How can hardware technologies such as sensors and cameras be utilized and integrated to improve the monitoring of airport runway weather, road conditions, and foreign object debris (FOD) detection for take-off, landing, and ground transportation?

Objective: We are developing an AI-driven system to enhance the monitoring and reporting of runway and road conditions at Canadian airports, with a focus on weather conditions, foreign object debris (FOD), and infrastructure deterioration. This initiative is aimed at supporting safer and more efficient aircraft landings and ground transportation.

Background: Operating under the challenging weather conditions prevalent in Canada, maintaining the safety and condition of multiple airport runways and access roads is critical. The current manual monitoring methods are inadequate for addressing the rapid changes in weather, detecting FOD, and identifying infrastructure deterioration promptly—factors that are crucial for safe and efficient airport operations.

Problem: The harsh and variable Canadian climate often renders traditional monitoring methods ineffective, resulting in delays in obtaining timely and accurate data essential for the safety of aircraft landings and ground transportation. Such delays in detecting FOD and infrastructure deterioration compromise safety, lead to increased maintenance costs, and cause operational disruptions. Additionally, environmental concerns call for the adoption of more efficient and sustainable maintenance practices.

Need: There is an urgent need for an innovative solution that utilizes AI and other technology to automate the process of condition monitoring. By equipping vehicles with cameras and sensors to traverse airport runways and roads, we can capture real-time images for AI analysis. This method will enable continuous, accurate assessments of weather impacts, detect FOD, and evaluate infrastructure health, thereby facilitating immediate corrective actions, reducing operational costs, and enhancing overall airport safety.

How do we gain acceptance from internal and external stakeholders, including regulatory bodies, the public, and industry partners for adopting various sustainability strategies and technologies considering complexities, trade-offs, and infrastructure needs?

Problem/Opportunity:
As Boeing works toward strategies to help the aviation industry achieve net-zero emissions by 2050, a key challenge lies in effectively communicating the trade-offs and infrastructure requirements associated with sustainable technologies. Stakeholders, from regulatory bodies to the general public, need to understand the complexities of adopting alternative energy carriers and infrastructures needed as prerequisites. For instance, even if hydrogen or hybrid-electric aircraft are successfully developed, their environmental benefits could be negated if the energy infrastructure needed to sustainably produce (i.e., low lifecycle CO2e/MJ) and distribute hydrogen or electricity is not available at every airport our aircraft operate out of globally. Additionally, these emerging technologies involve trade-offs related to operation, performance, safety, and cost that must be carefully balanced. Boeing has an opportunity to refine its communication strategies, ensuring that the technical challenges, risks, and benefits are presented in a way that builds confidence in the company’s commitment to innovation and sustainability. A robust communication framework that emphasizes Boeing’s dedication to safety, innovation, and sustainability will help foster industry-wide collaboration and bolster Boeing’s reputation as a pioneer in sustainable aviation.

Background Information:
The need for sustainability strategies, such as sustainable energy carriers or novel propulsion concepts, is critical to meeting global emissions targets. However, these technologies come with trade-offs. Boeing’s ability to communicate these challenges and landscapes effectively – both internally to drive company-wide initiatives and R&D efforts and regulators and the public – is key to securing the necessary buy-in and accelerating adoption. Furthermore, external stakeholders across the entire value chain – including airline operators, engine manufacturers, fuel providers, airports, governments, investors, regulatory bodies and academia – must also be engaged in these communications. Tools like Boeing’s CASCADE climate impact model can provide valuable data and visualizations of these trade-offs, and translating such technical insights into accessible and impactful narratives will be key.

How can we streamline the Technology Readiness Level (TRL) process in R&D to ensure a smooth transition of novel technologies to market-ready solutions?

Problem/Opportunity:
Boeing faces challenges in transitioning novel technologies – such as innovative aircraft configurations, alternative energy carriers, or new propulsion concept integration – from early-stage R&D into production-ready solutions. While low-fidelity R&D efforts are crucial for exploring new concepts, there is often a disconnect between these exploratory phases and the practical requirements of product development and large-scale manufacturing. This gap can slow down the integration of new technologies, particularly when ensuring they meet the rigorous standards of the aviation industry. Boeing has the opportunity to develop strategies and evaluation frameworks that allows for a smooth transition from novel technology to product. Addressing this challenge will be key for the company to maintain its leadership in aircraft technology and ensuring that innovative solutions meet stringent performance, safety, and regulatory standards.

Background Information:
Boeing’s historical focus has been on designing and manufacturing conventional tube-and-wing aircraft with turbofan engines burning Jet-A fuel. This expertise has allowed for precise refinement and understanding of traditional aircraft design space and manufacturing. However, this background can lead to discomfort and reluctance when facing novel technologies that are not yet fully mature. On the other hand, early stage R&D efforts can sometimes not be fully aligned on practical considerations required for product development, leading to inefficiencies and disconnects in the development cycle. Boeing must develop strategies to ensure smoother transition of innovative technologies into the production pipeline. Addressing this gap is critical for ensuring Boeing’s success in bringing cutting-edge technologies to market.

How can Boeing optimize aircrew training methods to ensure operators are ready to adopt new methods for improving fuel burn in large commercial aircraft (example of prior technologies include CDA & RNP)?

Problem/Opportunity:
In addition to technology that can provide substantial fuel burn benefit over the current generation aircraft while meeting ambitious sustainability goals, there is also a need to help airline operators more readily adopt procedures and tools that can deliver operational efficiency into their current fleets. To achieve this, there is a need to incorporate training and human factors that complement technology.

Background Information:
The demand for sustainable aviation has accelerated the exploration of novel technologies in aerodynamics, propulsion, and SAF. While these technologies hold significant potential for reducing emissions, their integration into existing aircraft requires acceptance and adoption while balancing key factors such as airline operational cost, safety, and regulatory requirements. Developing a comprehensive evaluation framework will be critical to improving the adoption of new procedures and communicating their benefits and externally.

CDA: Continuous Descent Approach (CDA) is an optimized approach procedure where the aircraft descends continually at idle thrust from cruise to landing
RNP: Required navigation performance (RNP) is a type of performance-based navigation (PBN) that allows an aircraft to fly a specific path between two 3D-defined points in space

How do we develop and validate an AI/ML digital twin of real time flying patterns to evaluate fuel burn to identify and develop efficiencies in fuel use?

Currently, there is delay because of weather and airport congestion, using digital twin and ML, the system can provide airlines a potential opportunity to improve the efficiency of airlines (ie to delay or maybe reschedule flights) based on digital twin projections impacting flights to an airport or region.

How can we leverage VR technologies and utilize AI and ML principles to optimize and enhance diagnostic accuracy and efficiency of flight instructors in identifying and correcting the root causes of student pilot errors?

Problem/Opportunity
Despite significant advancements in the technology used for flight training, the core instructional methods have remained largely unchanged. Instructors rely heavily on their experience to monitor student performance, diagnose errors, and provide corrective feedback. This traditional approach can be time-consuming and may require extensive flight hours, as pinpointing the root cause of a student’s difficulties is often challenging. There is a significant opportunity to integrate AI and ML optimization techniques in combination with VR technologies into flight training to improve the speed and accuracy of error diagnosis, thereby reducing the flight hours required for students to achieve proficiency and potentially revolutionizing the instructional process.

Background Information
The introduction of advanced technologies such as AI and VR into flight training presents a promising avenue for innovation in instructional methodologies. Traditional flight training relies on the instructor’s experience and intuition to diagnose the root causes of student errors, which can be a subjective and time-intensive process. By incorporating AI, machine learning, and other optimization techniques which can analyze complex data patterns, and VR, which can simulate a wide range of flight scenarios, instructors could gain new tools for understanding student behavior and performance. For example, eye-tracking technology could be used to determine where a pilot is focusing their attention during critical tasks, providing valuable insights into potential sources of error. The challenge lies in developing these technologies to a point where they can reliably assist instructors in real-time and in a manner that is accessible and effective within the training environment. Success in this area could lead to significant reductions in training time and costs, as well as improvements in the overall quality of pilot training.

What cognitive processes, decision-making strategies, and situational monitoring behaviors can we implement and analyze that differentiate expert pilots from novice student pilots during flight, and how can these be effectively identified, measured, and transferred to enhance flight training outcomes?

Problem/Opportunity
In flight training, it is common to observe that two student pilots with similar backgrounds and experience can have vastly different learning curves. While one student may achieve the required training objectives efficiently, the other may struggle, necessitating additional flight hours and repeated lessons. Current training methodologies primarily focus on performance metrics but do not adequately capture the underlying cognitive and situational awareness strategies that may contribute to these disparities. Identifying and understanding these expert behaviors presents an opportunity to optimize training processes, reduce costs, and improve the efficiency and effectiveness of pilot training programs.

Background Information
The aviation industry is heavily reliant on the proficiency and expertise of pilots to ensure safety and operational success. However, the traditional approach to pilot training has focused predominantly on the outcomes of flight performance rather than the cognitive strategies employed to achieve these outcomes. Expert pilots possess a wealth of experience and tacit knowledge that enables them to navigate complex scenarios with efficiency and precision, yet these skills remain largely intangible and difficult to convey to students. By investigating what expert pilots focus on, how they process information, and the decisions they make in real-time, it may be possible to develop new training tools and methodologies that can better bridge the gap between novice and expert performance. The impact of such research could lead to more effective training programs, a reduction in training costs, and ultimately, a higher standard of pilot competency. However, challenges include accurately capturing these cognitive processes and translating them into actionable training interventions.

How to create flexible light modular automation through vision systems:
What research methodologies could be implemented to create an automation system to support flexible applications in aircraft sub-assembly or major assembly.

Current automated and robotic system are purpose built, immobile, and are a significant investment to implement and maintain. Having a more flexible system that could allow for Health and Safety Requirements of the operator and multi-use functionality would improve uptake. Areas of interest are related to drilling, fastening, inspecting and sealing related to the Vision Systems technology while maintaining high accuracy, mobility, and multiple operations.

2.0 Flexible Modular Paint & Process Vertical Integration for Metallic and Composite Fabrication
How do we improve the current paint process to identify opportunities to develop in-house paint and process capabilities?

To be globally competitive we need to make fabricators vertically integrated with in-house paint and process capabilities. Fabrication times have been greatly reduced over the years, however, paint & process times are the same since the 50’s and 60’s. An in-house process would reduce time and cost requirements while minimizing environmental effects of transportation of parts and inspection requirements.

Currently, fabricated (machined, sheet metal, composites) parts are made by a Fabrication Supplier, then sent to a Paint & Process Supplier, and then back to the Fabrication Supplier for Final Inspection. and finally, on to OEM or Tier 1. This Considerable amount of Multiple Transport Activities that can be local, provincial, within North America, or Globally requiring multiple inspections for check-in and check-out of individual facilities. Considerations for a modular paint and process installed at the fabricator site would include ability to develop modules that are expandable, self-monitoring, self-cleaning and continuous flow and include capabilities that anodize, alodine, alkaline clean, rinse, primer, top coat, flash-off, bake.

How can we use technology and implement research methodologies in human-computer-interaction (HCI), UX, UI, and gamification to provide air traffic controller (ATC) students with an enhanced opportunity to learn anywhere / anytime and at their own pace?

The training process to become an air traffic controller involves hands-on practice, where simulators replicate real-world air traffic scenarios. This allows trainees to practice controlling aircraft in a safe and controlled environment. However, legacy ATC simulators have limitations that can may impact a student’s progress:

• Simulators are limited in number and are located at NAV CANADA facilities.
• An instructor must be present to provide feedback.
• ATC simulation scenarios are pre-defined, significant effort to define and update.
• For specialized training, a simulator pilot is also needed to respond to the ATC student’s instructions.

There is a desire to improve the student experience and outcomes by enabling them to learn anywhere, anytime, through technology that provides immediate and customized instruction and feedback without requiring invention from a human instructor. How can we apply human-computer-interaction (HCI), UX, UI, and gamification research principles to validate new training methods and help enhance the experience for students. What could that technology look like and what aspects do we need to be mindful of to ensure students’ willingness to engage with a new learning platform.

What are the technical, operational, and human challenges of introducing automation and artificial intelligence in the provision of active air traffic control services? How can we overcome them?

Introducing automation and artificial intelligence into air traffic control systems has the potential to improve efficiency, safety, and scalability of air traffic management. However, due to the safety-critical nature of this task, there are many challenges that must be addressed before automation and AI can be safely integrated into this domain.
What are the technical, operational, and human challenges of introducing AI and automation in ATC, and what strategies can be employed to address these challenges? How can AI be tested, validated, and incrementally introduced into ATC environments? How can we design systems to support collaboration between human controllers and automated systems? How can we assess the capabilities of an air traffic controller in a system that is highly automated? What will be the key considerations in the design and development of new ATM systems to ensure safety and to enable humans to recover from automation failures.
Can we develop a joint human-machine system framework or roadmap for air traffic control systems that mitigates these issues?

What methods or tools could be used to leverage ensemble weather forecasts in aviation?

Flight Planning is already a computationally expensive process, however leveraging ensemble weather forecasts may provide additional opportunities to optimize for robustness.

Ensemble weather forecasts present a set (or ensemble) of forecasts which aim to give an indication of the range of possible future states of the atmosphere. Flight Planning aims at finding the most cost efficient (fuel, time and navigational charges) route between two airports and the weather is one of the most important inputs which impact the chosen route of flight. Currently, flight planning uses the traditional weather models which provide one forecast determined to be the most likely. Flight planning is already computationally very expensive due to the 4 dimensional aspect, the large option set of possible waypoints and complex airspace rules that must be taken into account. Adding ensemble weather would add further complexity to this and could result in, operationally impractical compute times. However ensemble forecasts could already present an opportunity to build more robust routes, less likely to experience significant disruption.