Improved Road Network Extraction Through Reinforcement Learning
ID: OSD23C-001Type: Phase I
Overview

Topic

Improved Road Network Extraction Through Reinforcement Learning

Agency

Department of DefenseN/A

Program

Type: STTRPhase: Phase IYear: 2023

Topic Link

https://www.sbir.gov/node/2448125

Additional Information

https://www.defensesbirsttr.mil/
Timeline
  1. 1
    Release Aug 23, 2023 12:00 AM
  2. 2
    Open Sep 20, 2023 12:00 AM
  3. 3
    Next Submission Due Oct 18, 2023 12:00 AM
  4. 4
    Close Oct 18, 2023 12:00 AM
Description

The Department of Defense (DoD) is seeking proposals for the topic of "Improved Road Network Extraction Through Reinforcement Learning" as part of their Small Business Innovation Research (SBIR) Phase I program. The specific agency involved in this solicitation is the National Geospatial-Intelligence Agency (NGA). The objective of this research is to develop an automated geographic feature extraction system that replicates human performance using reinforcement learning. Currently, the production of foundation feature data vector (FFD) features such as roads and building outlines is a labor-intensive and time-consuming manual process. The proposed technology aims to enhance or replace existing computer vision methods by augmenting them with reinforcement learning to improve completeness and accuracy. The Phase I proposal should focus on demonstrating the feasibility of extracting roads in a small geographic area using reinforcement learning. Phase II will involve developing prototypes for road and building footprint extraction in areas of varying complexity and testing the accuracy improvements over existing methods. The ultimate goal is to fully develop and transition the technology for Department of Defense (DoD) and other commercial feature extraction applications. The project duration and funding specifics can be found on the solicitation agency's website.

Files
No associated files provided.
Similar Opportunities
DOD SBIR 24.4 Annual - Deep Terrain Shaping
Active
Department of Defense
The Department of Defense (DOD) is seeking proposals for the topic of "Deep Terrain Shaping" as part of its SBIR 24.4 Annual solicitation. The Army branch is specifically interested in solutions or components of solutions that can delay, deter, and deny enemy forces freedom of movement 70-150km+ beyond the forward line of troops (FLOT). Currently, the Army uses cannon-fired or air-dropped anti-tank mines for terrain shaping, but these systems are aging and resource-intensive. The Army is looking for innovative technology solutions that can shape existing terrain, position explosive loitering munitions, activate when a threat is identified, and initiate lethal or non-lethal effectors from behind the front line. Integration of remote sensing and lethal effectors with human-in-the-loop is also of interest. The objective of Phase I is to design a proof-of-concept solution or component(s) for terrain shaping in the deep fight. Phase II involves developing and demonstrating a prototype, while Phase III focuses on commercialization objectives. The project duration is not specified, but the solicitation is open until March 31, 2025. More details can be found on the DOD SBIR website (https://www.defensesbirsttr.mil/SBIR-STTR/Opportunities/).
DOD SBIR 24.4 Annual - Deep Terrain Shaping
Active
Department of Defense
The Department of Defense (DOD) is seeking proposals for the topic of "Deep Terrain Shaping" as part of its SBIR 24.4 Annual solicitation. The Army branch is specifically interested in solutions or components of solutions that can delay, deter, and deny enemy forces freedom of movement 70-150km+ beyond the forward line of troops (FLOT). The current systems used by the Army for terrain shaping operations are aging and resource-intensive, and there are restrictions on their use outside of the Korean peninsula. The Army is looking for deep terrain shaping obstacles (DTSO) that can impede enemy movement and operations. This can include uncrewed systems capable of forming obstacles, positioning explosive loitering munitions, or activating when a threat is identified. The integration of remote sensing and lethal effectors at machine speed with human-in-the-loop is also of interest. The solutions should allow Soldiers to conduct terrain-shaping operations 70km+ beyond the FLOT and should be scalable for different desired effects on enemy maneuver. The solicitation is currently open, with a close date of March 31, 2025. The project will be conducted in two phases. Phase I involves designing a proof-of-concept solution or component(s) of a solution for terrain shaping in the deep fight. Phase II focuses on developing, building, and demonstrating a prototype of the concept advanced during Phase I. Awardees may also be eligible for a Phase IIb award to extend the period of performance with additional funding. Phase III aims to pursue commercialization objectives and may involve developing a manufacturing-ready product design and engaging in laboratory or operational testing. The technology within this topic is restricted under the International Traffic in Arms Regulation (ITAR) or the Export Administration Regulation (EAR), and offerors must disclose any proposed use of foreign nationals. The full solicitation can be found at the following link: [SBIR Topic Link](https://www.sbir.gov/node/2484463).
DOD SBIR 24.4 Annual - Continuous Time Spiking Neural Network Field Programmable Neural Network Array
Active
Department of Defense
The Department of Defense (DOD) is seeking proposals for the development of a continuous time spiking neural network field programmable neural network array. This technology falls under the Integrated Network Systems-of-Systems critical technology area. The objective is to create a mixed signal, programmable spiking neural network array integrated circuit. This field programmable neural network array would provide flexibility and low cost for neural network applications in the DoD and Army. The research will focus on the feasibility of developing the network using analog memory, field programmable gate arrays (FPGA), and field programmable analog arrays (FPAA). The project will be conducted in two phases, with the second phase involving the development of a prototype and the proposal of a Future of Vertical Flight/UAS demonstration project. The ultimate goal is to fabricate the neural network array integrated circuit and commercialize it for both government and commercial applications, including automotive vision, medical electronics, and big data analytics. The project duration is from 2024 to 2025, and interested parties can find more information on the grants.gov website.
DOD SBIR 24.4 Annual - Artificial Intelligence/ Machine Learning (AI/ML) Focused Open Topic
Active
Department of Defense
The Department of Defense (DOD) is seeking proposals for an Artificial Intelligence/Machine Learning (AI/ML) Focused Open Topic. The purpose of this open topic is to bring potentially valuable small business innovations to the Army and expand the relevance of the Army SBIR program to firms who do not normally compete for SBIR awards. The topic accepts both Phase I and Direct to Phase II submissions. Phase I proposals are accepted for a cost up to $250,000 for a 6-month period of performance, while Direct to Phase II proposals are accepted for a cost up to $2,000,000 for a 24-month period of performance. The research areas of focus include synthetic data generation, data validation and verification, AI risk mitigation, large language models, retrieval augmented generation, and collaborative AI technologies. Phase I submissions require a 5-page technical volume, an 8-slide commercialization plan, and a statement of work outlining deliverables. Phase II submissions require a 10-page technical volume, a 5-page feasibility documentation, an 8-slide commercialization plan, and a statement of work. During Phase II, firms must produce prototype solutions that are practical and feasible to operate in edge and austere environments. Phase III focuses on the maturation of the technology to TRL 6/7 and the production of prototypes to support further development and commercialization. The Army will evaluate each product in a realistic field environment and provide solutions to stakeholders for further evaluation. The submission deadline is March 31, 2025. For more information, visit the [solicitation link](https://www.sbir.gov/node/2651299).
DOD STTR 24.D Annual - Reasoned Cyber Visualization (RC-Vis)
Active
Department of Defense
The Department of Defense (DOD) is seeking proposals for the Reasoned Cyber Visualization (RC-Vis) topic as part of the Small Business Innovation Research (SBIR) Phase I program. The objective of RC-Vis is to develop semantic technology that generates tiered visualizations of cyber defense coverage and interactions to assess cyber vulnerability. The technology aims to address the gap in reasoning and visualizing how multiple cyber defenses interrelate and the implications of known threats. The project duration for Phase I is six months with a funding amount of $250,000. Successful proposals should include an architecture for producing a modular, intermediate semantic representation, a methodology for reasoning over this representation, a constructive and/or generative approach for creating tiered visualizations, and a graphic user interface. Phase II, with a duration of 24 months and funding of $1.8 million, focuses on developing a full prototype that can generate both semantic and graphic representations. The technology resulting from this SBIR has potential applications in risk management, cyber security training, and improving cyber security posture.