Program

Abstract: In future mixed traffic scenarios, human road users and autonomous vehicles will need to interact as they share and potentially compete for the same traffic space. This competition will take place at dedicated spatial locations, such as junctions and even more so in shared spaces. But there will be other situations and locations where negotiation between humans and machines will be necessary, such as when a person wants to cross a street. Humans typically have experience and also expectations of other people's possible behavior - but it will be difficult for them to figure out how a machine would react. So one solution is to make AV actions human-like - and therefore predictable - as well. Still, in a human-human interaction there are additional means of communication that are used to ensure that both partners have understood the interaction (e.g., gestures or eye contact). Therefore, such means of communication should also be provided for AV, e.g., through visual signs or projections. Another solution is to code the human knowledge (e.g. where children potentially might cross a road) in maps, which can then serve as information layer to code potential behavior.

Abstract: It seems that autonomous driving systems are substituting human responsibilities in the driving task. However, this does not mean that vehicles should not interact with their driver anymore, even in the case of full automation. One reason is that the automation is not yet advanced enough to predict other road user’s behavior in complex situations, which can lead to sub-optimal action choices, decrease comfort and user experience. In contrast, a human driver may have a more reliable understanding of other road users’ intentions which could complement that of the automation. We propose a framework that distinguishes between four levels for interaction with automation. Based on the framework, we introduce a concept which allows drivers to provide prediction-level guidance to an automated driving system through gaze-speech interaction. Results of a pilot user study and an integration of a real autonomous driving system show that people hold a positive attitude towards prediction-level intervention.

Abstract: In the future, Automated Vehicles (AVs) will need to interact with other road users, such as cyclists, pedestrians, and other vehicles. To enhance safety, improve traffic flow, and increase user acceptance and trust in AVs; pedestrians and other road users need to understand the AVs' intentions, communication, and behavior. As the AVs will not be controlled by onboard drivers any more, any forms of conventional communication via the drivers will be missing (i.e., hand gestures, head nodding). Although there is mixed evidence as to the extent to which these types of explicit communication arise, new forms of external Human-Machine Interfaces (eHMIs) have been designed in an effort to replace human-human communication, and increase the acceptability and safety of AVs. In this presentation, we will look into how implicit cues (i.e., vehicle movement), eHMIs, and drivers' presence affect pedestrians' crossing behavior and subjective evaluations. The state-of-the-art literature and work completed as part of the interACT project will be presented.

Abstract: An external human machine interface (eHMI) can be viewed as an explicit communication method for providing driving intentions of an automated driving vehicle (AV) to pedestrians. However, the eHMI may not guarantee that the pedestrians will fully recognize the intention of the AV. In this paper, we proposed that the instruction of the eHMI's rationale can help pedestrians correctly understand the driving intentions and predict the behavior of the AV, and thus their subjective feelings (i.e., dangerous feeling, trust in the AV, and feeling of relief) and decision-making are also improved. The results of an interaction experiment in a road-crossing scene indicate that it was easier for the participants to understand the driving intention and predict driving behavior of the AV w/ eHMI after the instruction. Further, the subjective feelings and the hesitation related to decision-making were improved and reached the same standards as that for the manual driving vehicle.

Abstract: An external human machine interface (eHMI) can be viewed as an External Human-Machine Interfaces (eHMIs) are expected to bridge the communication gap between an automated vehicle (AV) and pedestrians to replace the missing driver-pedestrian interaction. However, the relative impact of movement-based implicit communication and explicit communication with the aid of eHMIs on pedestrians has not been studied and empirically evaluated. How effective are eHMIs in situations when the behavior of the AV seems to disagree with the message of the eHMI? Do pedestrians trust eHMIs universally regardless of the context of the interaction? In this talk, I discuss the roles that vehicle kinematics (implicit communication) and eHMI (explicit communication) play AV-pedestrian interactions during road-crossing decisions, especially when both forms of communication are present, and even contradict each other.

Abstract: In comparison to conventional traffic designs, shared spaces promote a more pleasant urban environment with slower motorized movement, smoother traffic, and less congestion. In the foreseeable future, shared spaces will be populated with a mixture of autonomous vehicles (AVs) and vulnerable road users (VRUs) like pedestrians and cyclists. However, a driver-less AV lacks a way to communicate with the VRUs when they have to reach an agreement of a negotiation, which brings new challenges to the safety and smoothness of the traffic. Through our study, novel eHMIs might be the solution to integrating AVs seamlessly into shared-space traffic. Hence, a potential eHMI design concept was proposed for different VRUs to meet their various expectations. In the end, we further discussed the effects of the eHMIs on improving the sociality in shared spaces and the autonomous driving systems.