HR001118S0036.pdf

HR001118S0036

Broad Agency Announcement

Urban Reconnaissance through Supervised Autonomy

(URSA)

TACTICAL TECHNOLOGY OFFICE

May 10, 2018

Contents

PART II: FULL TEXT OF ANNOUNCEMENT

I. Funding Opportunity Description

A. Program Overview B. Program Plan C. Program Metrics and Phase 2 Go/No-Go Decision D. Phase 1 Objectives – Track A E. Phase 2 Objectives – Track A F. Phase 1 Objectives – Track B

II. Award Information A. General Award Information B. Fundamental Research

III. Eligibility Information A. Eligible Applicants B. Organizational Conflicts of Interest C. Cost Sharing/Matching

IV. Application and Submission Information A. Address to Request Application Package B. General Format Guidance C. Abstract Content and Format – Track A D. Abstract Content and Format – Track B E. Volume I, Technical and Management Proposal Content and Format – Track A F. Volume I, Technical and Management Proposal Content and Format – Track B G. Volume II, Cost Proposal Content and Format – Track A and Track B H. Additional Proposal Information

V. Application Review Information A. Evaluation Criteria – Track A B. Evaluation Criteria – Track B C. Review of Proposals

VI. Award Administration Information A. Selection Notices and Notifications B. Administrative and National Policy Requirements C. Reporting

D. Electronic Systems VII. Agency Contacts VIII. Other Information

PART I: OVERVIEW INFORMATION

Federal Agency Name – Defense Advanced Research Projects Agency (DARPA), Tactical Technology Office (TTO)

Funding Opportunity Title – Urban Reconnaissance through Supervised Autonomy

(URSA)

Announcement Type – Initial announcement

Funding Opportunity Number – HR001118S0036

Catalog of Federal Domestic Assistance Numbers (CFDA) – Not Applicable

Dates

• Proposers Day: May 1, 2018

• Networking and One on One Discussions: May 1, 2018

• BAA Posting Date: May 10, 2018

• Abstract Due Date and Time: May 24, 2018; 12:00PM Eastern

• Abstract Feedback: Goal of May 31, 2018 depending on number of abstracts received

• BAA Questions Due: May 31, 2018

• Full Proposals Due: July 3, 2018; 1:00PM Eastern

Concise description of the funding opportunity – The goal of the URSA program is to assess the feasibility and effectiveness of integrating unmanned systems, sensor technologies, and advanced autonomy algorithms to enable improved techniques for rapidly discriminating hostile intent and filtering out threats in complex urban environments.

Total amount anticipated to be awarded – Up to $22.6M for Phase 1.

Anticipated individual awards – Multiple awards are anticipated.

Types of instruments that may be awarded – Procurement contract or other transaction for prototype.

Agency contact o Points of Contact

The BAA Coordinator for this effort can be reached at:

HR001118S0036@darpa.mil

DARPA/TTO

ATTN: HR001118S0036

675 North Randolph Street Arlington, VA 22203-2114

PART II: FULL TEXT OF ANNOUNCEMENT

I. Funding Opportunity Description This publication constitutes a Broad Agency Announcement (BAA) as contemplated in Federal Acquisition Regulation (FAR) 6.102(d)(2) and 35.016 and 2 CFR § 200.203. Any resultant award negotiations will follow all pertinent law and regulation, and any negotiations and/or awards for procurement contracts will use procedures under FAR 15.4, Contract Pricing, as specified in the

BAA.

Reconnaissance, surveillance, and target acquisition within urban terrain remains a vexing problem for the U.S. military. Urban spaces can mask threat personnel as they move and obscure threats as they approach. Additionally, the urban environment includes civilians who must be protected, challenging the military’s ability to claim Positive Identification (PID) of combatants. Enemy combatants may seek to co-locate with noncombatants and mimic their appearance, actively impeding the U.S. military’s ability to discriminate quickly between the two populations. Current state-of-the-art reconnaissance systems and sensors are not sophisticated enough to overcome the challenges posed by obstructed urban sight lines and fleeting targets, or to reliably discriminate between threats and noncombatants. Therefore, U.S. forces must rely on dismounted warfighters to actively patrol urban areas to ferret out threats and maintain safety and security. Continuous patrolling is manpower and time intensive and exposes those warfighters to significant risk.

The Urban Reconnaissance through Supervised Autonomy (URSA) vision is to develop technology to enable autonomous systems operated and supervised by U.S. ground forces to detect hostile forces and establish PID before any U.S. troops come in contact with them. The URSA program seeks to overcome the complexity of the urban environment by combining new knowledge about human behaviors, autonomy algorithms, integrated sensors, multiple sensor modalities, and measurable human responses to discriminate the subtle differences between belligerents and innocent bystanders. DARPA believes that through an autonomous, active process of accumulating and filtering data from multiple sources and sensing modalities, it will be possible to rapidly and reliably discriminate between threats and non-combatants. In addition to traditional sensing modalities, DARPA seeks to leverage natural or created stimuli to elicit behavioral responses among humans in an area and sense differing reactions in threats and noncombatants.

Key aspects of this program include the ability to exploit new dimensions of evidence such as human behaviors or responses that indicate hostile intent; autonomously fuse information from multiple sources to optimize area search and confidence; and employ advanced algorithms to rapidly synthesize and accumulate evidence over time to filter out threats and enable sufficiently accurate PID.

The URSA program will explore situations and behaviors that will enable identification and discrimination between innocent civilians and individuals with hostile intent. Although the development of these probing behaviors will be an output of the program, a simple example of an URSA engagement may help clarify the program’s intended end-state and related technical challenges. For example: a static sensor located near an overseas military installation detects an individual moving across an urban intersection and towards the installation outside of normal pedestrian pathways. An unmanned aerial system (UAS) equipped with a loudspeaker delivers a warning message. The person is then observed running into a neighboring building. Later, URSA detects an individual emerging from a different door at the opposite end of the building, but confirms it is the same person and sends a different UAS to investigate. This second UAS determines that the individual has resumed movement toward a restricted area. It releases a non-lethal flash-bang device at a safe distance to ensure the individual attends to the second message and delivers a sterner warning. This second UAS takes video of the subject and determines that the person’s gait and direction are unchanged even when a third UAS flies directly in front of the person and illuminates him with an eye-safe laser dot. URSA then alerts the human supervisor and provides a summary of these observations, warning actions, and the person’s responses and current location.

Performers will be expected to explore a full range of URSA user scenarios to maximize the utility of their proposed URSA approach. Performers will also be expected to examine the full solution trade space. There are many facets of the above example that illustrate the breadth of the trade space. Ground robotics could provide superior endurance and payload compared to UAS, and these robots could persistently patrol a critical pedestrian area. Static modes could combine sensing, local computation, and limited effects such as loud speakers or illumination methods. Jamming specific electromagnetic spectrum frequency ranges might cause specific reactions and provide unique insights. Crowds often have a wisdom of their own, and introducing a stimulus near a crowd might reveal individuals that react differently than others. Providing discriminatory capability is just as vital in security scenarios where deployed forces are static as when warfighters are actively moving into and through an area. Nowhere is the URSA vision more challenged than detecting and discriminating enemy snipers from noncombatants within the urban landscape, and snipers remain a pernicious threat to warfighters exactly because their detection and discrimination is so challenging.

While the implementation of an URSA system and associated concept of operations may appear straightforward, it requires significant advances in active sensing, behavior understanding, and autonomous decision making to determine intent.

A. Program Overview The objective of this BAA is to establish the feasibility and effectiveness of achieving the URSA vision by developing and evaluating prototype capabilities. BAA research will focus on answering the following key questions:

• What combinations of sensors, personnel signatures, and behaviors best enable discrimination between threats and non-combatants?

• What is the potential of various actions (e.g., Unmanned Aircraft System (UAS) overflight, loudspeakers, spotlight-like/spray-like/firecracker-like effects, jammed communications) to spur additional detectable responses that help to further differentiate between threats and noncombatants?

• How can the system accumulate sufficient evidence over time, e.g., by making multiple sensor passes from different perspectives in combination or various stimulating actions, to reliably, accurately, and autonomously identify and characterize threats while posing low risk to noncombatants?

• Can this entire process be executed rapidly enough to meet dismounted operational requirements, including timelines, situational awareness and safety?

• What is the appropriate level of autonomy and appropriate degree of human-in-the-loop interaction with the system to make rapid and accurate decisions?

• Can the system track and re-identify targets with sufficient robustness to qualify as actionable intelligence?

For this effort, performers should only consider operations in a complex, non-permissive 3D urban environment with a mix of threat and non-threat individuals. Proposers should focus on the critical enabling exploitation, autonomy and decision support algorithm technologies and features of URSA, prioritizing development and demonstration of new algorithms and techniques to rapidly discriminate between threats and noncombatants, as opposed to sensor, effector and platform development. For affordability, where possible, proposers should leverage existing hardware, software, simulation infrastructure and physical interfaces that are adequate for demonstrating URSA algorithms and techniques. It is envisioned that the demonstrations will be conducted using an evolutionary framework that progressively builds up capability over time, culminating in live field demonstrations.

To further assist proposers in developing initial URSA concepts and scoping their effort, DARPA offers the following additional guidance regarding the desired solution space.

Capabilities of interest include, but are not limited to:

• Behavior-based and other novel means of threat detection, classification, recognition, identification, and classification

• Intelligent sensor placement and/or unmanned system employment to enable optimized autonomous area search that efficiently gathers and fuses data from multiple sources and optimizes threat discrimination in militarily relevant, dense urban environments

• Autonomous identification of appropriate stimulating actions and timing of implementation to interact with or elicit behaviors in personnel of interest that assist in deducing their intent

• Information fusing techniques to iteratively synthesize and accumulate threat discrimination evidence from multiple data sources

• Mission planning approaches that account for a thinking, dynamic adversary

• Risk-based decision theory and implementation in accordance with an ethical framework

• Behavior science to model expected human reaction to proposed autonomous system behaviors

• Ability to explore how, to what degree, and where to integrate a human supervisor into the decision loop

• Ability for the human supervisor to retain insight into why certain autonomy decisions are being made and to interact with autonomous systems for making independent assessments Technical elements for consideration include, but are not limited to:

• Complex human behavior recognition and understanding

• Precursor actions or behaviors that are indications of hostile intent prior to hostile action

• Unique approaches for leveraging existing data sets and exploiting novel data sets

• Coordinated planning and behaviors

• Cognitive-behavioral models

• Novel decision frameworks

• Detection of fleeting personnel

• Leveraging of existing or emerging modeling and simulation engines/environments, to include interfaces/visualizations

• Person re-identification

• 3D planning and searching techniques

• Reactive behaviors such as object detection/object avoidance

• Sensor system area coverage approaches for a militarily relevant dense urban environment

• Multiple phenomenology cueing and fusion

• Active sensing, e.g., maneuvering or cueing/reallocating system resources to improve detection

• Integration of dynamic and static sensors to improve detection

• Machine learning

• Triaged display of expert system logic and system status

• Consumer-technology based human interface modalities

• Approaches for developing personnel data, scenarios and scripts for training the URSA system and input data for validation demonstrations DARPA specifically discourages proposals in the following areas:

• Evolutionary upgrades to existing technical capabilities that do not focus on URSA technology areas or address the URSA vision

• Monolithic, single platform/sensor solutions

• Machine vision-only solutions that exclusively exploit subject signatures and do not take behavior into account (e.g., upgrades to Automated Target Recognition or sensor fusion algorithms when used by themselves)

• Significant hardware development in relatively mature technology areas such as unmanned platforms, sensors, mission control equipment, heads up displays or another interface equipment

• Significant development of simulation engines, unmanned systems vehicle management and mission management software, or other software development not required to demonstrate URSA capabilities

• Significant development of autonomous sensor emplacement mechanisms or techniques

• Significant modification or development of digital communications, to include radios, waveforms, and networking technologies

• Significant development of lethal or nonlethal rounds, payloads, or effects and methods of delivery

• Systems or experimentation using live animals

• Interactions with humans that could result in potential injury

B. Program Plan The URSA program is a two-phase, 36-month development effort. The URSA program is intended to be an aggressive effort focused on addressing the key risks associated with the URSA concept.

Proposals should be scoped to provide innovative approaches that develop and evaluate new URSA autonomy technology and evaluate technical maturity of supporting technology without the effort required for a full system development. DARPA envisions rapid prototyping best practices, including significant hardware and software content re-use, in order to maximize leveraging of existing, proven systems.

Phase 1 will include initial technology research and trade studies to develop an evolutionary demonstration architecture and demonstration approach. The Phase 1 program will be comprised of two performer tracks. Track A will be focused on system-level solutions and demonstrations.

Track B will be used to fund compelling critical enabling capabilities such as component-level algorithms, behavioral analysis techniques, technologies or other unique research that could enhance multiple system level approaches. The objective of Track B is to enable participation by companies with niche expertise who can only offer partial solutions to URSA. Track B performer results will be due approximately 12 months after award to enable assessment and potential teaming with Track A performers for Phase 2. In Phase 2, one or more Track A performers will continue to enhance their system-level capabilities and migrate to an urban environment test site for field demonstrations.

The envisioned Program Schedule is provided in Figure 1. While the phasing structure is fixed, the specific schedule of events and demonstrations shown within Phase 1 is notional. Proposers should define the details of their program based on their unique approach and deliverables schedule.

Figure 1. URSA Program Schedule

1. Program Acquisition Strategy

At this time, DARPA is soliciting full proposals for Phase 1 only. Proposers shall also provide an initial program plan, schedule, and ROM cost for Phase 2. Track A Phase 1 proposals shall be comprised of an 18-month base period and a 3-month option period. As described in II.C below, DARPA will conduct a go/no go review no later than 18 months after award to assess whether Phase 1 success metrics have been met by one or more Track A performers and whether the program warrants proceeding to Phase 2. The Phase 2 competition will be limited to only URSA Phase 1 Track A prime contractors. Updated proposal guidance for Phase 2 will be provided to Phase 1 performers toward the end of Phase 1. Upon selection of the Phase 2 performers, DARPA will exercise the 3-month Phase 1 options of the selected performers to mitigate risk of a gap in performance between Phases 1 and 2.

2. Track A and Track B Performer Collaboration Track A performers are expected to collaborate with all Track B performers and consider the results of these efforts when developing their system-level solution and demonstration approach.

The Government will host all performers for common, technical interchange meetings (TIMs) at six (6) months and 12 months after award. At these reviews, the Government expects Track B performers to brief results to all of the Track A performers, and Track A performers will share progress and insights with the Track B performers. In addition to open sessions, the Government will also arrange for break-out meeting room to enable collaborative meetings between Track A and B performers to facilitate teaming discussions.

3. Program Management and Government Collaboration DARPA envisions close collaboration with the performers, particularly during the Phase 1 requirements development and trade study activities. DARPA will staff a team of subject matter experts from Government and support contractors in relevant technical areas, including behavioral science, CONOPS/rules of engagement, human use/ethics and other disciplines to assist in developing a robust URSA solution. This Government team will attend program reviews to provide feedback to the Program Manager. In addition to formal program reviews, DARPA will hold regular teleconferences to enhance communications and collaboration with the Government team.

4. Human Subjects Research (HSR) DARPA anticipates that, at a minimum, Phase 2 will include field demonstrations with live participants. Proposers will determine whether HSR is required to support their program in Phase

1. Proposers must be prepared to comply with all relevant statutory HSR requirements and provide relevant information in the proposal. See Section IV.E below for proposal instructions.

5. Intellectual Property DARPA recognizes that aspects of proposed re-used or off-the-shelf hardware and software may have proprietary restrictions. Due to the evolutionary nature of URSA and potential follow-on activities, DARPA desires at a minimum Government Purpose Rights to all of the hardware and software interfaces to enable future expansion and “plug and play” of alternative sensor or other data streams.

C. Program Metrics and Phase 2 Go/No-Go Decision The ability to achieve sufficient accuracy and timeliness in discriminating human threats in a dense urban environment will be the key to whether this novel capability is technically feasible and can provide operational value to the warfighter. Therefore, DARPA has established a set of program metrics to assess progress toward addressing key risks in Phase 1 and performance goals to be achieved by the end of Phase 2. In Phase 1, it is expected that Track A performers will substantiate that they meet the Phase 1 metrics shown in Table 1 via a combination of analysis, simulation, and demonstration of key critical behaviors and hardware components. Track A performers must address how they have developed their personnel and scenario input data for the Phase 1 final demonstration and to ensure that the results are valid. Track B performers should show traceability to the appropriate metrics for their enabling capability.

Table 1. Phase 1 Metrics

Task Conditions Metrics

Detect Hunter-Killer team

• 4 people

• 2 locations

• Coordinated activity

• Evaluate in representative training sector:

5,000 m2, 10 structures

• Duration: 2 hours

• Individuals: 20 combatants characterized by movement, appearance and intent; 20 noncombatants

• Detect and discriminate 12 of 20 threats, out of 40 presentations

• Maximum 4 false threat detections

• Demonstrate novel autonomous agents and techniques that can detect and discriminate threats with a true positive rate of 0.60 and false positive rate of 0.20

Test environment to be the equivalent of a simulation representation - ~5,000m2 and ~10 urban structures (and corresponding dense urban corridors/pathways)

For URSA Phase 1, DARPA envisions the Table 1 metrics could be applied to:

The proposer’s simulated environment (multiscale) A proposer’s local “proving grounds” site for real-world characterizations and validations appropriate to their proposed effort, and DARPA notional test sites (representative, illustrative, and for proposal analysis/costing purposes only).

The specific demonstration approach for Phase 1 metrics is at the discretion of the proposer, depending on proposed schedule and budget. The Government reserves the right to provide an independent data set or interact independently with the final Phase 1 demonstration.

Point of departure examples for a simulated URSA environment (left) and DARPA Phase 1 notional test environment (right) are shown in Figure 2.

Figure 2. Environment Examples At the end of Phase 1, DARPA will conduct a go/no-go review of the results of Phase 1 activities and demonstrations to assess whether:

The performer has credibly demonstrated that their URSA solution can detect and discriminate threats and meet the metrics described in Table 1. The performer is responsible for providing the justification that their approach has adequate fidelity to substantiate their performance predictions.

The performer has completed a System Requirements Review (see Section I.D.4.b) and URSA Development and Demonstration Plan (UDDP) that are credible for maturing URSA through Phase 2 and can result in a product with operational value to the Services

The performer has developed a credible, executable Phase 2 program plan This go/no-go review must convince DARPA that: (1) URSA is a feasible and effective option for discriminating threats from non-combatants in an urban environment; (2) the UDDP presents a feasible and affordable approach to reduce system risk within the program schedule and budget;

and (3) continuation into Phase 2 is warranted.

A description of Phase 2 metrics and environments is provided in Table 2. These are initial metrics provided to assist the performer in scoping the envisioned complexity of the Phase 2 live demonstrations and ensure the demonstration architecture enables adequate expansion/capability enhancements to address Phase 2 objectives. In Phase 2, DARPA will assess the performance of the URSA technologies using a series of live field evaluation experiments with increasing threat complexity. The Phase 2 experiments will be run by DARPA. Progress will be measured against the program success metrics provided in Table 2. Details of Phase 2 live test scenarios and test site selection will be established during Phase 1 and included in the Phase 2 proposal request.

Table 2. Phase 2 Metrics

Task Conditions Metrics

Detect Sniper

• 1-2 persons at a time

• Multiple locations

• Simultaneous activity

• Evaluate in representative urban neighborhood: 40,000 m2, 25 structures

• Duration: 2 hours

• Personnel: 8 combatants, 32 noncombatants

• Detect and discriminate 6 of 8 threats (sequential and random over 2 hours)

• Maximum 4 false threat detections

Detect Hunter-Killer team

• 4 people

• 2 locations

• Coordinated activity

• Evaluate in representative urban neighborhood: 40,000 m2, 25 structures

• Duration: 3 hours

• Personnel: 20 combatants, 20 noncombatants

• Detect and discriminate 16 of 20 threats (sequential and random over 3 hours)

• Maximum 4 false threat detections

Test environment to be the equivalent of both a simulation and live representation - ~40,000m2 and ~25 urban structures (and corresponding dense urban corridors/pathways)

D. Phase 1 Objectives – Track A The primary objectives of Phase 1 are to conduct trade studies, define functional capabilities necessary to develop an optimized URSA vision; mature elemental technologies, features and capabilities; and conduct initial system-level demonstrations. The final Phase 1 demonstration should substantiate the ability to meet URSA Phase 1 program metrics. In parallel, performers will continue to mature their Phase 2 plan.

DARPA has defined the term “URSA Integrated Testbed (UIT)” to describe the unique way that each performer will use simulation, software, and hardware to support URSA functionality and capability demonstrations. The UIT is not a monolithic demonstration system intended to have operational utility; rather, it is a flexible and evolutionary environment that can accelerate URSA development and be used to demonstrate and assess various URSA elemental and system-level capabilities. For example, a performer’s UIT could include a 3D simulation of an urban space that can be populated by simulated or live agents representing U.S. forces, hostile actors and non-combatants. Such a UIT would accept data streams from multiple sources, run sensor fusion and data analytics algorithms, and incorporate other URSA attributes in sufficient detail to allow DARPA to assess the system’s ability to meet program metrics. Each proposer should clearly define what constitutes their version of a UIT and how it supports the proposed technical approach.

Over the course of the program, performers will enhance the fidelity of their respective UIT, culminating in live experiments in an operationally representative environment. DARPA desires that each performer describe how their UIT will enable rapid increases in capability and incorporate results of emerging research. DARPA envisions that each performer’s UIT will evolve as capabilities are matured, and may include simulation, software-in-the loop (SITL) features such as various levels of autonomy, and hardware-in-the-loop (HITL) functionality such as data collection from sensor assets. Performing live demonstrations by the end of Phase 1 is not required, but is a desirable end state. In any case, proposers will need to demonstrate a robust ability to perform field experiments in Phase 2.

The following paragraphs outline envisioned Phase 1 activities. Proposers are free to propose alternative program approaches that meet the same objectives.

1. URSA System Trade Studies and UIT Requirements Development The performer shall implement a disciplined systems engineering process to ensure a robust and high value UIT solution. The performer shall conduct trade studies and analyses to characterize elemental capabilities and develop UIT functional requirements traceable to their overall URSA vision and the Phase 1 success metrics. The performer should ensure that the UIT has adequate functionality to explore the key questions in Section II.A. It is expected that these trade studies will explore areas including, but not limited to:

• Alternative stimulating actions, potential effects and what can be measured/discriminated

• Identification and assessment of candidate dimensions of evidence and their correlation to human intent

• Effectiveness of various sensor modalities, platform/sensor combinations and integration of data streams

• Candidate unmanned platforms to assist in data gathering

• Data analysis techniques for iteratively fusing and assessing data from multiple sources

• Behavior-based analysis approach and decision engines

• Algorithm functionality/levels of autonomy

• Human Machine Interface (HMI)/mission control approach

• Operational feasibility/value of UIT functionality and capability demonstrations

The results of these activities will provide the performer and DARPA with significant insights into the URSA trade space and ensure a high value UIT design.

The performer shall conduct system-level analysis of the predicted performance of their URSA technical approach and architecture against the URSA program metrics and demonstration objectives to derive a full set of system architecture requirements that maximize UIT utility. In parallel, the performer shall conduct design trade studies to assess the feasibility, technical complexity, development risk, transition potential, and affordability of alternative UIT approaches in meeting these requirements.

As described in Section D above, DARPA believes that the UIT is a largely software-based, performer-defined entity that will evolve over time. Therefore, rather than a traditional hardware development paradigm, DARPA envisions a software-centric development approach like Agile development. This approach will be well suited to evolve the UIT over time, migrating from an initial pure simulation instantiation to progressively more complex software-in-the-loop and hardware-in-the-loop instantiations. The UIT should have the flexibility and adaptability to fully explore the URSA capability and functionality trade space and to assess the level of autonomy and opportunities/need for human interaction. It is envisioned that initial instantiations will include a human in the loop as part of the sensor fusion and supervisory control and that the level of human contribution will evolve as the UIT matures and the level of autonomy increases.

Leveraging of promising emerging tools and development models with extensible software architectures implemented in a game-like environment based on open source and/or industry-standard engines should be fully considered. Notional examples:

Unreal and Unity style game engine environments Gazebo physics-based development environment originally used for unmanned/manned system performance development and visualization Robot Operating System (ROS) and equivalent sets of software libraries and tools to rapidly develop complex and highly capable software-hardware systems.

These environments and libraries allow a UIT to offer realistic, virtual development “worlds” where dense urban and other relevant operational environments can be utilized, scaled, and expanded. Importantly, a UIT environment must stress verticality, primarily driven by building height (and associated features – windows, balconies, overhangs, lighting effects, UxV obstacles), of the dense urban environment that is difficult to replicate or experience in real training sites.

Miniaturized computing and a large consumer device market have spawned a wave of highly accessible and highly capable voice and touch-based interface modalities. A variety of open and Government-owned standards exist or are emerging to support common interfaces with diverse systems (e.g., relevant Standardization Agreements (STANAGs), Cursor-on-Target (COT), Unmanned Aircraft System/UAS C2 Initiative (UCI), or UAS Control Segment (UCS)), and compliant interfaces may be useful for future URSA extensibility. Government-owned systems such as the Android Tactical Assault Kit (ATAK) provide robust map engines and application development kits. Wherever reasonable and prudent, the Government desires to leverage free, open-source, or open-standard software elements to maximize the value of URSA development investment.

2. URSA Development and Demonstration Plan (UDDP) The performer shall refine and add details to the UDDP provided in the proposal. The UDDP will define the team’s overall approach to mitigating risk and maturing their UIT. The UDDP should also describe the approach to behavioral analysis and evidence accumulation, including the approach for periodically incorporating results from emerging research in human behavior and intent. The UDDP should define the risk reduction, technology maturation, algorithm and process development maturation, and evolutionary UIT functionality and associated demonstration activities that will be conducted to validate the ability to achieve URSA program objectives. The UDDP will provide an integrated basis for all development and demonstration activities and detail the full progression of UIT instantiations envisioned to achieve the final Phase 2 objective of live demonstration at an operationally representative test site. The success metrics described in the Program Plan are a minimum set of demonstration objectives for each phase. It is expected that performers will conduct additional demonstration events no less frequently than at six-month intervals throughout the program to demonstrate the maturation of their UIT. The plan should describe the objectives and system-level maturity expected at each demonstration event and the type/fidelity of the demonstration (e.g., software simulation, hardware in the loop simulation, live test). The plan shall also include a complete UIT demonstration schedule as well as Phase 2 ROM cost. The UDDP will be finalized by the first quarterly review. The UDDP and Phase 2 program plan will be updated quarterly throughout Phase 1.

3. Phase 1 UIT Development, Risk Reduction and Demonstrations The performer shall conduct UIT simulation engine trades/selection, development, risk reduction and demonstration activities to achieve Phase 1 program objectives. The performer will mature the Phase 1 UIT instantiation and functionality as well as an appropriate set of enabling capabilities, including component-level algorithms, technologies or other unique research to achieve Phase I demonstrations and metrics. DARPA envisions that performers may also conduct initial data gathering in Phase 1 to assist in populating their UIT Phase 1 instantiation. DARPA desires at a minimum a robust simulation and analysis-based demonstration to meet the Phase 1 success metrics. Proposers who exceed the baseline level of fidelity, e.g., include hardware- or software-in-the-loop simulation for substantial elements of the architecture, will be viewed more favorably. In Phase 1, performers are expected to develop the input data that will be used in demonstrations and to assess the Phase 1 metrics. Performers must substantiate that their input data set(s) adequately represent an urban population of threats and non-combatants. Supporting analysis should substantiate and validate assumptions related to analysis of the identified dimensions of evidence and their correlation to human intent. The Phase 1 UIT evolutionary development and demonstrations should show a clear path to the Phase 2 demonstrations.

During Phase 1, DARPA envisions that UIT demonstrations will be conducted at a performer facility. If a proposer desires to conduct Phase 1 testing at a Government facility, the proposer must include this cost as part of their proposal in accordance with the proposal instructions in Section IV.2 below. For budgetary purposes, the cost of the Phase 1 Government furnished facility will be counted towards the total Phase 1 performer cost. Upon award, if more cost-effective, DARPA may elect to fund the Government test entity directly.

4. Phase 1 Reviews and Deliverables DARPA will host a kick-off meeting within one (1) month of contract award. DARPA desires that the program include quarterly program reviews. For proposal purposes, proposers should assume that DARPA will host the kickoff meeting, the 6-month and the 12-month program reviews in Arlington, Virginia. All other quarterly reviews will be held at the performer’s facility or by teleconference. The objective of these reviews will be to assess progress, provide feedback and stay abreast of any emerging technical, cost, or schedule issues. To successfully achieve the Phase 1 objectives and to ensure consistency among performers, DARPA has developed a minimum list of events and deliverables that must be included in the proposer’s Phase 1 program. Each of these minimum events and deliverables is described below. Proposers should populate their program schedule with these minimum deliverables and supplement this list with additional deliverables/material to be presented at each quarterly review in accordance with their unique program schedule and development approach. System architecture and design updates, technical status, schedule and execution status, and results of any risk reduction/UIT demonstrations shall be provided at each quarterly review. Each review will also include an analysis of current system-level performance and progress towards achieving Phase 1 and Phase 2 metrics.

As described in Section II.B.2 above, the 6-month and 12-month reviews will also include collaborative discussions with Track B performers. The Government plans to host individual sessions with each Track A performer as well as group sessions with Track B performers.

Additional guidance regarding the format and schedule of these reviews will be provided after award.

a) Kick-off Meeting The objective of this meeting will be to discuss the performer’s approach to the program and provide feedback to guide the performer in executing their Phase 1 program. The Government and the performer will also establish the program review schedule as well a schedule of interim informal interactions, including routine management and technical telecoms.

b) UIT System Requirements Review The objective of this meeting will be to review the performer’s optimized UIT system engine and system architecture and development approach. It is expected that this review will detail the design trades and analyses conducted to define the performer’s UIT simulation engine selection, architecture design, system and functional requirements, and UDDP. The review should also detail the dimensions of evidence to be assessed in the UIT, including, but not limited to, personnel signatures and behavioral modalities, with evidence to support their correlation to identifying hostile/non-hostile intent. The review should fully describe the planned instantiations of UIT. This review should fully detail the proposed UIT system capabilities, functions and interfaces at each instantiation and show how these trace to Phase 1 and Phase 2 performance and capability objectives as well as the overall URSA vision. The performer shall show how they will maintain requirements traceability at each instantiation of the UIT. Performers shall discuss their approach for modeling the test environment, generating input data sets and validating demonstration results for each instantiation of the UIT. Key interfaces should be defined and described. Finally, this review shall provide the roadmap for maturing the capability and fully describe the Phase 1 UIT demonstration plans. This includes describing the initial UIT instantiation as well as any additional Phase 1 instantiations.

c) Phase 1 Risk Reduction and UIT Demonstrations Performers should demonstrate capability and functionality of the UIT at periodic major UIT demonstration events. Each proposer should define the optimal frequency and timing of these events in their Phase 1 proposal based on the progress and maturity of their UIT as described within their UDDP. Performers shall provide monthly updates on UIT development progress as part of the teleconference schedule Performers may also conduct parallel risk reduction activities to validate enabling capabilities. The performer will document the results of all Phase 1 risk reduction and UIT demonstrations. Results should be presented at quarterly reviews and include an assessment of performance with relation to the URSA system level objectives and Phase 1 and 2 metrics. The proposer should identify the UIT hardware and software deliverables to be provided at the completion of Phase 1 as appropriate for their proposed UIT.

d) UDDP Quarterly Updates The performer will provide a final Phase 1 UDDP not later than the first quarterly review based on feedback and discussions with the Government at the kickoff meeting. Subsequently, the performer will update their UDDP to reflect emerging Phase 1 results and add additional details as the Phase 2 program plan matures and a Phase 2 test site is identified.

e) Phase 2 Program Plan Quarterly Updates The performer will update Phase 2 program plan, including additional detail regarding the functionality, content and objectives of planned Phase 2 demonstrations, cost and schedule information. These updates should be briefed at quarterly design reviews.

E. Phase 2 Objectives – Track A As described in the Program Plan, DARPA intends to request proposals for Phase 2 prior to the completion of Phase 1. DARPA plans to provide updated Phase 2 objectives with the proposal request that reflects lessons learned from the Phase 1 program and to provide further guidance regarding UIT demonstrations, test facilities, deliverables, etc. Evaluation of the Phase 2 proposal will be based on criteria to be further defined in the proposal request. These criteria will be consistent with the evaluation criteria in this BAA, but tailored to the Phase 2 proposal content.

The objective of Phase 2 is to continue progressive capability build-up of UIT demonstrations including SITL, HITL, and field demonstrations. The details of the Phase 2 plan and demonstrations will be defined by the proposer based on their unique UIT development and demonstration plan. DARPA desires a final Phase 2 demonstration that not only substantiates the ability to meet the Phase 2 metrics, but that is also compelling to potential users and transition partners.

In Phase 2, UIT live field demos will be conducted at a Government-furnished, operationally representative urban test facility, such as Muscatatuck Urban Training Center or the Marine Corps Air-Ground Combat Center (MCAGCC) Twentynine Palms (Ranges 200, 215 and 220).

Performers should identify additional candidate sites for consideration. During Phase 1, DARPA will assess and select the Phase 2 test site.

F. Phase 1 Objectives – Track B The objective of Track B is to develop and mature critical enabling capabilities to support URSA system-level approaches. Track B performers should mature the critical enabling capability to a level that supports incorporation into a Track A system at the end of the Track B effort. Maturation approaches may include simulation, SITL/HITL testing, laboratory experiments, and/or other relevant demonstrations.

DARPA strongly encourages the Track B proposers to achieve the highest level of maturity for their capability possible by Month 12, as well as to develop a plan for how their capability could be integrated into a system-level approach. Incorporation of Track B efforts into Track A efforts is at the discretion of the Track A performers. Working prototypes, models, or test data are highly encouraged to substantiate the value of the Track B effort to the Track A performers.

DARPA desires that the program include quarterly program reviews. For proposal purposes, proposers should assume that DARPA will host the kickoff meeting, the 6-month and the 12-month program reviews in Arlington, Virginia. The 9-month quarterly review will be held at the performer’s facility. The objective of these reviews will be to assess progress, provide feedback and stay abreast of any emerging technical, cost, or schedule issues.

Close collaboration between the Track A and Track B performers will be critical to the program.

As described in Section II.B.2 above, Track B performers will be requested to present at Technical Interchange Meetings (TIM) hosted by DARPA six (6) months and 12 months after award.

Programmatic aspects of the program will be reviewed in private meetings with only the Government team in attendance.

II. Award Information A. General Award Information

Multiple awards are anticipated for a total Phase 1 budget of $22.6M. DARPA envisions three to four Track A performers and multiple Track B performers. The amount of resources made available under this BAA will depend on the quality of the proposals received and the availability of funds.

The Government reserves the right to select for negotiation all, some, one, or none of the proposals received in response to this solicitation and to make awards without discussions with proposers.

The Government also reserves the right to conduct discussions if it is later determined to be necessary. If warranted, portions of resulting awards may be segregated into pre-priced options.

Additionally, DARPA reserves the right to accept proposals in their entirety or to select only portions of proposals for award. In the event that DARPA desires to award only portions of a proposal, negotiations may be opened with that proposer. The Government reserves the right to fund proposals in phases with options for continued work, as applicable.

The Government reserves the right to request any additional, necessary documentation once it makes the award instrument determination. Such additional information may include but is not limited to Representations and Certifications (see Section VI.B.2, “Representations and Certifications”). The Government reserves the right to remove proposals from award consideration, should the parties fail to reach agreement on award terms, conditions, and/or cost/price within a reasonable time, or the proposer fails to provide requested additional information in a timely manner. Proposals identified for negotiation may result in a procurement contract or other transaction for prototype, depending upon the nature of the work proposed, the required degree of interaction between parties, whether or not the research is classified as Fundamental Research, and other factors.

Proposers looking for innovative, commercial-like contractual arrangements are encouraged to consider requesting Other Transactions. To understand the flexibility and options associated with Other Transactions, consult http://www.darpa.mil/work-with-us/contract-management#OtherTransactions.

In all cases, the Government contracting officer shall have sole discretion to select award instrument type, regardless of instrument type proposed, and to negotiate all instrument terms and conditions with selectees. DARPA will apply publication or other restrictions, as necessary, if it determines that the research resulting from the proposed effort will present a high likelihood of disclosing performance characteristics of military systems or manufacturing technologies that are unique and critical to defense. Any award resulting from such a determination will include a requirement for DARPA permission before publishing any information or results on the program.

For more information on publication restrictions, see the section below on Fundamental Research.

B. Fundamental Research It is DoD policy that the publication of products of fundamental research will remain unrestricted to the maximum extent possible. National Security Decision Directive (NSDD) 189 defines fundamental research as follows:

‘Fundamental research’ means basic and applied research in science and engineering, the results of which ordinarily are published and shared broadly within the scientific community, as distinguished from proprietary research and from industrial development, design, production, and product utilization, the results of which ordinarily are restricted for proprietary or national security reasons.

As of the date of publication of this BAA, the Government expects that program goals as described herein may be met by proposers intending to perform fundamental research and proposers not intending to perform fundamental research or the proposed research may present a high likelihood of disclosing performance characteristics of military systems or manufacturing technologies that are unique and critical to defense. Based on the nature of the performer and the nature of the work, the Government anticipates that some awards will include restrictions on the resultant research that will require the awardee to seek DARPA permission before publishing any information or results relative to the program.

Proposers should indicate in their proposal whether they believe the scope of the research included in their proposal is fundamental or not. While proposers should clearly explain the intended results of their research, the Government shall have sole discretion to select award instrument type and to negotiate all instrument terms and conditions with selectees. Appropriate clauses will be included in resultant awards for non-fundamental research to prescribe publication requirements and other restrictions, as appropriate. This clause can be found at http://www.darpa.mil/work-with-us/additional-baa.

For certain research projects, it may be possible that although the research being performed by the awardee is restricted research, a subawardee may be conducting fundamental research.