Welcome!
I am an Assistant Professor in the Aerospace and Ocean Engineering Department at Virginia Tech. I received my M.S. and Ph.D. degrees in Autonomous Systems from the University of Colorado Boulder, where I was advised by Prof. Zachary Sunberg and Prof. Morteza Lahijanian.
My research develops principled and computationally tractable techniques for autonomous decision-making under uncertainty. I am particularly interested in how autonomous agents should act when they have incomplete information about the state of the world, imperfect or uncertain models, and opportunities to acquire information or adapt their behavior over time.
I focus on algorithm design supported by rigorous theoretical analysis, including formal guarantees, robustness and sensitivity analysis, together with empirical evaluation. My research draws on probabilistic planning, formal methods, control, and machine learning, including MDPs and POMDPs, temporal logic, hybrid systems, stochastic games, reinforcement learning, and adaptive decision-making. My work finds applications in self-driving cars, uncrewed aerial vehicles, spacecraft and space robots, underwater vehicles, smart grids, and logistics.
📢 Opportunities: I am actively hiring highly motivated M.S. and Ph.D. students to pursue cutting-edge research in decision-making under uncertainty for autonomous systems. If you are interested in joining my lab, please contact me at: qihengho [at] vt.edu.
Research: Assured Autonomous Systems
My research focuses on designing Assured Autonomous Systems that operate safely and reliably under uncertainty, partial observability, and incomplete information. I am broadly interested in theoretical analysis, designing efficient algorithms, and practical techniques for:
- Decision-making under uncertainty (MDPs, POMDPs, Games)
- Constrained and risk-aware planning
- Formal synthesis and verification
- Reinforcement learning for partially observable systems
- Data-driven models for planning and control
- Multi-layered autonomous system architectures
- Integrated Task and Motion planning under uncertainty
- Temporally extended tasks (Temporal Logic specifications, Non-Markovian objectives, long horizon sparse reward problems)
- Applications in robotics and space systems
–>
Recent Publications
Below are a few recent highlights. For a complete list and access to all papers, please visit my Publications page.
- Perrault, N., Ho, Q. H., & Lahijanian, M. (2025). Kino-PAX: Highly Parallel Kinodynamic Sampling-based Planner. Robotics and Automation Letters (RA-L).
- Muvvala, K., Ho, Q. H., & Lahijanian, M. (2025). Beyond Winning Strategies: Admissible and Admissible Winning Strategies for Quantitative Reachability Games. International Joint Conference on Artificial Intelligence (IJCAI).
- Ho, Q. H., Feather, M., Rossi, F., Sunberg, Z., & Lahijanian, M. (2024). Sound and Efficient Algorithms for POMDPs with Reachability Objectives via Heuristic Search. Conference on Uncertainty in Artificial Intelligence (UAI).
- Ho, Q. H., Becker, T., Kraske, B., Laouar, Z., Feather, M., Rossi, F., Sunberg, Z., & Lahijanian, M. (2024). Recursively-Constrained Partially Observable Markov Decision Processes. Conference on Uncertainty in Artificial Intelligence (UAI).
- Ho, Q. H., Sunberg, Z., & Lahijanian, M. (2023). Planning with SiMBA: Motion Planning under Uncertainty for Temporal Goals using Simplified Belief Guides. IEEE International Conference on Robotics and Automation (ICRA).
- Ho, Q. H., Sunberg, Z., & Lahijanian, M. (2022). Gaussian Belief Trees for Chance Constrained Asymptotically Optimal Motion Planning. IEEE International Conference on Robotics and Automation (ICRA).
- Luo*, Y., Meghjani*, M., Ho*, Q. H., Hsu, D., & Rus, D. (2021). Interactive Planning for Autonomous Urban Driving in Adversarial Scenarios. IEEE International Conference on Robotics and Automation (ICRA).