自动驾驶场景下的轨迹预测技术综述

轨迹预测是自动驾驶和智能交通领域的关键技术,对于车辆和移动行人轨迹的准确预测可提升自动驾驶系统对周围环境变化的感知能力,保障自动驾驶系统的安全性。数据驱动轨迹预测方法可捕捉智能体之间的交互特征,对场景内智能体历史运动和静态环境信息进行分析,准确预测智能体的未来轨迹。介绍轨迹预测的数学模型并将其分为传统轨迹预测方法和数据驱动轨迹预测方法 2类,阐述主流数据驱动轨迹预测方法所面临的智能体交互建模、运动行为意图预测、轨迹多样性预测、场景内静态环境信息融合等4个主要挑战,从轨迹预测数据集使用、性能评价指标、模型特点等方面出发对典型数据驱动轨迹预测方法进行分析与对比,总结归纳这些典型数据驱动轨迹预测方法针对上述挑战的解决思路和应用场景,并对自动驾驶场景下轨迹预测技术的未来发展方向进行展望。     

自动驾驶中量子认知与决策问题研究

自动驾驶车辆对人类驾驶车辆和行人的意图估计及其相互作用研究是极其重要的,现有的研究不能很好的解释人类交通参与者的不确定因素和非理性行为,这对研究自动驾驶车辆在真实道路交通场景中运行形成了阻碍,本文基于量子理论和锚定效应,针对自动驾驶车辆右转时与非机动车和行人交互场景,构建量子决策模型.仿真分析和数据集实验证明了在与人类交通参与者进行交互时,锚定效应下的量子决策模型可以考虑存在不确定性因素和非理性行为时进行加速或减速的决策,且相比于累积前景理论模型(CPT)更加贴合实际情况.     

一种红外多点触摸式双手交互技术

随着人机交互技术由以往的以计算机为中心向以用户为中心发展,新型交互方式成为近年来研究的热点.双手交互作为一种自然的人机交互形式,不但符合人的认知习惯和行为特征,而且能提高计算机输入的带宽.本文研究了一种红外多点触摸的定位技术,识别并描述了双手触摸式交互动作,并建立了双手触摸式交互模型,实验证明了这种交互技术比传统的鼠标操作更加自然直观,大大提高了人机交互的效率.     

基于道路环境上下文的行人跟踪方法

针对目前城市交通中人车混行场景中行人跟踪效果不佳的问题,提出了一种基于道路环境上下文的行人跟踪方法。首先通过对道路环境上下文进行分析,建立道路模型;其次在道路模型的约束下建立行人与环境的交互运动模型;最后利用该模型进行行人的跟踪。在真实场景中的实验表明使用了道路上下文信息的跟踪方法与连续离散连续能量最小化的多行人跟踪方法相比,多目标跟踪准确度从47.6%提升至63.2%,多目标跟踪精度从68.8%提升至74.3%。数值结果表明道路上下文信息对于提高人车混行场景中行人跟踪效果的有效性。     

基于时空图的行人轨迹预测

在蓬勃发展的自动驾驶技术中, 行人轨迹预测的结果往往会影响到自动驾驶的安全性. 行人轨迹预测技术目前面临着在实际场景中应用时与他人的交互问题, 需要在预测轨迹的同时考虑社会交互性与逻辑自洽. 因此, 提出了一种基于时空图的行人轨迹预测方法, 该方法采用图注意力网络对场景中的行人交互进行建模, 并使用一种自动生成正负样本的方法来通过对比学习降低输出轨迹的碰撞率, 达到了提高输出轨迹的安全性以及逻辑自洽的效果. 在ETH和UCY数据集上进行模型训练与测试, 结果分析表明, 本文提出的方法有效降低了碰撞率, 且预测准确度优于主流算法.     

智能用户界面的发展及趋势

智能用户界面是致力于改善人机交互的高效率、有效性和自然性的人机界面。它通过表达、推理，并按照用户模型、领域模型、任务模型、谈话模型和媒体模型来实现人机交互。本文首先介绍了人机交互的基本内容，然后从用户和用户需求的多样化以及技术的变化为线索介绍了智能用户界面的发展，给出了智能用户界面的体系结构，总结了当前智能用户界面的主要研究课题。最后，简要介绍了智能用户界面当前的研究热点。未来的用户界面不仅能够通过认知因素来了解用户，也能够从非认知因素方面感知和理解用户。随着新的交互方式的出现和技术的更进一步发展，人们将很难区分当前进行的交互是人-机交互，还是人-人交互。     

无人物流车的车外屏人机界面设计研究

随着智能汽车和物流行业快速发展,产业结合促进了无人物流车的出现。为了提 高无人物流车的安全、效率和用户体验,对无人物流车的车外屏人机界面设计进行研究。首先 提出了基于无人物流车的人-车-环境关系理论,并且结合物流车的运行场景流程对车外屏人机 界面的设计需求进行了研究。在此基础上,对无人物流车的车外屏人机界面的信息架构、多通 道交互模式及界面设计进行了探讨和设计实践,并且对物品回收功能的初步原型设计进行了可 用性测试评估。测试结果显示初步的无人物流车车外屏交互原型逻辑流畅,可用性较高。调查 结果显示用户希望无人车定位准确,并且可以利用积分制来兑换物质奖励。研究表明车外屏人 机界面设计可以提高无人物流车的安全、效率和用户体验。对无人物流车的车外屏设计进行修 改和完善,并且经过测试迭代后,将会不断提升车外屏设计。     

AdvSce:面向自动驾驶系统的安全关键场景生成工具

AdvSce是一个面向自动驾驶系统的安全关键场景生成工具,能够在给定初始场景的基础上,以添加额外交通参与者的方式,生成挑战自动驾驶系统控制车辆(主车)安全性的扰动场景,用于自动驾驶系统的仿真测试.不同于既往研究中,首先确定场景参数空间,再使用黑盒优化算法生成安全关键场景的工具或方法, AdvSce可以基于对主车行为的分析,在场景生成过程中动态地构造能够挑战主车安全性的场景参数空间,从而实现高度自动化且高效的安全关键场景生成.我们使用AdvSce在LGSVL仿真器中生成了面向Apollo 7.0自动驾驶系统的测试场景.结果表明,相比现有的安全关键场景生成工具, AdvSce具有更高的安全问题场景生成效率.     

虚拟装配交互界面中的隐式交互算法研究

针对现有虚拟装配系统中交互是以设备为中心的显式交互,不能有效地感知用户操作意图,用户认知负担和操作负担较高的问题,为了提高虚拟装配系统的智能性,将隐式人机交互引入虚拟装配系统,提出一种基于场景任务的用户意图感知算法.首先建立场景知识模型和用户知识模型,并分别构建显式交互知识库和隐式交互知识库;然后利用专家系统推理用户显式操作意图和隐式操作意图,实现人手向目标位置平移时场景主动拉近和抓放场景物体时物体主动旋转2种情景下的人机相向互动.实验结果表明,该算法实现了人机协同交互,降低了用户的操作负担和认知负担.     

普适计算的人机交互框架研究

普适计算通过向用户提供透明的计算服务使其注意力回归到任务本身．它正在逐步发展成主流的计算模式．人机交互的效率和自然性是影响其发展的关键因素之一．文章从认知心理学的角度分析了用户在普适计算环境中的认知特征，论证了人类有限的认知是普适人机交互中的瓶颈，计算系统的交互模式必须适应用户的认知特征．据此提出了普适计算模式的Multimodal context-sensitive交互框架，对上下文信息和用户多通道主动输入信息进行无缝融合，作者将其在移动导游导航系统TGH中加以实现．用户评测结果初步证明该框架对于提高普适计算人机交互效率和自然性具有良好的效果。     

Investigating the Importance of Trust on Adopting an Autonomous Vehicle

The objective of this study is to examine the user’s adoption aspects of autonomous vehicle, as well as to investigate what factors drive people to trust an autonomous vehicle. A model explaining the impact of different factors on autonomous vehicles’ intention is developed based on the technology acceptance model and trust theory. A survey of 552 drivers was conducted and the results were analyzed using partial least squares. The results demonstrated that perceived usefulness and trust are major important determinants of intention to use autonomous vehicles. The results also show that three constructs—system transparency, technical competence, and situation management—have a positive effect on trust. The study identified that trust has a negative effect on perceived risk. Among the driving-related personality traits, locus of control has significant effects on behavioral intention, whereas sensation seeking did not. This study investigated that the developed model explains the factors that influence the acceptance of autonomous vehicle. The results of this study provide evidence on the importance of trust in the user’s acceptance of an autonomous vehicle.     

Research Issues in Smart Vehicles and Elderly Drivers: A Literature Review

This article reviewed both studies on general smart car technologies and human–computer interaction (HCI)/human–vehicle interaction studies that were published in journals and conferences so that the current status of research can be identified and future research directions can be suggested. Furthermore, previous studies on elderly drivers were reviewed, as these drivers could be the most vulnerable social group in terms of new technology acceptance. A total of 257 articles for HCI research and 45 articles for elderly drivers were selected and reviewed from 11,267 collected articles (2010–2014). According to the results, most articles were mainly related to safety and adaptive features (e.g., driver’s state recognition, vehicle surrounding monitoring, driver action-suggestion), and infotainment research in terms of HCI (e.g., information technology devices–vehicle interaction, vehicle–vehicle interaction) was relatively insufficient despite its high research demand. According to the results of the literature review and technological trends analysis based on previous technical road maps, from HCI/human factors engineering (HFE) perspectives, research related to “Assistance systems,” “Physiological & mental state recognition,” “Position sensor technology,” “Behavior recognition,” and “Infotainment” was suggested to HCI/HFE researchers for further research. In particular, HCI/HFE researchers need to focus on research on acceptable levels of automation, observing new driving behaviors, investigation of driver characteristics to develop personalized services, and new technology acceptance to develop and improve smart cars in the future.     

In Automatic We Trust: Investigating the Impact of Trust,Control, Personality Characteristics,and Extrinsic and Intrinsic Motivations on the Acceptance of Autonomous Vehicles

ABSTRACT

According to industry research, the automation of vehicles promises a revolution in traffic safety, mobility, and quality of life. However, the success of such vehicles depends on their acceptance. This study investigates the influence of trust in technology, concerns of giving up control, perceived usefulness, perceived ease of use, the personality factor innovativeness, and the enjoyment of driving a car on the a priori intention to adopt an autonomous vehicle. By means of an online survey with 369 German participants, our study shows that trust in the technology and the concern about handing over control to a machine go hand in hand as respondents’ cognitive and affective perception of this innovation. Moreover, perceived usefulness represents an influential factor, while the enjoyment of driving a car is a barrier to the technology’s acceptance. Innovators represent a promising target for campaigns, as they are more likely to adopt an autonomous vehicle.     

Modeling vehicle–pedestrian interactions outside of crosswalks

Pedestrian and driver behaviors as well as their interactions, are essential in planning, designing and operating highway facilities. Pedestrian crossing outside of a marked or unmarked crosswalk (i.e. jaywalking), is one of those pedestrian behaviors that may highly affect safety and operations. Unlike permissible crossings at crosswalks, jaywalking events are not often anticipated by drivers, which may result in less driver reaction time and different vehicle operation dynamics. It is important to understand pedestrian crossing behavior outside of crosswalks, as well as driver yielding behavior towards them. To date, limited quantitative and behavioral research has been conducted to investigate this interaction or simulate it microscopically. This paper aims to explore both pedestrian jaywalking behavior (gap acceptance and speeds) and the corresponding driver reactions (yielding behavior) for modeling the vehicle–pedestrian interactions (VPI) outside the crosswalks in a micro-simulation environment. The study also quantifies the differences between vehicle–jaywalker and vehicle-permissible crossing. An observational study and an instrumented vehicle study were conducted on the campus of the University of Florida to collect data from pedestrian and driver perspectives, respectively.Crossing speed, yield acceptance and delay of jaywalking crossings and permissible crossings were observed in the study and these attributed can be used for replicating pedestrian operations in simulators. Moreover, behaviors of driver approaching jaywalkers versus pedestrians crossing at designated crosswalks were compared on the basis of yield rates, and vehicle speed profiles. Vehicle yield dynamics were analyzed to model the driver reactions towards jaywalkers. Lastly, it was found that the locations of jaywalking events are highly concentrated and influenced by the crossing environment, such as pedestrian and vehicular volume, bus stops presence and crossing distance.This paper establishes several quantitative relationships describing interactions between pedestrians crossing outside of crosswalks and approaching drivers, which provide the basis and assumptions for modeling such interactions in a micro-simulation environment for traffic operational analyses.     

Vehicle–pedestrian interaction for mixed traffic simulation

Simulation of real‐world traffic scenarios is widely needed in virtual environments. Different from many previous works on simulating vehicles or pedestrians separately, our approach aims to capture the realistic process of vehicle–pedestrian interaction for mixed traffic simulation. We model a decision‐making process for their interaction based on a gap acceptance judging criterion and then design a novel environmental feedback mechanism for both vehicles' and pedestrians' behavior‐control models to drive their motions. We demonstrate that our proposed method can soundly model vehicle–pedestrian interaction behaviors in a realistic and efficient manner and is convenient to be plugged into various traffic simulation systems. Copyright © 2015 John Wiley & Sons, Ltd.     

An empirical study of the determinants of the intention to participate in user-created contents (UCC) services

Up to now UCC services have been dominating the majority of the internet traffic, yet the answers to what motivates people to participate in the UCC services still remain vague and unclear. It is the motivation to find these answers that lead to this study. We adopted technology acceptance model (TAM) to our model and examined the effects of external variables—social identity, telepresence, altruism, perceived playfulness and social trust. Data was collected from undergraduate students in Jeonju University, South Korea, who had experience in UCC. The findings showed that social trust and perceived playfulness play a pivotal role in explaining the individual’s behavioral intention to participate in UCC services. Also, perceived encouragement was found to have significant influence on social trust instead of its direct effect on the intention to participate in UCC services. Additionally, social identity and telepresence were the most important factors of perceived encouragement. This implication can help both researchers and Web practitioners to better understand user behavior in UCC context.     

Vibration analysis of footbridges due to vertical human loads

Pedestrian footbridges have been constructed with increasingly daring structures encompassing the experience and knowledge of structural designers by using newly developed materials and technologies. This fact has generated very slender structural footbridges and, consequently, changed their associated serviceability and ultimate limit states. A direct consequence of this design trend was a considerable increase of structural vibration problems. In the particular case of pedestrian footbridges this phenomenon occurs when the structural fundamental frequency is near the load excitation frequencies, or higher frequencies multiples. This was the main motivation for the development of a design methodology to better evaluate the footbridge user’s comfort and safety. Considering all these aspects a linear elastic finite element analysis contemplating the dynamical response of pedestrian footbridges focusing on critical acceleration values was conducted. The investigated model was based on an existing footbridge located at the city of Rio de Janeiro, Brazil. Four different loading models were developed to incorporate the dynamical effects, induced by people walking, in the dynamical response of pedestrian footbridges. The results indicated that this footbridge can reach high vibration levels hat could compromise the user’s comfort limit state.     

Factors affecting engineers’ acceptance of asynchronous e-learning systems in high-tech companies

With the rapid change in all types of working environment, there is a need to implement electronic learning (e-learning) systems to train people in new technologies, products, and services. However, the large investment in e-learning has made user acceptance an increasingly critical issue for technology implementation and management. Although user acceptance received fairly extensive attention in prior research, efforts were needed to examine or validate previous results, especially in different technologies, user populations, and/or organizational contexts. We therefore proposed a new construct, perceived credibility, to examine the applicability of the technology acceptance model (TAM) in explaining engineers’ decisions to accept e-learning, and address a pragmatic technology management issue. Based on a sample of 140 engineers taken from six international companies, the results strongly support the extended TAM in predicting engineers’ intention to use e-learning.     

Age differences in the perception of social presence in the use of 3D virtual world for social interaction

3D virtual worlds are becoming increasingly popular as tool for social interaction, with the potential of augmenting the user’s perception of physical and social presence. Thus, this technology could be of great benefit to older people, providing home-bound older users with access to social, educational and recreational resources. However, so far there have been few studies looking into how older people engage with virtual worlds, as most research in this area focuses on younger users. In this study, an online experiment was conducted with 30 older and 30 younger users to investigate age differences in the perception of presence in the use of virtual worlds for social interaction. Overall, we found that factors such as navigation and prior experience with text messaging tools played a key role in older people’s perception of presence. Both physical and social presence was found to be linked to the quality of social interaction for users of both age groups. In addition, older people displayed proxemic behavior which was more similar to proxemic behavior in the physical world when compared to younger users.