Communication-Aware Dispersed Autonomy and Safety (CODAS)

The goal of this project is to model, predict, and control the dynamic communication environment experienced by collaborative autonomous aviation systems. The heart of NASA's Sky for All vision is adaptive collaboration based on extensive shared world views. Realizing this vision will rely heavily on assured networked communication, therefore our project focuses on achieving validated flexible coordination based on air, ground, cloud, and edge autonomy architectures where agents reason jointly over communication, mobility, and computation. The communication environment will be highly dynamic and uncertain due to the nonlinear, stochastic nature of radio propagation; the communication traffic demands created by networked vehicles in shared airspaces; and the overlap between aviation systems with other public communication networks, e.g. mobile broadband and the Internet. Our Communication-aware Dispersed Autonomy and Safety (CODAS) framework will mean: efficient use of limited communication bandwidth; improved safety through quality of service guarantees for delivery of information; enhanced human-autonomy interactions based on reliable information streams; increased navigation accuracy through fusion of opportunistic signals; and new applications that leverage air mobility to augment or provide communication services.

Traditional distributed collaborative systems view communication as a limitation and focus on deploying algorithms that are robust to perturbations induced by them. By contrast, this project will develop a cross-cutting autonomy framework that can actively regulate the movement of information through the networked system in parallel to managing the movement of the vehicles themselves. Cross-layer communication modeling considers the relative importance of different data streams and uses navigation data to detect interference sources in the RF environment. Cross-plane decision-making combines reasoning over the motion (the ``control plane''), communication (the ``network plane"), and computational resources of the system. Cross-scale algorithms deployed on dispersed resources balance individual platform, team, and system-wide objectives. Together, these cross-cutting methods lead to communication-aware dispersed autonomy and safety.

The main innovation of this work is to treat communication as a variable that can be learned, predicted, and controlled, rather than a barrier to be overcome. Three major technical challenges are addressed with a culminating set of experiments. The first technical challenge is to understand, classify, and predict the flow of information, rather than just data, in dynamic collaborative aviation networks. Given this understanding, the second challenge is to establish a quality-of-service framework that improves the safety and efficiency of platform mobility, communication routing, and computational resource allocation compared to siloed state-of-the-art approaches. Further building on these technologies, the third challenge is to create communication-aware planning, routing, and design techniques that allow dispersed stakeholders assured, safe, and equitable access to shared physical and networked environments during collaborative operations. Innovations addressing these challenges will be motivated by and assessed in a series of scenarios in package delivery, drone-as-service, and wildfire fighting applications.

Workforce development and technology transition opportunities will be weaved throughout the projects. Undergraduate and graduate students will participate in all research tasks, including experimental assessment in the field. Project outcomes will be included in new curricular elements and shared across partner universities. Industry partners Draper and Aurora Flight Sciences will guide test scenario development and share expertise in designing, deploying, and evaluating autonomous systems and related technologies.

This project will produce tools and techniques for understanding, exploiting, and assuring the dynamic communication environment of distributed collaborative aviation systems. Understanding and exploiting the communication environment will provide safe, efficient, adaptable and sustainable transportation of people, goods, and information. Specific benefits will include algorithms that will be published in the open literature; open source software packages for communication mapping and prediction engines, communication-aware planning and routing, and human-autonomy interfaces; data sets from a variety of communication environments; experimental characterization and evaluation in dense (urban/suburban), sparse (suburban/rural), and remote (rural/disaster) environments; and demonstration of new concepts of operation and new applications with communication-aware autonomy.

This is early/mid-stage (TRL 1) — the most realistic path in is NASA SBIR/STTR, which funds small businesses and research institutions to develop technology aligned with NASA's needs (equity-free, phased funding). Check whether a current SBIR/STTR solicitation topic overlaps with this project's technology area, or contact the project directly (above) to ask.

None of these are guaranteed paths for this specific project — TechPort itself doesn't have an "apply" button. Reaching out to the contact(s) above with a specific question is usually the fastest way to find out what's actually open.