Adversarial Reasoning for Advanced Unmanned Teaming (AVERT)

Toyon proposes to develop adversarial target prediction algorithms and a mission execution framework that supports collaborative teaming of airborne and ground based Unmanned Systems (UMS) to enable tracking and surveillance of uncooperative targets. The proposed AVERT system will include automatic video processing, global fusion and tracking, adversarial reasoning and prediction, UMS control logic, and an application for a handheld iPhone, iPad, or Android device enabling the operator to interface with the system. Toyon's field-proven video processing algorithms will automatically detect moving targets in video, then digitize and compress the video stream for low-bandwidth transmission to the handheld device. Target detections will be automatically geo-registered using sensor state data from the platform GPS and IMU, then fused into target tracks in the ground plane, enabling autonomous tracking even in urban and complex environments. Ground plane tracks will be sent to the UMS operator for viewing and passed on to advanced UMS control algorithms. Motion control algorithms will use adversarial modeling to anticipate future actions of the target, then optimize the platform trajectory and sensor orientation to obtain clear-line-of-sight to the target and maintain persistent surveillance. A decentralized control architecture will be used to enable each UMS to operate autonomously or optimize collaborative actions between several UMS, while keeping bandwidth use low. The AVERT handheld application will receive data from all UMS within range, fuse multiple data streams to display an aggregate operational picture, and respond to the Warfighter's requests.