Artificial Intelligence and Formal Methods Join Forces for Reliable Autonomy (Dagstuhl Seminar 24361)

Nils Jansen, Mykel J. Kochenderfer, Jan Kretínský, Jana Tumova, Maris F. L. Galesloot

Abstract: This report documents the program and outcomes of Dagstuhl Seminar 24361, "Artificial Intelligence and Formal Methods Join Forces for Reliable Autonomy." AI is a disruptive force with growing applications in everyday life. Therefore, AI systems require serious safety, correctness, and reliability considerations. Recently, the field of safety in AI has triggered a vast amount of research. This seminar brought together experts from the fields of artificial intelligence, formal methods, and robotics. Via a diverse program with ample space for open yet guided discussion, a common understanding of problems was developed. Consequently, the seminar provided a means to identify key challenges and open problems in the research areas that underpin reliable autonomy.