Papers
6
Total Citations
70
H-Index
5
About
Leonardo Zacchini is a leading researcher in marine robotics, specializing in autonomous underwater vehicles (AUVs) and their application to environmental monitoring and seabed inspection. His work lies at the intersection of deep learning, path planning, and sensor-driven autonomy, with a focus on enabling AUVs to intelligently perceive and interact with complex underwater environments. Zacchini’s major contributions include pioneering deep learning-based automatic target recognition for both optical and acoustic imagery, a breakthrough that allows AUVs to autonomously identify objects and features during missions. He also developed a receding-horizon, sampling-based coverage planning strategy that optimizes seabed inspections by balancing exploration and sensor constraints. His recent work on automatic target recognition and geolocalisation of natural gas seeps demonstrates the real-world impact of his research, enabling autonomous detection and mapping of underwater gas emissions—a critical tool for climate and oceanographic studies. With over 70 citations across his most-cited papers, Zacchini’s research is widely recognized for advancing the autonomy and intelligence of underwater robots. His innovative approaches to informative path planning and online distribution learning have set new standards for efficient data collection in unknown environments. Through projects like EUMarineRobots, he continues to push the boundaries of what AUVs can achieve, making him a key figure in the future of autonomous ocean exploration.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6