Affective Robot Influence on Driver Adherence to Safety, Cognitive Load Reduction and Sociability

Abstract

Humans can be deeply influenced by affective behaviors during social interaction. Specifically, emotional cues from others can be a powerful way to persuade people to modify their behaviors. With this motivation in mind, we explore how a social robot called AIDA (Affective Intelligent Driving Agent) can better persuade drivers to adhere to road safety guidelines as compared to existing technologies, and AIDA's persuasiveness as compared to a human passenger. An Android smartphone, which mounts in the robot's head, serves as AIDA's main computational unit. Because the smartphone contains personal information about the driver (e.g. contacts, calendar and music preferences), leveraging this device can create a more deeply personalized experience. We conducted a user study in which participants completed tasks in a driving simulator with the help of: 1) a smartphone alone, 2) AIDA as a static-mounted agent, 3) AIDA as an expressive robot, or 4) a smartphone plus a human passenger. AIDA was able to promote safe driving behaviors and reduce cognitive load better than a smartphone alone. Overall, the AIDA robot paralleled in performance as compared to the human passenger. The AIDA robot also facilitated more sociability with the driver than the smartphone or static agent. Further, AIDA's proactive launching of the driver's favorite music better promoted overall enjoyment.

Improving Driver Emotions with Affective Strategies

“…Hoedemaeker and Neerincx present an in-car interface which adapts its informational content based on the detected cognitive load of the driver [10]. Williams et al explored another facet of emotional interaction in the car with a social robot, which also had positive effects on driving performance [33]. We take this aspect of adaptive and social interaction and connect it to an affect-integrated driver model in order to intervene within the driver-vehicle interaction loop [1,16,34].…”

“…Drivers can, however, be distracted from negative affective states as long as the stimuli do not influence driving safety. Previous work has shown concepts to tackle negative states by changing routing options towards routes with a better view [33,37]. Another widespread concept to distract drivers from negative emotions is using adaptive music playback in order to nudge them towards more positive feelings [38][39][40][41].…”

Implicit Personalization in Driving Assistance: State-of-the-Art and Open Issues

“…This learns a driver's preferences incrementally and is embedded into an Android App, named smartNoti. In interactive assistance, compared to explicit personalization [136,137] which relies on manual setting, implicit methods (e.g. the combination of incremental Gaussian mixture models and support vector machines [135]) are more convenient and efficient which is demonstrated in real-time vehicle tests.…”

“…To cooperate with driver seamlessly and naturally, digital driving assistants should be able to recognize emotions or states of a specific driver by using speech and video as indicated by [135][136][137]. In [136,137], an in-car assistant robot is developed to interact with a driver socially. Therefore, the robot can understand a driver's requirements better so as to provide proper assistance.…”

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

“…et al, 2013) Advanced vehicle motion control delegation Fan et al, 2014;Meng & Sun, 2014;Vaitkus et al, 2014;Weyer et al, 2015; A c c e p t e d M a n u s c r i p t 88 al., 2012;Haberstroh et al, 2010;Hess et al, 2013;Jung & Qin, 2013;Kim & Son, 2011;Kim et al, 2011;Kim et al, 2012;Manseer & Riener, 2014;MarinLamellet & Haustein, 2014;Masala & Grosso, 2013;Meng & Sun, 2014;Moussa et al, 2012;Munro et al, 2010;Nakagawa & Park, 2014;Nakano et al, 2013;Rödel et al, 2014;Schall et al, 2012;Son et al, 2013;Taib et al, 2013;Vardaki & Karlaftis, 2011;Vhaduri et al, 2014;Vitabile et al, 2011;Williams et al, 2014;Young & Bunce, 2011) Infotainment Note. Springer Link and ACM Digital Library did not support the metadata search function, so we picked the articles related to HCI/HVI from the potentially related articles.…”