M-HATT addresses a key barrier to widespread use of unmanned aircraft systems (UAS) operations in the national airspace system (NAS):  the lack of tools that enable operators to team with automation to control multiple UAS with minimal human oversight.  This, in turn, requires addressing several more basic issues: seamless sharing/trading of control, and trust and transparency, between humans and increasingly autonomous systems.

M-HATT development includes four builds:

  1. A ground control station (GCS) that controls multiple UAS with basic interfaces and is capable of ingesting unmanned traffic management (UTM) services’ information in two basic tests (package delivery and search & rescue);
  2. Adding multi-model human-automation teaming interfaces and algorithms, and testing with NASA’s Live Virtual Constructive-Distributed Environment (LVC-DE) and STANAG 4586;
  3. Adding a framework for incorporating machine learning algorithms (MLA) into M-HATT and demonstrating its utility with representative MLAs, and testing with UTM; and
  4. Integration and testing with Shadow Mode Assessment with Realistic Technology in the national airspace systems (SMART-NAS) beta test.