TECHNOLOGY AREA(S): Air Platform, Battlespace, Information Systems

ACQUISITION PROGRAM: NAE Chief Technology Office

The technology within this topic is restricted under the International Traffic in Arms Regulation (ITAR), 22 CFR Parts 120-130, which controls the export and import of defense-related material and services, including export of sensitive technical data, or the Export Administration Regulation (EAR), 15 CFR Parts 730-774, which controls dual use items. Offerors must disclose any proposed use of foreign nationals (FNs), their country(ies) of origin, the type of visa or work permit possessed, and the statement of work (SOW) tasks intended for accomplishment by the FN(s) in accordance with section 3.5 of the Announcement. Offerors are advised foreign nationals proposed to perform on this topic may be restricted due to the technical data under US Export Control Laws.

OBJECTIVE: Develop novel Artificial Intelligence (AI) methods that predict future actions of an adversary using their assets, the arrangement of those assets, and the recent behaviors of those assets. In the case where adversarial action can result in a �mission kill�, �hard kill�, or �soft kill� of U.S. assets, develop additional AI methods to automate a countermeasure response coupled with maneuver and pattern egress from potentially lethal encounters. Additionally, ensure that precautions are in place to avoid leading an encounter into an unintended escalation. Knowledge gained from this effort could further allow the DON to counter known vulnerabilities in autonomous capability design efforts.

DESCRIPTION: The tempo of warfare is increasing. Winning wars will require faster decision-making, which must be based on reading not only what adversaries have done, but also what future actions they are likely to undertake. Drawing inspiration from team sports where there is both offensive and defensive play (e.g., football, soccer, basketball), the defensive team must quickly and accurately read the offensive team�s actions to determine how best to counter the offense�s future actions. When playing defense, the coach and players need to �read� the offense and adjust their defensive posture to thwart the offensive drive. The �reading� is based on a combination of observation and learned experience. The observation is to collect data on the disposition, but the interpretation of the data is based on experience and knowledge of how the game is played.

In the case of a future conflict where Unmanned Air Systems (UAS) are sent on offensive missions, perhaps in vast numbers, we currently do not have a way to train, learn, and build up the years of experience that make a good defense. Further complicating matters, the two sides could be asymmetrical; one side could have much larger assets to bring to the conflict in terms of quantity and/or capability. In the case where a UAS is at risk from a potentially lethal engagement by one or more threat systems, the ability is needed to effectively predict a lethal outcome, automate optimal implementation of countermeasures, and egress to a standoff location or non-hostile terrain. Surviving an engagement is dependent on precise maneuvering and countermeasure response, and rarely anticipates follow-on threat activity. The technology would need to maintain situational awareness of known threats and real-time threat activity in order to optimize the countermeasure response and successfully escape the threat environment.

Develop a scope of operations that can offer reasonable balance between plausible and manageable.
- Consider how to provide stimulus to the algorithms.
- What is the novel AI algorithm? Propose a �Defensive Coordinator.�
- Ideally, proposed solutions�� will be implemented into UAS. Consider processing power required for the algorithms.
- Propose a method and metric for quantifying success.
- What defensive options are available? Consider the range, mobility, and reach of defensive options.
- Consider the possibility of algorithms to assist with finding vulnerabilities in current DON autonomous vehicle designs.
- The objective is full automation, however showing that a human can be maintained in the loop for awareness is worth having.

Work produced in Phase II may become classified. Note: The prospective contractor(s) must be U.S. owned and operated with no foreign influence as defined by DoD 5220.22-M, National Industrial Security Program Operating Manual, unless acceptable mitigating procedures can and have been implemented and approved by the Defense Security Service (DSS). The selected contractor and/or subcontractor must be able to acquire and maintain a secret level facility and Personnel Security Clearances, in order to perform on advanced phases of this project as set forth by DSS and NAVAIR in order to gain access to classified information pertaining to the national defense of the United States and its allies; this will be an inherent requirement. The selected company will be required to safeguard classified material IAW DoD 5220.22-M during the advanced phases of this contract.

PHASE I: Develop initial bounded algorithms for a UAS-implemented �Defensive Coordinator� by modifying/using existing algorithms and demonstrating a proposed design in a representative war game context. Identify the data required and existing hardware capabilities to collect the data; define requirements to real-time collate and process the data; and identify the human machine interface necessary for a survivable maneuver, countermeasure response, and egress solution.

PHASE II: Extend the research toward more operationally realistic scenarios with consideration to directing defensive actions. Develop and refine ground-up prototype algorithms, incorporating lessons learned from the Phase I exploratory work into the design. Potentially demonstrate simulated ability of algorithms to engage countermeasures, initiate aircraft maneuvering, and perform egress routing. Employ threats that will be modelled using existing modelling and simulation software. Demonstrate algorithms in a mission simulation.

Work in Phase II may become classified. Please see note in Description.

PHASE III DUAL USE APPLICATIONS: Due to the broad nature of this topic, applications for proposed algorithms and lessons learned are wide and varied depending on the approaches defined in Phase II. As AI becomes more prevalent in the private sector, the autonomous driving industry is a commercial area that would benefit from a �defensive coordinator.� More robust systems are required in autonomous civilian vehicles to both predict oncoming threats/pedestrians/traffic and execute time-critical options for life saving and collision avoidance.

REFERENCES:

1. Office of the Under Secretary of Defense for Acquisition, Technology, and Logistics (2016). Report of the Defense Science Board (DSB) Summer Study on Autonomy. https://www.hsdl.org/?view&did=794641

2. Office of the Under Secretary of Defense for Acquisition, Technology, and Logistics (2008). Report of the Joint DSB Intelligence Science Board Task Force on Integrating Sensor-Collected Intelligence. https://fas.org/irp/agency/dod/dsb/sensors.pdf

KEYWORDS: Autonomous; Artificial Intelligence; AI; Unmanned Air System; UAS; Threat Detection; Offensive Counter; Decision Making