Curating Uncertainty for Reliable Exploitation and Collaboration (CURE-C)

XAnalytix Systems (XA) and the University at Buffalo (UB) proposed two levels of advances to collaborative systems that will enable the integration of multi-agent cyber-physical-human (CPH) teams where the entities have various levels of uncertainty and trustworthiness. Phase I, titled CURE-C: Curating Uncertainty for Reliable Exploitation and Collaboration, focused on a mission planning system for ground-based vehicle tasking in the context of an automated resupply system for a planet with several outlying bases supporting human life. However, the research is applicable to almost any planning process when the input data is stochastic or unknown. In Phase 2, the team will validate the work that in Phase 1 in a relevant environment as well as provide design of sensor architecture for intelligence-on-the-edge given the stochastic aspects of a mission The innovative aspects of our proposed work for Phase 1 that will be the basis for our follow- up work of Phase 2 are based on creating trusted stochastic distributions for a planning process. Incomplete, noisy, or otherwise uncertain data is the way it is, no purely computational method can magically fix it. Numerous techniques developed by the database and programming languages communities exist to help users cope with uncertain data. Specifically, these tools allow users to define business logic over uncertain (i.e., incomplete, possibilistic, or probabilistic) data as if it were idealized deterministic data. The tool instruments the business logic (e.g., a relational database query) according to a model of uncertainty in the source data, to derive a model of uncertainty over the outputs. Tools for uncertain data management are crucial for working with real-world data but suffer from a range of usability challenges that this proposal aims to address. • Objective 1: The goal of this objective is to develop an algorithm for efficiently summarizing groups of related conflicts. This will allow for efficient corrective actions across similar disparities.  • Objective 2: In our setting, this objective aims to develop a strategy for selecting a repair for the workflow that resulted in the inconsistent data. • Objective 3: We will include a third dimension (time) to Quadtrees to develop Octrees.  • Objective 4: goal of this objective will be to assess the system's viability on large, multi-terabyte datasets and to address any pain points identified through this evaluation. • Objective 5:  This objective aims to provide higher-level interfaces to the core functionality developed through both phases 1 and 2. • Stretch Objective 6: Dynamic Sensor Management (DSM) during missions involving uncertainty refers to the real-time allocation and adaptation of sensors to optimize performance in the presence of unpredictable environmental, operational, or mission-related conditions.  Proposed Deliverables: •    Clustering Conflicts Algorithm •    Repair Recommendations •    Octree Development •    Evaluate and Optimize Scalability •    Spark and Vizier Integration •    Sensor Design to Minimize Uncertainty of Input •    Monthly or Quarterly Reports  •    Software updates every Quarter •    Test and Evaluation results  •    Final Report and Software suite 

Formation flying is a field of high interest for many satellite applications.  These missions may require a high accuracy in relative navigation (position, attitude) between satellites.  Specific examples in space missions include Global Positioning Satellites (GPS), weather satellites, the Magnetospheric Multiscale (MMS) mission, as well as formations of weather satellites use an “A-Train” trailing formation or  a swarm of satellites, similar to NASA’s Swarm Orbital Dynamics Advisor (SODA) program  could be employed for surveillance. Data fusion principles with combined Uncertainty Quantification will be employed in Phase 2.  The use case will also employ multi-agent CPH teams, where humans will have supervisory and mission execution directives.  This could be applied to various problems, from traveling during a natural disaster to police patrolling and routing of hazardous materials. 

This is early/mid-stage (TRL 4) — 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.