Improved UAS Robustness through Augmented Onboard Intelligence

This work will focus on the development of a highly capable avionics subsystem and machine learning algorithms to provide early warning of potential failures of critical subsystems on small UAS. This modular system will consist of networked onboard monitoring nodes capable of observing operations and providing notification of off-nominal conditions to the autopilot as well as the operator, mitigating the risk of failure, and providing critical information regarding required maintenance. The boards, while computationally powerful will be limited in size, weight and power to avoid significantly impacting the performance of current vehicles and simplify its installation. Furthermore, the networked devices will be able to communicate with each other as well as the autopilot, allowing for vehicle wide information to contribute to a high degree of awareness of the vehicle's well-being. The primary objectives are: 1.Determination of a set of subsystems commonly employed by UAS whose failure would cause a system critical issue. 2.The identification of a set of sensors and machine learning algorithms capable of providing the necessary inputs to detect the health and status of its associated subsystem, and determining the probability of a fault occurring in the near future. 3.The design of a monitoring node capable of interfacing to the required set of sensors and implementing the machine learning algorithms. The nodes will also be limited to a size and weight that will allow for them to be installed on most UAS without impacting the vehicle's performance. 4.The design of an onboard network capable of supporting communications between all smart monitoring nodes on the aircraft. Each node can then communicate any potential failures to the autopilot and/or operator as well as share information that will allow for the implementation of distributed machine learning algorithms between the nodes and recognition of cross-correlation between systems.

The small size and modularity of the proposed system allows for integration into many UAS missions flown or funded by NASA. Automated warnings and actions during flight will reduce the need for expert operators to be able to deal with these contingencies. Over the past several years BST has operated UAS for scientists (both at NASA and NOAA) for scientific field campaigns including severe storm measurements and satellite calibration missions with various sensors. It is the goal of this technology to remove the need for expert UAS operators, and allow scientists to directly conduct these field campaigns without sacrificing safety. Achieving this will allow wider adoption by NASA personnel since this will reduce the reduce costs and stress on scheduling flight crews. NASA has a history of conducting new and difficult missions with UAS in challenging environments such as the Arctic The proposed system will be designed in such a way to extend the monitoring capabilities to new types of missions and reduce flight risks. One example of this sort of new capability is the plan to extend the technology in Phase II and beyond for the detection of aircraft icing using machine learning approaches that try and predict icing by looking at environmental conditions combined with reductions in aircraft performance. This type of capability can then be employed in even smaller UAS than usual allowing more flight campaigns that will help increase the market for NASA Earth Science missions.

BST is excited about the potential of this technology for the commercial side of our UAS business. BST's commercial UAS are primarily used to generate 3D point clouds and orthomosaic imagery. Up until now BST has focused on ease of use and intuitive control from an Android tablet to lower the barrier of entry for operators. This is important especially for small businesses that do not have the resources to hire full time UAS pilots, but can greatly benefit from this technology in their day to day business. BST aims to utilize the proposed technology to further lower the barrier of entry and reduce the risk of mission failure. By making the UAS more reliable by both reducing the chances of failure from inconsistent maintenance and better dealing with in flight anomalies, new types of missions and sensing packages will become possible. Commercial customers will be able to begin using more expensive sensors with less fear of crashing. This capability will also be one important aspect in allowing beyond visual line of sight operations. Certain markets will eventually need this capability to grow to their potential; specifically pipeline monitoring and higher altitude missions for atmospheric science. BST has operated demo missions for NOAA that really will only have long term value if allowed to operate much beyond the current limitations of 400 ft AGL. Pipeline inspection with UAS is much more valuable with beyond line of sight operations.

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.