Urban Reconnaissance through Supervised Autonomy (URSA)*
Abstract
*Formerly PDUE: Autonomous Building Search Persistent Deterrence in Urban Environments The goal of the Urban Reconnaissance through Supervised Autonomy (URSA) program is to develop and demonstrate new autonomous agents and techniques that can rapidly discriminate hostile intent and filter out threats during missions ranging from minutes to hours, leveraging natural or created stimuli to elicit behavioral responses among humans in an area. The program seeks to create a system of autonomous ground and air platforms operating in conjunction with U.S. ground forces that monitor an area overtly to detect hostile forces and establish Positive Identification (PID) before any U.S. troops come into contact. Military units follow strict rules of engagement (ROEs) that prescribe an escalation of force appropriate with the level of hostilities and confidence that an individual is engaged in nefarious behavior. This program will establish a Legal, Moral, Ethical (LME) working group comprising multiple individuals (technologists, military, university professors, ethicists, legal experts) to develop an understanding of how escalation of force can and should be appropriately applied in the context of supervised autonomous systems. URSA will explore scenarios and probing behaviors that will enable identifying innocent civilians and individuals with hostile intent. This mission will require the integration and maturation of novel sensors, and unmanned ground and air vehicles which leverage current techniques in perspective and reactive autonomy to navigate cluttered urban environments. URSA will develop new search and probing behaviors to expose human intent and serve as evidence that a potential target is a threat. It will implement new dimensions of evidence such as the human reactions to these probing actions to improve confidence in its decisions, and will build a novel framework for escalating nonlethal force.
Document Details
- Document Type
- Accomplishment
- Publication Date
- Oct 01, 2020
- Source ID
- 0eb8937b64bb187de759b5e37420e136
Related Documents
- Root: TACTICAL TECHNOLOGY