Standing passengers in public buses face increased fall risk during sudden braking and acceleration, yet they often remain standing despite available seats due to proxemic discomfort, seating norms, and trip goals. We present a two-day, in-the-wild deployment of a minimal social robot “conductor” that delivered real-time, context-aware greetings and seating/safety prompts on regular bus routes, driven by an AI-based electronic control unit (AI-ECU) pipeline that recognized passenger state and seat-zone availability (front, priority, rear) from onboard cameras. Using synchronized video and system logs, we analyzed 74 compliance-potential episodes among 670 boardings. Overall seat-taking compliance was 27.0% (20/74) and tended to be higher when passengers visibly attended to the robot. When passengers complied, they were more likely to choose rear seating, suggesting that compliance depended on the emergence of a socially unambiguous, low-friction option rather than availability alone. The findings show that robotic safety prompts are negotiated through situational constraints and normative seating logics, motivating designs that make socially acceptable seating options salient, low-friction, and well-timed in shared public environments.

To mitigate the occurrence of traffic accidents, addressing the human factors pertinent to road safety, particularly driver operational errors, is essential. Drivers in urban environments can benefit from readiness evaluations and feedback, which help mitigate errors, promote safer driving speeds, and enhance situational awareness. This study aimed to develop and validate a driver behavior assessment system centered around the concept of stepwise driver readiness. The system is designed to evaluate driver behavior and provide progressive feedback to improve performance. We extrapolated the original concept of driver readiness to create a stepwise readiness evaluation system, which was implemented and tested on urban roads to evaluate its effectiveness. The results demonstrate that the system effectively evaluates readiness, and the stepwise feedback mechanism significantly enhances driver performance. Notably, the success of the feedback process was influenced by the level of driver acceptance. These results highlight the importance of the expanded driver readiness concept in managing human factor-related driving risks and improving road safety.

A highly anthropomorphic Robotic Human Machine Interface (RHMI) integrated into car dashboards has shown effectiveness in promoting safe driving behaviors, as it is accepted as a driving agent. However, which anthropomorphic elements in the RHMI’s appearance are essential for achieving driver acceptance remains unclear. Identifying these elements could facilitate the development of a minimal design and reduced installation costs for RHMIs on car dashboards. In this study, we conducted an online video experiment to explore the impact of RHMI embodiment and anthropomorphism levels on user acceptance. The findings provide insights for designing cost-effective and minimalist RHMIs as driving agents.

Soon, autonomous cars are expected to become widespread, but at present, it is still common for people to drive cars manually. A driving support agent (DSA) is used to support driving using the human-agent interaction approach. In previous research, it was shown that DSAs can be useful in assisting the user through voice utterances. However, previous studies focusing on DSA utterance design have not compared off-record strategies with other politeness strategies that explicitly communicate the speaker's intentions, and it was not clear whether DSA should provide explicit utterances to the user. Therefore, in this study, a video-based subjective evaluation experiment (n=240) was conducted to compare the acceptability of off-record strategies, positive politeness strategies, negative politeness strategies, and direct utterances without politeness strategies. The results of the experiment showed that the negative politeness strategy was evaluated significantly higher than the off-record strategy on evaluation items related to functionality. This result suggests the usefulness of providing explicit instructions with linguistic consideration (politeness) when DSA provides driving assistance to users. In addition to the above findings, there were several correlations between the user's personality characteristics and the subjective evaluation of the DSA. Specifically, there was a significant positive correlation between the level of conscientiousness of the user and the direct utterance evaluation value. For the positive politeness strategy and off-record strategy, there were no significant correlations between evaluation categories of the dislikeability and users' personality characteristics. These results suggest that individual differences in n egative impressions due to personality characteristics are small in the positive politeness and off-record strategies.

Automated driving systems are envisioned as the future mode of transportation owing to their projected ability to reduce human error and achieve more efficient and comfortable transportation. Accordingly, designing an interface that ensures the situational awareness of the human operator to reduce confusion, false expectations, and over-reliance on the automated system is important. When a human operator is in control, the automated system is expected to handle troublesome situations that the human is unable to manage. Thus, an interface is required to provide the appropriate information when necessary so that the human operator can easily perceive the reason for the sudden automated intervention. In this study, such a scenario is highlighted, in which a simulated automated intervention avoided a potential collision with a pedestrian who suddenly appeared on the roadside. To convey the reason for the automated intervention, an augmented reality-based head-up display (AR-HUD) cue that targets the pedestrian is developed. To understand the effects of the AR-HUD cue on the speed at which a human operator can recognize a pedestrian and the contribution of this visual cue to the perception of acceptability and credibility of the automated intervention, we compared AR-HUD with a static head-up display (S-HUD) that displays a pedestrian symbol at the bottom portion of the windshield. The results showed that the AR-HUD cue yielded faster recognition of the targeted pedestrian and provided a relatively more acceptable perception of the automated intervention.

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, to ensure driving safety, we study a driver agent system that provides driving and feedback support to the elderly drivers for encouraging them to improve their driving. In this paper, we present a summary of the proposed agent and report on a set of experiments using our agent for the elderly and non-elderly drivers in an actual environment with car on public roads. From the analysis of driving operations and fixation points during driving, the results revealed that the acceptability of the agent was high, the agent in the actual car environment did not distract the driver, and the agent could improve driving behavior.

Older drivers experience a high rate of crashes due to road intersections, unseen objects, and failure to find the traffic signals. These characteristics would be recognized if a system could watch and monitor the behaviors of the drivers inside their car. Therefore, in this study, current advances in driver monitoring cameras are used for measuring the head movements of older drivers to evaluate the visual intent of the driver. Several quantitative metrics that compute the temporal and spatial aspects of head movements allow for assessing the behaviors of older and middle-aged drivers. A driving simulator study using urban road scenarios shows that at high vehicle speed, on average, older drivers move their heads more slowly within a narrower range and glance too quickly to recognize surrounding traffic correctly. Correlation analysis validated the high prediction capabilities of head-movement measures towards the future evaluation of driving risks.

The purpose of this research is to analyze overconfidence and dependence caused by receiving the utterance from a driving support robot when a driver drives a car. Comfortable driving can be performed by receiving support from the driving support robot. However, it is expected that drivers will lead to accidents by the dependence or overconfidence bias on support robots. The dependence bias is that driver decreases the quality of driving behavior with respect to the function of the safety system, and the overconfidence bias is that driver embraces expectations more than the performance of the driving support robot. Although this problem includes the fuzziness of human characteristics, the conventional driving support system does not take into consideration such influence of the overconfidence or dependent bias. In order to verify whether driver has the bias against driving support robot in this paper, we investigated the impression of the robot when the driving support with driving animation and robot and report the results.

Cars represent an important mode of transportation for the elderly; however, in recent years, the number of traffic accidents caused by elderly drivers in Japan has increased. Thus, to ensure driving safety, we are researching a driver agent system that provides driving support and feedback support to elderly drivers to encourage them to improve their driving. In this paper, we report on a set of preliminary experiments using our agent in an actual car environment designed to evaluate the subjective acceptability of and distraction by the agent based on subjective evaluation and analysis of driver fixation points during driving. The results revealed that the acceptability of the agent was high and that the agent in an actual car environment did not distract the driver.

In recent years, the number of traffic accidents caused by elderly drivers in Japan has increased. Cars are an important mode of transportation for the elderly. Thus, to ensure their driving safety, a system that can assist elderly drivers is required. In this study, we propose a driver agent system that provides support to elderly drivers during and after driving and encourages them to improve their driving. In this paper, we describe the proposed driver agent system. We conducted an experiment to evaluate driving behavior improvement through three types of support: driving support, review support, and a combination of both. The results revealed that the combination of both supports lead to the greatest improvements in driving behavior and was most acceptable to elderly drivers.

This paper presents a model for safe driving at blind intersections and its integration to a local planner based on a Frenet frame. The model predicts potential moving obstacles from blind intersections to proactively slow down to avoid potential collisions. The derivation of the model is described and its parameters are detailed. The local planner computes smooth trajectories with smooth velocity profiles so that the vehicle can follow the paths without jerk and sudden accelerations resulting in safe and comfortable navigation. Experimental results in simulation and in the real field with an autonomous car, show that the proposed predictive driving framework can reproduce human expert driver's trajectories and velocities when facing blind intersections.

In this paper, we present a localization approach that is based on a point-cloud matching method (normal distribution transform “NDT”) and road-marker matching based on the light detection and ranging intensity. Point-cloud map-based localization methods enable autonomous vehicles to accurately estimate their own positions. However, accurate localization and “matching error” estimations cannot be performed when the appearance of the environment changes, and this is common in rural environments. To cope with these inaccuracies, in this work, we propose to estimate the error of NDT scan matching beforehand (off-line). Then, as the vehicle navigates in the environment, the appropriate uncertainty is assigned to the scan matching. 3D NDT scan matching utilizes the uncertainty information that is estimated off-line, and is combined with a road-marker matching approach using a particle-filtering algorithm. As a result, accurate localization can be performed in areas in which 3D NDT failed. In addition, the uncertainty of the localization is reduced. Experimental results show the performance of the proposed method.

This paper presents a model for velocity control in blind corners and intersections based on expert driver data. Accurate expert driver data was collected with a car equipped with a 3D LiDAR and high definition maps. A model based on human expert driver data is used to control the velocity of the ego-vehicle when facing blind intersections. The model regulates ego-vehicle velocity based on the visibility of the road at the blind intersection. As the vehicle approximates the intersection and crossing roads are not visible, the vehicle slows down, then as the roads become visible the vehicle accelerates. Experimental results show the performance of the velocity model compared towards 270 trajectories taken from 7 expert drivers towards 6 different intersections without mandatory stops.

Tacit learning is the novel learning scheme based on the principle of biological control to create the appropriate behaviors adapted to the environment. Signal accumulation is the key factor for tacit learning in the process of behavior adaptation. To clarify the role of the signal accumulation in the learning process, we analyzed it dividing into the two processes depending on the control speed. The fast process is used for the behavior control and the slow process is used for the behavior adaptation to the environment. We developed the continuous-time controller for tacit learning with the integrators and showed that the signal accumulation can estimate a part of the robot model through the interactions between the robot body and the environment. This capability of tacit learning is useful to control a plant where the modeling errors and model changes are the critical problems for the stable controls. As the prominent example of the control of such plant, we experimentally verified that tacit learning can create the bipedal walking gait that pushes the ground by the support leg at the moment of losing contact with the ground.

In biological regulatory systems, all computations result from spatial and temporal combination of simple and homogeneous computational media. This computational scheme realize the adaptability to unpredictable environmental changes, which is one of the most salient features of biological regulations. To investigate the learning process behind this computational scheme, we propose a learning method that embodies the features of biological systems, termed tacit learning. We have constructed a controller based on the notion of tacit learning and applied it to the control of the 36DOF humanoid robot to create the bipedal walking adapted to the environment. Experiments on walking showed a remarkably high adaptation capability of tacit learning in terms of gait generations, power consumption and robustness.