Alexander Biddulph

Papers

Total Citations

H-Index

About

Alexander Biddulph is a researcher at the intersection of robotics and artificial intelligence, with a primary focus on deep learning for humanoid platforms and evolutionary optimization of robotic motion. His most influential work, "Comparing Computing Platforms for Deep Learning on a Humanoid Robot" (2018, 14 citations), provides a systematic evaluation of hardware architectures—from embedded GPUs to cloud-based systems—for deploying neural networks on resource-constrained humanoid robots, offering practical guidance for real-time perception and control. In a complementary study, "Optimization of Robot Movements Using Genetic Algorithms and Simulation" (2019, 4 citations), Biddulph demonstrates how evolutionary computation can efficiently generate smooth, energy-efficient motion trajectories in simulated environments, reducing the need for extensive physical trials. Together, these contributions address two critical challenges in autonomous robotics: computational feasibility and motion planning. While his citation counts reflect an emerging career, Biddulph’s work is notable for bridging theoretical optimization methods with tangible hardware constraints, making it valuable for students and engineers seeking to implement AI on physical robotic systems. His research continues to explore scalable learning approaches for embodied agents.