RTU Research Information System
Latviešu English

Publikācija: A Framework for Predicting the Mission-Specific Performance of Autonomous Unmanned Systems

Publication Type Full-text conference paper published in conference proceedings indexed in SCOPUS or WOS database
Funding for basic activity Unknown
Defending: ,
Publication language English (en)
Title in original language A Framework for Predicting the Mission-Specific Performance of Autonomous Unmanned Systems
Field of research 2. Engineering and technology
Sub-field of research 2.2 Electrical engineering, Electronic engineering, Information and communication engineering
Authors Phillip Durst
Wendell Gray
Agris Ņikitenko
João Caetano
Michael Trentini
Roger King
Keywords Intelligent unmanned systems, unmanned aerial vehicles, mission performance, target tracking
Abstract While many methodologies have been proposed for calculating a quantitative level of autonomy for intelligent Unmanned Systems (UMS), no one definitive measure of autonomy or autonomous performance has been validated and adopted by the UMS community. Particularly for military applications, a simple performance metric that is based on the UMSs mission profile and is comparable between UMS systems is critical. This metric would not only help define the features a UMS needs to successfully perform its mission, both in terms of hardware and software, but also enable the use of UMS for a broader range of applications at an increased level of autonomy. This paper presents the development of a new methodology for calculating a single-number performance metric for autonomous UMS, and this metric is called the Mission Performance Potential (MPP). Rather than a retroactive measure of UMS performance and autonomy level for one iteration of a given scenario, the MPP separates autonomy level and mission performance to provide a predictive measure of a UMS's expected performance for a mission set and level of autonomy. As an example application, the MPP is calculated for an Unmanned Aerial Vehicle (UAV) performing a target tracking mission, and this MPP value is compared to the results of field-testing with this system.
DOI: 10.1109/IROS.2014.6942823
Hyperlink: http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=6942823 
Reference Durst, P., Gray, W., Ņikitenko, A., Caetano, J., Trentini, M., King, R. A Framework for Predicting the Mission-Specific Performance of Autonomous Unmanned Systems. In: Proceedings of the 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2014), United States of America, Chicago, 14-18 September, 2014. Piscataway: IEEE, 2014, pp.1962-1969. ISBN 978-147996934-0. ISSN 2153-0858. Available from: doi:10.1109/IROS.2014.6942823
Additional information Citation count:
ID 19925