Nan Rong

Papers

Total Citations

H-Index

About

Nan Rong is a leading researcher in robotics and artificial intelligence, with a primary focus on decision-making under uncertainty and autonomous target tracking. Her seminal work, "A point-based POMDP planner for target tracking" (2008, 80 citations), revolutionized how robots handle the dual challenges of target searching and target following. By applying partially observable Markov decision processes (POMDPs), she developed a unified framework that enables robots to efficiently locate initially invisible targets and maintain visibility on moving ones—a critical capability for surveillance, search-and-rescue, and autonomous navigation. This contribution remains a cornerstone reference in the field, demonstrating her ability to bridge theoretical planning algorithms with practical robotic applications. More recently, Rong has advanced the frontier of decision-making in robotics through her work on "MDPs with Unawareness in Robotics" (2020), which formalizes how continuous-time Markov decision processes can be approximated via discretization to handle scenarios where robots lack complete knowledge of their environment. This innovative approach addresses a fundamental limitation in traditional MDP models, opening new pathways for robust autonomous systems. Her research continues to inspire students and engineers seeking to build intelligent robots that operate reliably in complex, uncertain real-world settings.