Model-based On-board Decision Making for Autonomous Aircraft



Published Sep 22, 2019
Johann Martin Schumann Nagabhushan Mahadevan Michael Lowry Gabor Karsai


Powerful, small and lightweight sensors in combination with advanced failure detection, diagnosis, and prognostics techniques provide up-to-date data on the health status of a Unmanned Aerial System (UAS). In an autonomous UAS, this information must be used for automatic planning and execution of contingency actions to keep the UAS safe in adverse conditions.
We present DM (Decision Maker), a software component which uses model-based reasoning, backtracking search to iteratively construct contingency plans
that are safe for the UAS to execute and pose minimal interruption to the mission goals. The DM, which has been developed within the NASA Autonomous Operating System (AOS) project thus fills the gap between Prognostics and Health Management and autonomous flight operations.In this paper, we describe DM and its reasoning/search algorithm and present the supporting modeling framework for the construction of system and fault models. An flight with a DJI S1000+ octocopter with fault injection will be used as our case study.

How to Cite

Schumann, J. M., Mahadevan, N., Lowry, M., & Karsai, G. (2019). Model-based On-board Decision Making for Autonomous Aircraft. Annual Conference of the PHM Society, 11(1).
Abstract 196 | PDF Downloads 337



UAS, On-board decision making, contingency planning

Technical Papers