Prior to beginning graduate studies, I was a system engineer at Motorola Solutions’ Upgrade Operations, performing system upgrades to critical radio infrastructure.
My research interests are targeted towards high performance system-level optimizations in order to make advanced robotics more viable. I am particularly interested in ways to leverage GPU hardware resources for accelerating sampling-based and learning-based robotics, and more generally integrating bleeding-edge computing paradigms into the domain of physical AI. In addition, I also aim to develop more robust tools tailored to effective hardware accelerated robotics research.
My broader interests in Computer Science include machine learning, system level software engineering, computational statistics and linear algebra, and GPU related IT infrastructure.
Global Tensor Motion Planning (GTMP) solves motion planning with batched tensor operations over a layered multipartite graph. We generalize GTMP so that adjacent-layer edges are realized by any black-box local planner (e.g., linear interpolation, splines, sampling-based planning, trajectory optimization, or generative sampling). We provide two anytime policies on top of this generalization: Anytime GTMP with random restarts at a fixed budget, which covers every homotopy class almost surely, and AO-GTMP with informed expansion with growing budgets, which converges to the optimal cost. We prove that a single sampled graph covers every endpoint-fixed homotopy class admitting a delta-clear representative of bounded length. We also prove that additional samples per layer reduce the per-layer miss probability exponentially, whereas stronger local planners reduce the required layer count only sublinearly. On manipulation benchmarks the method matches state-of-the-art performance, and on 2D navigation it returns batches of topologically diverse solutions, while the informed baselines concentrate on one or two classes.
@misc{coumar2026anytime,archiveprefix={arXiv},author={Coumar, Sai and Le, An T. and Kingston, Zachary},eprint={2608.25830},note={Under Review},primaryclass={cs.RO},title={Anytime Global Tensor Motion Planning},year={2026}}
2025
arXiv
Foam: A Tool for Spherical Approximation of Robot Geometry
Many applications in robotics require primitive spherical geometry, especially in cases where efficient distance queries are necessary. Manual creation of spherical models is time-consuming and prone to errors. This paper presents Foam, a tool to generate spherical approximations of robot geometry from an input Universal Robot Description Format (URDF) file. Foam provides a robust preprocessing pipeline to handle mesh defects and a number of configuration parameters to control the level and approximation of the spherization, and generates an output URDF with collision geometry specified only by spheres. We demonstrate Foam on a number of standard robot models on common tasks, and demonstrate improved collision checking and distance query performance with only a minor loss in fidelity compared to the true collision geometry. We release our tool as an open source Python library and containerized command-line application to facilitate adoption across the robotics community.
@misc{coumar2025foam,archiveprefix={arXiv},author={Coumar, Sai and Chang, Gilbert and Kodkani, Nihar and Kingston, Zachary},eprint={2503.13704},primaryclass={cs.RO},title={Foam: A Tool for Spherical Approximation of Robot Geometry},year={2025}}
