Towards a reliable air traffic control (original) (raw)
Related papers
A multi-agent approach to reliable air traffic control
2008
Abstract Air Traffic Control (ATC) is going to be a typical critical socio-technical system in which controllers use a large number of distributed software tools to provide safety ATC services. The reliability of these services relies on the availability of the various tools. In the process of integrating more and more sophisticated tools in their daily work, controllers need to feel confident in the reliability of their tool set. This paper presents a multiagent approach to this reliability problem.
Agent-Based Support for Distributed Air/Ground Traffic Management Simulation Research
AIAA Modeling and Simulation Technologies Conference and Exhibit, 2003
NASA researchers are extending a large-scale distributed simulation to assess the feasibility, benefits, and scalability of Distributed Air/Ground Traffic Management (DAG-TM) concepts. This paper describes applications of software agents to support these efforts. This paper identifies applications ranging from assistants to replacements for human confederate participants and support personnel. The applications span air traffic control positions, flight simulators, pseudoaircraft control stations, and simulation support functions. The paper first provides an overview of the DAG-TM simulation, including the Multi Aircraft Control System (MACS), and describes the responsibilities of various participants. It then discusses agent applications that address problems and leverage capabilities demonstrated in previous research. Of particular interest are agents that can control air traffic and pilot aircraft, implemented within the MACS framework. Agents provide a means for focusing required subject training, reducing variability and problems attributable to human confederates, supporting partially staffed and part-task studies within the full simulation environment, and enabling fast-time simulations to investigate DAG-TM concept scalability. The paper concludes with a discussion that emphasizes the importance of interplay between complementary human-in-the-loop and agent-based simulations.
An airline schedule seldom operates as planned. Problems related with aircrafts, crew members and passengers are common and the actions towards the solution of these problems are usually known as operations recovery or disruption management. The Airline Operations Control Center (AOCC) tries to solve these problems with the minimum impact in the airline schedule, with the minimum cost and, at the same time, satisfying all the required safety rules. Usually, each problem is treated separately and some tools have been proposed to help in the decision making process of the airline coordinators. We have observed the AOCC of TAP Portugal, the major Portuguese airline, and, from those observations, several hypotheses have been identified and some of them experimented. We believe, and that is one of our main hypothesis, that the Multi-Agent System (MAS) paradigm is more adequate to represent the multi-level hierarchy organization and the several roles that are played in an AOCC. In this thesis we propose the design and partial implementation of a Distributed MAS representing the existing roles in an AOCC. We hypothesize that if we take advantage of the fact that each operational base has specific resources (both crew and aircrafts) and that if we include information regarding costs involved (for example, crew payroll information and hotels costs, among others), the solutions to the detected problems will be faster to find and less expensive. We also hypothesize that if we use specialized software agents that implement different solutions (heuristic and other solutions based in operations research models and artificial intelligence algorithms), to the same problem, the robustness of the system will increase. Finally, we believe that the inclusion of some kind of learning mechanism that learns from previous utilization of crew members will improve the solutions quality. Extending that learning mechanism to learn each crew member profile, and applying that knowledge for generating future schedules, the management of that expensive resource will be much more efficient and the level of satisfaction of each crew member will increase. We also present a real case study taken from TAP Portugal AOCC, where a crew recovery problem is solved using the MAS. Computational results using a real airline schedule are presented, including a comparison with a solution for the same problem found by the human operators in the Airline Operations Control Center. We show that, even for simple problems, and when comparing with solutions found by human operators in the case of this airline company, it is possible to find valid solutions, in less time and with a smaller cost. In this thesis we also show how we complement the GAIA methodology in order to better analyze and design the proposed MAS for the AOCC. Besides showing the rationale behind the analysis, design and implementation of our system, we also present how we mapped the abstractions used in agent-oriented design to specific constructs in JADE. The advantages of using a goal-oriented early requirements analysis and its influence on subsequent phases of analysis and design are also presented. Finally, we also propose UML 2.0 diagrams at several different levels for representation of GAIA deliverables, like organizational structure, role and interaction model, agent and service model.
A Multi-Agent System for Airline Operations Control
Advances in Soft Computing
The Airline Operations Control Center (AOCC) tries to solve unexpected problems that might occur during the airline operation. Problems related to aircrafts, crewmembers and passengers are common and the actions towards the solution of these problems are usually known as operations recovery. In this paper we present the implementation of a Distributed Multi-Agent System (MAS) representing the existing roles in an AOCC. This MAS has several specialized software agents that implement different algorithms, competing to find the best solution for each problem and that include not only operational costs but, also, quality costs so that passenger satisfaction can be considered in the final decision. We present a real case study where a crew recovery problem is solved. We show that it is possible to find valid solutions, with better passenger satisfaction and, in certain conditions, without increasing significantly the operational costs.
Recovering from Airline Operational Problems with a Multi-Agent System: a Case Study
The Airline Operations Control Centre (AOCC) tries to solve unexpected problems during the airline operation. Problems with aircraft, crewmembers and passengers are common and very hard to solve due to the several variables involved. This paper presents the implementation of a real-world multi-agent system for operations recovery in an airline company. The analysis and design of the system was done following a GAIA based methodology. We present the system specification as well as the implementation using JADE. A case study is included, where we present how the system solved a real problem.
Eats: An Agent-Based Air Traffic Simulator
2007
We present an Experimental Air Traffic Simulator (EATS).It is conceived as a tool for preliminary evaluation of flight procedures, algorithms and human-machine interfaces to be used in future Navigation and Air Traffic surrounding the new Communication, Navigation and Surveillance System to Air Traffic Management (CNS/ATM). The proposed EATS simulator version provides realistic data for the aircraft dynamic and includes the exchange of information among the aircraft from the point of view of the Air Traffic Control (ATC). It also takes into account the meteorological conditions and terrain constraints. This system has been designed as a Multi-Agent System and implemented on a JADE framework. Its architecture facilitates its later extension to incorporate and to evaluate new communication protocols and negotiation between agents operating in a specific air space.
Iscapdcs, 2003
The U.S. Army is faced with the challenge of dramatically improving its war fighting capability through advanced technologies. Any new technology must provide significant improvement over existing technologies, yet be reliable enough to provide a fielded system. The focus of this paper is to assess the novelty and maturity of agent technology for use in the Future Combat System. The Future Combat System (FCS) concept represents the U.S. Army's "mounted" form of the Objective Force. This concept of vehicles, communications, and weaponry is viewed as a "system of systems" which includes net-centric command and control (C 2) capabilities. This networked C 2 is an important transformation from the historically centralized, or platform-based, C 2 function, since a centralized command architecture may become a decision-making and execution bottleneck, particularly as the pace of war accelerates. A mechanism to ensure an effective network-centric C 2 capacity-combining intelligence-gathering and analysis available at lower levels in the military hierarchy-is needed. Achieving a networked C 2 capability will require breakthroughs in current software technology. Many have proposed the use of agent technology as a potential solution. Agents are an emerging technology, and it is not yet clear whether it is suitable for addressing the networked C 2 challenge, particularly in satisfying battlespace scalability, mobility, and security expectations. We have developed a set of software requirements for FCS based on military requirements for this system. We have then evaluated these software requirements against current computer science technology. This analysis provides a set of limitations in the current technology when applied to the FCS challenge. Agent technology is compared against this set of limitations to provide a means of assessing the novelty of agent technology in an FCS environment. From this analysis we find that existing technologies will not likely be sufficient to meet the networked C 2 requirements of FCS due to limitations in scalability, mobility, and security. Agent technology provides a number of advantages in these areas, mainly through much stronger messaging and coordination models. These models theoretically allow for significant improvements in many areas, including scalability, mobility, and security. However, the demonstration of such capabilities in an FCS environment does not currently exist, although a number of strong agent-based systems have been deployed in related areas. Additionally, there are challenges in FCS that neither current technology, nor agent technology are particularly well suited for, such as information fusion and decision support. In summary, we believe that agent technology has the capability to support most of the networked C 2 requirements of FCS. However, we would recommend proof of principle experiments to verify the theoretical advantages of this technology in an FCS environment.
An Agent-Based Approach for the Design of the Future European Air Traffic Management System
Advances in Practical Applications of Heterogeneous Multi-Agent Systems. The PAAMS Collection, 2014
This paper describes an agent-based approach for the simulation of air traffic management (ATM) in Europe that was designed to help analyze proposals for future ATM systems. This approach is able to represent new collaborative decision processes for flow traffic management, it uses an intermediate level of abstraction (useful for simulations at larger scales), and was designed to be a practical tool (open and reusable) for the development of different ATM studies. It was successfully applied in three studies related to the design of future ATM systems in Europe.
A Logical Architecture for Decision-Making Support in Air Traffic Management
2006
In the current scenario of growing demand concerning Air Traffic Control Sectors and airports, decisions about air traffic management (ATM) and individual aircraft control are based on information provided by messages of several specific computer applications. A better general performance in exploiting the air transportation resources is achieved when information, from all applications, is available in order to take a single decision, in collaborative operations, and decisions are made public for all involved participants. This way of making decisions can be more efficient and stable when supported by safe, high performance and highly available computer networks, message handlers, and databases. This study proposes the multi-agent approach for decision-making, where agents use a proper message system and distributed database architecture. Finally, a case study is presented, in which we evaluate fuel savings that may be provided by a collaborative decision-making approach. JOURNAL OF THE BRAZILIAN AIR TRANSPORTATION RESEARCH SOCIETY • NUMBER 2 • 2006 42 1.