Bridge-to-Bridge Radio for Unmanned Surface Vehicles
Navy SBIR 2020.1 - Topic N201-041
NAVSEA - Mr. Dean Putnam - dean.r.putnam@navy.mil
Opens: January 14, 2020 - Closes: February 12, 2020 (8:00 PM ET)

N201-041

TITLE: Bridge-to-Bridge Radio for Unmanned Surface Vehicles

 

TECHNOLOGY AREA(S): Ground/Sea Vehicles

ACQUISITION PROGRAM: PMS 406, Unmanned Maritime Systems Program 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: Create a system that converts VHF Bridge-to-Bridge radio transmissions from voice to text to meaning and integrates them into a COLREGS reasoning engine; and generates an intelligent reply to a proposed maneuver.

DESCRIPTION: The nautical rules of the road (COLREGS) provide clear guidance for encounters between two vessels, but they do not directly specify what should happen when three or more vessels come in close proximity to each other at nearly the same time. Mariners commonly deal with such situations by communicating via VHF Bridge-to-Bridge radio. Current Unmanned Surface Vehicles (USVs) have COLREGS reasoning engines, but they cannot incorporate information from Bridge-to-Bridge conversations, nor can they reply to simple maneuver proposals. Component technologies exist to convert voice signals to text, to convert text to meaning, and to maneuver unmanned vessels to avoid collisions while following COLREGS. The Navy seeks an integrated solution that will enable a USV to act much like a human mariner; in particular, the USV should be able to understand secure Bridge-to-Bridge radio transmissions, incorporate their meaning into its world model, develop appropriate maneuvering plans, and respond via voice on the Bridge-to-Bridge radio. Partial solutions to the problem may be acceptable, though preference will be given to approaches that are comprehensive and achievable.

PHASE I: Provide a concept to solve part of or the entire USV Bridge-to-Bridge radio problem stated in the Description. Demonstrate the feasibility of that concept. Ensure that, at a minimum, the proposed end product includes recognizing common call-ups such as “Sea Hunter, this is Sun Princess; propose a port-to-port passage.” Produce English language transmissions from native speakers. Integration with an actual VHF radio is not required in Phase I, but Phase I should include a plan to extend the product in Phase II and beyond, analysis showing viability of that plan, and a proposed approach to Phase II testing.

The Phase I Option, if exercised, will include the initial design specifications and capabilities description to build a prototype solution in Phase II that incorporates an actual VHF radio, extends functionality to mariners who speak English as a second language, and generates English replies to proposed maneuvers.

PHASE II: Build a prototype system for testing and evaluation. Incorporate into the prototype, at a minimum, an actual VHF radio, extend functionality to recognize English spoken by non-native speakers, and generate English replies to proposed maneuvers. Explore additional functionalities if feasible, such as integration with a COLREGS reasoning engine and world model. Ensure that the prototype is delivered at least three months prior to the end of Phase II to facilitate ashore testing followed by at-sea testing. (Note: Phase II testing may be accomplished on a manned surrogate vessel with a stand-alone autonomy system running on a laptop or other computer but not actually controlling the vessel’s movements. Phase II testing may also be accomplished on a USV that is temporarily manned for evaluation and safety reasons.) Ensure that the prototype complies with the Unmanned Maritime Autonomy Architecture (UMAA). The Navy will provide UMAA documentation at the beginning of Phase II.

PHASE III DUAL USE APPLICATIONS: Support the Navy in transitioning the technology for Navy use. Produce a final end-to-end system that enables a USV to perform like a human mariner, particularly in its use of the VHF Bridge-to-Bridge radio for negotiating maneuvers in situations involving three or more vessels. The Navy will provide a candidate COLREGS reasoning engine for integration along with an Interface Control Document (ICD) at the beginning of Phase III if needed by the proposer. The Navy expects proposers to support transition to Phase III by integrating into the ICD, supporting additional laboratory and at-sea testing, and developing any required intermediate hardware. This technology will be used in the Medium Unmanned Surface Vehicle (MUSV) program, the Large Unmanned Surface Vehicle (LUSV) program, and possibly other USV programs. This technology will meet critical Navy needs by helping to ensure safe USV navigation in compliance with COLREGS. The product will be validated and tested through extensive laboratory trials followed by more limited at-sea trials.

The civilian market for unmanned vessels appears poised for take-off, and such vessels will need to be able to function even when satellite links to remote oversight facilities ashore are inoperative. Additionally, this technology can be used on minimally manned vessels and pleasure craft as an aid to a human operator.

REFERENCES:

1. Becchetti, Claudio and Ricotti, Klucio Prina. “Speech Recognition: Theory and C++ Implementation (With CD).” John Wiley & Sons, 2008. https://www.wiley.com/en-us/Speech+Recognition%3A+Theory+and+C%2B%2B+Implementation-p-9780471977308

2. McNamara, Danielle S. "Computational methods to extract meaning from text and advance theories of human cognition." Topics in Cognitive Science 3, no. 1 (2011): 3-17.

KEYWORDS: Speech Recognition Software; Voice to Text; Text to Meaning; COLREGS; VHF Bridge-to-Bridge Radio; USV COLREGS Compliance; Natural Language Processing