This letter presents the depth control of an autonomous micro diving agent called autonomous diving agent (ADA). ADA consists of off-the-shelf components and features open-source hardware and firmware. It can be deployed as a testbed for depth controllers, as well as a mobile sensor platform for research or in industrial tanks. We introduce a control law that is based on the feedback linearization method and enhanced by an adaptive fuzzy algorithm to cope with modeling inaccuracies. The proposed depth controller is computationally light enough to run on ADAs embedded hardware. In experiments performed in a wave tank, the adaptive fuzzy scheme shows the ability to deal with both depth regulation and depth profile tracking. ADA is even able to hold on to dynamic isobars despite external disturbances. We demonstrate that under the influence of waves, ADA describes orbital motions similar to water particles.

Advances in Artificial Intelligence (AI) introduce both promising real-world applications in various fields such as aviation but also challenges in assuring safety. Regulators in aviation mandate, as with any other application, compliance of these AI-based systems with high safety standards. This especially holds for Human-AI Teaming. The European Union Aviation Safety Agency (EASA) outlined in their concept paper the definitions of cooperation and collaboration between humans and AI, as well as the differences in terms of authority and task allocation. Therein, the question of safety in situations of collaboration with shared goals, dynamic task allocation, and partial authority within the Human-AI team is paramount. As a safety concept, EASA requires the usage of Operational Design Domains (ODDs) from the automotive field. In this work, the concept of ODDs is transferred to the Air Traffic Control (ATC) domain. An initial ODD is defined for an AI-based digital team partner that supports Air Traffic Controllers in their daily work even for safety-critical tasks such as conflict detection and resolution. Additionally, the required tools for successfully executing this task is demonstrated. Based on the ODD description, conflict scenarios are generated and tested in a simulation environment, showcasing situations inside and outside the ODD. Based on these results, the feasibility of using ODDs in ATC is discussed, outlining a potential step towards the safe application of Human-AI Teaming.

Applications based on artificial intelligence (AI) promise benefits, ranging from improved performance to increased capabilities in many industries. In the aviation domain, one example is the new Airborne Collision Avoidance System (ACAS X). The current investigation aims at combining ACAS X and AI to maintain its performance while decreasing the memory footprint. However, the anticipation of AI being increasingly used confronts regulators with challenges in terms of safety assurance and certification. Consequently, the European Union Aviation Safety Agency (EASA) published a concept paper for machine learning applications in aviation. Both, the Concept of Operation (ConOps) in combination with an Operational Design Domain (ODD), are listed as objectives to be met for the safety analysis. From a developer’s perspective, this raises questions on how to effectively derive the ODD from ConOps and test the given system based on the ODD description. Based on an exemplary use case of a Near Mid-Air Collision avoidance between two aircraft through the advisories of ACAS X, a highly automated framework for generating and testing synthetic data is proposed. Using this framework, 1800 Near Mid-Air Collision scenario files are created and automatically executed in the simulation environment FlightGear. Scenario-based testing is used for the logging of ACAS X advisory data and evaluating it against predefined requirements. By this approach, an efficient way of verifying system requirements and conducting automated testing based on the ODD definition is demonstrated. Throughout this process, Model-Based Systems Engineering (MBSE) is used to reduce and manage complexity. The framework in this paper enables a systematic and highly automated approach for scenario generation based on the ODD.

A continuous increase in artificial intelligence (AI)-based functions can be expected for future aviation systems, posing significant challenges to traditional development processes. Established systems engineering frameworks, such as the V-model, are not adequately addressing the novel challenges associated with AI-based systems. Consequently, the European Union Aviation Safety Agency (EASA) introduced the W-shaped process, an advancement of the V-model, to set a regulatory framework for the novel challenges of AI Engineering. In contrast, the agile Development Operations (DevOps) approach, widely adopted in software development, promotes a never-ending iterative development process. This article proposes a novel concept that integrates aspects of DevOps into the W-shaped process to create an AI Engineering framework suitable for aviation-specific applications. Furthermore, it builds upon proven ideas and methods using AI Engineering efforts from other domains. The proposed extension of the W-shaped process, compatible with ongoing standardizations from the G34/WG-114 Standardization Working Group, a joint effort between EUROCAE and SAE, addresses the need for a rigorous development process for AI-based systems while acknowledging its limitations and potential for future advancements. The proposed framework allows for a re-evaluation of the AI/ML constituent based on operational information, enabling improvements of the system’s capabilities with each iteration.

While Artificial Intelligence (AI) has become an important asset in many areas of science and technology, safety is often not treated as important as required for aviation. Neglecting safety is not an option for aviation, where strict laws and regulations govern the certification process of new aircraft. Thus, a solid understanding of the underlying AI-based system is important to certify such systems. To this day, manual inspection by humans is an essential step for certification, however requires proper tooling. One such tool, called Advisory Viewer, is presented in this work, helping to break down the high-dimensional vector space of neural networks. The tool presented here can visualize decisions derived from assemblies of neural networks for arbitrary 2-dimensional parameter sweeps and provides real-time feedback upon any parameter change. It is designed to better understand the neural networks behind openCAS, an open-source implementation for the Airborne Collision Avoidance System X (ACAS X), the upcoming implementation for collision avoidance in aviation. However, as currently designed, implementing ACAS X is not feasible on current aviation hardware, as the required memory is not available. Here, neural networks and their ability to compress and generalize can be a solution. Therefore, it is of utmost importance that the AI-based system behind ACAS X always produces correct predictions. Finally, to fix the detected irregularities, this work implements a Safety Net to ensure the correct output for the ACAS X use case. Safety Nets are designed on the idea of sparse lookup tables (LUTs), storing only the points where the neural networks are known to fail. By deploying a system consisting of a Safety Net together with neural network(s), a small, yet potentially certifiable system can be designed and built. This work presents a generic data format for LUTs and recommended algorithms to populate and organize said LUTs for quick access during runtime. Combined, this serves as a generic framework for 100 % assurance of small neural networks, joined by the visualization tooling for the specific use case of openCAS.

In recent years, artificial intelligence (AI) has been applied to a wide range of safety-critical domains, such as automotive, robotics, and aviation. Especially the automotive and robotics domains have seen a rapid increase in the number of AI-based systems that are being deployed in real-world applications. However, real-world applications in the aviation domain are still sparse, given the challenges of AI engineering in combination with strict safety requirements. A first possible application of AI in the aviation domain might be the future collision avoidance system Airborne Collision Avoidance Systems X (ACAS X). The goal of collision avoidance systems is to issue advisories to the pilot to avoid near mid-air collisions (NMACs). The two important variants of ACAS X for this work are ACAS XA, providing vertical advisories and meant as a drop-in replacement for current systems in commercial air flight, and ACAS Xu, providing horizontal advisories for the ever-growing unmanned aircraft systems market. This work brings both variants closer to real-world deployment by implementing a vertical collision avoidance system, based upon ACAS XA, and a horizontal collision avoidance system, based upon ACAS Xu, for the research flight simulator FlightGear. Using advisories given by this implementation, this work furthermore provides an auto-avoid function that can command an airplane in FlightGear to safely avoid NMACs. Finally, this work will show that the ACAS X implementation can avoid collisions in a simulated environment. For this task, an Operational Design Domain will be defined serving as a basis for safety considerations and evaluating the implementation of the ACAS X. In the end, simulation-based testing will be used separately for VCAS and HCAS showing the successful utilization of advisory predictions as autopilot inputs. Summarizing, this work not only presents an open-source implementation of ACAS XA and ACAS Xu for FlightGear but also shows how the generated advisories can be used to successfully avoid NMACs.