Context-sensitive distraction warnings – Effects on drivers׳ visual behavior and acceptance

In this study, we investigated the effects of context-sensitive distraction warnings on drivers׳ in-car glance behaviors and acceptance. The studied prototype warning application functions on a smart phone. The novelty of the application is its proactive and context-sensitive approach to the adjustment of warning thresholds according to the estimated visual demands of the driving situation ahead. In our study, novice and experienced drivers conducted in-car tasks with a smart phone on a test track with and without the warnings. The application gave a warning if the driver׳s gaze was recognized to remain on the smart phone over a situation-specific threshold time, or if the driver was approaching a high-demand part of the track (an intersection or a tight curve). Glance metrics indicated a significant increasing effect of the warnings on glance time on road while multitasking. The effect varied between 5% and 30% increase depending on the in-car task. A text message reading task was the most visually demanding activity and indicated the greatest effect of the warnings on glance time on road. Driving experience did not have an effect on the efficiency of the warnings. The proposed gaze tracking with current smart phone technology proved to be highly unreliable in varying lighting conditions. However, the findings suggest that location-based proactive distraction warnings of high-demanding driving situations ahead could help all drivers in overcoming the inability to evaluate situational demands while interacting with complex in-car tasks and to place more attention on the road. Furthermore, survey results indicate that it is possible to achieve high levels of trust, perceived usefulness, and acceptance with these kinds of context-sensitive distraction warnings for drivers.     

Utilization of Visual Information Perception Characteristics to Improve Classification Accuracy of Driver’s Visual Search Intention for Intelligent Vehicle

Understanding and predicting a driver’s behaviors in a vehicle is a prospective function embedded in a smart car. Beyond the patterns of observable behaviors, driver’s intention could be identified based on goal-driven behaviors. A computational model to classify driver intention in visual search which is finding a target with one’s eyes as moving selective attention across a search field, could improve the level of intelligence that a smart car could demonstrate. To develop a computational cognitive that explains the underlying cognitive process and reproduces drivers’ behaviors, particular parameters in human cognitive process should be specified. In this study, 2 issues are considered as influential factors on a driver’s eye movements: a driver’s visual information processing characteristics (VIPCs) and the purpose of visual search. To assess an individual’s VIPC, 4 psychological experiments—Donders’s reaction time, mental rotation, signal detection, and Stroop experiments—were utilized. Upon applying k-means clustering method, 114 drivers were divided into 9 driver groups. To investigate the influence of task goal on a driver’s eye movement, driving simulation was conducted to collect a driver’s eye movement data under the given purpose of visual search (perceptual and cognitive tasks). The empirical data showed that there were significant differences in a driver’s oculomotor behavior, such as response time, average fixation time, and average glance duration between the driver groups and the purposes of visual search. The effectiveness of using VIPC for grouping drivers was tested with task goal classification model by comparing the models’ performance when drivers were grouped by typical demographic data such as gender. Results show that grouping based on VIPC improves accuracy and stability of prediction of the model on a driver’s intention underlying visual search behaviors. This study would benefit future studies focusing on personalization and adaptive interfaces in the development of smart car.     

A collaborative multi-agent message transmission mechanism in intelligent transportation system – A smart freeway example

Although drivers obtain road information through radio broadcasting or specific in-car equipment, there is still a wide gap between the synchronization of information and the actual conditions on the road. In the absence of adequate information, drivers often react to conditions with inefficient behaviors that do not contribute to their own driving goals, but increase traffic complication. Therefore, this study applies the features of information exchanged between “Multi-Agents” and mutual communication and collaboration mechanisms to intelligent transportation systems (ITS). If drivers could achieve distributed communication, share their driving information, and submit their own reasoned driving advice to others, many traffic situations will improve effectively. Additionally, the efficiency of the computing processes could have improved through distributed communication. At the same time, this paper proposes an architecture design, including vehicle components, OBU (On-Board Unit) devices and roadside device components (Roadside Unit) with hybrid architecture, which is intended to establish intelligent diversified road services to provide information support and applications.     

Multisensory in-car warning signals for collision avoidance

OBJECTIVE: A driving simulator study was conducted in order to assess the relative utility of unimodal auditory, unimodal vibrotactile, and combined audiotactile (i.e., multisensory) in-car warning signals to alert and inform drivers of likely front-to-rear-end collision events in a situation modeled on real-world driving. BACKGROUND: The implementation of nonvisual in-car warning signals may have important safety implications in lessening any visual overload during driving. Multisensory integration can provide synergistic facilitation effects. METHOD: The participants drove along a rural road in a car-following scenario in either the presence or absence of a radio program in the background. The brake light signals of the lead vehicle were also unpredictably either enabled or disabled on a trial-by-trial basis. RESULTS: The results showed that the participants initiated their braking responses significantly more rapidly following the presentation of audiotactile warning signals than following the presentation of either unimodal auditory or unimodal vibrotactile warning signals. CONCLUSION: Multisensory warning signals offer a particularly effective means of capturing driver attention in demanding situations such as driving. APPLICATION: The potential value of such multisensory in-car warning signals is explained with reference to recent cognitive neuroscience research.     

Use of the Backseat Driving Technique in Evaluation of a Perceptually Optimized In-Car Navigation Display

Recently drivers have greatly benefited from new vehicular technologies such as in-car navigation systems, but at the same time they can be easily distracted from those technologies. Consequently, creating displays that balance the communication of information with the attentional demand imposed on the driver is of increasing importance. A set of research has been conducted to minimize the driver’s attentional cost toward the navigational displays while driving. However, accurate evaluation methods to assess the effects of these displays in realistic environments are not yet available. This article introduces the backseat driving technique for high-fidelity, safe, and inexpensive evaluation of interaction with in-car displays. This technique makes use of a real vehicle driving on a real road. As a result it allows for the exploration of some types of research questions using audio, visual, and kinesthetic stimulus at least equal in fidelity to very high-end driving simulators, without requiring such a specialized and expensive facility. Further, it allows for the employment of detailed and fine-grained measures of attentional demand, which cannot be safely used with subjects who are actually driving. Although the backseat driving technique can address only some types of questions and so is not a full replacement for high-realism driving simulators, it may offer a new approach, which augments laboratory, simulator, and real driving for many studies. As a part of the work presented here, the backseat driving technique is used to evaluate a previously developed in-car navigation display—the MOVE system. The technique allowed for new questions to be asked, which were not able to be considered in previous laboratory studies, and for the use of study measures that were only previously able to be used in the laboratory due to driving safety concerns. Specifically, the display was shown to work well when real-world stimulus are used to navigate along a real route, reducing the navigation error rate nearly threefold, and up to sixfold when compared to displays providing more or less contextual information. In addition the display was shown to cut total display fixation time (which is time spent looking away from the road) almost in half in both cases.     

The design of next generation in-vehicle navigation systems for the older driver

It has been proposed that the current design of in-vehicle displays may not be appropriate for the older driver. This paper describes an empirical, road-based investigation of the benefits to older and younger drivers of providing landmarks within the instructions presented by an in-vehicle navigation system. Thirty two participants navigated a challenging urban route using either landmarks or distance information to identify the location of forthcoming manoeuvres. A range of driver behaviour measures were collected, including visual glance data, driving errors, driver workload, navigation errors, navigation confidence, and pre and post-trial driver attitudinal responses. Results show that, for older and younger drivers, landmarks reduced the time spent glancing to a visual display, reduced navigation and driving errors, and influenced driver confidence. There were some key differences between the older and younger drivers. The wider implications for the design of in-car interfaces for the older driver are discussed.     

Perceptual processes used by drivers during overtaking in a driving simulator

This study investigated the control strategies and decision making of drivers who were executing overtaking maneuvers in a fixed-base driving simulator. It was found that drivers were frequently inaccurate in deciding whether it was safe to overtake in front of an oncoming vehicle. One source of error in this situation was the control strategy adopted by the driver; in several instances our drivers initiated an overtaking maneuver when the oncoming car's distance was above a critical value, even though there was not sufficient time to complete a safe maneuver. Adaptation to closing speed (produced by driving on a straight open road) also had large effects on overtaking behavior. For all participants, closing speed adaptation resulted in decisions that were delayed, of higher risk, and more variable. Actual or potential applications of this research include improved training for younger drivers and the development of in-car interfaces that reduce closing speed adaptation.     

Spatial frequency-specific visual adaptation may cause paradoxical transient improvements in visual acuity: computer simulation and confirmatory experiments

In the visual cortex of monkeys and humans, several types of processing are conducted, such as orientation-selective edge detection. It was also reported by Campbell and associates that the cerebral visual cortex conducts processing consisting of spatial-frequency-and-orientation-specific multiple narrow-band channels. It has also been reported that spatial-frequency-and-orientation-specific visual stimuli cause adaptations in the corresponding channels, resulting in reductions of the visual sensitivity around some frequency ranges. In the course of simulation studies using Landolt rings to measure visual acuity, we found that spatial-frequency-specific adaptations would cause paradoxical transient improvements in visual acuity. We therefore conducted perceptual experiments to see if these improvements in visual acuity take place after spatial-frequency-specific visual adaptation, with positive results. These findings may be significant in designing road information boards for car drivers, because such an adaptation often occurs while driving a car. This work was presented in part at the Sixth International Symposium on Artificial Life and Robotics, Tokyo, January 15–17, 2001     

In-car usage-based insurance feedback strategies. A comparative driving simulator study

Usage-Based Insurances (UBI) enable policyholders to actively reduce the impact of vehicle insurance costs by adopting a safer and more eco-friendly driving style. UBI is especially relevant for younger drivers, who are a high-risk population. The effectiveness of UBI should be enhanced by providing in-car feedback optimised for individual drivers. Thirty young novice drivers were therefore invited to complete six experimental drives with an in-car interface that provided real-time information on rewards gained, their driving behaviour and the speed limit. Reward size was either displayed directly in euro, indirectly as a relatively large amount of credits, or as a percentage of the maximum available bonus. Also, interfaces were investigated that provided partial information to reduce the potential for driver distraction. Compared to a control no-UBI condition, behaviour improved similarly across interfaces, suggesting that interface personalisation after an initial familiarisation period could be feasible without compromising feedback effectiveness.

Practitioner Summary: User experiences and effects on driving behaviour of six in-car interfaces were compared. The interface provided information on driving behaviour and rewards in a UBI setting. Results suggest that some personalisation of interfaces may be an option after an initial familiarisation period as driving behaviour improved similarly across interfaces.     

基于VR的驾驶仿真及安全教育系统开发

针对全国道路交通事故高发现状及传统驾驶安全教育方式单一、培训效果差的缺点,基于虚拟现实技术（VR）,在引发交通事故人为因素理论基础上,开发驾驶仿真及安全教育系统。系统基于Unity3D引擎,构建了基于道路实景数据的虚拟场景,并联合SUMO实现了道路交通流仿真,通过VR技术仿真驾驶环境及驾驶行为;基于碰撞检测原理,建立了关卡违规触发机制,编码自定义屏幕空间渲染方式模拟驾驶员视觉效果,并构建了基于图像的交通事故现场三维全景,从认知、感知层面培训驾驶员安全驾驶。实用性测试结果表明,系统实现了不同道路场景、气象条件与交通状况下的驾驶模拟及安全培训,增强了使用者的学习兴趣,提高了使用者驾驶安全素养,具有较强的实用性。     

Drivers’ Performance Examination using a Personalized Adaptive Curve Speed Warning: Driving Simulator Study

ABSTRACT

A great number of traffic accidents occur during curve negotiation maneuvers. Most of these accidents could be avoided if drivers are provided with information that better guide them through the maneuver. Advanced Driver Assistance Systems (ADAS) such as Curve Speed Warning (CSW) have shown to be effective to improve safety on curve maneuvers by warning drivers of the speed required to make a safe curve maneuver. The effectiveness of such warning systems can potentially improve if the warnings are not only adapted to road and traffic condition but also adapted to individual drivers’ behavior. In this study, an Adaptive Curve Speed Warning (ACSW) system is developed that presents drivers a two-level visual and audio warning considering the variation in individual drivers’ perception-reaction time (PRT). The warning timing is adjusted according to a reward/punishment function to reinforce safer actions while providing an individualized in-time warning. Next, within a driving simulator environment, drivers’ performance using ACSW is compared to a CSW that does not consider PRT variation among drivers. Further, variation in drivers’ performance on curve maneuvers is discussed with respect to drivers’ approaching speed, variation in PRT, and braking behavior. Results show that drivers’ interaction with warning systems varies significantly based on their age and gender. In addition, results show how drivers approaching speed to a curve varies significantly based on road characteristics such as curve advisory speed and curve direction. Results from this study contribute to the development of more intelligent ADAS that could improve drivers’ comfort and safety.     

Hybrid-augmented intelligence: collaboration and cognition

The long-term goal of artificial intelligence (AI) is to make machines learn and think like human beings. Due to the high levels of uncertainty and vulnerability in human life and the open-ended nature of problems that humans are facing, no matter how intelligent machines are, they are unable to completely replace humans. Therefore, it is necessary to introduce human cognitive capabilities or human-like cognitive models into AI systems to develop a new form of AI, that is, hybrid-augmented intelligence. This form of AI or machine intelligence is a feasible and important developing model. Hybrid-augmented intelligence can be divided into two basic models: one is human-in-the-loop augmented intelligence with human-computer collaboration, and the other is cognitive computing based augmented intelligence, in which a cognitive model is embedded in the machine learning system. This survey describes a basic framework for human-computer collaborative hybrid-augmented intelligence, and the basic elements of hybrid-augmented intelligence based on cognitive computing. These elements include intuitive reasoning, causal models, evolution of memory and knowledge, especially the role and basic principles of intuitive reasoning for complex problem solving, and the cognitive learning framework for visual scene understanding based on memory and reasoning. Several typical applications of hybrid-augmented intelligence in related fields are given.     

An analysis of 'looked but failed to see' accidents involving parked police vehicles

Drivers who collide with a vehicle that is parked on the hard shoulder of a motorway or dual-carriageway sometimes claim not to have seen it before the collision. Previous research into vehicle conspicuity has taken such ‘looked but failed to see’ claims at face value, and concentrated on attempting to remedy the problem by making vehicles more conspicuous in sensory terms. However, the present study describes investigations into accidents of this kind which have involved stationary police cars, vehicles which are objectively highly conspicuous. Two laboratory studies showed that experienced drivers viewing a film of dual-carriageway driving were slower to respond to a parked police car as a ‘hazard’ if it was parked directly in the direction of travel than if it was parked at an angle; this effect was more pronounced when the driver's attention was distracted with a secondary reasoning task. Taken together with the accident reports, these results suggest that ‘looked but failed to see’ accidents may arise not because the parked vehicle is difficult to see, but for more cognitive reasons, such as vigilance failure, or possession by the driver of a ‘false hypothesis’ about the road conditions ahead. An emergency vehicle parked in the direction of travel, with only its blue lights flashing, may encourage drivers to believe that the vehicle is moving rather than stationary. Parking at an angle in the road, and avoiding the use of blue lights alone while parked, are two steps that drivers of parked emergency vehicles should consider taking in order to alert approaching drivers to the fact that a stationary vehicle is ahead.     

Immersive stereo displays,intuitive reasoning,and cognitive engineering

Abstract— Stereoscopic displays have generated great interest in the display community in recent years. Despite this interest, there can be a problem with their use when such displays contain high‐level cue conflict, which refers to multiple cues conveying different depths to a viewer, creating “eye” strain and discomfort. It can be argued that the basis for this discomfort is to be found in the mental processes of human reasoning. Specifically, immersive stereo displays that depict real‐world scenes primarily engage an intuitive reasoning system, which attempts (and fails) to make reasoned sense out of conflicting perceptual information. Because not all displays have the potential to create this problem, it is proposed that information displays be subdivided into two types: analytical reasoning‐inducing displays and intuitive reasoning‐inducing displays. All information displays, even stereo displays, involve issues of cognitive engineering.     

Towards human-like and transhuman perception in AI 2.0: a review

Perception is the interaction interface between an intelligent system and the real world. Without sophisticated and flexible perceptual capabilities, it is impossible to create advanced artificial intelligence (AI) systems. For the next-generation AI, called ‘AI 2.0’, one of the most significant features will be that AI is empowered with intelligent perceptual capabilities, which can simulate human brain’s mechanisms and are likely to surpass human brain in terms of performance. In this paper, we briefly review the state-of-the-art advances across different areas of perception, including visual perception, auditory perception, speech perception, and perceptual information processing and learning engines. On this basis, we envision several R&D trends in intelligent perception for the forthcoming era of AI 2.0, including: (1) human-like and transhuman active vision; (2) auditory perception and computation in an actual auditory setting; (3) speech perception and computation in a natural interaction setting; (4) autonomous learning of perceptual information; (5) large-scale perceptual information processing and learning platforms; and (6) urban omnidirectional intelligent perception and reasoning engines. We believe these research directions should be highlighted in the future plans for AI 2.0.     

视觉知识：跨媒体智能进化的新支点

回顾跨媒体智能的发展历程,分析跨媒体智能的新趋势与现实瓶颈,展望跨媒体智能的未来前景。跨媒体智能旨在融合多来源、多模态数据,并试图利用不同媒体数据间的关系进行高层次语义理解与逻辑推理。现有跨媒体算法主要遵循了单媒体表达到多媒体融合的范式,其中特征学习与逻辑推理两个过程相对割裂,无法综合多源多层次的语义信息以获得统一特征,阻碍了推理和学习过程的相互促进和修正。这类范式缺乏显式知识积累与多级结构理解的过程,同时限制了模型可信度与鲁棒性。在这样的背景下,本文转向一种新的智能表达方式——视觉知识。以视觉知识驱动的跨媒体智能具有多层次建模和知识推理的特点,并易于进行视觉操作与重建。本文介绍了视觉知识的3个基本要素,即视觉概念、视觉关系和视觉推理,并对每个要素展开详细讨论与分析。视觉知识有助于实现数据与知识驱动的统一框架,学习可归因可溯源的结构化表达,推动跨媒体知识关联与智能推理。视觉知识具有强大的知识抽象表达能力和多重知识互补能力,为跨媒体智能进化提供了新的有力支点。     

因果知识的表示和推理

本文介绍了因果推理的两个主要应用：预测行为的间接结果，找出给定事实的真正原因，指出了用逻辑描述的因果关系在解决这两个问题中存在的不足。本文也简单地介绍了J．Pearl提出的因果推理方法，该方法的基本思想是把因果推理看成是一种“计算模式”，而这种把智能归结为“计算模式”的想法正是认知科学中的核心思想。本文最后比较了基于逻辑的方法和基于认知科学的方法实现智能的区别，指出了因果推理应该在认知科学的框架内得到解决。     

In-car speed estimations with real,virtual, and no view

Car handling, and hence, safety, is affected by the way we estimate speed. Speed, however, is often underestimated in degraded visual environments, including virtual environments such as driving simulators. In simulators the visual and physical motion are typically incongruent as limited by quality and amplitude, respectively, which may cause a negative transfer of training. To improve the (training) quality of simulators and make them feel more real, it would be helpful to fill a knowledge gap on in-car speed perception as affected by real and virtual views, within a single group of subjects. We did so by testing whether estimations of speed in terms of km/h could be a valid metric for that purpose.We therefore exposed 17 subjects, seated as passengers in the front of a car on a straight road to four experimental conditions: (1) driving with a real out-the-window view, (2) driving with a live video view, (3) standing still watching pre-recorded video's, and (4) driving with eyes closed. Field-of-view was made equal in all conditions. Speeds tested ranged between 20 and 60 km/h.On average, speed was estimated 5 km/h less than actual, while we did not find a statistically significant difference between the four conditions tested.These results seem to contradict previous observations on motion perception, in particular in simulators, that have been ascribed to the quality of the visuals used. This finding may yet be explained by the assumption that speed estimations in terms of km/h are dominated by (conscious) cognitive processes, while visual-vestibular coherence between visual and physical motion, is dominated by (unconscious) sensorial driven perceptual processes. This disqualifies perceived speed as a valid metric for studying motion perception related to the optimisation of simulators.     

Evaluation of in-vehicle HMI using occlusion techniques: experimental results and practical implications

Despite the usefulness of new on-board information systems one has to be concerned about the potential distraction effects that they impose on the driver. Therefore, methods and procedures are necessary to assess the visual demand that is connected to the usage of an on-board system. The occlusion-method is considered a strong candidate as a procedure for evaluating display designs with regard to their visual demand. This paper reports results from two experimental studies conducted to further evaluate this method. In the first study, performance in using an in-car navigation system was measured under three conditions: static (parking lot), occlusion (shutter glasses), and driving. The results show that the occlusion-procedure can be used to simulate visual requirements of real traffic conditions. In a second study the occlusion method was compared to a global evaluation criterion based on the total task time. It can be demonstrated that the occlusion method can identify tasks which meet this criterion, but are yet irresolvable under driving conditions. It is concluded that the occlusion technique seems to be a reliable and valid method for evaluating visual and dialogue aspects of in-car information systems.     

Drivers’ willingness to drive in old age: a case study on young and mid-aged drivers in China

Previous studies on driving have found connections among age, gender, perceived driving ability, self-regulatory behavior and driving intentions. However, young and mid-aged drivers’ willingness to drive in old age has not been examined in prior studies. The aim of the present study was to gain a better understanding of Chinese drivers’ willingness to drive in old age as well as the influence of predictors of this willingness. A sample of 334 participants (aged 20–62 years) completed the perceived driving abilities scale, the driving willingness scale and scales of driving behavior and general information. A multivariate logistic model was used to explore the factors that changed individuals’ willingness to drive in old age. The results indicated that drivers’ willingness to drive in old age was significantly correlated with age, current driving experience and perceived driving ability in the future. With respect to drivers’ perceived driving abilities, visual acuity and executive skills were important predictors of drivers’ willingness to drive in old age. In addition, both subjective attitudes and objective attitudes significantly impaired drivers’ willingness. Conversely, we found that drivers’ willingness to drive increased with restrictive measures. These findings extend our understanding of how attitudes and awareness can influence drivers’ willingness to drive in old age. Although drivers’ current willingness may subsequently change, the findings are valuable for the study of the driving behavior of older drivers in China.