Active-Vision Control Systems for Complex Adversarial 3-D Environments

摘要

This project has included development of methods that utilize 2-D and 3-D imagery (e.g., from visual, FLIR, LADAR, acoustic) to enable aerial vehicles to autonomously detect and prosecute targets in uncertain complex 3-D adversarial environments, including capabilities and approaches inspired by those found in nature, and without relying upon highly accurate 3-D models of the environment. The new capabilities of autonomous sensing and control enable UAV/munition operations: in a clandestine/covert manner; in close proximity to hazards, structures, and/or terrain; and in uncertain/adversarial 3-D environments. Furthermore, the team performed a productive flying testbed activity as part of the program. This ensures that the methods are sound in the sense that they are: (l) implementable in real-time, (2) capable of practical use in the field, and (3) based on realistic/achievable sensor capabilities. This project is a Multidisciplinary University Research Initiative (MURI).