Nikhil Devraj
Papers
2
Total Citations
13
H-Index
2
About
Nikhil Devraj is a robotics researcher whose work focuses on enabling autonomous systems to make intelligent decisions under uncertainty. His primary research areas include task and motion planning, probabilistic inference, and constrained optimization for long-horizon robotic tasks. Devraj’s major contributions address two critical challenges in real-world robotics: planning under partial observability and optimizing constrained action sequences. In his highly cited 2021 paper, “Probabilistic Inference in Planning for Partially Observable Long Horizon Problems,” he tackled the limitation of traditional task and motion planners that assume full state observability, proposing a framework that allows service robots to act effectively in stochastic, partially observable environments. His 2022 work, “Optimal Constrained Task Planning as Mixed Integer Programming,” introduced a novel approach that formulates robot task planning as a mixed integer programming problem, enabling robots to generate action sequences that are both optimal with respect to a specified objective and compliant with real-world constraints. With 13 combined citations across these two papers, Devraj’s contributions are gaining recognition for bridging the gap between theoretical planning algorithms and practical deployment in autonomous service robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2Optimal Constrained Task Planning as Mixed Integer Programming6 citations · 2022