Saurav Agarwal
Papers
7
Total Citations
100
H-Index
4
About
Saurav Agarwal is a robotics researcher specializing in autonomous systems, motion planning under uncertainty, and probabilistic decision-making. His work centers on enabling mobile robots to navigate and make decisions in complex, uncertain environments — a challenge at the intersection of localization, planning, and control theory. Agarwal's most significant contribution is the development of SLAP (Simultaneous Localization and Planning), a framework that tackles one of robotics' most demanding problems: allowing robots to plan and localize concurrently under uncertainty. By formulating SLAP as a continuous partially observable Markov decision process (POMDP) and enabling dynamic replanning in belief space, his work — cited over 40 times — pushed the boundaries of what autonomous robots can achieve in real-world conditions. His parallel work on the Feedback-based Information RoadMap (FIRM) framework, cited 31 times, advanced roadmap-based planning under both motion and sensing uncertainty for physical mobile robots. Agarwal has also extended these methods to non-Gaussian belief spaces and aerial vehicle control, addressing challenges like data association ambiguity and multimodal state hypotheses. His research bridges theoretical rigor with practical implementation, with demonstrations on physical mobile robots underscoring the real-world applicability of his contributions to autonomous navigation and stochastic control.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6
- 7Motion Planning for Global Localization in Non-Gaussian Belief Spaces2 citations · 2015