Papers
1
Total Citations
17
H-Index
1
About
Wenda Sheng is a rising researcher in the field of multi-robot systems and reinforcement learning, with a primary focus on enabling reliable, intelligent coordination among autonomous agents. Their most notable contribution is the introduction of the "multi-robot reliable search" (MuRRS) problem, a novel formulation that addresses the challenge of searching for a non-adversarial moving target with a guarantee of reliability. In their highly cited 2022 paper, "PD-FAC: Probability Density Factorized Multi-Agent Distributional Reinforcement Learning for Multi-Robot Reliable Search," Sheng and co-authors developed a groundbreaking algorithm that leverages distributional reinforcement learning and probability density factorization. This work, which has already garnered 17 citations, redefines reliability as the expectation of a utility function over the target’s probability density function, moving beyond traditional search metrics. By tackling the inherent uncertainty in target location and robot coordination, Sheng’s research provides a robust theoretical and practical framework for deploying multi-robot teams in critical applications like disaster response and environmental monitoring. Their work stands as a key advancement in making autonomous multi-agent systems both more efficient and trustworthy.
Research Focus
Key Achievements
Top Papers
- 1