Ole Andreas Alsos

Norwegian University of Science and Technology

Papers

Total Citations

H-Index

About

Ole Andreas Alsos is a leading researcher at the intersection of human-computer interaction, explainable artificial intelligence (XAI), and autonomous systems, with a particular focus on marine robotics and human-robot trust. His work addresses the critical challenge of making deep neural networks transparent and interpretable, as demonstrated in his most-cited paper (14 citations) on using linear model trees to explain a deep reinforcement learning docking agent. This research provides user-adapted visualizations that help operators understand and trust autonomous decision-making in complex maritime environments. Alsos has also advanced gesture-based interaction methodologies, exploring their potential for more intuitive human-machine interfaces. His contributions extend to the social dynamics of autonomous systems, notably in his work on designing for bystanders and secondary users, which examines how trust is built not only with operators but also with those indirectly affected by autonomous technologies. By bridging technical XAI methods with user-centered design principles, Alsos is shaping safer, more trustworthy autonomous systems for real-world deployment.