An online hazard perception training course reduces heavy braking,speeding, and over-revving rates during everyday driving

In essence, driver training involves learning the skills required to drive safely and avoid dangerous events. However, in traditional on-road driver instruction, drivers virtually never accrue experience of the most significant types of events that they are learning to avoid: crashes. One means of providing this experience safely is to present novice drivers with video clips of real crashes, as part of structured learning exercises. A six-week automated online hazard perception training course for drivers, incorporating evidence-based training methods and over a hundred crash clips, was previously found to improve novice drivers’ hazard perception skill, which is known to be an important attribute for avoiding crashes. However, since hazard perception was measured using computer-based methods, the possibility remained that the training effect might not transfer to actual driving. We report a randomized control trial in which novice drivers were recruited to assess everyday driving behaviour objectively, using g-force triggered dashcams and GPS trackers installed in their vehicles. On-road data were collected for a one-month baseline period, and for a further two months after half of the sample completed the hazard perception training course. Drivers who completed the course significantly reduced their rate of heavy-braking events, their speeding behaviour, and their rate of over-revving events. These findings support the proposal that a relatively inexpensive and highly scalable hazard perception training intervention can improve on-road driving behaviour, with the clear potential to impact real-world driver safety.     

How to identify the take-over criticality in conditionally automated driving? An examination using drivers’ physiological parameters and situational factors

Autonomous vehicles and advanced driver assistance technology are growing exponentially, and vehicles equipped with conditional automation, which has features like Traffic Jam Pilot and Highway Assist, are already available in the market. And this could expose the driver to a stressful driving condition during the takeover mission. To identify stressful takeover situations and better interact with automated systems, the relationship and effect between drivers’ physiological responses, situational factors (e.g., takeover request [TOR] lead time, takeover frequencies, and scenario types), and takeover criticality were investigated.34 participants were involved in a series of takeover events in a simulated driving environment, which are varied by different TOR lead time conditions and driving scenes. The situational factors, drivers’ skin conductance (SC), heart rate (HR), gaze behaviors, and takeover criticality ratings were collected and analyzed. The results indicated that drivers had a higher takeover criticality rating when they experienced a shorter TOR lead time level or at first to fourth take-overs. Besides, drivers who encountered a dynamic obstacle reported higher takeover criticality ratings when they were at the same Time to collision (TTC). We also observed that the takeover situations of higher criticality have larger driver’s maximum HR, mean pupil size, and maximum change in the SC (relative to the initial value of a takeover stage). Those findings of situational factors and physiological responses can provide additional support for the designing of adaptive alert systems and environmental soothing technology in conditionally automated driving, which will improve the takeover performances and drivers’ experience.     

Automatic question generation and answer assessment for subjective examination

Automatic generation of questions and evaluating their answers is a highly challenging task in natural language processing and educational technology. This work focuses on generating subjective questions and also an evaluation system is suggested for assessing the answers. For generating the questionnaires, key-phrases are extracted from the course curriculum (syllabus). Next, based on the key-phrases, different types of subjective questions are generated. Finally, the evaluation of student’s responses is achieved using a multi-criteria-decision-making approach. It uses a set of model answers taken from different textbooks and subject experts to evaluate the answers. Multiple measures are used to assess the answers by comparing them with this model set. The results of the profound system reveal that the automated appraisal process can reduce the manual effort of the human.     

Towards autonomous artificial agents with an active self: Modeling sense of control in situated action

In this paper we present a computational modeling account of an active self in artificial agents. In particular we focus on how an agent can be equipped with a sense of control and how it arises in autonomous situated action and, in turn, influences action control. We argue that this requires laying out an embodied cognitive model that combines bottom-up processes (sensorimotor learning and fine-grained adaptation of control) with top-down processes (cognitive processes for strategy selection and decision-making). We present such a conceptual computational architecture based on principles of predictive processing and free energy minimization. Using this general model, we describe how a sense of control can form across the levels of a control hierarchy and how this can support action control in an unpredictable environment. We present an implementation of this model as well as first evaluations in a simulated task scenario, in which an autonomous agent has to cope with un-/predictable situations and experiences corresponding sense of control. We explore different model parameter settings that lead to different ways of combining low-level and high-level action control. The results show the importance of appropriately weighting information in situations where the need for low/high-level action control varies and they demonstrate how the sense of control can facilitate this.     

Driving around bends with or without shoulders: The influence of bend direction

Paved shoulders have long been used to create “forgiving” roads where drivers can maintain control of their vehicles even when as they drift out of the lane. While the safety benefits of shoulders have been well documented, their effects on driver behavior around curves have scarcely been examined. The purpose of this paper is to fill this gap by assessing whether the addition of shoulders affects driver behavior differently as a function of bend direction. Driver behavior in a driving simulator was analyzed on left and right curves of two-lane rural roads in the presence and absence of 0.75-m and 1.25-m shoulders. The results demonstrated significant changes in drivers’ lateral control when shoulders were provided. In the absence of oncoming traffic, the shoulders caused participants to deviate more toward the inner lane edge at curve entry, at the apex and at the innermost position on right bends but not left ones. In the presence of oncoming traffic, this also occurred at the apex and the innermost position, leading participants to spend more time off the lane on right curves. Participants did not slow down in either traffic condition to compensate for steering farther inside, thereby increasing the risk of lane departure on right curves equipped with shoulders. These findings highlight the direction-specific influence of shoulders on a driver’s steering control when driving around bends. They provide arguments supporting the idea that drivers view paved shoulders as a new field of safe travel on right curves. Recommendations are made to encourage drivers to keep their vehicle within the lane on right bends and to prevent potential interference with cyclists when a shoulder is present.     

视觉观点采择需要抑制控制的参与：一项负启动研究

从抑制控制模型出发,采用负启动范式考察视觉观点采择的认知机制。实验1采用自身体转换任务(N=35) 、实验2采用圆点数量判断任务(N=33)分别考察成人在完成二级和一级视觉观点采择任务时是否需要抑制控制的参与。结果发现,成人在完成两类视觉观点采择任务时均出现了负启动效应,说明当他人观点和自我观点不一致时,个体需要抑制自我的观点才能成功采择他人的观点。     

负性情绪在冲突适应中的作用机制：分离与整合视角

负性情绪如何影响冲突适应一直以来受到领域内研究者们的广泛关注。根据负性情绪产生的源头(冲突外部操纵vs.冲突内部固有), 对于该问题的论述可以分别从认知与情绪的分离与整合视角展开。分离视角下, 操纵于冲突之外的负性情绪(外部负性情绪)独立于冲突加工过程, 通过情绪加工系统或个体自身的动机/唤醒水平影响冲突适应。近些年来的研究发现冲突加工自动产生负性情绪(固有负性情绪), 寓示着认知冲突与负性情绪间的内在关联, 固有负性情绪因此可被视作诱发冲突适应的另一个有效来源。整合视角下, 操纵于冲突内部的(固有)负性情绪高度整合于冲突加工过程, 其功能与冲突信息类似, 通过内在地促进目标导向行为直接诱发冲突适应。对这一主题的论述加深了我们对负性情绪如何作用于冲突适应过程的理解, 也为探索认知与情绪系统的整合过程及作用机制提供了一个全新的视角, 在此基础上, 我们也提出一些未来可行的研究方向。     

Children’s effortful control and academic achievement: do relational peer victimization and classroom participation operate as mediators?

Given that early academic achievement is related to numerous developmental outcomes, understanding processes that promote early success in school is important. This study was designed to clarify how students’ (N = 291; M age in fall of kindergarten = 5.66 years, SD = 0.39 year) effortful control, relational peer victimization, and classroom participation relate to achievement, as students progress from kindergarten to first grade. Effortful control and achievement were assessed in kindergarten, classroom participation and relational peer victimization were assessed in the fall of first grade, and achievement was reassessed in the spring of first grade. Classroom participation, but not relational peer victimization, mediated relations between effortful control and first grade standardized and teacher-rated achievement, controlling for kindergarten achievement. Findings suggest that aspects of classroom participation, such as the ability to work independently, may be useful targets of intervention for enhancing academic achievement in young children.