基于视频分析的空管员违规行为识别方法*

为利用视频数据对空管员违规行为进行智能化分析,降低不安全事件发生率,提出2阶段的违规行为识别模型（AR-ResNeXt）,基于实地调研构建空管员视频数据集,利用最小化动态多实例学习损失函数和中心损失函数,获得违规行为检测的判别特征表示,结合异常回归网络和ResNeXt网络,完成对空管员违规行为的时序区间检测与动作分类。研究结果表明:AR-ResNeXt模型在自制数据集中,其帧级AUC达到82.9%,分类准确率达到87.8%,可准确识别空管员发生违规行为的时序区间并进行分类,研究结果可为保障空中交通安全奠定基础。     

A model of the air traffic controller's picture

This paper reviews the development of a model of the air traffic controller's mental image, ‘picture’, or situation awareness, used for controlling air traffic. The computerised model's development, origins and theoretical basis are outlined, and the model is described in some detail in the context of current air traffic operations. The model can be utilised to explore the potential impacts of future automation on the cognitive performance of the air traffic controller. The general potential contributions of the area of cognitive modelling to system design and training in accelerating industries such as air traffic control, are also discussed.     

基于信息加工模型的管制员差错分类与分析

在Wickens的人类信息加工模型的基础上,加入注意功能、情景意识、内部和外部操作成形因素,建立了管制员信息处理模型。按照该模型,空中交通管制人为差错可按照认知领域分为感知与警觉性差错、短时记忆差错、长时记忆差错、判断与计划差错、响应选择差错和响应执行差错;影响管制员操作的情境条件可分为外部操作成形因素和内部操作成形因素。对以往空管人为差错的分析表明,在信息加工层面分类的人为差错更宜于确定差错的心理致因。基于该理论模型的差错分类系统可以改进人为差错分析的有效性和一致性,从而提高差错管理的有效性。     

空中交通管制员与飞行员通信风险评估指标体系研究

对空管安全风险管理的关键环节——管制员与飞行员的通信过程进行分析,探讨管制员与飞行员通信失误的表现,分析造成通信失误的原因,从人员、设备、环境和管理4个方面探讨通信风险因素。在此基础上,构建管制员与飞行员通信风险评估指标体系,包括总体层、因素层和指标层3个层次及18项评估指标。通过对通信风险进行监测、评价和管控,帮助管理人员发现通信过程存在的安全隐患,增强管制员与飞行员通信工作的可靠性,从而提高空中交通安全水平。     

民航空管安全文化建设探析

根据民航空管安全发展的客观规律,在综合考虑践行空管持续安全理念、减少空管人为差错、建设空管安全管理体系的基础上,提出要实现我国民航的持续安全,就要构建并不断完善空管安全文化建设的有效手段和途径。对空管安全文化建设的途径展开了深入探索,并提出了相关建议和措施,包括开展技能竞赛等文化娱乐活动、建立管制员心理培训与辅导机制、提升管制员新技术适应能力等。空管安全文化的建设是空管发展的坚强后盾,有效手段和措施建设的推进将成为航空运行安全的有力保障。     

Stress among air traffic controllers: Occupational sources of coronary heart disease risk

This study attempts to assess the sources of occupational stress on air traffic controllers. It is based on data collected from a majority of air traffic controllers at a large U.K. airport. There are two unique methodological features described in this article. First, the use of the repertory grid technique as a method of generating work stressor variables, and second, the use of the multiple logistic equation as a coronary heart disease risk index.     

Estimation of air traffic longitudinal conflict probability based on the reaction time of controllers

To estimate air traffic longitudinal conflict probability influenced by human factors, an analytic model considering the reaction time of controllers is proposed. In the model, the decelerating process of two close flights is described, and the reaction time of controllers is considered a stochastic variable. Then one hundred data of the controller reaction time are collected and analysed. Maximum likelihood estimate is used for parameter estimation. The Anderson–Darling Goodness of Fit test is used for significance test. The results show that the reaction time of controllers fits lognormal distribution at levels of significance 0.05, 0.025, 0.01 and 0.005 respectively. Case study is then performed to certify the rationality of the model, and the impact of the controller reaction time on air traffic longitudinal conflict probability is shown.     

管制员认知偏差测评量表的编制与应用

利用信息加工模型,结合管制工作的特殊性,编制出管制员认知偏差测评量表。利用该量表对管制员认知偏差进行测量,结果表明管制员管制过程中存在较大的认知偏差;不同性别及年龄的管制员在认知偏差方面存在显著差异。     

The role of the controller in the accelerating industry of air traffic management

This paper considers the role of the controller in future Air Traffic Management (ATM), an industry which is undergoing considerable and rapid change at this time. In particular, the paper focuses on the area of allocation of function, i.e. the determination of what the (human) controller should do, what the hardware and software (machine) should do, and what tasks they should share, and who (or what) is in control, in this increasingly complex system. The premise of the paper is that traditional criteria for allocation of function, so-called Fitts List approaches, are no longer clear-cut to apply, if they ever were. Technology is reaching the point where many traditionally human functions and roles can be supported or even completely autonomously carried out by automated systems. The question is quite simple — what functions, roles, and even responsibilities should be automated? This question is becoming an imperative in currently accelerating technologies such as ATM. As an example, aviation saw a huge insurgence of automation into the cockpit, with four generations of so-called glass cockpit designs, culminating in aircraft which are completely fly-by-wire, and where some aircraft have envelope protection such that the pilot's control actions are monitored and may be overridden by the machine. However, this transition from largely manual flight to glass-cockpit control was not without problems and automation-assisted accidents, and the air traffic industry would do well to avoid such problems. ATM is an area that has been relatively non-automated for the past 30 years. But as traffic levels continue to rise rapidly, there is general agreement that ATM systems must adopt some level(s) of automation support in order to maintain safety and efficiency of air traffic operations. However, ATM development is currently also highly technology-driven, perhaps with most emphasis on what technology can do for us, rather than what we need it to do. From a human factors perspective, the question of what we need from technology and automation is the critical one. As technology continues to accelerate, it is probable that it will be able to deliver whatever functions we wish it to. It is therefore appropriate to consider what the role of the human should be. If such considerations are not made now, then accelerating technology and traffic levels, and the need for ATM systems that can cope, will deliver systems which, if they fail, will lead to the types of negative experiences and fatal accidents that the aviation world has already experienced. Quite simply, if the role of the human is not considered now, it will be too late to consider it. Furthermore, if this occurs, then future as yet unforseen automation-assisted accidents will inevitably be attributed to human error. This paper considers some of the factors and issues surrounding the difficult area of automation and allocation of function, and gives an example of one method, based on error analysis, which has been used to try to answer some of the difficult automation questions currently facing ATM and human factors.     

Coding ATC incident data using HFACS: Inter-coder consensus

Reliability studies for coding contributing factors of incident reports in high hazard industries are rarely conducted and reported. Although the Human Factors Analysis and Classification System (HFACS) appears to have a larger number of such studies completed than most other systems doubt exists as the accuracy and comparability of results between studies due to aspects of methodology and reporting. This paper reports on a trial conducted on HFACS to determine its reliability in the context of military air traffic control (ATC). Two groups participated in the trial: one group comprised of specialists in the field of human factors and the other group comprised air traffic controllers. All participants were given standardised training via a self-paced workbook and then read 14 incident reports and coded the associated findings. The results show similarly low consensus for both groups of participants. Several reasons for the results are proposed associated with the HFACS model, the context within which incident reporting occurs in real organisations and the conduct of the studies.     

A mobile flight case learning system for ATC miscommunications

Aviation’s highest priority is safety. The primary risk to safety derives not from automated systems but from human factors, most notably air traffic control. We present results from development of a flight case learning system designed to operate on mobile phones used by air traffic controllers (ATCs). Our system takes advantage of key Ontology concepts, a case-based system development procedure, human-centered design (HCD) strategies, and appropriate small-screen interface design protocols. A questionnaire to assess user interaction satisfaction (QUIS) was deployed for subsequent usability testing and to verify acceptance of, and satisfaction with, the system. Twelve subjects participated in the questionnaire-based evaluation of subjective satisfaction. In addition, two flight experts served on a review panel for domain knowledge verification and acceptance of the interface design. Our results confirm that the system is a suitably designed mobile learning system that can accelerate self-learning for ATCs.     

Tipping point: The narrow path between automation acceptance and rejection in air traffic management

Capacity limits on the air traffic management (ATM) system are of global concern. One solution to increase the efficiency of existing ATM system is through the implementation of advanced automation. However, past experience suggests ATCOs are selective and critical about the forms of automation they are given. Therefore, this study aimed to determine if a threshold or tipping point exists, a point after which users (Air Traffic Control Operators; ATCOs) of automation are no longer willing to accept or cooperate with the automation. 500 Air Traffic Control Operators completed an on-line survey that comprised a series of demographic questions as well as two hypothetical but plausible futuristic air traffic management tools. Each tool contained seven different situations involving different levels of automation involvement ranging from fully manual operation to fully automated. Participants were asked to rate on a five point Likert scale the extent to which they agreed with the statements describing their interaction with the new tools. The results revealed a ‘tipping point’ in automation acceptance/rejection reflecting the point where the applied level of automation shifted the locus of decision-making away from the operator. The results are discussed from a theoretical and applied perspective.     

Work domain analysis for air traffic controller weather displays

INTRODUCTION: Adverse weather conditions have a major impact on National Airspace System (NAS) operations. They create safety hazards for pilots, constrain the usable airspace for air traffic control (ATC), and reduce the overall capacity of the NAS. A system-wide dissemination of weather information to controllers could theoretically improve safety and efficiency. PROBLEM: However, it is currently unclear what weather information would be beneficial for tactical operations. Furthermore, no previous research has empirically evaluated optimal presentation designs for ATC weather displays. Ill-designed weather displays can cause safety hazards by presenting redundant information (i.e., by increasing the cognitive load) and display clutter (e.g., by interfering with the visual extraction of traffic data). METHOD: In the present paper, we outline our use of cognitive work analysis (CWA) techniques for the assessment of weather information needs for terminal controllers. RESULTS: Specifically, we describe how the CWA modeling tools helped us reveal instances in the terminal domain where weather information is lacking or insufficiently disseminated. We used our CWA results to drive the development of weather display concepts and to set up a high-fidelity simulation capability. IMPACT ON INDUSTRY: By means of high-fidelity simulations, we can empirically evaluate controller weather information needs in order to propose weather displays for increased aircraft safety and efficiency of terminal operations.     

空中交通管制员职业素质模糊综合评价

提出一种管制员综合素质的评价方法;构建管制员综合素质评价指标体系和模糊综合评价模型;应用专家打分法确定指标的权重判断矩阵数据和隶属度数据;采用层次分析法对判断矩阵进行处理得到指标权重数据;按照评价模型的程序对权重数据和隶属度数据进行处理,最终得到管制员综合素质的评价值,根据评价结果提出了提高管制员综合素质的对策。     

基于Fuzzy-ANP的空管安全风险评估研究

空中交通管制对于保障飞行安全至关重要,如何进行空管安全风险评估是亟待研究的问题。在分析三角模糊数学和ANP原理的基础上,针对空管安全风险因素相互影响的特点,建立基于Fuzzy-ANP的空管安全风险评估模型。以某空管单位为例进行实证分析,通过计算评价指标权重,找到影响空管安全风险的关键指标。结果表明,影响该空管单位安全的主要因素为管理标准效能、员工培训次数和人员语言及交流沟通状况等,该空管单位应重点改善这3个因素并兼顾其他影响因素。研究表明,Fuzzy-ANP分析法有助于确定安全风险评估的重点。     

管制员安全能力模型研究

为准确评价管制员安全能力,基于能力的定义和管制员工作职责,界定管制员安全能力的内涵;依据该内涵及其工作特性,建立由身体素质、业务素质和意识3个结构维度组成的管制员安全能力模型。其中,身体素质包括生理状况和心理状况;业务素质包括教育状况、培训状况、技能状况和经验状况;意识包括安全意识和工作意识。在各项指标性质差异较大情况下,利用功效系数法实现评价指标的标准化以减小误差,客观反映指标情况,同时采用G1-法和熵值法集成的主客观综合赋权法确定指标的权重,在一定程度上弥补主客观单一赋权的不足,最后通过逼近理想解排序法(TOPSIS)评价管制员安全能力。结果表明,按照从大到小排序对管制员安全能力的影响因素依次为意识、身体素质和业务素质。就对所论能力的影响而言,心理状况强于生理状况;技能状况强教育、培训和经验状况;安全意识对意识的影响大于工作意识。     

基于CREAM和贝叶斯网络的空管人误概率预测方法

针对研究管制人因可靠性时存在的模糊性和片面性问题，采用认知可靠性与失误分析方法（CREAM）中的扩展预测法，计算10项管制通用任务的人误概率；在此基础上，以管制行为形成因子作为根节点构建贝叶斯网络，建立其与情景控制模式的不确定关系模型，对管制员在多任务中的人误概率进行预测。研究结果表明:在由相同评判者给出行为形成因子影响效应的前提下，由CREAM扩展预测法和构建贝叶斯网络的方法预测得到的多数任务的人误概率差异较大，从方法的客观性、合理性和适用性角度分析，贝叶斯网络在研究该问题时更具优势。     

Multi-agent traffic simulations to estimate the impact of automated technologies on safety

Abstract

Objective: The objective of this article was to develop a multi-agent traffic simulation methodology to estimate the potential road safety improvements of automated vehicle technologies.

Methods: We developed a computer program that merges road infrastructure data with a large number of vehicles, drivers, and pedestrians. Human errors are induced by modeling inattention, aimless driving, insufficient safety confirmation, misjudgment, and inadequate operation. The program was applied to simulate traffic in a prescribed area in Tsukuba city. First, a 100% manual driving scenario was set to simulate traffic for a total preset vehicle travel distance. The crashes from this simulation were compared with real-world crash data from the prescribed area from 2012 to 2017. Thereafter, 4 additional scenarios of increasing levels of automation penetration (including combinations of automated emergency braking [AEB], lane departure warning [LDW], and SAE Level 4 functions) were implemented to estimate their impact on safety.

Results: Under manual driving, the system simulated a total of 859 crashes including single-car lane departure, car-to-car, and car-to-pedestrian crashes. These crashes tended to occur in locations similar to real-world crashes. The number of crashes predicted decreased to 156 cases with increasing level of automation. All of the technologies considered contributed to the decrease in crashes. Crash reductions attributable to AEB and LDW in the simulations were comparable to those reported in recent field studies. For the highest levels of automation, no assessment data were available and hence the results should be carefully treated. Further, in modeling automated functions, potentially negative aspects such as sensing failure or human overreliance were not incorporated.

Conclusions: We developed a multi-agent traffic simulation methodology to estimate the effect of different automated vehicle technologies on safety. The crash locations resulting from simulations of manual driving within a limited area in Japan were preliminary assessed by comparison with real-world crash data collected in the same area. Increasing penetration levels of AEB and LDW led to a large reduction in both the frequency and severity of rear-end crashes, followed by car-to-car head-on crashes and single-vehicle lane departure crashes. Preliminary estimations of the potential safety improvements that may be achieved with highly automated driving technologies were also obtained.     

管制员不安全行为干预策略研究

为了制定科学合理的干预策略、防止由管制员导致的两机相撞等不安全事件发生,运用系统动力学方法(SD)构建了管制员不安全行为干预策略模型,以S空管站为例,运用Vensim软件仿真模拟不同安全奖惩政策对管制员不安全行为的干预结果。结果表明:安全奖励政策可以有效干预管制员的差错行为,安全惩罚政策可以有效干预管制员的违章行为;高强度奖励政策-中强度惩罚政策组合干预效果最佳,即当对管制员奖励强度达管制员月薪的3.2倍,惩罚强度达管制员月薪的0.82倍,管制员不安全行为造成的不安全事件率能够降低85.6%。     

改进模糊Petri网在空管安全风险评估中的应用

科学、有效的空管安全风险评估是进行安全风险管理的重要环节,是保证航空事业健康发展的必要前提。遵循计划(P)—实施(I)—检查(C)—处理(A)的程序,建立了具有针对性的空管安全风险评价体系。在评估过程中采用模糊Petri网方法,同时针对其节点过多和变迁权值主观性强的缺点,引入风险等级阀值和层次分析法(Analytic Hierarchy Process,AHP),运用逆向搜索的方法简约复杂的模糊Petri网,在保证能够找出威胁安全的主要因素和准确评估空管系统安全状态的前提下,简化后续计算和推理过程,快速得到评价结果,实例验证该方法有效、可行。