Model Predictive Control with Matched and Unmatched Uncertainty,” 2021. (Submitted)

    Abstract: We propose a learning-based robust predictive control algorithm that can handle large uncertainty in the dynamics for a class of discrete-time systems that are nominally linear with an additive nonlinear dynamics component. Such systems commonly model the nonlinear effects of an unknown environment on a nominal system. Motivated by an inability of existing learning-based predictive control algorithms to achieve safety guarantees in the presence of uncertainties of large magnitude in this setting, we achieve significant performance improvements by optimizing over a novel class of nonlinear feedback policies inspired by certainty equivalent “estimate-and-cancel” control laws pioneered in classical adaptive control. In contrast with previous work in robust adaptive MPC, this allows us to take advantage of the structure in the a priori unknown dynamics that are learned online through function approximation. Our approach also extends typical nonlinear adaptive control methods to systems with state and input constraints even when an additive uncertain function cannot directly be canceled from the dynamics. Moreover, our approach allows us to apply contemporary statistical estimation techniques to certify the safety of the system through persistent constraint satisfaction with high probability. We show that our method allows us to consider larger unknown terms in the dynamics than existing methods through simulated examples.

    @inproceedings{SinhaHarrisonEtAl2021,
      author = {Sinha, R. and Harrison, J. and Richards, S. M. and Pavone, M.},
      title = {Adaptive Robust Model Predictive Control with Matched and Unmatched Uncertainty},
      year = {2021},
      note = {Submitted},
      keywords = {sub},
      url = {https://arxiv.org/pdf/2104.08261.pdf},
      owner = {rhnsinha},
      timestamp = {2021-06-04}
    }