Parv Kapoor

prof_pic.jpg

Ph.D. Student in Software Engineering
Software and Societal Systems Department
School of Computer Science
Carnegie Mellon University

parvk [at] cs [dot] cmu [dot] edu
CV / Google Scholar / Linkedin


Update: I am in Seattle over the summer interning at Scaled Foundations working on Robotics Foundation Models!

Hi! I am a third-year Ph.D. student at Carnegie Mellon University advised by Dr. Eunsuk Kang and Dr. Sebastian Scherer. I also work with the Robotics Institute (CMU), the AI for Systems Group (Microsoft Research New York City) and Intelligent Connected Systems Group (Toyota Infotech Labs).

I am deeply passionate about the intersection of Software Engineering and Artificial Intelligence, particularly in leveraging software engineering methodologies to guarantee the safety and reliability of AI systems. My ongoing research involves:

  1. Enhancing the robustness of reinforcement learning agents [1] [2]
  2. Designing safe controllers for autonomous systems while adhering to formal high-level system specifications [3] [4]
  3. Constraining Behavior of Robotics Foundation Models [5]

I am currently a part of AirLab and SoDA. Prior to joining CMU, I worked with Dr. Jyotirmoy Deshmukh’s CPS VIDA lab at University of Southern California. I have also researched with Dr. Thao Dang at the Université Grenoble Alpes and Dr. David Marshall at the Cardiff University.

news

Jul 6, 2024 Our paper titled “Logically Constrained Robotics Transformers for Enhanced Perception-Action Planning” was accepted to Robotics Science and Systems: Towards Safe Autonomy. This work was done in collaboration with Sai Vemprala and Ashish Kapoor.
Jun 23, 2024 Gave a talk at NASA Ames Research Center and Toyota Infotech Labs.
Jun 18, 2024 Our paper titled “Tolerance of Reinforcement Learning Controllers against Deviations in Cyber Physical Systems” was accepted to Formal Methods 2024! See you in Milan!
May 7, 2024 Interning at Scaled Foundations with Dr. Ashish Kapoor and Dr. Sai Vemprala for Summer 24. working on Software Hardware Codesign for GRID and providing Assurances for Robotics Foundation Models(PACT)!
Apr 15, 2024 Gave a guest lecture on Software Design for AI based Systems for 17-723.