武汉理工大学毕业论文（设计）
外文翻译
学院（系）： 汽车工程学院
专业班级： 汽服1601
学生姓名： 许 琮 辉
指导老师： 李 江 天
原文
“Driver Take Over”: A preliminary exploration of driver trust and performance in autonomous vehicles
Michelle Hester, Kevin Lee, and Brian P. Dyre
Abstract
Automated vehicles are becoming more prominent in research and development. These automated vehicles introduce issues that have been seen in other autonomous systems such as decreases in situation awareness, complacency, and trust. Previous literature has looked at the effects of alerts and voice agents on driving performance. This preliminary study compares different in-car alerts (no alert, sound alert, task irrelevant voice alert, and task relevant voice alert) on trust and the driverrsquo;s ability to get back in-the-loop when the automation has failed. Participants were asked to monitor a simulated automated vehicle as it drove down a straight two-lane road. The main statistical results of our study show no difference in trust between the four different conditions; however, more participants avoided collision with a leading car in the task relevant voice condition in comparison to the three other conditions. These preliminary findings have important implications for the design of automated vehicles.
Advancements in automotive technology have reduced the amount of physical inputs and cognitive load for human drivers; some of these new advancements include vehicle backup cameras, adaptive cruise control, and automatic parking. Recently, the role of the driver has been reimagined as autonomous vehicles become more than just a science fiction concept with major companies investing heavily in their development. These vehicles receive feedback from the environment to make decisions in real time and do not need human passengers to give input to navigate. Automated vehicles are seen to be a benefit over manual automobiles as a way of promoting safety through the reduction of crashes caused by human error. Automated vehicles are also more accessible to different populations and reduce the high level demands necessary to complete a driving task. However, automated vehicles change the entire nature of the driving task for passengers. Human operators change from an active to passive role in heavily automated tasks. This role change presents new challenges for both drivers and designers of automated vehicles.
The primary driving task for a human passenger shifts from manual control of the car to a supervisory control of the automation (Strand, Nilsson, Karlsson, amp; Nilsson, 2014). Without active participation, drivers are no longer in-the-loop of the driving task and instead take on a passive role where they attend less to their environment and the control decisions implemented by the automated vehicle (Merat, Jamson, Lai, Daly, amp; Carsten, 2014). Without this situation awareness, drivers often cannot resume adequate control of the vehicle in emergency situations in which the automation fails (Weyer, Fink, amp; Adelt, 2015). The introduction of higher levels of automation into a task also increases the likelihood that drivers will engage in other activities unrelated to the primary driving task (Vollrath, Schleicher, amp; Gelau, 2011).
The lack of attention to monitoring the automated agent leads to a lack of understanding of what the automation was doing at the time of the failure. Human operators often find themselves surprised by these failures and unable to take the appropriate steps to remedy the problem. Situation awareness relates to the human operatorrsquo;s perception of their environment, comprehension of the environment and its elements, and the projections of future states (Endsley, 1995). Situation awareness can impact performance and decision making during complex tasks. Tasks involving human operator monitoring can also lead to complacency (Parasuraman amp; Manzey, 2010). Human operators will work less optimally which impacts their ability to detect automation failures. An important factor that plays into these misuses of automation is trust (Parasuraman, Sheridan, amp; Wickens, 2008). However, trust must be calibrated appropriately so that the human operator has the right amount of reliance on the automation.
Automated vehicles should be designed to be “hands and feet free” but not “mind-free” (Banks, Stanton, amp; Harvey, 2014). Automated vehicles must be designed to help keep the driver somewhat engaged to the driving task. One way of promoting driver safety and attention is the use of auditory interfaces to keep the driver engaged. Alarms in vehicles have been used in the past to convey messages to drivers. Alerts in current vehicles include proximity, door ajar, seatbelt, and headlight reminders. Automobiles have also begun using voice alerts to convey messages to the driver
Voices provide humans with social cues that often promote automatic responses (Large amp; Burnett, 2014). Studies have shown that humans respond to technology and computer voices similarly to how they would respond to other humans (Reevesamp; Nass, 1996). However, these social responses have a different role in the driving context as people assign personality to voices. These perceived personalities or emotions can have a positive or negative impact on driving performance depending on how well they match with the driver (Jonsson, Nass, Harris, amp; Takayama, 2005; Nass et al., 2005). Previous research has also shown that auditory systems in vehicles influence the driver. Aspects of auditory systems such as emotional state, perceived information quality, and anthropomorphism have been shown to have an effect on driving performance, trust, and blame (Takayama amp; Nass, 2008; Waytz, Heafner, amp; Epley, 2014). Feedback can be used to increase driver awareness and reduce crashes. The scale of the effect for feedback relies on t
剩余内容已隐藏，支付完成后下载完整资料
原文
“Driver Take Over”: A preliminary exploration of driver trust and performance in autonomous vehicles
Michelle Hester, Kevin Lee, and Brian P. Dyre
Abstract
Automated vehicles are becoming more prominent in research and development. These automated vehicles introduce issues that have been seen in other autonomous systems such as decreases in situation awareness, complacency, and trust. Previous literature has looked at the effects of alerts and voice agents on driving performance. This preliminary study compares different in-car alerts (no alert, sound alert, task irrelevant voice alert, and task relevant voice alert) on trust and the driverrsquo;s ability to get back in-the-loop when the automation has failed. Participants were asked to monitor a simulated automated vehicle as it drove down a straight two-lane road. The main statistical results of our study show no difference in trust between the four different conditions; however, more participants avoided collision with a leading car in the task relevant voice condition in comparison to the three other conditions. These preliminary findings have important implications for the design of automated vehicles.
Advancements in automotive technology have reduced the amount of physical inputs and cognitive load for human drivers; some of these new advancements include vehicle backup cameras, adaptive cruise control, and automatic parking. Recently, the role of the driver has been reimagined as autonomous vehicles become more than just a science fiction concept with major companies investing heavily in their development. These vehicles receive feedback from the environment to make decisions in real time and do not need human passengers to give input to navigate. Automated vehicles are seen to be a benefit over manual automobiles as a way of promoting safety through the reduction of crashes caused by human error. Automated vehicles are also more accessible to different populations and reduce the high level demands necessary to complete a driving task. However, automated vehicles change the entire nature of the driving task for passengers. Human operators change from an active to passive role in heavily automated tasks. This role change presents new challenges for both drivers and designers of automated vehicles.
The primary driving task for a human passenger shifts from manual control of the car to a supervisory control of the automation (Strand, Nilsson, Karlsson, amp; Nilsson, 2014). Without active participation, drivers are no longer in-the-loop of the driving task and instead take on a passive role where they attend less to their environment and the control decisions implemented by the automated vehicle (Merat, Jamson, Lai, Daly, amp; Carsten, 2014). Without this situation awareness, drivers often cannot resume adequate control of the vehicle in emergency situations in which the automation fails (Weyer, Fink, amp; Adelt, 2015). The introduction of higher levels of automation into a task also increases the likelihood that drivers will engage in other activities unrelated to the primary driving task (Vollrath, Schleicher, amp; Gelau, 2011).
The lack of attention to monitoring the automated agent leads to a lack of understanding of what the automation was doing at the time of the failure. Human operators often find themselves surprised by these failures and unable to take the appropriate steps to remedy the problem. Situation awareness relates to the human operatorrsquo;s perception of their environment, comprehension of the environment and its elements, and the projections of future states (Endsley, 1995). Situation awareness can impact performance and decision making during complex tasks. Tasks involving human operator monitoring can also lead to complacency (Parasuraman amp; Manzey, 2010). Human operators will work less optimally which impacts their ability to detect automation failures. An important factor that plays into these misuses of automation is trust (Parasuraman, Sheridan, amp; Wickens, 2008). However, trust must be calibrated appropriately so that the human operator has the right amount of reliance on the automation.
Automated vehicles should be designed to be “hands and feet free” but not “mind-free” (Banks, Stanton, amp; Harvey, 2014). Automated vehicles must be designed to help keep the driver somewhat engaged to the driving task. One way of promoting driver safety and attention is the use of auditory interfaces to keep the driver engaged. Alarms in vehicles have been used in the past to convey messages to drivers. Alerts in current vehicles include proximity, door ajar, seatbelt, and headlight reminders. Automobiles have also begun using voice alerts to convey messages to the driver
Voices provide humans with social cues that often promote automatic responses (Large amp; Burnett, 2014). Studies have shown that humans respond to technology and computer voices similarly to how they would respond to other humans (Reevesamp; Nass, 1996). However, these social responses have a different role in the driving context as people assign personality to voices. These perceived personalities or emotions can have a positive or negative impact on driving performance depending on how well they match with the driver (Jonsson, Nass, Harris, amp; Takayama, 2005; Nass et al., 2005). Previous research has also shown that auditory systems in vehicles influence the driver. Aspects of auditory systems such as emotional state, perceived information quality, and anthropomorphism have been shown to have an effect on driving performance, trust, and blame (Takayama amp; Nass, 2008; Waytz, Heafner, amp; Epley, 2014). Feedback can be used to increase driver awareness and reduce crashes. The scale of the effect for feedback relies on t
剩余内容已隐藏，支付完成后下载完整资料
资料编号：[237062]，资料为PDF文档或Word文档，PDF文档可免费转换为Word
以上是毕业论文外文翻译，课题毕业论文、任务书、文献综述、开题报告、程序设计、图纸设计等资料可联系客服协助查找。
