*********************************
There is now a CONTENT FREEZE for Mercury while we switch to a new platform. It began on Friday, March 10 at 6pm and will end on Wednesday, March 15 at noon. No new content can be created during this time, but all material in the system as of the beginning of the freeze will be migrated to the new platform, including users and groups. Functionally the new site is identical to the old one. webteam@gatech.edu
*********************************
Title: Real-time Mobility Estimation for Autonomous Aerial Vehicles To Support Long-Term Autonomy
Committee:
Dr. Costello, Advisor
Dr. Coogan, Co-Advisor
Dr. Rogers, Chair
Dr. Ferri
Abstract: The objective of the proposed research is to design a real-time mobility estimation algorithm for autonomous air vehicles using online machine learning. The kernel of the proposed algorithm is online estimation of the total power required and total power available as a function of airspeed. Applying a sparse gaussian process to estimate the power required at various speeds presents an opportunity to exploit the relationship to assess the utility with the addition of confidence intervals. From this core estimate, all key mobility characteristics can be computed in real-time including uncertainty estimates. Continuous estimation of the performance envelope of an air vehicle is a necessary element for long-term autonomy of air vehicles to ensure survivability.