A human factors perspective on automated driving

ABSTRACT

Automated driving can fundamentally change road transportation and improve quality of life. However, at present, the role of humans in automated vehicles (AVs) is not clearly established. Interviews were conducted in April and May 2015 with 12 expert researchers in the field of human factors (HFs) of automated driving to identify commonalities and distinctive perspectives regarding HF challenges in the development of AVs. The experts indicated that an AV up to SAE Level 4 should inform its driver about the AV's capabilities and operational status, and ensure safety while changing between automated and manual modes. HF research should particularly address interactions between AVs, human drivers and vulnerable road users. Additionally, driver-training programmes may have to be modified to ensure that humans are capable of using AVs. Finally, a reflection on the interviews is provided, showing discordance between the interviewees’ statements – which appear to be in line with a long history of HFs research – and the rapid development of automation technology. We expect our perspective to be instrumental for stakeholders involved in AV development and instructive to other parties.     

Examination of trust and sustainability concerns in autonomous vehicle adoption

The latest developments regarding autonomous vehicles (AVs) have drawn the attention of tech-savvy individuals and marketers. AVs are expected to cause a major change in the markets of vehicle selling, transportation and logistics. Therefore, it is crucial to understand consumer acceptance so that the companies in these markets can develop their penetration strategies accordingly and technology companies can shape their technology development strategies. This study aims to examine individuals' adoption attitudes toward AVs by considering trust and sustainability concerns. This was achieved by expanding the technology acceptance model (TAM). A survey of 391 participants was conducted and the data were analyzed using structural equation modeling (SEM). The results confirmed previous technology acceptance models by showing the relationships between perceived usefulness, perceived ease of use, and behavioral intention. Moreover, the direct and indirect effects of trust on behavioral intention were also shown. This study provides evidence to extend the TAM to the adoption of AVs by uncovering individuals’ sustainability concerns.     

A comparison of the views of experts and the public on automated vehicles technologies and societal implications

Automated vehicles (AVs) are seen as a gateway to safer and more accessible mobility, while others see AVs as unrealistic and dangerous. Public perception of AVs is not always in line with experts' views on issues relating to technology and public safety. To explore how the views of the public and experts compare, two qualitative studies were conducted with the aim of understanding attitudes, opinions, and expertise on a variety of matters relating to emerging AV technology and its societal impacts. Interviews were conducted with 11 AV experts from a variety of fields of expertise including optometry, engineering, computer science and psychology. Additionally, eight focus groups were held with 34 members of the public to discuss their opinions about AV technologies. Views from the public and experts were divided into 12 themes, with three categories (positive, mixed, and negative feelings towards AVs). The five themes under the positive category included topics of the danger of conventional vehicles, inclusive mobility, the use of time and space, familiarisation with AVs, and safety benefits. The two themes under the mixed feelings categories were, concerns about trust and the legal challenges. The five themes under the negative category were, the technological challenges, the complexity of monitoring, mixed-fleet danger, skills atrophy, and cybersecurity. The results showed that both the experts and public participants were enthusiastic about AVs, with a minority from both groups sceptical about this emerging technology. Insights from this research can be used to help inform 1) how the law can be adapted to AVs and 2) areas that can be focused on to alleviate the public's concerns around AVs.     

多机器人存取系统中的机器人群无冲突调度方法

多机器人存取系统由大量自寻址机器人构成,机器人群体运动过程会频繁发生冲突并引发大量启停,给能耗带来损失并影响机器人寿命。针对该问题,借鉴无等待作业车间调度,基于主动等待提出了机器人群无冲突调度方法。建立了机器人群无冲突调度数学模型并基于模拟退火算法优化任务顺序,进一步建立机器人群调度评估方法。实验结果表明,所提方法与传统方法相比,能够在不弱化运作效率的基础上大幅减少机器人群的启停次数,在节能和延长机器人寿命方面具有显著优势。     

Will automated vehicles solve the truck driver shortages? Perspectives from the trucking industry

The United States (U.S.) has experienced persistent truck driver shortages for the past several decades, as demand for truckers has increased while individuals willing to fill driving jobs have decreased. Studies in the transportation literature have not examined industry views on driver shortages, which are expected to become more severe, in combination with trucking industry perspectives on the impact of automated vehicles (AVs) on driving jobs. This study addresses these knowledge gaps through focus groups with trucking industry participants (N = 67) working in three organizational levels (25 upper-level management or owners, 20 supervisors or dispatchers, and 22 drivers) and a supplemental online survey. Using an inductive thematic analysis approach, findings indicate that companies struggle to address driver shortages because of difficulties recruiting younger workers related to quality-of-life issues, job requirements, and low rates of pay. AVs were thought to be a potential solution to the driver shortage, although there will be a continued need for drivers to perform certain tasks. The potential changes in industry positions could attract new workers but would require older workers to adapt to using new technology. From a workforce development perspective, training programs targeting technicians and drivers can help prepare the trucking workforce for an autonomous future.     

Deep Learning Control for Autonomous Robot

Several applications of machine learning and artificial intelligence, have acquired importance and come to the fore as a result of recent advances and improvements in these approaches. Autonomous cars are one such application. This is expected to have a significant and revolutionary influence on society. Integration with smart cities, new infrastructure and urban planning with sophisticated cyber-security are some of the current ramifications of self-driving automobiles. The autonomous automobile, often known as self-driving systems or driverless vehicles, is a vehicle that can perceive its surroundings and navigate predetermined routes without human involvement. Cars are on the verge of evolving into autonomous robots, thanks to significant breakthroughs in artificial intelligence and related technologies, and this will have a wide range of socio-economic implications. However, in order for these automobiles to become a reality, they must be endowed with the perception and cognition necessary to deal with high-pressure real-life events and make proper judgments and take appropriate action. The majority of self-driving car technologies are based on computer systems that automate vehicle control parts. From forward-collision warning and antilock brakes to lane-keeping and adaptive drive control, to fully automated driving, these technological components have a wide range of capabilities. A self-driving car combines a wide range of sensors, actuators, and cameras. Recent researches on computer vision and deep learning are used to control autonomous driving systems. For self-driving automobiles, lane-keeping is crucial. This study presents a deep learning approach to obtain the proper steering angle to maintain the robot in the lane. We propose an advanced control for a self-driving robot by using two controllers simultaneously. Convolutional neural networks (CNNs) are employed, to predict the car’ and a proportional-integral-derivative (PID) controller is designed for speed and steering control. This study uses a Raspberry PI based camera to control the robot car.     

基于自动驾驶汽车接受度的个性化用户研究

目的 自动驾驶汽车出现以来,如何提升其大众接受度一直是学术界和工业界的关注热点。本文通过对影响自动驾驶汽车接受度的个性特征进行梳理,为后续提升用户接受度的个性化设计实践提供参考。方法 对近10年来有关自动驾驶接受度的研究进行系统性梳理,总结了社会人口学特征、经验水平和心理特质三类用户因素对自动驾驶接受度的影响。结果 影响自动驾驶汽车接受度的社会人口学因素主要包括性别、年龄、地域、教育、收入,以及身体状况等方面。用户驾驶经验和先验知识水平亦会影响自动驾驶汽车的接受度。心理特质是解释用户接受度差异的核心因素,包括大五人格、自我认知、个人控制、焦虑特征等维度。根据前述用户特征可知,从包容性设计、娱乐交互组件、信息交换方式、自动驾驶风格和外观五个方面开展个性化设计将有助于提升用户接受度。结论 基于用户特征的个性化设计实践,将是提升用户自动驾驶汽车接受度的重要途径。未来应进一步开展多维用户因素的交互机制及权重分析研究,并通过实证研究来明确不同个性化设计的作用,以推进自动驾驶汽车的普及。     

液氮汽车的研究

液氮汽车作为一种环保交通工具 ,与电动汽车相比 ,具有很多优点 ,亦是当前环保汽车的一大发展趋势。目前国内对液氮汽车的研究基本上还是空白 ,国外的研究也是刚刚起步。文章在阐述液氮汽车研究现状的同时 ,得出现有液氮汽车系统中存在的主要问题 ,并提出解决现有问题的技术措施 ,探索新型循环系统的原理以及各关键部件和过程的优化模型 ,为实用且环保的液氮汽车的发展提供理论依据     

Architectural design and reliability analysis of a fail-operational brake-by-wire system from ISO 26262 perspectives

Next generation drive-by-wire automotive systems enabling autonomous driving will build on the fail-operational capabilities of electronics, control and software (ECS) architectural solutions. Developing such architectural designs that would meet dependability requirements and satisfy other system constraints is a challenging task and will possibly lead to a paradigm shift in automotive ECS architecture design and development activities. This aspect is becoming quite relevant while designing battery-driven electric vehicles with integrated in-wheel drive-train and chassis subsystems.In such highly integrated dependable systems, many of the primary features and functions are attributed to the highest safety critical ratings. Brake-by-wire is one such system that interfaces with active safety features built into an automobile, and which in turn is expected to provide fail-operational capabilities. In this paper, building up on the basic concepts of fail-silent and fail-operational systems design we propose a system-architecture for a brake-by-wire system with fail-operational capabilities. The design choices are supported with proper rationale and design trade-offs. Safety and reliability analysis of the proposed system architecture is performed as per the ISO 26262 standard for functional safety of electrical/electronic systems in road vehicles.     

Intelligent Mining Technology for an Underground Metal Mine Based on Unmanned Equipment

This article analyzes the current research status and development trend of intelligent technologies for underground metal mines in China, where such technologies are under development for use to develop mineral resources in a safe, efficient, and environmentally friendly manner. We analyze and summarize the research status of underground metal mining technology at home and abroad, including some specific examples of equipment, technology, and applications. We introduce the latest equipment and technologies with independent intellectual property rights for unmanned mining, including intelligent and unmanned control technologies for rock-drilling jumbos, down-the-hole (DTH) drills, underground scrapers, underground mining trucks, and underground charging vehicles. Three basic platforms are used for intelligent and unmanned mining: the positioning and navigation platform, information-acquisition and communication platform, and scheduling and control platform. Unmanned equipment was tested in the Fankou Lead-Zinc Mine in China, and industrial tests on the basic platforms of intelligent and unmanned mining were carried out in the mine. The experiment focused on the intelligent scraper, which can achieve autonomous intelligent driving by relying on a wireless communication system, location and navigation system, and data-acquisition system. These industrial experiments indicate that the technology is feasible. The results show that unmanned mining can promote mining technology in China to an intelligent level and can enhance the core competitive ability of China’s mining industry.     

eCorner: Propulsion by Hub Motors

The requirements of motor vehicles are constantly increasing, both in terms of consumption and emissions, as well as comfort and safety. Through the integration of sensors, the replacement and the intelligent processing of data and information, a lot of driver assistance functions have emerged. The evolving trend towards intelligent driver assistance systems and self autonomous driving is feasible nowadays. The vision of the car of the future could lie in the realisation of the eCorner. Here, every one of the four wheels can be controlled, steered and braked individually, through "by‐wire" commands.     

人-无人车交互中的可解释性交互研究

目的 随着现代人工智能技术在自动驾驶系统中的广泛应用,其可解释性问题日益凸显,为此探讨人-无人车交互过程中的可解释性交互的框架以及设计要素等问题,以增强自动驾驶系统的决策透明性、安全性和用户信任度。方法 结合可解释人工智能和人机交互的基本理论与方法,本文首先介绍了可解释性人工智能,对当前可解释内容的提取方法进行总结,然后以人-机器人交互的透明度模型为基础,建立人-无人车交互中可解释性交互的框架。最后从解释的对象、方式和评价等多个设计维度对可解释性的交互设计问题进行探讨,并结合案例进行分析。结论 可解释性作为人与模型决策之间的接口,不仅仅是一个人工智能技术问题,而且与人密切相关,涉及到人-无人车交互中的多个层次。本文提出人-无人车交互中可解释性交互的框架,得出在人-无人车交互每个阶段需要的解释内容以及可解释交互设计的要素。     

Hybrid In-Vehicle Background Noise Reduction for Robust Speech Recognition: The Possibilities of Next Generation 5G Data Networks

This pilot study focuses on employment of hybrid LMS-ICA system for in-vehicle background noise reduction. Modern vehicles are nowadays increasingly supporting voice commands, which are one of the pillars of autonomous and SMART vehicles. Robust speaker recognition for context-aware in-vehicle applications is limited to a certain extent by in-vehicle background noise. This article presents the new concept of a hybrid system, which is implemented as a virtual instrument. The highly modular concept of the virtual car used in combination with real recordings of various driving scenarios enables effective testing of the investigated methods of in-vehicle background noise reduction. The study also presents a unique concept of an adaptive system using intelligent clusters of distributed next generation 5G data networks, which allows the exchange of interference information and/or optimal hybrid algorithm settings between individual vehicles. On average, the unfiltered voice commands were successfully recognized in 29.34% of all scenarios, while the LMS reached up to 71.81%, and LMS-ICA hybrid improved the performance further to 73.03%.     

A review of theoretical analysis techniques for cracking and corrosive degradation of film-substrate systems

This paper contains a review of the most vital concepts regarding the analysis and design of film systems. Various techniques have been presented to analyse and predict the failure of films for all common types of failure: fracture, delamination, general yield, cathodic blistering, erosive and corrosive wear in both organic and inorganic films. Interfacial fracture or delamination is the loss of bonding strength of film from substrate, and is normally analysed based on the fracture mechanics concepts of bi-material systems. Therefore, keeping the focus of this review on bonding strength, the emphasis will be on the interfacial cracking of films and the corresponding stresses responsible for driving the delamination process. The bi-material characteristics of film systems make the nature of interfacial cracks as mixed mode, with cracks exhibiting various complex patterns such as telephone cord blisters. Such interfacial fracture phenomenon has been widely studied by using fracture mechanics based applicable analysis to model and predict the fracture strength of interface in film systems. The incorporation of interfacial fracture mechanics concepts with the thermodynamics/diffusion concepts further leads to the development of corrosive degradation theories of film systems such as cathodic blistering. This review presents suggestions for improvements in existing analysis techniques to overcome some of limitations in film failure modelling. This comprehensive review will help researchers, scientists, and academics to understand, develop and improve the existing models and methods of film-substrate systems.     

Intelligent systems using triboelectric,piezoelectric, and pyroelectric nanogenerators

Recent advances in artificial intelligence, computer science, communication, sensing and actuation technologies have resulted in the development of several novel intelligent systems. At the same time, the emergence of nanogenerators has opened a new research avenue with the overarching goal of developing self-powered sensing systems. The concepts of self-powered sensing, based on nanogenerators and intelligent systems can be fused together to open a new area of interdisciplinary research. In this article, we aim to show how these two emerging technologies have been combined to develop self-powered intelligent sensing systems. We first focus on the main keywords in the area of nanogenerators. Keyword co-occurrence network graphs are generated based on the most used keywords in the area of nanogenerators to select key concepts that are directly connected to the concept of intelligent systems. Thus, a detailed review is provided on different intelligent self-powered sensing systems based on nanogenerators. We also discuss the challenges presented by combining intelligent systems and self-powered sensing. As most of intelligent devices rely on machine learning techniques, a comprehensive section is allocated to this topic to focus on its applications in nanogenerator-based devices.     

Suspicious minds? – users’ perceptions of autonomous and connected driving

Abstract

In this article, the public perception and acceptance of novel vehicle technologies – autonomous driving (AD) and connected driving (CD) – is investigated. Following a multistep empirical procedure, we explore participants’ cognitions towards AD and CD. Therefore, a questionnaire study was run in which the perceived benefits and barriers of the technologies were evaluated by 443 participants in a wide age range (18–76 years). In addition, we took a closer look at the impact of user diversity (gender, age, need for privacy, control, risk taking tolerance and technical self-efficacy) on the evaluation of both driving technologies. Finally, cluster analyses were used out to identify evaluation profiles in both benefits and barriers, respectively. Overall, CD is seen significantly more positive compared to AD. With increasing risk taking tolerance and technical self-efficacy, the perception of the benefits was higher. In contrast, the perception of barriers in novel vehicle technologies was independent of personality factors and attitudes. Here, privacy and data protection issues were seen as key disadvantages. The findings can be used to develop timely and individually tailored public information and communication strategies for automated and connected vehicle technologies.     

语音提示和错误类型对有条件自动驾驶接管的影响

目的 在有条件自动驾驶中,驾驶员会根据系统发出的接管提示而选择进入手动驾驶模式。由于技术限制,自动驾驶系统有时会发出错误的接管提示,这可能会影响驾驶员的人机信任及后续的接管决策。此外,不同类型的接管提示音类型也会影响驾驶者对接管的响应。因此,探究不同声音类型下接管提示错误类型对人机信任和接管绩效的潜在影响,对自动驾驶系统的接管提示设计具有重要意义。方法 以行人预警为例,通过模拟驾驶实验,从绩效、主观评价两方面探究提示音类型(语音和耳标)和接管提示错误类型(漏报和虚报)对驾驶员人机信任和驾驶行为的影响。结论 相较于语音提示,驾驶员在耳标提示下的接管反应时间更短,可用性和满意度更高。在经历漏报提示后,驾驶员的人机信任水平降低并对随后正确接管提示的反应变快。     

Dispatch control of a fleet of remote-controlled/automatic load-haul-dump vehicles in underground mines

Recently, a concept for automating load-haul-dump (LHD) vehicles has stimulated considerable interest in the world mining industry. In this concept, the tramming and dumping operations of an LHD should be automatic. During loading, an operator from a control room fills the bucket of a vehicle via remote-control aided by a television system. The application of such a remote-controlled/automatic LH D (RAL) system in underground mines exhibits some operational and traffic control characteristics that have not been studied previously in mining (e.g. vehicle motion in bidirectional lane-segments, lack of alternative routes to the same destination, stochastic nature of an RAL system due to human involvement in the loading operation). This paper presents and discusses a dispatch and traffic control procedure for a fleet of RAL vehicles operating in an underground mining transport layout. The development of this procedure has been based on concepts in graph theory.     

Human-autonomy teaming in military settings

ABSTRACT

In this Thematic Issue ‘Human-Autonomy Teaming’ of Theoretical Issues in Ergonomics Science, five U.S. military-funded research efforts are presented to discuss human factors issues in a variety of military human-autonomy teaming mission environments: dismounted infantry working with a small ground robot; intelligence analysis; human working with an intelligent agent to manage a team of heterogeneous unmanned vehicles; vehicle-mounted ground penetrating radar. The research issues addressed in this Issue are diverse – from display designs to operator performance and trust in the systems. The results and insights documented in these five articles should provide useful resources to researchers and practitioners working on intelligent and autonomous systems.