Description

TSM Special Topic - OUSW R&E CDAO Enterprise Autonomy Division: Advanced Data Labeling Response Date: June 09, 2026, 12:00PM EST I. BACKGROUND The Chief Digital and Artificial Intelligence Office (CDAO) Enterprise Autonomy Division provides enterprise capabilities to support the development and fielding of artificial intelligence (AI) and autonomous systems across the Department of War (DoW). This portfolio includes the curation and management of data for the purposes of training computer vision (CV) models used within autonomous platforms. While CDAO has existing labeling capabilities and a vast repository of data for training AI algorithms, warfighter needs demand that CDAO continue to research and evaluate new labeling providers as the industry rapidly evolves due to technological advances and generative AI. This Special Topic Opportunity is focused on advanced data labeling capabilities to prepare multimodal imagery for training and testing CV algorithms to be used within autonomous systems. This includes the labeling of fields and image characteristics necessary for informing autonomous platform maneuvers and precision guidance. II. PROBLEM DESCRIPTION There is widespread interest throughout the DoW for enterprise-level data curation and labeling capabilities necessary for processing and preparing electro-optical / infrared (EO/IR) imagery and full-motion video (FMV) for training, validating, and testing CV algorithms used within autonomous platforms. The development of more advanced behaviors and decision-making schemas for autonomous systems has been constrained by the way training data has been labeled with bounding boxes and object classification. Labeled data limited to bounding boxes and object classification is insufficient for the development of the next generation of intelligent autonomous systems. Autonomous platforms across domains require additional information from the platform perception software to inform autonomous behaviors like object avoidance or maintaining standoff distance localized to a point on the object. Such information may include: • Weather conditions (e.g., sunny, cloudy, foggy, and rain) • Lighting conditions and source orientation • EO/IR sensor characteristics (e.g., type, resolution, look angle, and distortion factors) • Object environment and sensor domain (i.e., maritime, aerial, terrestrial, or sub-surface) • Object dimensions (e.g., length, and height) • Object pose, orientation, and bearing • Segmentation or boundaries of key object features • Percentage of object occlusion • Semantic segmentation of complex objects and scenes The solution space for these capabilities is vast, so CDAO is pursuing solutions across a range of data labeling services and capabilities. Performers should provide solutions that address a subset of the information listed above and any additional information that the performer believes would be valuable for training autonomous systems. …

Contacts