I am a PhD student in Aerospace Engineering at the University of Colorado Boulder, co-advised by Professors Zachary Sunberg and Bradley Hayes.
My research is about robot decision making under uncertainty. Robots that work alongside people, or that collect data in unpredictable environments, rarely know the full state of the world. I build planning algorithms that reason about this uncertainty directly and still run fast enough for real robots. My work covers:
Continuous-space POMDPs and BeliefMDPs: online tree search and belief-space planning methods that scale to continuous states, actions and observations.
Autonomous navigation among people: intention-aware navigation in crowds, and planning to intercept moving targets instead of driving to fixed goals.
Active information gathering: deciding where a robot should go to learn the most, for example sending autonomous vehicles to observe severe weather.
Multi-robot motion planning: scaling coordination to many robots under kinodynamic constraints via precomputed, translation-invariant primitives.
Before my PhD, I earned an M.S. in Computer Science at CU Boulder, where my thesis was on autonomous navigation among dynamic obstacles. Before that, I spent two years as a data engineer and scientist at JioSaavn, building large-scale recommendation systems. I received my B.Tech in Computer Science from IIT Ropar. In summer 2023, I was a research intern in Prof. Han-Lim Choi’s lab at KAIST, working on multi-robot motion planning.
I am looking for research internships for Summer 2027 in motion planning, autonomous systems and robot learning. Please feel free to reach out.
Presented Particle Belief Representations for Reinforcement Learning under Partial Observability at the 4th Workshop on Learning Effective Abstractions for Planning (LEAP) at CoRL 2026 in Austin.
Oct 2026
Presented Beyond Fixed Goal Delivery: Online POMDP Planning for Target Interception in Crowds at IROS 2026. Project page
Jan 2026
Decisions.jl, a framework for representing and transforming decision problem classes in Julia, was accepted at AAMAS 2026.
Jun 2025
Presented Toward Decentralized Planning in Belief MDPs at the RSS 2025 Workshop on Scalable and Resilient Multi-Robot Systems.
May 2024
Presented my doctoral consortium paper on continuous-space BeliefMDP solutions for navigation and active sensing at AAMAS 2024.
@inproceedings{gupta2026tic,title={Beyond Fixed Goal Delivery: Online {POMDP} Planning for Target Interception in Crowds},author={Gupta, Himanshu and Aladum, Kelvin and Ahmed, Nisar and Hayes, Bradley and Sunberg, Zachary},booktitle={IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},year={2026},}
Preprint
Efficient Multi-Robot Motion Planning with Precomputed Translation-Invariant Edge Bundles
Himanshu Gupta, Paul Motter, Aritra Chakrabarty, Rishabh Sodani, Bradley Hayes, and Zachary Sunberg
@article{gupta2026edgebundles,title={Efficient Multi-Robot Motion Planning with Precomputed Translation-Invariant Edge Bundles},author={Gupta, Himanshu and Motter, Paul and Chakrabarty, Aritra and Sodani, Rishabh and Hayes, Bradley and Sunberg, Zachary},journal={arXiv preprint arXiv:2605.09801},year={2026},}
@inproceedings{gupta2024beliefmdp,title={Efficient Continuous Space {BeliefMDP} Solutions for Navigation and Active Sensing},author={Gupta, Himanshu},booktitle={Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems (AAMAS), Doctoral Consortium},year={2024},}
@inproceedings{gupta2022intention,title={Intention-Aware Navigation in Crowds with Extended-Space {POMDP} Planning},author={Gupta, Himanshu and Hayes, Bradley and Sunberg, Zachary},booktitle={Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems (AAMAS)},year={2022},}
