Pranit Mohnot

Contacts:

Email: pmohnot at stanford dot edu

Pranit Mohnot

Pranit Mohnot is a PhD student in Stanford’s Department of Aeronautics and Astronautics. His work primarily deals with learning-based control for safe and efficient autonomy. He is also active in the Student Advisory Committee, which liaises between the AA department and student body to improve student life and quality of education. In 2023, Pranit graduated from UC Berkeley with Bachelor of Science in Mechanical Engineering, with a minor in Computer Science. At Berkeley, he conducted research on robust optimal control for hybrid systems (e.g. legged robots) as part of the Hybrid Robotics Lab. Prior to that, he helped design hardware for a tech demo of Computed Axial Lithography in microgravity (and flew on a Zero-G plane!), with the Design for Emerging and Nanoscale Manufacturing Lab. While not in the lab, Pranit can often be found playing various sports (most poorly, some decently), cooking (he is a massive cheese nerd), or generally chatting about anything and everything (with anyone).


ASL Publications

  1. D. Morton, P. Mohnot, and M. Pavone, “Constrained Whole-Body Tracking for Humanoid Robots,” 2026. (Submitted)

    [BibTeX] [Abstract]

    Abstract: Recent advances in reinforcement learning (RL) have demonstrated impressive whole-body agility for humanoid robots, yet ensuring safety and satisfying constraints – particularly those specified after training – remains a challenge. Towards this goal, we present ConstrainedMimic, a control framework that leverages whole-body kinematics and dynamics for real-time constraint enforcement within RL tracking policies. By integrating principles from operational space control and control barrier functions (CBFs), we enable the satisfaction of arbitrary runtime constraints on both the kinematic reference motion and the underlying dynamics. In whole-body motion-tracking and teleoperation experiments on a (simulated) Unitree G1 with a learned policy, we demonstrate collision avoidance (both with the robot body and external obstacles), joint limits, and center of mass stability constraints. By remaining consistent with the current contact mode and tracking objectives, we minimally restrict the capabilities of the policy when constraints are active. Our method is fully differentiable, runs on CPU, GPU, and TPU, and can be deployed at up to 300-500 Hz. All software will be freely available upon publication.

     
    @article{Morton2026constrained,
  author = {Morton, Daniel and Mohnot, Pranit and Pavone, Marco},
  title = {Constrained Whole-Body Tracking for Humanoid Robots},
  year = {2026},
  owner = {dmorton},
  timestamp = {2026-05-29},
  keywords = {sub},
  url = {https://arxiv.org/pdf/2606.00374}
}