In social environment navigation, robots inevitably exhibit behaviors that are perceived as inappropriate by humans. Current robots lack the ability to adapt to such human perceptions, leading to repeated inappropriate behaviors. This study employs a mixed-methods approach to explore human-preferred robot adaptations, combining qualitative data from a series of human-robot interactions and a semi-structured interview, and quantitative data from an online survey. 12 participants were recruited to interact with a mobile robot in an indoor setting, reporting 139 instances of inappropriate robot behaviors. The subsequent semi-structured interviews regarding these instances yielded 9 types of inappropriate behaviors and 10 major types of human-preferred robot adaptations, ranging from general ones, such as stopping the motion, to more specific ones, like moving away and then stopping. Additionally, 12 human-preferred adaptations were selected from the interview data and presented to the same participants through an online survey to evaluate their effectiveness in addressing the inappropriate behaviors previously identified. The results reveal the human preference for the robot to move to the side and then stop in most scenarios, which might serve as a general adaptation for addressing inappropriate robot navigation behaviors.@en

Good sleep is conducive to the recovery process of hospital patients - and yet, in many wards, sleep duration and quality can often be suboptimal, in part due to modifiable hospital-related sounds and noises. At the neurological ward of the Reinier de Graaf hospital in Delft, the Netherlands, we developed and evaluated a prototype information exchange system to raise awareness of specific sounds as disturbing patients' sleep. The system both classifies different relevant sound events and tracks sleep quality (using a Fitbit device). This information is then visualized for patients and staff to present the influence of the soundscape on patients' sleep hygiene in a friendly and comprehensive way. We discuss the design process, including a context study and various evaluations of the technology, interface, and created affordances. Our initial findings indicate that visualizing hospital soundscapes may, indeed, support both patients and staff in their efforts towards better sleep hygiene.

@en

Our interactions form an intricate 'dance' - a dance requiring a fluent integration of both expressivity (e.g. to approach someone) and sensitivity (e.g. detect if you 'should' approach someone). Work on behaving artefacts has focused mostly on the social, emotional and aesthetic qualities that can be evoked - expressed - through interactions involving such artefacts. Meanwhile, novel methods from social signal processing and affective computing are beginning to imbue artefacts with a reflective awareness - a sensitivity - to the emergent social aspects of the interaction. Can we empower the expressivity of behaving artefacts by integrating it with such sensitivity? With this workshop we aim to bring together a range of perspectives, on the performative and technological opportunities for such artefacts, as well as on their potential (adverse) social and societal implications; to jointly establish what will be necessary to achieve Expressive\Sensitive artefacts that positively enrich and participate in the 'dance' of social interaction.

@en

When mobile urban robots will share the sidewalk with people, the resulting interactions can cause unexpected undesirable outcomes to emerge – from people running away scared to people deliberately teasing and harassing such systems. How can we design such AI systems to aptly handle the unexpected? Directly anticipating and/or detecting these kinds of situations will inherently be unreliable; they are unexpected, after all. And yet, there exists a very clear signal for social slip-ups: the emotional response of people. We thus argue that such systems need to be imbued with a capacity to interpret the socio-emotional reactions to their own behavior.@en

Delivery robots are being deployed on sidewalks, but do we actually know which conflicts we should aim to avoid in the design and creation of these systems? Current approaches to social navigation focus on implementing well-established social norms such as proxemics, but it is dubious if these norms are sufficiently applicable to the context of dynamic interactions between such robots and pedestrians. We argue that, to get rich insight in the actual conflicts, we should confront them within their context. Based on this argument, we outline a new method for user observation that aims to elicit and explore representative social conflicts by ignoring humans: context-confrontation. Our first preliminary observations using this method suggest unexpected and novel conflicts, well outside of what current approaches seem to be focusing on – perhaps we, the designers/engineers of these robotic systems, should get out there a bit more, to find the conflicts that really matter.@en

The Internet of Things makes human activity data - what people do, how they move, how they socialise - an abundant resource. However, this rich and intimate perspective on people, which uniquely shape and characterise their behaviours, can have tremendous ethical implication if data is handled irresponsibly. Being personal, contextual and accessible, mobile devices are key facilitators of (ir)responsible collection and use of data. In this workshop, we will use the Future Workshop approach to develop a research agenda towards ethical data-centric design of intelligent behaviours. As part of this approach, we will (1) criticise the current mechanisms and infrastructure to frame ethical challenges, (2) fantasise on futures which support user and designer values, and (3) implement a research agenda for the MobileHCI community to emphasise the barriers to tackle. The outcomes of this workshop will foster ethical research and inspire the MobileHCI community.

@en

What if a robot could detect when you think it got too close to you during its approach? This would allow it to correct or compensate for its social ‘mistake’. It would also allow for a responsive approach, where that robot would reactively find suitable approach behavior through and during the interaction. We investigated if it is possible to automatically detect such social feedback cues in the context of a robot approaching a person.

We collected a dataset in which our robot would repeatedly approach people (n=30) to verbally deliver a message. Approach distance and environmental noise were manipulated, and our participants were tracked (position and orientation of upper body and head). We evaluated their perception of the robot’s behavior through questionnaires and found no single or joint effects of the manipulations. This showed that, in this case, personal differences are more important than contextual cues – thus highlighting the importance of responding to behavioral feedback. This dataset is being made publicly available as part of this publication (http://doi.org/10.4121/uuid:b76c3a6f-f7d5-418e-874a-d6140853e1fa).

On this dataset, we then trained a random forest classifier to infer people’s perception of the robot’s approach behavior from features generated from the response behaviors. This resulted in a set of relevant features that perform significantly better than chance for a participant-dependent classifier; which implies that the behaviors of our participants, even with our relatively limited tracking, contain interpretable information about their perception of the robot’s behavior.

Our findings demonstrate, for this specific context, that the observable behavior of people does indeed contain usable information about their subjective perception of a robot’s behavior. As such they, together with the dataset, provide a stepping stone for future research into the automatic detection of such social feedback cues, e.g. with other or more fine-grained observations of people’s behavior (such as facial expressions), with more sophisticated machine learning techniques, and/or in different contexts.@en