Papers

2

Total Citations

42

H-Index

2

About

Miguel Bande Firvida is a robotics researcher whose work sits at the critical intersection of autonomous underwater vehicles (AUVs) and advanced computer vision. His primary research areas include underwater robotics, sonar perception, and self-supervised learning for marine environments. Firvida’s most impactful contribution is his pioneering application of self-supervised learning to sonar image classification (2022, 26 citations), a method that enables underwater robots to learn robust visual representations without requiring large, costly labeled datasets—a major bottleneck in marine AI. This work significantly improves the perception capabilities of AUVs operating in low-visibility conditions. He is also the lead developer of the **AUV<sup>x</sup>**, a novel miniaturized autonomous underwater vehicle created within the DAEDALUS project at DFKI (2017, 16 citations). This compact, battery-powered explorer represents a key achievement in making deep-sea research more accessible and efficient. Through his dual focus on innovative hardware design and cutting-edge machine learning, Firvida is advancing the autonomy and intelligence of underwater systems for exploration and scientific research.

Research Focus

Key Achievements

2
H-Index
2
Papers
42
Total Citations
21
Avg Citations/Paper
🏆 Most Cited Paper
Self-supervised Learning for Sonar Image Classification
26 citations · 2022
📈 Most Prolific Year: 2022 (1 Papers)
🤝 Key Collaborators: 11
🏛 Institutions: German Research Centre for Artificial Intelligence, University of Bremen

Top Papers

  1. 1
  2. 2

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago