This paper describes a computer vision-based method to detect aerodrome taxiway lines and to esti... more This paper describes a computer vision-based method to detect aerodrome taxiway lines and to estimate the deviation of a large passenger aircraft from the taxiway centerline using an onboard camera located on the vertical stabilizer of the aircraft. This method could be applied as part of a larger system to increase the situation awareness of pilots during taxiing and to alert them if the aircraft deviates from the centerline. The proposed method takes advantage of color and edge information in the camera images and proposes a Sliding Window (SW) method and clustering techniques to detect and process taxiways markings. First, the input image is transformed to a top-down view by applying the Homographic Transform. Then, color and edge detection techniques are applied to the top-down view to generate a binary map of pixels belonging to taxiway lines. Then, the region of the image directly in front of the aircraft is processed to determine whether the aircraft is turning or moving in a straight line. If it is determined that the aircraft is turning, the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering technique is applied to the binary map; otherwise, a SW method is used to detect the taxiway centerline ahead of the aircraft and to detect any taxiway branches or junctions. Finally, the aircraft's lateral deviation from the taxiway centerline is estimated using a template matching approach. Tests on simulated video sequences show that the SW technique achieves a detection rate of 80% and a false positive rate of 3%. On the other hand, the clustering technique achieves a detection rate of 76% and a false positive rate of 4%. The aircraft's deviation from the taxiway centerline is estimated with a mean error of 0.8 pixels and a worst case error of ±3 pixels.
2018 IEEE/AIAA 37th Digital Avionics Systems Conference (DASC), 2018
To date, most of the interactions between pilots and avionic systems of commercial passenger airc... more To date, most of the interactions between pilots and avionic systems of commercial passenger aircraft are carried out using physical controls. This paper discusses the evaluation of a multimodal interface which allows pilots to control various avionic systems using a combination of touchscreen gestures (via a single touchscreen interface) and voice commands. This interface was evaluated by eight commercial airline pilots in a fixed-based flight simulator. Although various improvements can be made to the interface, the evaluations successfully demonstrated the feasibility and potential benefits of using a multimodal interface in commercial flight.
2021 IEEE/AIAA 40th Digital Avionics Systems Conference (DASC), 2021
One of the solutions proposed by the aerospace industry to reduce fuel consumption, air pollution... more One of the solutions proposed by the aerospace industry to reduce fuel consumption, air pollution and noise at airports consists of using electric tow trucks to tow aircraft from the gate to the runway (or vice-versa). However, the introduction of tow trucks results in an increase in surface traffic, potentially increasing the workload of Air Traffic Controllers (ATC). Many solutions have been proposed in the literature in an attempt to mitigate this problem through the introduction of automated planning and execution. The majority of these solutions have been tested only under strict scenario conditions using a limited number of performance metrics. This paper proposes a simulation testbed that characterizes and compares the performance of such algorithms. By adopting common performance metrics, the testbed allows an objective comparison through the extraction of statistical data using a significant number of scenarios.
2018 International Conference on Unmanned Aircraft Systems (ICUAS), 2018
There is an ever-increasing urge to integrate unmanned air systems (UAS) into the same airspace a... more There is an ever-increasing urge to integrate unmanned air systems (UAS) into the same airspace as manned aircraft. A step towards achieving this goal is to develop Sense and Avoid (SAA) capabilities to provide UAS with the required technology to detect and maneuver around traffic. This paper details an algorithm which enables an unmanned vehicle to reach a target waypoint by following the shortest path and avoiding fixed obstacles and moving traffic. In this context, a multi-layer planner is developed to enable planning of trajectories in cluttered environment containing fixed and moving obstacles. The planner is segmented into three layers; a high-level planner using Voronoi techniques that enable the planner to segregate individual obstacles into broad no-fly zones; a mid-level planner for representing the no-fly zones as convex hulls and a low-level planner that solves the resulting planning problem using mixed-integer linear programming (MILP), taking into account the convex no-fly zones and all neighboring traffic. Preliminary performance results suggest that the multi-layer planner is able to consistently identify optimal conflict-free paths in cluttered environments with execution speeds that are suitable for fast off-line planning operations.
This paper analyses the increasing trend of using modern machine learning technologies to analyze... more This paper analyses the increasing trend of using modern machine learning technologies to analyze flight data efficiently. Flight data offers an important insight into the operations of an aircraft. This paper reviews the research undertaken so far on the use of Machine Learning techniques for the analyses of flight data by evaluating various anomaly detection algorithms and the significance of feature selection in Flight Data Monitoring. These algorithms are compared to determine the best class of algorithms for highlighting significant flight anomalies. Furthermore, these algorithms are analyzed for various flight data parameters to determine which class of algorithms is sensitive to continuous parameters and which is sensitive to discrete parameters of flight data. The paper also addresses the ability of each anomaly detection algorithm to be easily adaptable to different datasets and different phases of flight, including take-off and landing.
This paper addresses pilot error due to distractions, lack of situational awareness and misjudgme... more This paper addresses pilot error due to distractions, lack of situational awareness and misjudgment of separation during taxi manoeuvers. A display is being developed to minimize these errors and assist pilots to determine safe passage while navigating during taxi. Part of the development consisted of the implementation of a tracking algorithm-based on the particle filter-which is being presented in this paper. The tracking algorithm tracks obstacles that have been detected and reconstructed using stereo vision techniques. Afterwards, the tracked obstacles are highlighted on a display. Experiments show that the algorithm successfully detects and tracks aircraft in an airfield.
2021 IEEE/AIAA 40th Digital Avionics Systems Conference (DASC), 2021
Despite the on-board automation and protection systems of modern commercial aircraft, aerodynamic... more Despite the on-board automation and protection systems of modern commercial aircraft, aerodynamic stall events are still a possible occurrence. This paper proposes Machine Learning algorithms – based on Reinforcement Learning and Supervised Learning – to automatically recover an aircraft from two types of aerodynamic stall: unaccelerated wings level (1G) stall and a stall during a turn. The algorithms were tested by exposing them to 105 simulated stall scenarios with different initial conditions (including altitude, bank angle and wind speed) and an acceptable stall recovery was achieved in 85.7% of the test cases. The overall recovery time increased with an increase in altitude, with the best and worst recovery times obtained at 10,000ft and 30,000ft respectively. Further work will focus on improving the performance of the algorithms such as by reducing the time to recover from a stall, decreasing the altitude loss and training the algorithms over a larger range of altitudes, up to cruise level.
2015 IEEE/AIAA 34th Digital Avionics Systems Conference (DASC), 2015
Touch screen technology is already present on the flight deck of various categories of aircraft, ... more Touch screen technology is already present on the flight deck of various categories of aircraft, with the majority of current solutions based on the use of multiple touch screen displays situated on the main instrument panel and/or the central pedestal. This often requires the crew to lean forward or sideways to interact with different displays and makes it harder to make accurate selections, particularly in turbulent conditions. This paper proposes a novel touch screen concept which enables the crew of single and dual pilot aircraft to interact with various avionic systems throughout a flight using a single tablet-like device positioned in front of each crew member. Such a device could be fitted to current flight deck environments and used as an alternative method of interacting with the aircraft, i.e. while retaining all existing controls and displays. The concept focusses on the use of touch screen techniques within each of the following functional areas: autopilot control, navigation, aircraft performance, and systems. This paper describes the requirements, design, and pilot evaluation of this concept (developed to a technology readiness level of 3) and discusses the results.
2015 IEEE/AIAA 34th Digital Avionics Systems Conference (DASC), 2015
Hazardous weather can pose a significant threat to aircraft safety and may result in a substantia... more Hazardous weather can pose a significant threat to aircraft safety and may result in a substantial increase in crew workload, such as during departure manoeuvers. If the weather hazard conflicts with the flight plan, including the Standard Instrument Departure (SID) route, the pilots need to plan and execute an avoidance manoeuver. To date, this is still mostly a manual process, with the crew gathering information from multiple sources (including Air Traffic Control (ATC), weather forecasts and onboard weather radar returns) in order to determine an avoidance route. This paper proposes a tool to assist pilots by partially automating the task of avoiding hazardous weather during departure. The tool functions by detecting weather conflicts along the SID and presenting the crew with options to delay the take-off manoeuver or to fly an alternative path in order to avoid the weather hazards, while also ensuring safe separation from terrain. As a result, the tool has the potential to reduce crew workload and increase situation awareness. This paper discusses the proposed decision support tool in terms of (a) the algorithm used to detect and avoid bad weather and (b) the Human Machine Interface (HMI) that has been designed to present weather avoidance solutions to the crew.
This paper describes a computer vision-based method to detect aerodrome taxiway lines and to esti... more This paper describes a computer vision-based method to detect aerodrome taxiway lines and to estimate the deviation of a large passenger aircraft from the taxiway centerline using an onboard camera located on the vertical stabilizer of the aircraft. This method could be applied as part of a larger system to increase the situation awareness of pilots during taxiing and to alert them if the aircraft deviates from the centerline. The proposed method takes advantage of color and edge information in the camera images and proposes a Sliding Window (SW) method and clustering techniques to detect and process taxiways markings. First, the input image is transformed to a top-down view by applying the Homographic Transform. Then, color and edge detection techniques are applied to the top-down view to generate a binary map of pixels belonging to taxiway lines. Then, the region of the image directly in front of the aircraft is processed to determine whether the aircraft is turning or moving in a straight line. If it is determined that the aircraft is turning, the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering technique is applied to the binary map; otherwise, a SW method is used to detect the taxiway centerline ahead of the aircraft and to detect any taxiway branches or junctions. Finally, the aircraft's lateral deviation from the taxiway centerline is estimated using a template matching approach. Tests on simulated video sequences show that the SW technique achieves a detection rate of 80% and a false positive rate of 3%. On the other hand, the clustering technique achieves a detection rate of 76% and a false positive rate of 4%. The aircraft's deviation from the taxiway centerline is estimated with a mean error of 0.8 pixels and a worst case error of ±3 pixels.
2018 IEEE/AIAA 37th Digital Avionics Systems Conference (DASC), 2018
To date, most of the interactions between pilots and avionic systems of commercial passenger airc... more To date, most of the interactions between pilots and avionic systems of commercial passenger aircraft are carried out using physical controls. This paper discusses the evaluation of a multimodal interface which allows pilots to control various avionic systems using a combination of touchscreen gestures (via a single touchscreen interface) and voice commands. This interface was evaluated by eight commercial airline pilots in a fixed-based flight simulator. Although various improvements can be made to the interface, the evaluations successfully demonstrated the feasibility and potential benefits of using a multimodal interface in commercial flight.
2021 IEEE/AIAA 40th Digital Avionics Systems Conference (DASC), 2021
One of the solutions proposed by the aerospace industry to reduce fuel consumption, air pollution... more One of the solutions proposed by the aerospace industry to reduce fuel consumption, air pollution and noise at airports consists of using electric tow trucks to tow aircraft from the gate to the runway (or vice-versa). However, the introduction of tow trucks results in an increase in surface traffic, potentially increasing the workload of Air Traffic Controllers (ATC). Many solutions have been proposed in the literature in an attempt to mitigate this problem through the introduction of automated planning and execution. The majority of these solutions have been tested only under strict scenario conditions using a limited number of performance metrics. This paper proposes a simulation testbed that characterizes and compares the performance of such algorithms. By adopting common performance metrics, the testbed allows an objective comparison through the extraction of statistical data using a significant number of scenarios.
2018 International Conference on Unmanned Aircraft Systems (ICUAS), 2018
There is an ever-increasing urge to integrate unmanned air systems (UAS) into the same airspace a... more There is an ever-increasing urge to integrate unmanned air systems (UAS) into the same airspace as manned aircraft. A step towards achieving this goal is to develop Sense and Avoid (SAA) capabilities to provide UAS with the required technology to detect and maneuver around traffic. This paper details an algorithm which enables an unmanned vehicle to reach a target waypoint by following the shortest path and avoiding fixed obstacles and moving traffic. In this context, a multi-layer planner is developed to enable planning of trajectories in cluttered environment containing fixed and moving obstacles. The planner is segmented into three layers; a high-level planner using Voronoi techniques that enable the planner to segregate individual obstacles into broad no-fly zones; a mid-level planner for representing the no-fly zones as convex hulls and a low-level planner that solves the resulting planning problem using mixed-integer linear programming (MILP), taking into account the convex no-fly zones and all neighboring traffic. Preliminary performance results suggest that the multi-layer planner is able to consistently identify optimal conflict-free paths in cluttered environments with execution speeds that are suitable for fast off-line planning operations.
This paper analyses the increasing trend of using modern machine learning technologies to analyze... more This paper analyses the increasing trend of using modern machine learning technologies to analyze flight data efficiently. Flight data offers an important insight into the operations of an aircraft. This paper reviews the research undertaken so far on the use of Machine Learning techniques for the analyses of flight data by evaluating various anomaly detection algorithms and the significance of feature selection in Flight Data Monitoring. These algorithms are compared to determine the best class of algorithms for highlighting significant flight anomalies. Furthermore, these algorithms are analyzed for various flight data parameters to determine which class of algorithms is sensitive to continuous parameters and which is sensitive to discrete parameters of flight data. The paper also addresses the ability of each anomaly detection algorithm to be easily adaptable to different datasets and different phases of flight, including take-off and landing.
This paper addresses pilot error due to distractions, lack of situational awareness and misjudgme... more This paper addresses pilot error due to distractions, lack of situational awareness and misjudgment of separation during taxi manoeuvers. A display is being developed to minimize these errors and assist pilots to determine safe passage while navigating during taxi. Part of the development consisted of the implementation of a tracking algorithm-based on the particle filter-which is being presented in this paper. The tracking algorithm tracks obstacles that have been detected and reconstructed using stereo vision techniques. Afterwards, the tracked obstacles are highlighted on a display. Experiments show that the algorithm successfully detects and tracks aircraft in an airfield.
2021 IEEE/AIAA 40th Digital Avionics Systems Conference (DASC), 2021
Despite the on-board automation and protection systems of modern commercial aircraft, aerodynamic... more Despite the on-board automation and protection systems of modern commercial aircraft, aerodynamic stall events are still a possible occurrence. This paper proposes Machine Learning algorithms – based on Reinforcement Learning and Supervised Learning – to automatically recover an aircraft from two types of aerodynamic stall: unaccelerated wings level (1G) stall and a stall during a turn. The algorithms were tested by exposing them to 105 simulated stall scenarios with different initial conditions (including altitude, bank angle and wind speed) and an acceptable stall recovery was achieved in 85.7% of the test cases. The overall recovery time increased with an increase in altitude, with the best and worst recovery times obtained at 10,000ft and 30,000ft respectively. Further work will focus on improving the performance of the algorithms such as by reducing the time to recover from a stall, decreasing the altitude loss and training the algorithms over a larger range of altitudes, up to cruise level.
2015 IEEE/AIAA 34th Digital Avionics Systems Conference (DASC), 2015
Touch screen technology is already present on the flight deck of various categories of aircraft, ... more Touch screen technology is already present on the flight deck of various categories of aircraft, with the majority of current solutions based on the use of multiple touch screen displays situated on the main instrument panel and/or the central pedestal. This often requires the crew to lean forward or sideways to interact with different displays and makes it harder to make accurate selections, particularly in turbulent conditions. This paper proposes a novel touch screen concept which enables the crew of single and dual pilot aircraft to interact with various avionic systems throughout a flight using a single tablet-like device positioned in front of each crew member. Such a device could be fitted to current flight deck environments and used as an alternative method of interacting with the aircraft, i.e. while retaining all existing controls and displays. The concept focusses on the use of touch screen techniques within each of the following functional areas: autopilot control, navigation, aircraft performance, and systems. This paper describes the requirements, design, and pilot evaluation of this concept (developed to a technology readiness level of 3) and discusses the results.
2015 IEEE/AIAA 34th Digital Avionics Systems Conference (DASC), 2015
Hazardous weather can pose a significant threat to aircraft safety and may result in a substantia... more Hazardous weather can pose a significant threat to aircraft safety and may result in a substantial increase in crew workload, such as during departure manoeuvers. If the weather hazard conflicts with the flight plan, including the Standard Instrument Departure (SID) route, the pilots need to plan and execute an avoidance manoeuver. To date, this is still mostly a manual process, with the crew gathering information from multiple sources (including Air Traffic Control (ATC), weather forecasts and onboard weather radar returns) in order to determine an avoidance route. This paper proposes a tool to assist pilots by partially automating the task of avoiding hazardous weather during departure. The tool functions by detecting weather conflicts along the SID and presenting the crew with options to delay the take-off manoeuver or to fly an alternative path in order to avoid the weather hazards, while also ensuring safe separation from terrain. As a result, the tool has the potential to reduce crew workload and increase situation awareness. This paper discusses the proposed decision support tool in terms of (a) the algorithm used to detect and avoid bad weather and (b) the Human Machine Interface (HMI) that has been designed to present weather avoidance solutions to the crew.
Uploads
Papers by Jason Gauci