Digital Mission Planning Tools for Air Cushion Vehicles
Navy SBIR 2020.1 - Topic N201-031
NAVSEA - Mr. Dean Putnam - dean.r.putnam@navy.mil
Opens: January 14, 2020 - Closes: February 12, 2020 (8:00 PM ET)

N201-031

TITLE: Digital Mission Planning Tools for Air Cushion Vehicles

 

TECHNOLOGY AREA(S): Information Systems

ACQUISITION PROGRAM: PMS 377, Amphibious Warfare Program Office, Ship-to-Shore Connector.

OBJECTIVE: Develop a mission-planning tool implementing Artificial Intelligence (AI) and machine learning (ML) for afloat mission data collection and analysis.

DESCRIPTION: The Ship-to-Shore Connector (SSC) is an Air Cushion Vehicle (ACV), or “hovercraft”, providing amphibious transportation of equipment and personnel from ship-to-shore and shore-to-shore.

The ACV crews need a Mission Planning System (MPS) to support mission planning and post mission analysis for ACV operations that is integrated and synchronized with a lightweight and easy to use handheld tool for use onboard the craft. The LCAC Mission Assessment Tools (LMAT) along with Mission Planning Software (MPS)/Personal Digital Assistant (PDA) will give the Navy Landing Craft, Air Cushion (LCAC) crews the ability to adapt more quickly to requests by the United States Marine Corps (USMC) and accommodate rapidly changing mission parameters such as fuel burn rate and endurance with ease. The MPS will be able to develop and Integrate Mission Plans, Communication Plans, and selected navigation charts to the craft. The MPS should be able to process and display post mission data extracted from the craft. MPS will be a Windows10-based application that will provide mission planning, briefing, and debriefing support to LCAC operational crews and amphibious planning staffs. MPS will also support mission execution by generating electronic mission data packages for use in interfacing the craft's on-board navigation and communication systems. Mission data packages will include Digital Nautical Charts (DNC), operational, navigational and training overlays, mission navigation plans, engine performance and communication plans.

The capability to develop mission plans will support the gamut of Service Life Extension Program (SLEP) and LCAC 100 Class operations, ranging from single craft proficiency-training missions to complex multi-mission, multi-wave amphibious assault operations. This support will include proper route planning, environment-based predictive performance computations to ensure mission viability and conformance to approved operational envelopes, and post-mission analysis of executed missions through playback of recorded navigation, engineering, and communication data.

The system will provide a means to conduct off-craft mission planning and to perform post mission analysis of craft recorded data. Mission planning for ACVs currently takes over four hours and requires use of multiple volumes of manuals and data for implementation and years of training to do properly. Application of AI and ML to the solution will condense the mission planning to a single application based on a series of inputs, which include environmental conditions, cargo, distance, and crew day (calculated Main Engine start to Main Engine stop), greatly decreasing the amount of time needed to plan a mission and allow for greater flexibility when mission requirements change. There are unique sets of performance data for the SLEP LCAC with deep skirt as well as different power settings and engine performance tables for ETF40B engines which include fuel burn rate and endurance. This performance data will be contained within the software installed on each PDA and Land Based mission planning computer system. The MPS/LMAT will allow removal of the bulk of the performance data from the Safe Engineering and Operations (SEAOPS) Volumes and eliminate the complex iterative hand calculations within the planning process.

The MPS software will replace SLEP LCAC systems that are currently in fleet use and contains the following applications:
- Vehicle weight database
- LCAC Weight Allocation Calculator
- Crew Day Calculator
- Electronic Version of SEAOPS OCP Mission Planning Checklist
- LCAC Performance and Analysis System (LPAS)/MPS Computers

The LMAT will give the Navy LCAC crews the ability to adapt more quickly to requests by the USMC and accommodate rapidly changing mission parameters with ease. This is critical for an ACV, which has a defined balance of fuel and payload versus range.

Software developed must be executable on Government-approved Navy/Marine Corps Intranet (NMCI) compliant computing devices and integrated into standard NMCI software loads or software compatible with NMCI systems. Software must be adaptable by Navy System Subject Matter Experts to meet emerging needs and changes to mission priorities. The handheld tool will allow for greater flexibility by being able to be carried with the crew for on-the-fly mission changes. Prototype software is to be loaded on an ACV or appropriate test platform for human factors and regression testing at Naval Surface Warfare Center Panama City Division (NSWC-PCD).

PHASE I: Develop a concept for an MPS/LMAT for ACVs with an onboard handheld device that meets the requirements of mission planning tools for the unique sets of performance tables/data for the LCAC 100 Class with Advanced skirt, and SLEP LCAC with deep skirt as well as different power settings and engine performance tables for MT7 andETF40B engines. Ensure that the performance data will be contained within the software installed in a PDA-type device and the land-based desktop system, which will allow removal of the bulk of the performance data from the SEAOPS Volumes and eliminate the complex iterative hand calculations within the planning process. Incorporate latest data from all SEAOPS Volumes into PDA as described above. Demonstrate the feasibility of the concept in meeting Navy needs and demonstrate that the MPS concept can be readily and cost-effectively manufactured through standard industry practices by proof testing and analytical modeling. The Phase I Option, if exercised, should include the initial layout and capabilities to build the prototype in Phase II.

PHASE II: Develop and deliver a prototype MPS/LMAT with an onboard handheld device that meets the intent of the Description.  Demonstrate the prototype on an ACV or appropriate test platform for human factors and regression testing at NSWC-PCD and support the testing. Evaluate the prototype to determine its compatibility with current craft layout and ability to perform to requirements. Use evaluation results to refine the prototype into a design that will meet the LCAC SLEP and LCAC 100 class Specifications. Prepare a Phase III development plan and cost analysis to transition the technology to Navy use.  Provide detailed drawings, code and specifications in Navy-defined format.

PHASE III DUAL USE APPLICATIONS: Support the Navy in transitioning the MPS for use on the Navy ACV program. Refine the design of the MPS, according to the PMS 377 Phase III SOW, for evaluation to determine its effectiveness in an operationally relevant environment.

The SSC MPS will have private sector commercial potential for craft of this scale operating in the near-shore or on-shore environment. Commercial applications include hovercrafts, airplanes, helicopters, ferries, the oil and mineral exploration/retrieval, automotive, and cold climate research and exploration.

REFERENCES:

1. Englander, Jacob A., Conway, Bruce A., and Williams, Trevor. “Automated Mission Planning via Evolutionary Algorithms.”  Journal of Guidance, Control, and Dynamics, Vol. 35, No. 6, November-December 2012. https://arc.aiaa.org/doi/abs/10.2514/1.54101

2. Damilano, Luca, Guglieri, Giorgio, Quagliotti, Fulvia, Sale, Ilaria  and Lunghi, Alessio. “Ground Control Station Embedded Mission Planning for UAS.”  Journal of Intelligent & Robotic Systems, January 2013, Volume 69, Issue 1-4, pp. 241-256.  https://link.springer.com/article/10.1007/s10846-012-9697-2

KEYWORDS: Ship-to-Shore Connector; Air Cushion Vehicle; Mission Planning Software; Machine Learning; Hovercraft; Artificial Intelligence; ACV; ML; AI