Alexei Harvard

Papers

Total Citations

H-Index

About

Alexei Harvard is a pioneering researcher in spacecraft guidance, navigation, and control (GNC), with a focus on multi-agent autonomy and perception for space missions. His primary research areas include information-driven guidance architectures, deep learning for optical flow, and uncertainty estimation in robotic perception. Harvard’s most notable contribution is the development of an information-based guidance and control architecture for multi-spacecraft on-orbit inspection, enabling multiple observer spacecraft to map target vehicles in low Earth orbit using stable passive relative orbits (PROs). This work, cited 41 times, directly addresses the trade-offs in sensor data collection for future autonomous space operations. Additionally, Harvard has advanced fast uncertainty estimation for deep learning-based optical flow, reducing processing time for critical robotic applications—a method cited 7 times and essential for mission-critical fields like space robotics. His research bridges theoretical information theory with practical GNC systems, offering scalable solutions for autonomous inspection, debris removal, and satellite servicing. Harvard’s work is recognized for its direct impact on enhancing the reliability and efficiency of autonomous spacecraft operations, positioning him as a key figure in the next generation of space exploration technology.