Abdelhafid Zenati

Papers

Total Citations

H-Index

About

Abdelhafid Zenati is at the forefront of autonomous space exploration, pioneering robust navigation and cooperative control systems for planetary robots. His research centers on three critical pillars: deep learning-based pose estimation for space landers, cooperative visual navigation for extraterrestrial rovers, and distributed optimization for multi-robot task allocation. Zenati’s most impactful work, "Robust deep learning LiDAR-based pose estimation for autonomous space landers" (2022, 16 citations), addresses the fundamental challenge of precise localization during planetary descent—a capability essential for safe landing in GPS-denied environments. He further advances planetary robotics with "Autonomous Cooperative Visual Navigation for Planetary Exploration Robots" (2021, 6 citations), enabling teams of robots to collaboratively map and localize on alien terrains. In "Distributed Fuzzy Semi-Infinite Auction Based Optimization for Cooperative Robots Tasks Allocation" (2022, 2 citations), Zenati tackles the inherent imprecision in multi-agent task assignment, using fuzzy logic and sampling-based approximations to enhance robustness. His work bridges deep learning, fuzzy systems, and distributed optimization, directly supporting future NASA and ESA missions where autonomous, cooperative robot teams must operate reliably without human intervention. Zenati’s contributions are shaping the next generation of intelligent, self-sufficient explorers for the Moon, Mars, and beyond.