Working Set Selection Using Second Order Information for Training Support Vector Machines
The Journal of Machine Learning Research
A Multi-UAS Cooperative Mission Over Non-Segregated Civil Areas
Journal of Intelligent and Robotic Systems
Hi-index | 0.00 |
We present the implementation and demonstration of a team of two fixed-wing Unmanned Aerial Vehicles whose task is to improve the localization accuracy of a number of ground-based features. The underlying algorithmic paradigm is based on over a decadeâ聙聶s worth of work on Decentralized Data Fusion and Control. We present the components of the architecture, including vehicle localization, feature tracking, path planning and cooperative control. The algorithms described are implemented on a complete Unmanned Aerial System. Three demonstrations were performed, with varying levels of cooperation between team members. We present the results of these demonstrations and compare the performance of the team in completing the mission along with a quantitative understanding of the benefits achieved.