Preliminary Study for Feasibility of Driver Agent in Actual Car Environment<br/>—Driver Agent for Encouraging Safe Driving Behavior (3)

Abstract

Japan has become a more aged society and there are more drivers, 65 years of age and above. Cars represent an important mode of transportation for the elderly; however, in recent years, the number of traffic accidents caused by elderly drivers has been on the rise, and this has become a social issue. Thus, for the elderly drivers to encourage them to improve their driving, we study a driver agent system which consists of smartphone, communication robot and cloud service and provides the driving support by attention awakening and the feedback support based on driving behavior evaluation. In this paper, we presented a summary of the proposed agent and reported on a set of preliminary experiments using our agent in an actual car environment. From the analysis of subjective evaluations and fixation points during driving, the results revealed the possibility that the drivers accept the agent and supports from the agent during driving and that the agent in an actual car environment did not distract the driver.

Should a Driving Support Agent Provide Explicit Instructions to the User? Video-based Study Focused on Politeness Strategies

“…A driving support agent (DSA) is used as an engineering support method for manual driving (Figure 1). Previous studies on DSA [1][2][3] have shown the effectiveness of small dashboard robots, which assist the driver through voice utterances. In addition, research on DSA is a hot topic in the human-agent interaction (HAI) community, and a study of DSA [3] won the Best Paper Award at the International Conference on HAI 2017.…”

“…The main utterances of previous DSAs [1][2][3] were designed to give implicit instructions to avoid causing discomfort to the user (e.g., the DSA says "there is a pedestrian" and does not specify the driving behaviors the user should perform). According to politeness theory [4], a knowledge in the research field of sociolinguistics and pragmatics, such implicit instruction corresponds to the "hinting" strategy (off-record), which avoids directly communicating intentions to the other party.…”

“…Thus, in this study, we set a research question (RQ), "Should a driving support agent provide explicit instructions to the user?". Based on previous studies [1,2], the theoretical hypothesis of this study is "ORS is more acceptable than explicit strategies because it does not provide explicit instructions to users. "…”

“…In addition, since the acceptability of DSA utterances is thought to vary depending on the personality characteristics of the user, we analyzed the relationship between the acceptability of the utterance strategy and the personality characteristics of the user. As a dependent variable, we will use DSA acceptability evaluation measures [1,2]: the better the results of the evaluation measures [1,2], the higher the acceptability of the DSA by the users. The working hypothesis is that "the subjective evaluation of ORS will be higher than the evaluation of other strategies. "…”

“…However, to discuss the acceptability of DSA at a finer level, such as the relationship between the acceptability of DSA and the user's personality characteristics, it is necessary to conduct not only an empirical experiment but also an investigation with a large sample size, as in this study. In addition, in this study, the participants of the experiment were native speakers of Japanese, because the need for DSAs is considered to be particularly high in Japan [1][2][3]. The remainder of this paper is organized as follows: In Section 2, we describe related work on politeness strategy, politeness in DSAs and other agents, and the relationship between the user's personality characteristics and acceptability of agents.…”