Electrical and Computer Engineering Commons^™

Multi-Target Extension For Beacon Foraging Methods, Christopher Sanford, Ziong Jiao, Jae Oh

Electrical Engineering and Computer Science - All Scholarship

Robotic foraging is a complex problem that encompasses both the problem of exploring an area and retrieval of targets. To solve this, biologically inspired algorithms have been proposed that handle the scenario when only one target exists, but requires extension to multiple targets. In both scenarios there exists problems of robot allocation and congestion, and we analyze ways of optimizing both allocation and minimizing congestion for our algorithms. We demonstrate the results through parameterized metrics and compare the improvements in each scenario.

This is a technical report on artificial intelligence, 2017, written by Sanford, Jiao, and Oh.

Visual Multiple Target Tracking From A Descending Aerial Platform, Parker C. Lusk, Randal Beard

Student Works

A real-time visual multiple target tracker is demonstrated onboard a descending multirotor. Measurements of moving ground targets are generated using the Kanade-Lucas-Tomasi (KLT) tracking method. Homography-based image registration is used to align the measurements into the same coordinate frame, allowing for the detection of independently moving objects. The recently developed Recursive-RANSAC algorithm uses the visual measurements to estimate targets in clutter. Altitude-dependent tuning increases track continuity and coverage during the descent of the vehicle. The algorithm requires no operator interaction and increases the situation awareness of the unmanned aerial system. Real-time tracking efficiency is analyzed on GPUs and CPUs. Tracking …