SBIR OSW26BZ05-DV018 (Office of the Secretary of Defense): Artificial Intelligence / Machine Learning (AI/ML)-Based Radar Data Compression
U.S. Department of Defense — Office of the Secretary of Defense
Free. Verify your email, then we send one reminder only.
- Posted
- Aug 6, 2026
- Closes
- Sep 23, 2026 (in 27 days)
Similar opportunities open now
- SBIR OSW26BZ05-DV020 (Office of the Secretary of Defense): Joint Radar & Communication WaveformsSame funderOpenU.S. Department of Defense — Office of the Secretary of DefenseCloses in 27 days
- SBIR OSW26BZ05-NV017 (Office of the Secretary of Defense): Sensing Algorithms for Bandwidth Efficient Edge Radars (SABER)Same funderOpenU.S. Department of Defense — Office of the Secretary of DefenseCloses in 27 days
- SBIR OSW26BZ05-DV019 (Office of the Secretary of Defense): Collaborative Distributed Swarm RadarSame funderOpenU.S. Department of Defense — Office of the Secretary of DefenseCloses in 27 days
- SBIR OSW26BZ05-DV022 (Office of the Secretary of Defense): Signal Classification and Anomaly Detection in Contested Spectral EnvironmentsSame funderOpenU.S. Department of Defense — Office of the Secretary of DefenseCloses in 27 days
- SBIR DPA26BZ05-DV019 (DARPA): Semantically-Aware ISROpenU.S. Department of Defense — DARPACloses in 27 days
Amount
Amount not published by the funder
Who can apply
Small Business. Startup
About this opportunity
Office of the Secretary of Defense SBIR topic — under DoW SBIR 2026 BAA (Solicitation 26.BZ, Release 5) — Accepting submissions 2026-08-26 to 2026-09-23. Objective: Use deep learning (e.g. autoencoders or transformer models) to compress raw radar data into low-bit representations for efficient storage/transmission, with reconstruction that preserves radar utility. Description: Next-generation radars (especially synthetic aperture radar (SAR)) collect data with massive data rates. Traditional image compression is not optimized for raw radar returns. Recent work extends neural compression to the complex SAR domain. Phase I is to explore autoencoder architectures for radar data using, for example, a complex-valued neural network encoder/decoder that learns to compress raw pulses or range-Dopp...