Papers
12
Total Citations
351
H-Index
9
About
Wheeler Ruml is a leading researcher in artificial intelligence, with a focus on real-time heuristic search, multi-agent path finding (MAPF), and motion planning. His work addresses the critical challenge of enabling intelligent agents—from mobile robots to automated warehouse systems—to make decisions under strict time constraints. Ruml is best known for developing EECBS (Explicit Estimation Conflict-Based Search), a bounded-suboptimal algorithm for MAPF that dramatically reduces runtime while maintaining near-optimal solutions, a breakthrough with direct applications in logistics and robotics. His contributions to real-time search include pioneering methods for avoiding dead ends and handling dynamic environments, ensuring safe and efficient planning even when costs change unpredictably. With over 330 citations on his most-cited papers, Ruml’s impact is evident in both theory and practice. He has also advanced motion planning through abstraction-guided sampling, improving the efficiency of Rapidly-exploring Random Trees (RRTs). A frequent contributor to top venues like ICAPS, Ruml’s work bridges the gap between algorithmic rigor and real-world deployment, making him a key figure in autonomous decision-making.
Research Focus
Key Achievements
Top Papers
- 1EECBS: A Bounded-Suboptimal Search for Multi-Agent Path Finding186 citations · 2021
- 2EECBS: A Bounded-Suboptimal Search for Multi-Agent Path Finding28 citations · 2020
- 3Abstraction-Guided Sampling for Motion Planning26 citations · 2021
- 4Avoiding Dead Ends in Real-Time Heuristic Search21 citations · 2018
- 5Real-Time Search in Dynamic Worlds21 citations · 2010
- 6
- 7Replanning for Situated Robots13 citations · 2019
- 8Real-Time Motion Planning with Dynamic Obstacles13 citations · 2021
- 9
- 10