David McMinn

Papers

Total Citations

H-Index

About

David McMinn’s research lies at the intersection of evolutionary computation, artificial neural networks, and robotics, with a particular focus on designing adaptive control systems for animats—animal-like robots. His major contribution is pioneering the use of evolutionary artificial neural networks (EANNs) to generate hierarchical nervous systems for quadruped locomotion, reducing the need for labor-intensive manual design. In his landmark 2002 paper, “Evolutionary Artificial Neural Networks for Quadruped Locomotion,” McMinn demonstrated how evolutionary algorithms could autonomously evolve neural controllers capable of coordinating complex, multi-jointed movements. His 2001 thesis further expanded this work, addressing the limitations of single-task robotic systems by proposing scalable, hierarchical architectures that allow robots to adapt to diverse environments. Although his citation counts are modest—5 and 4 respectively—these early studies were foundational in demonstrating the feasibility of evolving neural circuits for legged robots, influencing later work in embodied AI and evolutionary robotics. McMinn’s research remains a touchstone for students exploring how nature-inspired algorithms can automate the design of intelligent, adaptive robotic behaviors.