Results for “Automated Air Traffic Management” — Page 22

NASA NTRSDate not supplied

Runway Configuration Management with Offline Reinforcement Learning

Runway configuration management (RCM) is a challenging task, and it affects the efficiency of the National Airspace System (NAS) and airport surface operations significantly. Each airport, depending on the geometry, capacity, local climate patterns, etc. has multiple configurations for the runway usage for arriving and departing flights. Many factors such as the incoming/outgoing traffic load, wind direction and speed, convective weather, cloud ceiling and other environmental factors might affect the choice of a runway configuration at any point in time. However, other factors such as safety measures and regulations, noise abatement, capacity of each configuration, and preference of the air traffic controllers (ATCs) can also play a significant role in selecting the configuration. A sub-optimal selection of the runway configuration, or delay in making configuration changes might result in significant increase in taxi times for aircraft on the surface of the airport, fuel and energy use of the aircraft, and maintenance costs. It can also lead to safety concerns, such as an aircraft performing one or more go-arounds before being able to land. All these factors make RCM an extremely important and challenging decision-making process for the ATCs. The current state of practice sets the runway configuration by the ATCs based on relevant information available at the time including weather, traffic, noise abatement, safety bounds, etc. This makes the decision-making process subjective based on the accuracy of the available information and the bias in human decision making. Unfortunately, this approach yields poor results (e.g., significant delays) if the predicted outcomes are uncertain and their relative impact is not well understood. This is especially evident when the uncertainty increases the size of possible predicted outcomes (combinatorial explosion in possible scenarios) that cannot be handled by human reasoning. On the other hand, an automated approach based on machine intelligence can make use of historical data and search through all (or significant amount of) possible scenarios under uncertainty and make well-informed decisions.

Milad Memarzadeh↗

NASA NTRSDate not supplied

Requirement Discovery Using Embedded Knowledge Graph with ChatGPT

The field of Advanced Air Mobility (AAM) is witnessing a transformation with innovations such as electric aircraft and increasingly automated airspace operations. Within AAM, the Urban Air Mobility (UAM) concept focuses on providing air-taxi services in densely populated urban areas. This research introduces the utilization of Large Language Models (LLMs), such as OpenAI's GPT-4, to enhance the UAM Requirement discovery process. This study explores two distinct approaches to leverage LLMs in the context of UAM Requirement discovery. The first approach evaluates the LLM's ability to provide responses without relying on additional outside systems, such as a relational or graph database. Instead, a vector store provides relevant information to the LLM based on the user’s question, a process known as Retrieval Augmented Generation (RAG). The second approach integrates the LLM with a graph database. The LLM acts as an intermediary between the user and the graph database, translating user questions into cypher queries for the database and database responses into human-readable answers for the user. Our team implemented and tested both solutions to analyze requirements within a UAM dataset. This paper will talk about our approaches, implementations, and findings related to both approaches.

systems engineering↗

NASA NTRSDate not supplied

Requirement Discovery Using Embedded Knowledge Graph With ChatGPT

The field of Advanced Air Mobility (AAM) is witnessing a transformation with innovations such as electric aircraft and increasingly automated airspace operations. Within AAM, the Urban Air Mobility (UAM) con-cept focuses on providing air-taxi services in densely populated urban areas. This research introduces the utilization of Large Language Models (LLMs), such as OpenAI's GPT-4, to enhance the UAM Requirement discovery process. This study explores two distinct approaches to leverage LLMs in the context of UAM Requirement discovery. The first approach evaluates the LLM's ability to provide responses without relying on additional outside systems, such as a relational or graph database. Instead, a vector store provides relevant information to the LLM based on the user’s question, a process known as Retrieval Augmented Generation (RAG). The second approach integrates the LLM with a graph database. The LLM acts as an intermediary between the user and the graph database, translating user questions into cypher queries for the database and database responses into human-readable answers for the user. Our team implemented and tested both solutions to analyze require-ments within a UAM dataset. This paper will talk about our approaches, implementations, and findings related to both approaches.

systems engineering↗

NASA NTRSDate not supplied

Requirement Discovery Using Embedded Knowledge Graph With ChatGPT - Poster

The field of Advanced Air Mobility (AAM) is witnessing a transformation with innovations such as electric aircraft and increasingly automated airspace operations. Within AAM, the Urban Air Mobility (UAM) con-cept focuses on providing air-taxi services in densely populated urban areas. This research introduces the utilization of Large Language Models (LLMs), such as OpenAI's GPT-4, to enhance the UAM Requirement discovery process. This study explores two distinct approaches to leverage LLMs in the context of UAM Requirement discovery. The first approach evaluates the LLM's ability to provide responses without relying on additional outside systems, such as a relational or graph database. Instead, a vector store provides relevant information to the LLM based on the user’s question, a process known as Retrieval Augmented Generation (RAG). The second approach integrates the LLM with a graph database. The LLM acts as an intermediary between the user and the graph database, translating user questions into cypher queries for the database and database responses into human-readable answers for the user. Our team implemented and tested both solutions to analyze require-ments within a UAM dataset. This paper will talk about our approaches, implementations, and findings related to both approaches.

systems engineering↗

NASA NTRSDate not supplied

An Approach to Identifying Aspects of Positive Pilot Behavior within the Aviation Safety Reporting System

The National Airspace System (NAS) is constantly evolving as air traffic continues to ramp up to pre-pandemic numbers and projected to grow to unprecedented levels in the coming years. As well as increasing demand to the current system, emerging operations such as Unmanned Autonomous Systems are also expected to add to complexity in the airspace. To address these issues, the industry and government agencies supporting the NAS will need to rely upon additional automation and new technologies to address future operational requirements, while continuing to be a world-leading safe transportation system. As these new technologies are implemented, the system continues to rely on human pilots and controllers in the loop to monitor the system and intervene in situations the automation cannot handle. The goal of proactively addressing safety is of foremost concern to ensure passenger confidence. The industry has implemented various Safety Monitoring Systems to identify safety risks and proactively address them before they result in a serious incident or accident. One such program is the Aviation Safety Reporting System (ASRS). ASRS is a long-established system where pilots and controllers voluntarily and anonymously report safety incidents they experienced and observed during line operations by providing rich text narratives describing the events, the environment, and conditions leading to the safety event of concern. These narratives provide insight and context around events of interest and can be used to identify emerging problems. They can trigger investigations within Flight Operational Quality Assurance or Flight Data Monitoring programs. However, this process typically focuses on the adverse events and the unsafe aspects of the operations surrounding the reported or detected events. This perspective of investigating factors that went wrong around an adverse event is commonly referred to as Safety I. Alternatively, characterizing successful actions that operators perform every day under varying conditions that keep the system within safe operating bounds is a concept referred to as Safety II. The benefit of the Safety II view is that the scope is much larger than that of Safety I since a vast majority of the operations result in successful flights. Many of the successful techniques used to manage operational threats are not documented in standard operating procedures or taught during training. They are typically acquired over time by working with experienced pilots during line operations or in many cases after experiencing a problem for the first time and reacting to it in situ, drawing from years of experience to manage the threat. In an attempt to quantify these positive actions, we are proposing an approach to extracting key behaviors within ASRS reports that can support the Safety II concept. Our analysis assumes that ASRS reports contain some descriptions of corrective actions that operators performed to prevent a situation from leading to an accident. Leveraging recent advances in Natural Language Process modeling, we have developed an approach to extract positive sentiment from reports, embed these positive statements in a vector space where they can be numerically analyzed, and clustering these statements into similar contextual categories. From these contextualized categories we can attempt to summarized and distilled aspects of the positive behavior. The goal is to identify categories of behavior that describe consistent operator techniques that supports the Safety II concept. With this information, airlines may enable learning from these positive actions, or address procedures that need to be changed to avoid having pilots implement a workaround. These insights can provide a lens into what is “going right” in the operations that may otherwise not be known widely within the community. It is envisioned that this approach can be extended to other narrative programs such as Line Operation Safety Audit or Learning Improvement Team reports where similar observed behavior can be analyzed to extract positive actions and inform the overall operations.

NLP↗

NASA NTRSDate not supplied

An Approach to Identifying Aspects of Positive Pilot Behavior within the Aviation Safety Reporting System

The National Airspace System (NAS) is constantly evolving as air traffic continues to ramp up to pre-pandemic numbers and projected to grow to unprecedented levels in the coming years. As well as increasing demand to the current system, emerging operations such as Unmanned Autonomous Systems are also expected to add to complexity in the airspace. To address these issues, the industry and government agencies supporting the NAS will need to rely upon additional automation and new technologies to address future operational requirements, while continuing to be a world-leading safe transportation system. As these new technologies are implemented, the system continues to rely on human pilots and controllers in the loop to monitor the system and intervene in situations the automation cannot handle. The goal of proactively addressing safety is of foremost concern to ensure passenger confidence. The industry has implemented various Safety Monitoring Systems to identify safety risks and proactively address them before they result in a serious incident or accident. One such program is the Aviation Safety Reporting System (ASRS). ASRS is a long-established system where pilots and controllers voluntarily and anonymously report safety incidents they experienced and observed during line operations by providing rich text narratives describing the events, the environment, and conditions leading to the safety event of concern. These narratives provide insight and context around events of interest and can be used to identify emerging problems. They can trigger investigations within Flight Operational Quality Assurance or Flight Data Monitoring programs. However, this process typically focuses on the adverse events and the unsafe aspects of the operations surrounding the reported or detected events. This perspective of investigating factors that went wrong around an adverse event is commonly referred to as Safety I. Alternatively, characterizing successful actions that operators perform every day under varying conditions that keep the system within safe operating bounds is a concept referred to as Safety II. The benefit of the Safety II view is that the scope is much larger than that of Safety I since a vast majority of the operations result in successful flights. Many of the successful techniques used to manage operational threats are not documented in standard operating procedures or taught during training. They are typically acquired over time by working with experienced pilots during line operations or in many cases after experiencing a problem for the first time and reacting to it in situ, drawing from years of experience to manage the threat. In an attempt to quantify these positive actions, we are proposing an approach to extracting key behaviors within ASRS reports that can support the Safety II concept. Our analysis assumes that ASRS reports contain some descriptions of corrective actions that operators performed to prevent a situation from leading to an accident. Leveraging recent advances in Natural Language Process modeling, we have developed an approach to extract positive sentiment from reports, embed these positive statements in a vector space where they can be numerically analyzed, and clustering these statements into similar contextual categories. From these contextualized categories we can attempt to summarized and distilled aspects of the positive behavior. The goal is to identify categories of behavior that describe consistent operator techniques that supports the Safety II concept. With this information, airlines may enable learning from these positive actions, or address procedures that need to be changed to avoid having pilots implement a workaround. These insights can provide a lens into what is “going right” in the operations that may otherwise not be known widely within the community. It is envisioned that this approach can be extended to other narrative programs such as Line Operation Safety Audit or Learning Improvement Team reports where similar observed behavior can be analyzed to extract positive actions and inform the overall operations.

NLP↗

NASA NTRSDate not supplied

An Approach to Identifying Aspects of Positive Pilot Behavior within the Aviation Safety Reporting System

The National Airspace System (NAS) is constantly evolving as air traffic continues to ramp up to pre-pandemic numbers and projected to grow to unprecedented levels in the coming years. As well as increasing demand to the current system, emerging operations such as Unmanned Autonomous Systems are also expected to add to complexity in the airspace. To address these issues, the industry and government agencies supporting the NAS will need to rely upon additional automation and new technologies to address future operational requirements, while continuing to be a world-leading safe transportation system. As these new technologies are implemented, the system continues to rely on human pilots and controllers in the loop to monitor the system and intervene in situations the automation cannot handle. The goal of proactively addressing safety is of foremost concern to ensure passenger confidence. The industry has implemented various Safety Monitoring Systems to identify safety risks and proactively address them before they result in a serious incident or accident. One such program is the Aviation Safety Reporting System (ASRS). ASRS is a long-established system where pilots and controllers voluntarily and anonymously report safety incidents they experienced and observed during line operations by providing rich text narratives describing the events, the environment, and conditions leading to the safety event of concern. These narratives provide insight and context around events of interest and can be used to identify emerging problems. They can trigger investigations within Flight Operational Quality Assurance or Flight Data Monitoring programs. However, this process typically focuses on the adverse events and the unsafe aspects of the operations surrounding the reported or detected events. This perspective of investigating factors that went wrong around an adverse event is commonly referred to as Safety I. Alternatively, characterizing successful actions that operators perform every day under varying conditions that keep the system within safe operating bounds is a concept referred to as Safety II. The benefit of the Safety II view is that the scope is much larger than that of Safety I since a vast majority of the operations result in successful flights. Many of the successful techniques used to manage operational threats are not documented in standard operating procedures or taught during training. They are typically acquired over time by working with experienced pilots during line operations or in many cases after experiencing a problem for the first time and reacting to it in situ, drawing from years of experience to manage the threat. In an attempt to quantify these positive actions, we are proposing an approach to extracting key behaviors within ASRS reports that can support the Safety II concept. Our analysis assumes that ASRS reports contain some descriptions of corrective actions that operators performed to prevent a situation from leading to an accident. Leveraging recent advances in Natural Language Process modeling, we have developed an approach to extract positive sentiment from reports, embed these positive statements in a vector space where they can be numerically analyzed, and clustering these statements into similar contextual categories. From these contextualized categories we can attempt to summarized and distilled aspects of the positive behavior. The goal is to identify categories of behavior that describe consistent operator techniques that supports the Safety II concept. With this information, airlines may enable learning from these positive actions, or address procedures that need to be changed to avoid having pilots implement a workaround. These insights can provide a lens into what is “going right” in the operations that may otherwise not be known widely within the community. It is envisioned that this approach can be extended to other narrative programs such as Line Operation Safety Audit or Learning Improvement Team reports where similar observed behavior can be analyzed to extract positive actions and inform the overall operations.

NLP↗

NASA NTRS2021

A Simulation Study of Bin-and-Sort Policies in a Distributed System for Flights Scheduling

This is a report on the results of a simulation experiment conducted on an automated distributed system for scheduling flights in a shared airspace. The scheduling is carried out by computer systems owned by the private operators of the flights, which interface through a centralized independent server. The scheduling requires determining which of the group of flights at hand (whether owned by the same operator or different ones) are to have the advantage of being scheduled before the others. A chosen method of grouping and prioritizing flights must: have the ability to schedule a flight promptly, prevent scheduling conflicts between pairs of overlapping flight routes, and be computationally feasible. Scheduling flights one by one is the First Come First Served policy. Scheduling too many at a time is infeasible. The type of scheduling policy proposed herein, called bin-and-sort, is an attempt to reach a compromise between these two extremes. Bin-and-sort allows for each operator to choose its criteria for prioritizing its flights, and for the centralized component to use different arbitration criteria. A number of these criteria are used in the simulation presented herein. The results of each criterion choice are reported and analyzed.

flight scheduling↗

NASA NTRS2021

A Simulation Study of Bin-and-Sort Policies in a Distributed System for Flights Scheduling

This is a report on the results of a simulation experiment conducted on an automated distributed system for scheduling flights in a shared airspace. The scheduling is carried out by computer systems owned by the private operators of the flights, which interface through a centralized independent server. The scheduling requires determining which of the group of flights at hand (whether owned by the same operator or different ones) are to have the advantage of being scheduled before the others. A chosen method of grouping and prioritizing flights must: have the ability to schedule a flight promptly, prevent scheduling conflicts between pairs of overlapping flight routes, and be computationally feasible. Scheduling flights one by one is the First Come First Served policy. Scheduling too many at a time is infeasible. The type of scheduling policy proposed herein, called bin-and-sort, is an attempt to reach a compromise between these two extremes. Bin-and-sort allows for each operator to choose its criteria for prioritizing its flights, and for the centralized component to use different arbitration criteria. A number of these criteria are used in the simulation presented herein. The results of each criterion choice are reported and analyzed.

flight scheduling↗

NASA NTRS1998

Steps Towards the Integration of Conflict Resolution with Metering and Scheduling

NASA Ames Research Center is developing decision support tool technology for air traffic controllers to improve the efficiency and capacity of National Airspace System. The goal is to provide technology, tools and procedures that result in the highest possible level of user preferred trajectories whenever possible with safe and efficient traffic management when necessary. The work is being conducted under the NASA Advanced Air Transportation Technology Program in cooperation with the FAA through the Inter-Agency Integrated Product Team. The objective is to develop technology and procedures that lead towards a seamless integration of conflict resolution with metering and scheduling for arrival aircraft and en route aircraft that are under metering restrictions. A requirement is that the integration incorporate user preferred trajectories. The ultimate goal is the implementation and validation of the Descent Advisor (DA) concept which provides clearance advisories to a sector controller that simultaneously meet metering constraints, are conflict free, incorporate a user preferred (e.g., minimum fuel) descent profile, and generally require no further corrective clearance as the aircraft transitions from en route cruise into the TRACON. The DA concept may also be applied to en route aircraft under metering constraints, e.g., miles-in-trail. To achieve the DA concept a stepwise development and field evaluation is anticipated. This paper addresses the initial steps towards implementation of the DA. The Traffic Management Advisor (TMA) computes arrival time sequence and required delay information for display to the sector controller during periods when arrivals must be metered due to landing rate restrictions at the airport. The Initial Conflict Probe (ICP) compares trajectory predictions for all aircraft and alerts the controller when any two aircraft are predicted to violate separation standards (5 mi. and 2000 ft. in en route airspace). ICP also includes a trial planning function allowing the controller to develop and check a separate "what if" trajectory for conflict resolution. TMA and ICP currently operate independent of one another and have separate controller displays. The TMA meter list is on the radar controller's plan view display. The ICP is still under development, but the current concept calls for a list of predicted conflicts at the data controller position. The research described herein address two steps towards the implementation of DA. The first is to develop a concept for integrated display of conflict and metering information on a controller's display. The objective is to provide the controller with situational awareness of one problem while he develops a solution to the other. The next step is to expand the concept for display of automated clearance advisories for one problem (e.g., metering) which take into account the other problems (e.g., conflicts). Information to be communicated between TMA and ICP to facilitate' manual or automated advisories is being identified as the concept matures. In order to study the ICP/TMA integration concept the CTAS conflict probe capability has been adapted to Ft. Worth Center. The system is being validated in the laboratory with all-track data and for non -interference with TMA, TMA is already running as a daily use prototype at Ft. Worth Center. A laboratory prototype system has been developed under the CTAS baseline which combines conflict and metering information on a common user interface. Elements of the user interface are shown in Figure 1. In this simple illustration the user sees the simultaneous effect of a trial plan on meter fix delay and conflict status. Delay information is shown in the aircraft flight data block, the meter list, and the TMA timeline. Experience during Descent Advisor development and observations at Ft. Worth Center high and low attitude arrival sectors during metering suggests that manual trial planning will be unworkable during rush periods due to high controller workload.

McNally, B. David↗

NASA NTRS2008

Effect of Surface Traffic Count on Taxi Time at Dallas-Fort Worth (DFW) International Airport

As the amount of air traffic increases over the years, most airports simply do not have the means of expanding to handle the intensified traffic on the surface that will ensue. Precise surveillance equipment and automation concepts, as well as advanced surface traffic algorithms are being developed to improve airport efficiency. These surface algorithms require inputs unique to each airport to ensure maximum efficiency, and minimal taxi delay. This study analyzes surface traffic at Dallas-Fort Worth International Airport (DFW) to determine the effect of the number of aircraft on the surface and the amount of stop and go situations they experience to the amount of additional taxi time encountered. If the surface capacity of an airport is known, minimal delay can be accomplished by limiting the number of taxiing aircraft to that capacity. This concept is related to highways, where traffic flow drastically decreases as more cars occupy the road. An attempt to minimize this effect on highways is seen with the use of metering lights at freeway on-ramps. Since the surface traffic at airports is highly regulated, and aircraft are less mobile on the ground, limiting the surface count to a certain number can greatly reduce the amount of additional taxi time encountered, as well as reduce hazardous emissions. This study will also find the regions of an airport that encounter the most additional taxi time when the number of aircraft in that area is increased. This could help surface traffic algorithms avoid congesting that area, or re-route aircraft to different runways when that area reaches its capacity. The relationship between the amount of stop and go situations an aircraft encounters and their effect on the taxi time of that aircraft will also be investigated. This will help to determine the effect of holding an aircraft on the taxiway as opposed to re-routing it. The lesser of the two should be used when developing surface traffic algorithms to further minimize the delay encountered. The fields investigated in this study include taxi time, the number of aircraft on the surface, the number of stop and go situations, and the time stopped for each aircraft. Taxi time is defined as spot to runway for departures, and runway to spot for arrivals. It does not include ramp area taxi time because the ramp area is controlled differently, and surface traffic schedulers do not currently incorporate them. Taxi time is found by finding the difference between take-off time (OFF) and spot crossing time for departures, and spot crossing time and landing time (ON) for arrivals. All surface data was either found directly using the Surface Operations Data Analysis and Adaptation (SODAA), a tool to analyze the Surface Management System (SMS) generated log files, or indirectly from SODAA using Matlab to derive values from SODAA data. The number of aircraft on the surface is found by looping through the ON times, OFF times, and spot times for each aircraft during a particular day. For each departure aircraft, surface counts are taken at its spot crossing and OFF time. The average of these two is used as the surface count for that aircraft. For arrivals, surface counts are taken at its ON time and its spot crossing time. The average of these two is used.

Kistler, Matthew Stephen↗