Daniel Kasenberg

Papers

Total Citations

H-Index

About

Daniel Kasenberg is a researcher at the forefront of AI safety and explainability, focusing on how autonomous systems can reason about, adhere to, and communicate human moral and social norms. His work bridges formal logic and human-centered AI, with a particular emphasis on temporal logic as a framework for encoding and inferring norms that robots must obey in complex, interactive environments. His 2018 paper, "Inferring and Obeying Norms in Temporal Logic," laid foundational groundwork for ensuring that artificial agents are not only capable but also trustworthy and socially compliant. Kasenberg’s most influential contribution, "Explaining in Time" (2021, 18 citations), tackles the critical challenge of explainability in AI by proposing criteria for what constitutes a good explanation and examining the computational feasibility of generating such explanations over time. This work is vital for developing AI systems that can justify their decisions in high-stakes domains like healthcare and autonomous driving. Through his research, Kasenberg is shaping a future where intelligent agents are both competent and accountable.