Yizhen Zhang

California Institute of Technology, Applied Materials (United States)

Papers

Total Citations

122

H-Index

About

Yizhen Zhang’s research lies at the intersection of swarm intelligence, evolutionary robotics, and intelligent transportation systems, with a focus on enabling autonomous systems to learn and adapt in noisy, real-world environments. Zhang’s most influential contribution is the pioneering work on particle swarm optimization (PSO) for unsupervised robotic learning, which demonstrated how to adapt noise-handling techniques from genetic algorithms to PSO, allowing robots to learn robust behaviors despite unreliable performance feedback. This paper, with 105 citations, has become a foundational reference for researchers tackling noisy optimization in robotics. Zhang also advanced collective robotics through the evolution of neural controllers for multi-robot inspection tasks, showing how swarms can coordinate without centralized control. In the domain of intelligent vehicles, Zhang developed a realistic simulator for designing and evaluating autonomous driving systems, addressing critical challenges in traffic congestion and driver safety. Though less cited, this work reflects Zhang’s commitment to bridging simulation and real-world deployment. Together, these contributions showcase Zhang’s impact on adaptive, decentralized robotic systems and their potential to transform transportation and industrial inspection.