Workshop on Assured Autonomy
Abstract
From simple logical constructs to complex deep neural network models, AI-agents are increasingly controlling physical/mechanical systems. Self-driving cars, drones, and smart cities are just examples of such systems to name a few. However, regardless of the explosion in the use of AI within a multitude of Cyber-Physical Systems (CPS) domains, the safety and reliability of these AI-controlled CPS is still an under-studied problem. It is then unsurprising the failure of these AI-controlled CPS in several, safety-critical, situations leading to human fatalities. Such safety and reliability concerns, if not proactively addressed, will pose a significant barrier of adopting these technologies permanently in mission-critical Army operations. To address these challenges, we propose to organize a workshop that brings together mathematicians, electrical engineers, and computer scientists to identify opportunities for future basic research in the area of assured autonomy. The goals of this workshop are to explore and identify the opportunities for long-term fundamental research in the exploitation of assured autonomy. Relevant topics include: ? How to use formal models and methods towards the assurance of autonomy. ? How to design autonomous systems that can interact with humans ? Attacks and countermeasures for autonomous cyber-physical systems ? Adaptive systems that can operate and cope with new environments ? Robust Reinforcement learning ? Assured Perception The two-day workshop will take place at the campus of the University of Maryland and will feature a number of long presentations, short presentations, poster session, and break-out discussions. The primary output will be a Workshop Report that will be submitted to the Army Research Office. The powerpoint presentations will also be made available to the attendees, researchers, and engineers in DoD laboratories.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Jan 06, 2020
- Source ID
- W911NF2010020
Entities
People
- Rama Chellappa
Organizations
- Army Contracting Command
- United States Army
- University of Maryland