SOLICITATION NOTICE
A -- Predictive Analysis For Naval Deployment Activities (PANDA)
- Notice Date
- 8/31/2005
- Notice Type
- Solicitation Notice
- NAICS
- 541710
— Research and Development in the Physical, Engineering, and Life Sciences
- Contracting Office
- Other Defense Agencies, Defense Advanced Research Projects Agency, Contracts Management Office, 3701 North Fairfax Drive, Arlington, VA, 22203-1714
- ZIP Code
- 22203-1714
- Solicitation Number
- BAA05-44
- Response Due
- 10/17/2005
- Archive Date
- 10/31/2005
- Description
- The Defense Advanced Research Projects Agency's (DARPA) Information Exploitation Office (IXO) is soliciting proposals for the Predictive Analysis for Naval Deployment Activities (PANDA) program under this Broad Agency Announcement(BAA). BACKGROUND: The current CONOPS for achieving situation awareness in the maritime domain calls for close monitoring of those entities that we already have reason to be concerned about (i.e., we already suspect are threats or which carry cargos that could be dangerous in the hands of the wrong people). This CONOPS is based on the Cold War model where we had the luxury of focusing on a small number of known hostile entities. The successes of the past were achieved by devoting billions of dollars and millions of person-years to manually track and understand the activities of this small number of entities. In today?s Global War on Terror, where a threat can emerge from any number of platforms, we no longer have this luxury. The goal of PANDA is to automatically evaluate the behavior of all larger surface maritime vessels (not just those that we are already concerned about), to determine which ones are deviating from their normal, expected behavior in ways that may be indicative of an emerging threat. PANDA will advance technologies and develop an architecture that will alert watchstanders to anomalous ship behavior as it occurs, allowing them to detect potentially dangerous or harmful behavior before it causes harm. These technologies and systems will be transitioned to various partners and customers throughout the development process, ensuring that the end product meets the needs of the services and watchstanders. Participants will work closely with the transition partners to aid in this process. PROGRAM OBJECTIVES/DESCRIPTION: The PANDA program has three objectives: First, automatically learn motion-based activity patterns from long-duration tracks and associated data. Second, automatically perform motion-based change detection. Third, provide anticipatory situation awareness and threat assessment to watchstanders across multiple echelons. It is envisioned that the PANDA technology components and system developed to meet those objectives will be designed to operate in a distributed, services-oriented architecture (SOA) consistent with the US Navy?s current FORCENet acquisition policy. Additionally, PANDA will be exercised against real data in a testbed via a series of carefully designed experiments to assess the accuracy, efficiency, and robustness of both the integrated system and the components. These assessments will involve integrating the PANDA components, both with one another and with the testbed, along with experiment planning, execution, and analysis to objectively measure progress toward program goals. The testbed itself, along with relevant subject matter experts, will be provided by the government. Proposers should strive to develop the highest level of accuracy, robustness, and automation possible for PANDA technology components and the overall system, recognizing that they will always be supervised by analysts and watchstanders. In particular, the Government is interested in solutions to the following technical components: Motion-Based Pattern Learning (MPL): Design and construct a system that learns motion-based activity models for individual, groups, and/or classes of vessels. This system should integrate local and global learning. Demonstrate increases in robustness, flexibility, and computational efficiency as the program progresses. Prediction and Activity Monitoring (PAM): Design and construct a vessel prediction and activity monitoring function, which compares the incoming and emerging vessel tracks/behaviors with the existing vessel patterns and can determine if the current behavior is consistent with the learned pattern. Demonstrate increases in accuracy, robustness, and computational efficiency as the program progresses. Adaptive Context Modeling (ACM): Design and construct a component that learns, maintains, and efficiently stores ?business process? models related to variations in surface maritime ship behavior as well as suspicious behaviors. Models can be entered manually by an analyst/watchstander or learned by the system by observing a watchstander?s activities in resolving previously unknown anomalies. Demonstrate increases in robustness, flexibility, and computational efficiency as the program progresses. Anomaly Processing and Presentation (APP): Design and construct a component that compares anomalies generated by PAM to the anomaly data base to determine if the anomaly is an emerging threat or not, and present the results to an analyst/watchstander for them to review or manually resolve. Demonstrate increases in robustness, flexibility, and computational efficiency as the program progresses. In addition to the four technical components listed above, this effort requires support for activities related to System Engineering and Integration (SEI) and Performance Evaluation (PE). For planning purposes, assume this effort starts 1 February 2006. The objective of this phased approach is to incrementally deliver technical components, integrate those components, and evaluate those components and the overall system. As the program progresses, the focus of each phase will change to ensure the Program Metrics are met and a fully integrated, transitionable system is produced. Each phase builds on the work of the previous phase or phases. The high-level objectives for each program phase are as follows: Phase I ? Learning and Detection: Demonstrate that individual and class-of-vessel motion-based activity patterns can be learned and used to detect anomalies; use patterns to predict movements and classify (groups of) vessels as potentially (non)hostile with a low incidence of false alarms; learn and detect multi-ship correlated activities; incorporate initial context models. Scale: To be specified by the proposer but no less than 1,000 vessels. Phase II ? Automation: Increase number of patterns detected (to be specified by the proposer, but at least an order of magnitude increase expected) and speed of detection (rapid relearning in response to sudden changes); improve accuracy of detection and classification of anomalies; automate integration technology component (MPL, PAM, ACM, APP) outputs. Phase III ? Integration: Increase number of patterns detected (to be specified by the proposer, but at least an order of magnitude increase expected) and speed of detection (learn on several exemplars); improve accuracy of detection and classification of anomalies; integrate across nodes for simultaneously function at multiple locations. Phase IV ? Technology Scaling and Transition: Leverage future detection/tracking capabilities to expand system to smaller (harbor) vessels (scale equal to world traffic); increase number of patterns detected; improve accuracy of detection and classification of anomalies; harden and transition PANDA system. SELECTION CRITERIA: Proposals will be selected through a technical/ scientific/ business decision process, with technical and scientific considerations being most important. Evaluations will be performed using the following criteria, listed in descending order of relative importance: (1) Overall technical and scientific merit, innovation, and depth; (2) Relevance to PANDA mission objectives and program concepts; (3) Personnel and corporate capabilities and experience; (4) Proposed schedule and metrics per Phase; (5) Project and technology transfer plans and potential transformative impact on military operations; and (6) Cost realism and value of proposed work to the Government. Further details may be found in the PIP, which can be accessed at the Uniform Resource Locator (URL) address provided in the next section. GENERAL INFORMATION: A Briefing to Industry (BTI) is scheduled for 16 September 2005 to be held at: MITRE facility, 7515 Colshire Drive, McLean, VA 22102-7508. The BTI will be classified SECRET/SCI and will cover the following topics: general overview of the PANDA program; contractual issues; proposal instructions; information on the PANDA problem domain, data, and technical and system aspects; and Q&A. Due to space limitations, attendance will be limited to one person per organization; if space permits, the government may elect to allow additional attendees. Additional information on the PANDA BTI may be found at: http://dtsn.darpa.mil/IXO/solicitations/PANDA/index.htm. Pre-registration for the PANDA BTI is required. The deadline for pre-registration is 9 September 2005 via the World Wide Web (WWW) at https://www.tfims.darpa.mil/bti/. Instructions for passing classified visit requests will be provided to PANDA BTI registrants. All pertinent information and materials presented at the UNCLASSIFIED session of the PANDA BTI will be made available at http://dtsn.darpa.mil/IXO/solicitations/PANDA/index.htm. PROPOSAL SUBMISSIONS: DARPA is expecting to receive CLASSIFIED and UNCLASSIFIED proposal submissions for this effort. If a CLASSIFIED proposal is planned, please follow the necessary submission guidelines that are provided in the Proposer?s Information Package (PIP) for BAA 05-44 at: http://dtsn.darpa.mil/IXO/solicitations/PANDA/index.htm, in particular those defined in Section B.4 (SECURITY AND SUBMISSION GUIDELINES). Proposers must be willing to cooperate and exchange software, data, and other information with other contractors in a manner that contributes to the success of the program. This includes routine coordination with other contractors or integrator, selected by DARPA, if appropriate. A statement of cooperation must be included in the final proposal. PROPOSAL DELIVERY: Proposal abstracts ARE NOT requested in advance of full proposals. All proposals must be received no later than 12:00 p.m. (Noon) EST, on 17 October 2005 to be considered for the initial evaluation phase. Please reference the URL provided in the PROPOSAL SUBMISSIONS section above for complete submission instructions. Proposals MUST NOT be submitted by fax or e-mail; any so sent will be disregarded. BAA 05-44, PANDA, will remain open until 12:00 p.m. (Noon) EST, 31 August 2006. Proposals may be submitted at any time from issuance of this BAA through 12:00 p.m. (Noon) EST, 31 August 2006. While the proposals submitted after the initial 17 October 2005 deadline will be evaluated by a Government review panel, proposers should keep in mind that the likelihood of funding such proposals is less than for those proposals submitted in connection with the initial evaluation and award schedule. PROTECTION OF INFORMATION: It is the policy of DARPA to treat all proposals as competitive information and to disclose contents only for the purposes of evaluation and assessment. The Government may use selected support contractor personnel from McNeil Technologies, Bradson Corporation, MITRE, CACI International, Schafer Corporation, and Strategic Analysis, Inc. to assist in administrative functions only. Those contractors sign binding non-disclosure agreements with DARPA. TECHNICAL AND ADMINISTRATIVE INQUIRIES: DARPA intends to use electronic mail for correspondence regarding BAA 05-44. Technical, contractual, or administrative questions must be sent to email address: BAA05-44@darpa.mil. Answers to all questions generally relevant to the technical, contractual, and administrative aspects of the solicitation will be posted for public access at http://dtsn.darpa.mil/IXO/solicitations/PANDA/index.htm under the title Frequently Asked Questions (FAQs). OTHER IMPORTANT INFORMATION: This BAA affords proposers the choice of submitting proposals for the award of a Grant, Cooperative Agreement, Procurement Contract, Technology Investment Agreement, Other Transaction for Prototype Agreement, or other such appropriate award instrument. The Government reserves the right to negotiate the type of award instrument determined appropriate under the circumstances. The Government reserves the right to select for award all, some, or none of the proposals received in response to this announcement and to award without discussions. All responsible sources may submit a proposal that shall be considered by DARPA. Small Disadvantaged Businesses and Historically Black Colleges and Universities (HBCUs)/Minority Institutions (MIs) are encouraged to submit proposals and join others in submitting proposals. However, no portion of this BAA will be set aside for HBCU and MI participation due to the impracticality of reserving discrete or severable areas of technology for exclusive competition among these entities. Government contractors are required to register at the Government?s Central Contractor Registration site in order to negotiate contracts with most government agencies. This URL is provided as a reference: http://www.ccr.gov. Since this FedBizOpps Announcement, along with the PIP, constitutes a Broad Agency Announcement as contemplated in the FAR 6.102 (d)(2)(i), all prospective proposers MUST also refer to the PIP before submitting a proposal. The administrative address for this BAA is: Fax: 703-741-0081, addressed to: DARPA/IXO BAA 05-44. Electronic mail: BAA05-44@darpa.mil. Electronic file retrieval: http://dtsn.darpa.mil/IXO/solicitations/PANDA/index.htm. The Government will not be liable for the cost of BTI attendance and/or proposal preparation and submission. Original Point of Contact: Michael Blackstone, Contracting Officer, email BAA05-44@darpa.mil.
- Record
- SN00884197-W 20050902/050831213043 (fbodaily.com)
- Source
-
FedBizOpps.gov Link to This Notice
(may not be valid after Archive Date)
| FSG Index | This Issue's Index | Today's FBO Daily Index Page |