Being guided from one place to another is a pervasive social practice that connects deeply with socially aware robot navigation. We examine how robots come to feature within the organisation of these established and well-worn leading and following practices, practices which are assembled 'in place' by the efforts of individuals and groups that are using robot guides. We deployed mobile robots in a museum context to provide additional information for visitors around multiple sequential exhibits. Our ethnomethodological video-based analysis of interaction centres on how the social organisation of being guided was practically managed by visitors: in initiation of following, doing following, and finding a place to stop. Our study shows how following and being led is more than just a mechanical activity, and describe the implications for socially aware robot navigation in addressing novel technical challenges that a shift in understanding following-leading phenomena presents.

Telepresence robots have the potential to change our experiences in galleries and museums, allowing for a range of hybrid interactions for visitors and museum professionals, improving accessibility, offering activities or information, and providing a range of practical use cases (e.g. the robots augmenting museum exhibits).We present the results of 3 qualitative studies conducted in the UK exploring the acceptability (1 -interviews with museum professionals with no previous exposure to telepresence), acceptance (2 -focus groups for initial exposure to telepresence robots), and adoption (3 -interviews with museum professionals with long-term exposure to

As robots enter the messy human world so the vital matter of safety takes on a fresh complexion with physical contact becoming inevitable and even desirable. We report on an artistic-exploration of how dancers, working as part of a multidisciplinary team, engaged in contact improvisation exer-cises to explore the opportunities and challenges of dancing with cobots. We reveal how they employed their honed bodily senses and physical skills to engage with the robots aesthetically and yet safely, interleaving improvised physical manipulations with reflections to grow their knowledge of how the robots behaved and felt. We introduce somatic safety, a holistic mind-body approach in which safety is learned, felt and enacted through bodily contact with robots in addition to being reasoned about. We conclude that robots need to be better designed for people to hold them and might recognise tacit safety cues among people. We propose that safety should be learned through iterative bodily experience interleaved with reflection.

Unsupervised object discovery (UOD) aims to detect and segment objects in 2D images without handcrafted anno- tations. Recent progress in self-supervised representation learning [9, 66] has led to some success in UOD algo- rithms [21, 53, 69]. However, the absence of ground truth provides existing UOD methods with two challenges: 1) determining if a discovered region is foreground or back- ground, and 2) knowing how many objects remain undiscov- ered. To address these two problems, previous solutions rely on foreground priors [53, 59, 67, 69] to distinguish if the discovered region is foreground, and conduct one or fixed it- erations of discovery. However, the existing foreground pri- ors are heuristic and not always robust, and a fixed number of discoveries leads to under or over-segmentation, since the number of objects in images varies. This paper intro- duces UnionCut, a robust and well-grounded foreground prior based on min-cut [2] and ensemble methods [18] that detects the union of foreground areas of an image, allow- ing UOD algorithms to identify foreground objects and stop discovery once the majority of the foreground union in the image is segmented. In addition, we propose UnionSeg, a distilled transformer of UnionCut that outputs the fore- ground union more efficiently and accurately. Our experiments show that by combining with UnionCut or UnionSeg, previous state-of-the-art UOD methods [21, 53, 54, 69] wit- ness an increase in the performance of single object discovery, saliency detection and self-supervised instance seg- mentation on various benchmarks. The code is available at https://github.com/YFaris/UnionCut.

This research study scopes the ethical implications associated with the deployment of social robots within workplace environments, in the context of an increased need of employee wellbeing. Progress in the domains of artificial intelligence (AI) and social robotics present a potential avenue for improving workplace wellbeing. However, it is necessary conduct a comprehensive evaluation of the impacts and ethical considerations associated with these emerging technologies. For this purpose, we carried out an ethical risk assessment for a telepresence robot programmed to function as a social robot in the workplace, which we named ’Cheerbot’. After introducing Cheerbot’s functions, the paper describes an ethical risk assessment process, which involves identifying potential hazards, the likelihood of the hazard occurring, potential consequences (harms), and a risk exposure rating for each hazard. Results are presented for three hypothetical scenarios, and potential mitigations for the highest rated risks are suggested. The findings highlight the value of proactively identifying and mitigating ethical risks from harms, ensuring responsible deployment of robotics aimed at supporting workplace wellbeing.

We reappraise the idea of colliding with robots, moving from a position that tries to avoid or mitigate collisions to one that considers them an important facet of human interaction. We report on a soma design workshop that explored how our bodies could collide with telepresence robots, mobility aids and a quadruped robot. Based on our findings, we employed soma trajectories to analyse collisions as extended experiences that negotiate key transitions of consent, preparation, launch, contact, ripple, sting, untangle, debris and reflect. We then employed these ideas to analyse two collision experiences, an accidental collision between a person and a drone and the deliberate design of a robot to play with cats, revealing how real-world collisions involve the complex and ongoing entanglement of soma trajectories. We discuss how viewing collisions as entangled trajectories, or ‘tangles’, can be used analytically, as a design approach, and as a lens to broach ethical complexity.

Previous research into using robots for pain man-agement has shown promise. However to date, there seems to have been little research investigating user requirements for robotic pain management devices which could be used by adults living with chronic pain, and how these might be translated into custom products. We carried out a user study comprising online surveys and interviews with people who have lived experience of chronic pain to investigate their perspectives. We had a total of 44 participants in our study. Our research revealed a preference for robotic devices for pain management which have an abstract or animal-like form, noting that contact points with the body should feel soft, warm, and light. Study participants also felt that the user should initiate the interaction and should have control of the robot, as well as the type and intensity of touch. Favored touch types included massaging, rubbing, and stroking. From the emerging requirements, given the diversity of experiences, design-related attributes identified could be used for a form-customization application, such as interactive evolutionary computation (IEC), as a means to personalize the embodiment of robotic devices. Prioritized form factors for customization through included size, weight, and feel.

A large number of deep learning based object detection algorithms have been proposed and applied in a wide range of domains such as security, autonomous driving and robotics. In practical usage, objects being occluded are common, and can result in reduced accuracy and reliability. To increase the robustness of object detection algorithms under occlusion scenarios, it is necessary to consider the influence of different types of occlusion on the performance of object detection approaches. Our research revealed a gap in benchmarking datasets that could provide exemplars of occlusion that covered a range of occlusion scenarios. In this paper, we present a new benchmarking dataset that includes a range of exemplars providing coverage of different types of occlusion cases. This dataset is designed for object detection of everyday objects in indoor scenarios, and comprises occlusion in three orthogonal atomic factors, namely, the degree of occlusion, the location of occlusion, and classes of occluded object and those occluding other objects. Our dataset is balanced in terms of classes and degrees of occlusion, with a total of 5970 sample images. The effect of these three atomic factors has been investigated on some classic general object detectors. Using this benchmarking dataset, we also present results on the impact of the distribution of the training dataset, in terms of degree of occlusion, on the robustness of several typical object detection algorithms (e.g. Fast RCNN, Faster RCNN, and FCOS, etc). The benchmark is available at “https://drive.google.com/drive/folders/13VkLgbx6t0-vA3vRWrlvHcjra-8BS4aL?usp=sharing”. This dataset is seen as a key contribution to research investigating the influence of occlusion on the performance of object detectors.

This research investigates how professional carers physically assist frail older adults. Carers were asked to discuss their approach and steps for providing safe physical assistance and highlight hazards that assistive robots would have to deal with in such situations. The aspects raised by carers indicate that irrespective of the degree of vulnerability of the older adults, carers can evaluate trust and the older adults' ability and willingness to collaborate during the assistive task through multiple modalities. These include tactile, visual and verbal cues, which the carers use to discern a measure of collaboration and adapt their assistance accordingly. Understanding these hazards and their effective collaboration is a vital step towards developing safe, physically assistive robots.

In this paper we apply the recent concept of robot Ethical Risk Assessment to an exemplar Socially Assistive Robot (SAR); specifically considering ethical risks posed by anthropomorphism in this context. We draw on two complimentary studies to demonstrate that anthropomorphism is important to overall SAR function and overall relatively low ethical risk. As such, rather than avoiding anthropomoprhism all together (as suggested in a recently published standard on robot ethics), we suggest anthropomorphism in SARs should be a customisable trait that can be adapted to the user.

Internet of Things (IoT) technology and Smart Home (SH) solutions are a growing area of research and development, particularly within health and social care where they have potential to offer information and support for self-management and independent living. However, successful design and deployment of these technologies are predicated on a clear understanding of user aspirations, needs, and requirements. This paper presents findings from seven one-to-one interviews with care staff who contributed their experiences representing a diverse range of job roles and categories of service-users supported. Our participants were from a regional supported-living provider with facilities for people with learning disabilities. The interviews provided insight into care service provision and service-users' needs, as well as helping to identify areas of the current service that can be supported by IoT based intelligent systems. The feedback that staff provided was based on their knowledge and understanding of the needs of specific service user groups and included information regarding the appropriateness and applicability of the technologies, as well as the appeal, acceptability and usability of these solutions.

Abstract This paper investigates the utility of unsupervised machine learning and data visualisation for tracking changes in user activity over time. This is done through analysing unlabelled data generated from passive and ambient smart home sensors, such as motion sensors, which are considered less intrusive than video cameras or wearables. The challenge in using unlabelled passive and ambient sensors data for activity recognition is to find practical methods that can provide meaningful information to support timely interventions based on changing user needs, without the overhead of having to label the data over long periods of time. The paper addresses this challenge to discover patterns in unlabelled sensor data using kernel density estimation (KDE) for pre-processing the data, together with t-distributed stochastic neighbour embedding and uniform manifold approximation and projection for visualising changes. The methodology is developed and tested on the Aruba CASAS smart home dataset and focusses on discovering and tracking changes in kitchen-based activities. The traditional approach of using sliding windows to segment the data requires a priori knowledge of the temporal characteristics of activities being identified. In this paper, we show how an adaptive approach for segmentation, KDE, is a suitable alternative for identifying temporal clusters of sensor events from unlabelled data that can represent an activity. The ability to visualise different recurring patterns of activity and changes to these over time is illustrated by mapping the data for separate days of the week. The paper then demonstrates how this can be used to track patterns over longer time-frames which could be used to help highlight differences in the user’s day-to-day behaviour. By presenting the data in a format that can be visually reviewed for temporal changes in activity over varying periods of time from unlabelled sensor data, opens up the opportunity for carers to then initiate further enquiry if variations to previous patterns are noted. This is seen as an accessible first step to enable carers to initiate informed discussions with the service user to understand what may be causing these changes and suggest appropriate interventions if the change is found to be detrimental to their well-being.

In this paper we present the results of an experimental study investigating the application of human persuasive strategies to a social robot. We demonstrate that robot displays of goodwill and similarity to the participant significantly increased robot persuasiveness, as measured objectively by participant behaviour. However, such strategies had no impact on subjective measures concerning perception of the robot, and perception of the robot did not correlate with participant behaviour. We hypothesise that this is due to difficulty in accurately measuring perception of a robot using subjective measures. We suggest our results are particularly relevant for the design and development of socially assistive robots.

In this paper we present the results of a qualitative study with therapists to inform social robotics and human robot interaction (HRI) for engagement in rehabilitative therapies. Our results add to growing evidence that socially assistive robots (SARs) could play a role in addressing patients' low engagement with self-directed exercise programmes. Specifically, we propose how SARs might augment or offer more pro-active assistance over existing technologies such as smartphone applications, computer software and fitness trackers also designed to tackle this issue. In addition, we present a series of design implications for such SARs based on therapists' expert knowledge and best practices extracted from our results. This includes an initial set of SAR requirements and key considerations concerning personalised and adaptive interaction strategies.

Robots that can assist in activities of daily living (ADL) such as dressing assistance, need to be capable of intuitive and safe interaction. Vision systems are often used to provide information on the position and movement of the robot and user. However, in a dressing context, technical complexity, occlusion and concerns over user privacy pushes research to investigate other approaches for human-robot interaction (HRI). We analysed verbal, proprioceptive and force feedback from 18 participants during a human-human dressing experiment where users received dressing assistance from a researcher mimicking robot behaviour. This paper investigates the occurrence of deictic speech in an assisted-dressing task and how any ambiguity could be resolved to ensure safe and reliable HRI. We focus on one of the most frequently occurring deictic words “up”, which was captured over 300 times during the experiments and is used as an example of an ambiguous command. We attempt to resolve the ambiguity of these commands through predictive models. These models were used to predict end effector choice and the direction in which the garment should move. The model for predicting end effector choice resulted in 70.4% accuracy based on the user's head orientation. For predicting garment direction, the model used the angle of the user's arm and resulted in 87.8% accuracy. We also found that additional categories such as the starting position of the user's arms and end-effector height may improve the accuracy of a predictive model. We present suggestions on how these inputs may be attained through non-visual means, for example through haptic perception of end-effector position, proximity sensors and acoustic source localisation.

Discovering older adults' perceptions and expectations of domestic care service robots are vital in informing the design and development of new technologies to ensure acceptability and usability. This paper identifies issues that were elicited from older adults using different methods to promote creative thinking about domestic robots at an emotional level, as well as pragmatic level. These included exploring people's ideal embodiment preferences and requirements for a domestic care service robot, and also what embodiments and functional aspects will not be acceptable. We analysed our findings using relevant constructs from the Unified Theory of Acceptance and Use of Technology, and Technology Acceptance models. In addition to some already well-established findings, we discovered some surprising aspects concerning interaction, behaviour and appearance and the ability for the robot to fit the relevant context, both physically and conceptually.

A pre-requisite for a human-centred design approach to technology development is gaining an intimate understanding of not only the people for whom the technology is being designed, but also the contexts within which they will be using it. This paper explores the use of cameras as cultural probes for gaining this understanding. In this study, probes were included as part of the requirements elicitation methodology for an EU FP7 research project, MOBISERV, developing an integrated intelligent home environment for the provision of health, nutrition and mobility services for older adults. During the initial phase of the project, modelling user requirements for MOBISERV components, disposable cameras were adopted as one of several methods for eliciting information. They were given to older adults (potential end users of the system) enabling them to provide an insight into personal aspects of their own lives. This paper presents the approach and gives a description and evaluation of the method used, considering the information obtained and its impact on enabling contextualisation of the issues and raising awareness of user needs.

This paper considers on a number of issues that arise when a trainable machine vision system learns directly from humans. We contrast this to the “normal” situation where machine learning (ML) techniques are applied to a “cleaned” data set which is considered to be perfectly labeled with complete accuracy. This paper is done within the context of a generic system for the visual surface inspection of manufactured parts; however, the issues treated are relevant not only to wider computer vision applications such as medical image screening but also to classification more generally. Many of the issues we consider arise from the nature of humans themselves: They will be not only internally inconsistent but also will often not be completely confident about their decisions, particularly if they are making decisions rapidly. People will also often differ systematically from each other in the decisions they make. Other issues may arise from the nature of the process, which may require the ML to have the capacity for real-time online adaptation in response to users' input. Because of this, it may be that the users cannot always provide input to a consistent level of detail. We describe how all of these issues may be tackled within a coherent methodology. By using a range of classifiers trained on data sets from a compact disc imprint production process, we present results which demonstrate that training methods designed to take proper consideration of these issues may actually lead to improved performance.

A rapidly emerging model in the field of adaptive computing is the symbiosis of human expertise with evolutionary algorithms for user controlled and directed search. The two aspects in any EA are the selection of individuals to reproduce based on some measure of their quality or fitness and the application of variation operators to produce new solutions. In the context of interactive evolution, these aspects are compounded by the need for rapid convergence to prevent user fatigue and to provide the user some control over the generation of new solutions. Elsewhere, in the work of the authors (2004), we have examined different policies for best incorporating the user into the evaluation and selection process. In this paper, we explore the hypothesis that user assigned fitness represents a source of information that can be used to control the variation process: effectively to broaden the search if none of the current solutions is promising, or focus the search and improve convergence speed in the vicinity of a good solution. The main aims of this study, therefore, are to analyse the advantages of using a user directed adaptive mutation strategy over fixed mutation step sizes in terms of time to converge and robustness of the resulting solution. We present results showing a qualitatively different type of search process can be obtained by using the user assigned fitness to control the nature of the mutation process. There is also a synergy between user-based selection and fitness-based mutation control which out performs either system on its own.