Lyndon While
Papers
2
Total Citations
47
H-Index
2
About
Lyndon While is a leading researcher in artificial intelligence and robotics, with key contributions in evolutionary computation, multi-agent systems, and 3-D object recognition. His work has been instrumental in demonstrating how evolutionary algorithms can solve complex coordination problems in autonomous systems. In his highly cited 2002 paper (37 citations), While pioneered the use of evolutionary algorithms to train autonomous agents in RoboCup Keepaway, showing that machine learning could effectively replace manual coordination in multi-agent environments—a foundational contribution to the field of cooperative robotics. More recently, While has advanced computer vision with his 2017 work on evolutionary feature learning for 3-D object recognition (10 citations), proposing a novel approach that automatically selects discriminative features critical for applications like autonomous navigation and scene understanding. His research bridges evolutionary optimization and practical robotics, offering scalable solutions to real-world challenges. While’s work continues to influence researchers in evolutionary robotics and autonomous systems, demonstrating the power of nature-inspired algorithms in creating intelligent, adaptive agents.
Research Focus
Key Achievements
Top Papers
- 1Learning In RoboCup Keepaway Using Evolutionary Algorithms37 citations · 2002
- 2Evolutionary Feature Learning for 3-D Object Recognition10 citations · 2017