Muhammad Suhail Saleem

Hi! I am a Ph.D. student at the Robotics Institute at Carnegie Mellon University, advised by Professor Maxim Likhachev. My thesis research, titled Manipulation in the Blind, focuses on enabling robot manipulators to leverage contacts in vision-impaired or occluded settings, allowing them to better perceive their environment and robustly and efficiently complete tasks.

More broadly, I am interested in developing and deploying reasoning, motion planning, and decision-making systems that enable robots to operate reliably in uncertain and unstructured real-world scenarios. My work has spanned a range of tasks, including non-prehensile manipulation, object stacking, inspection, and projectile interception, as well as across diverse robot embodiments such as manipulators, snake robots, ground robots, and mobile manipulators.

You can reach me at muhammadsuhail441 [at] gmail [dot] com.

News

Jan 2026 Our paper titled "A Contact-Driven Framework for Manipulating in the Blind" was accepted to ICRA 2026! See you in Vienna!
Jan 2026 Successfully defended my Ph.D. thesis! I may or may not volunteer during future medical emergencies.
July 2025 Our paper titled "Attractor-based Closed List Search: Sparsifying the Closed List for Efficient Memory-Constrained Planning" was accepted to IJCAI (International Joint Conference on Artificial Intelligence) 2025!
June 2025 Our paper titled "Lazy Heuristic Search for Solving POMDPs with Expensive-to-Compute Belief Transitions" was accepted to SoCS (Symposium on Combinatorial Search) 2025!

Selected Publications

Manipulation in the Blind: Motion Planning for Manipulation under Uncertainty using Contacts

Muhammad Suhail Saleem

Ph.D. Thesis, The Robotics Institute, School of Computer Science, Carnegie Mellon University, 2026

[PDF]
A Contact-Driven Framework for Manipulating in the Blind

Muhammad Suhail Saleem, Lai Yuan, and Maxim Likhachev

Accepted for publication at the IEEE International Conference on Robotics and Automation (ICRA), 2026

[PDF] [BibTeX]
Attractor-based Closed List Search: Sparsifying the Closed List for Efficient Memory-Constrained Planning

Alvin Zou, Muhammad Suhail Saleem, and Maxim Likhachev

Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), 2025

[PDF] [BibTeX]
Windowed MAPF with Completeness Guarantees

Rishi Veerapaneni, Muhammad Suhail Saleem, Jiaoyang Li, and Maxim Likhachev

Proceedings of the AAAI Conference on Artificial Intelligence, 2025

[PDF] [BibTeX]
Preprocessing-based Kinodynamic Motion Planning Framework for Intercepting Projectiles Using a Robot Manipulator

Ramkumar Natarajan, Hanlan Yang, Qintong Xie, Yash Oza, Manash Pratim Das, Fahad Islam, Muhammad Suhail Saleem, Howie Choset, and Maxim Likhachev

Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2024

[PDF] [BibTeX]