Self-driving cars, robotic home assistants, medical robots, and other diverse autonomous systems are becoming a reality worldwide. In order for these systems to be adopted in everyday life, autonomous systems must be shown to perform their required functions and do so in a trustworthy and safe manner.  Consequently, verification of autonomous systems—compelling evidence that autonomous systems satisfy their requirements—has become increasingly important. From software engineering to control systems design, we must ensure that autonomous systems behave as intended. In particular, that they behave safely—do not cause human injury or death, or damage or destruction of property. Efforts to propose methodologies and to develop tools related to the verification or verified design of autonomous systems are increasing worldwide. As technology progresses, and autonomous systems become more complex, with added intelligence and adaptive capabilities, the challenges of verification increase.

Our goal is to bring together experts in verification, autonomous and intelligent systems designers, and leading roboticists to discuss the main challenges in verification of autonomous systems, including the difficulty of defining meaningful requirements and of reasoning about highly unpredictable environments and complex interactions with people, as well as adaptation and learning mechanisms. We will present the state-of-the-art in verification of autonomous systems in terms of methodologies, techniques, ontologies, languages and successful applications. A major goal will be to find common ground to address the challenges relating to design for verification in robotics and verified robotic designs. We hope to open new avenues for future interdisciplinary collaboration among participants and expect that this will significantly advance the state of the art in this important area.