Non-Parametric, Closed-Loop Testing of Autonomy in Unmanned Aircraft Systems
Status: Completed
Start Date: 2015-05-14
End Date: 2018-02-13
Description: The proposed Phase II program aims to develop new methods to support safety testing for integration of Unmanned Aircraft Systems into the National Airspace (NAS) with a particular focus on testing the collision avoidance (CA) algorithms of a UAS Sense-and-Avoid (SAA) system. This research addresses the fundamental difficulty of verifying the performance of autonomous systems that dynamically react to the environment. In particular, this research program would develop novel methods for conducting non-parametric, closed-loop simulation testing of collision avoidance algorithms as well as other autonomous operations. The technology generates a campaign of simulation experiments that automatically adapt to the algorithms in question. The purpose of this innovation is to expose potential vulnerabilities in UAS autonomy that are generated through the interaction of autonomous UAS algorithms with other agents such as an intruding aircraft operating under ``right of way rules". This work augments both the probabilistic open-loop testing methods, where agents do not react, and closed-loop testing where agent behavior is fixed a priori.
Benefits: The immediate NASA application is safety analysis for the UAS Integration in the NAS program. In particular, this work would support the Separation Assurance/Sense and Avoid Interoperability (SSI) and Integrated Test and Evaluation (IT&E) subprograms within this effort through tools to improve the efficiency and effectiveness of fast-time and HITL simulation testing. In addition, this technology could be used to test autonomous algorithms within other domains at NASA, such as space exploration.
There is need to test and verify autonomous operations of unmanned aircraft in numerous domains. The Department of Defense has a deep need for testing complex (e.g., autonomous) systems where brute force testing methods are infeasible. This includes the US Air Force, where unmanned aircraft are increasingly ubiquitous, and Missile Defense Agency where Numerica is involved in parametric testing of the Ballistic Missile Defense System.
There is need to test and verify autonomous operations of unmanned aircraft in numerous domains. The Department of Defense has a deep need for testing complex (e.g., autonomous) systems where brute force testing methods are infeasible. This includes the US Air Force, where unmanned aircraft are increasingly ubiquitous, and Missile Defense Agency where Numerica is involved in parametric testing of the Ballistic Missile Defense System.
Lead Organization: Numerica Corporation