Mohamed Khodeir
Papers
2
Total Citations
34
H-Index
2
About
Mohamed Khodeir is a leading researcher in robotics and artificial intelligence, specializing in task and motion planning (TAMP) and large-scale 3D scene understanding. His work bridges the gap between high-level symbolic reasoning and low-level motion optimization, enabling robots to solve complex manipulation and navigation problems in real-world environments. Khodeir’s most cited paper, “Learning to Search in Task and Motion Planning With Streams” (2023, 22 citations), advances the state of the art by integrating machine learning with PDDLStream-based planning, reducing search complexity in hybrid discrete-continuous spaces. He is also the architect of TASKOGRAPHY (2022, 12 citations), the first benchmark for evaluating robot task planning over large 3D scene graphs—a critical step toward scalable, semantically rich robot autonomy. His contributions have been recognized for their impact on efficient, real-world deployment of autonomous systems, with his work cited in top robotics venues. Khodeir’s research is essential reading for anyone interested in the intersection of symbolic AI, motion planning, and 3D perception.
Research Focus
Key Achievements
Top Papers
- 1Learning to Search in Task and Motion Planning With Streams22 citations · 2023
- 2TASKOGRAPHY: Evaluating robot task planning over large 3D scene graphs12 citations · 2022