Sandip Kumar

Mitchell Institute, Texas A&M University

Papers

Total Citations

H-Index

About

Sandip Kumar’s research lies at the intersection of robotics, motion planning, and probabilistic algorithms, with a particular focus on handling uncertainty in dynamic environments. His most significant contribution is the development of adaptive sampling strategies for generalized probabilistic roadmaps (GPRMs), a class of planners designed to account for stochastic map and model uncertainty. By introducing an Adaptive Sampling technique for GPRMs in his 2010 and 2011 papers, Kumar enabled more efficient exploration of high-dimensional state spaces, directly addressing the computational intractability of solving Markov decision processes (MDPs) in complex robotic systems. His work on generalized sampling-based feedback motion planners further advanced the field by providing robust, feedback-driven solutions that scale beyond traditional MDP solvers. Though his citation counts are modest—with his most-cited paper reaching 9 citations—Kumar’s contributions are foundational for researchers tackling real-world motion planning under uncertainty, such as in autonomous navigation or manipulation. His adaptive sampling methods remain a key reference for those seeking to balance exploration and exploitation in probabilistic roadmap frameworks.