Howdy! I am a PhD Student in Mechanical Engineering at the University of California at Berkeley. I am a member of the ICON Lab, advised by Dr. Negar Mehr. My research focuses on learning intricate multi-robot behavior for safety-critical environments, with an emphasis on safe reinforcement learning and multiagent coordination. My latest publications are available on Google Scholar. In recognition of my recent work, I was awarded the NSF GRFP in 2024.

Prior to beginning my graduate studies, I earned my B.S. in Computational Engineering from the University of Texas at Austin. During my undergraduate degree, I had the privilege of doing research with Dr. Ufuk Topcu and Dr. Moriba Jah.

In his free time, Kartik enjoys reading science-fiction novels, travelling abroad, and making pizzas with his friends.

News

Jul 28, 2025 I co-taught a group of Masters’ students from National Cheng Kung University on AI & Transportation as part of the NCKU-BAIR Summer Program.
Jul 17, 2025 I’ve been invited by Dr. João Sacramento to give a presentation on Multi-Agent Learning at Google Research. The talk will be 50 minutes, followed by a 10-minute Q&A session.
Jun 06, 2025 I had the oppurtunity to present the lightning talk The Blame Game, Evolved: Fine-Tuning LLM Credit Critics for MARL at the Google-BAIR Commons Annual Workshop.
May 22, 2025 I travelled to Detroit, MI to give a 20-minute presentation at AAMAS on our paper Leveraging Large Language Models for Effective and Explainable Multi-Agent Credit Assignment.
Apr 10, 2025 Our paper titled DDAT: Diffusion Policies Enforcing Dynamically Admissible Robot Trajectories got accepted at the Conference on Robotics: Science and Systems (RSS) 2025!
Apr 10, 2025 I gave an hour long presentation on my paper titled Leveraging Large Language Models for Effective and Explainable Multi-Agent Credit Assignment at the UC Berkeley Control Seminar!
Apr 04, 2025 I delivered a lightning talk at the Spring 2025 BAIR Robotics Workshop: The Dawn of a General Purpose Robotics Era!