Visual Collision Detection and Avoidance for a Micro Air Vehicle
Agency / Branch:
DOD / USAF
This proposal presents the VAMAV system (Visual Awareness/Avoidance for a Micro Air Vehicle) for monocular visual collision detection and avoidance. Real time collision detection will be implemented using a time-to-collision approach based on area moment estimates of expansion from globally optimal image segmentation. This approach does not require explicit optical flow computations, and avoids noisy flow correspondence and differentiation. Real time collision avoidance will be implemented using rapidly exploring random trees (RRTs), which generate feasible trajectories given known obstacles and popup threats, while taking into account differential constraints arising from vehicle dynamics. The objective of the phase I investigation is to characterize the performance of the VAMAV system in simulation and on flight data. The phase I will investigate the performance of the VAMAV system using Monte Carlo simulations in the RIPTIDE simulator, resulting in a trade study of performance and MAV system constraints. Proof of concept for collision detection will be demonstrated on flight video data of a UAV in appropriate collision scenarios. Scientific Systems Company Inc. (SSCI) is joined in this investigation by team members Sarnoff Corporation and Brigham Young University.
Small Business Information at Submission:
SCIENTIFIC SYSTEMS CO., INC.
500 West Cummings Park - Ste 3000 Woburn, MA 01801
Number of Employees: