Alberto Viseras
Papers
13
Total Citations
271
H-Index
9
About
Alberto Viseras is a robotics and artificial intelligence researcher whose work sits at the intersection of multi-robot systems, information gathering, and machine learning. His research focuses on enabling autonomous robots to intelligently explore unknown environments, reconstruct spatial fields, and respond to real-world hazards — from gas leaks and wildfires to disaster scenarios requiring search and rescue. Viseras has made significant contributions to the field of robotic information gathering, particularly through the development of decentralized multi-agent exploration strategies powered by Gaussian processes, earning 63 citations for his foundational 2016 work in this area. He has pioneered the application of deep reinforcement learning to multi-robot coordination, most notably through his DeepIG framework (36 citations), which overcomes the limitations of model-dependent approaches by learning task-relevant strategies directly from experience. His work on gas source localization using reinforcement learning augmented by domain knowledge (29 citations) demonstrates a strong commitment to translating theoretical advances into safety-critical applications. Across more than ten papers and over 250 cumulative citations, Viseras has consistently addressed real-world constraints such as communication limitations, spatiotemporal dynamics, and scalability — even extending his vision to swarm robotics for space exploration. His body of work represents a compelling bridge between algorithmic innovation and practical autonomous systems deployment.
Research Focus
Key Achievements
Top Papers
- 1
- 2DeepIG: Multi-Robot Information Gathering With Deep Reinforcement Learning36 citations · 2019
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10Swarm Technologies For Future Space Exploration Missions8 citations · 2018