N231-025 TITLE: Autonomous Voice Coordination between Air Traffic Control and Foreign Object Debris Removal Systems

OUSD (R&E) CRITICAL TECHNOLOGY AREA(S): Artificial Intelligence (AI)/Machine Learning (ML); Autonomy

OBJECTIVE: Develop and demonstrate a software module to allow autonomous Foreign Object Debris (FOD) removal systems to properly coordinate�via voice�with Air Traffic Control (ATC) while operating on airfields.

DESCRIPTION: The U.S. Navy is developing a modern FOD system-of-systems solution to reduce the cost associated with engine damage due to FOD ingestion by 75%. Current FOD reduction approaches are split between base operations and squadrons. The base is responsible for runways, taxiways, and aprons. They use FOD sweeper trucks to clean high-priority areas on a regular schedule. These trucks take about one week to fully clean an airfield. The squadrons address the flight lines by requiring the entire squadron to walk up and down the flight line looking for and removing any FOD. These approaches take significant time away from other duties and still allow $150 million in engine damage each year. This cost will only increase as more advanced aircraft are developed. To address this, part of the FOD system-of-systems solution will develop an autonomous vehicle to replace the sweeper trucks and manual FOD walks. Additionally, this vehicle will be able to perform ad-hoc FOD removal operations as FOD is detected. This reduces overall maintenance costs and personnel workload requirements.

To enable autonomous ad-hoc FOD removal, the system must communicate with ATC over radio to ensure safe runway operations. This SBIR topic is requesting the development of a software module that provides this communication capability. This module will allow the automated system to communicate with ATC via voice over radio to negotiate permission on runways in need of FOD removal, respond to emergencies, and other standard operations. The goal is to enable integration of autonomous systems on airfields without requiring separate ATC procedures for autonomous versus human-crewed systems.

Current state-of-the-art autonomous systems typically incorporate an expertly trained human-in-the-loop approach. In this approach, the expert human supervises the autonomous systems and communicates with other humans on the automated system�s behalf. This results in additional, specifically trained, personnel on duty during all airfield operations, which adds to the overall operating costs.

This solution should follow proper ATC communication procedures, as outlined in Reference 1. References 2 and 3 also provide background on ATC and airfield operations. The current focus is on land-based airfields, but future operations may extend to carrier-based environments. The solution should also feature open interfaces to allow integration into various future FOD platforms. It will use these interfaces to allow the robot to request permission or information from ATC. These will then be translated into voice to send over standard radio channels. The solution must also provide the reverse to receive information from ATC. The actual radio, transmission, and receiving of the voice data does not have to be part of this solution. The system should understand a range of accents and enunciations from various ATC personnel. The system must also handle light background noise. This background noise is equivalent to talking to a person in the middle of a busy office. Additionally, this solution must run locally on the robot without any off-robot processing (such as cloud-based servers).

Note: NAVAIR will provide Phase I performers with the appropriate guidance required for human research protocols so that they have the information to use while preparing their Phase II Initial Proposal. Institutional Review Board (IRB) determination as well as processing, submission, and review of all paperwork required for human subject use can be a lengthy process. As such, no human research will be allowed until Phase II and work will not be authorized until approval has been obtained, typically as an option to be exercised during Phase II.

PHASE I: Develop a tentative framework for the software module highlighting how the module will address ATC communication protocols. Efforts will also show simple proof of concepts in constructing and interpreting voice responses. The Phase I effort will include prototype plans to be developed under Phase II.

Note: Please refer to the statement included in the Description above regarding human research protocol for Phase II.

PHASE II: Expand the efforts of Phase I by further developing, and fully implementing, the software and adapting the framework as needed. The effort should implement all communication protocols in a robust manner such as handling different accents and enunciations. Validation should occur with a variety of voice data to prove this robustness. This can occur in realistic lab settings or a live environment.)

Deliverables include a prototype; the open interface specification; software design documents; the uncompiled, human-readable source code; associated comments and documentation; and any tuned parameters and weights.

Note: Please refer to the statement included in the Description above regarding human research protocol for Phase II.

PHASE III DUAL USE APPLICATIONS: Phase III will incorporate the solution into any existing autonomous FOD platform designs. Efforts will focus on adapting the system to integrate with greater system and improving robustness.

This application directly benefits private and commercial airfields, in addition to military ones. All airfields have their own FOD mitigation plans. At least one commercial airport has indicated that they are exploring automated equipment for use throughout the airfield, as shown in Reference 4. This ATC voice-integration module will benefit those applications.

REFERENCES:

1.       Federal Aviation Administration. (2021, June 17). FAA Order JO 7110.65Z �Air Traffic Control. Department of Transportation. https://www.faa.gov/air_traffic/publications/atpubs/atc_html/

2.       Certification of Airports, 14 C.F.R. � 139 (2004). https://www.ecfr.gov/current/title-14/chapter-I/subchapter-G/part-139

3.       Office of Airport Safety and Operations. (2015, September 1). 150/5210-20A: Ground Vehicle Operations to include Taxiing or Towing an Aircraft on Airports. Federal Aviation Administration. https://www.faa.gov/documentLibrary/media/Advisory_Circular/150-5210-20A.pdf

4.       Cincinnati Airport Tests Autonomous Luggage Vehicle. (2021, May 21). https://www.govtech.com/fs/cincinnati-airport-tests-autonomous-luggage-vehicle

 

KEYWORDS: Autonomy; Natural Language Processing; Air Traffic Control; Open Interfaces; Foreign Object Debris; Voice Integration

---