Nuno Otero

Ambient Intelligence: Beyond the Inspiring Vision.

Ambient Intelligence (AmI) has emerged in the past 10 years as a multidisciplinary field within ubiquitous computing, attracting considerable research, funding and public attention and leading to many research groups, and conferences specifically focused on Ambient Intelligence topics. From its conception, AmI has always been a field strongly driven by a particular vision of how ICT technologies would shape our future. This has given the AmI vision, essentially as proposed by ISTAG, an excessively central role in shaping the field and setting its research agenda. We argue that this inspiring vision should no longer be the main driver for AmI research and that we should now re-interpret its role in the background of 10 years of research. In this paper, we reflect on what it means for AmI to move behind its foundational vision and we identify a number of emerging trends around some of its core concepts, more specifically the notion of intelligence, the system view and the requirements process. The main motivation is to search for alternative research directions that may be more effective in delivering today the essence of the AmI vision, even if they mean abandoning some of the currently prevailing approaches and assumptions. Overall, these trends provide a more holistic view of AmI and may represent important contributions for bringing this field closer to realisation, delivery and real social impact.

Eliciting Requirements for a Robotic Toy for Children with Autism - Results from User Panels

The work presented in this paper was carried out within the IROMEC project that develops a robotic toy for children. Play has an important role in child development with many potential contributions to therapy, education and enjoyment. The project investigates how robotic toys can become social mediators, encouraging children with disabilities to discover a range of play styles, from solitary to social and cooperative play (with peers, carers/teachers, parents etc). This paper presents design issues for such robotic toys related specifically to children with autism as the end user target group. In order to understand the play needs of this user group, and to investigate how robotic toys could be used as a play tool to assist in the childrens development, a panel of experts (therapists, teachers, parents) was formed and interviewed. Results of the expert panel interview s highlight key points characterizing the play of children with autism, and key points for consideration in the design of future robotic toys.

Distribution and Recognition of Gestures in Human-Robot Interaction

This paper presents an approach for human activity recognition focusing on gestures in a teaching scenario, together with the setup and results of user studies on human gestures exhibited in unconstrained human-robot interaction (HRI). The user studies analyze several aspects: the distribution of gestures, relations, and characteristics of these gestures, and the acceptability of different gesture types in a human-robot teaching scenario. The results are then evaluated with regard to the activity recognition approach. The main effort is to bridge the gap between human activity recognition methods on the one hand and naturally occuring or at least acceptable gestures for HRI on the other. The goal is two-fold: to provide recognition methods with information and requirements on the characteristics and features of human activities in HRI, and to identify human preferences and requirements for the recognition of gestures in human-robot teaching scenarios

Human to robot demonstrations of routine home tasks: exploring the role of the robot's feedback

In this paper, we explore some conceptual issues, relevant for the design of robotic systems aimed at interacting with humans in domestic environments. More specifically, we study the role of the robots feedback (positive or negative acknowledgment of understanding) on a human teachers demonstration of a routine home task (laying a table). Both the human and the systems perspectives are considered in the analysis and discussion of results from a human-robot user study, highlighting some important conceptual and practical issues. These include the lack of explicitness and consistency on peoples demonstration strategies. Furthermore, we discuss the need to investigate design strategies to elicit peoples knowledge about the task and also successfully advertize the robots abilities in order to promote peoples ability to provide appropriate demonstrations.

Teaching robot companions: the role of scaffolding and event structuring

For robots to be more capable interaction partners they will necessarily need to adapt to the needs and requirements of their human companions. One way that the human could aid this adaptation may be by teaching the robot new ways of doing things by physically demonstrating different behaviours and tasks such that the robot learns new skills by imitating the learnt behaviours in appropriate contexts. In human–human teaching, the concept of scaffolding describes the process whereby the teacher guides the pupil to new competence levels by exploiting and extending existing competencies. In addition, the idea of event structuring can be used to describe how the teacher highlights important moments in an overall interaction episode. Scaffolding and event structuring robot skills in this way may be an attractive route in achieving robot adaptation; however, there are many ways in which a particular behaviour might be scaffolded or structured and the interaction process itself may have an effect on the robots resulting performance. Our overall research goal is to understand how to design an appropriate human–robot interaction paradigm where the robot will be able to intervene and elicit knowledge from the human teacher in order to better understand the taught behaviour. In this article we examine some of these issues in two exploratory human–robot teaching scenarios. The first considers task structuring from the robots viewpoint by varying the way in which a robot is taught. The experimental results illustrate that the way in which teaching is carried out, and primarily how the teaching steps are decomposed, has a critical effect on the efficiency of human teaching and the effectiveness of robot learning. The second experiment studies the problem from the humans viewpoint in an attempt to study the human teachers spontaneous levels of event segmentation when analysing their own demonstrations of a routine home task to a robot. The results suggest the existence of some individual differences regarding the level of granularity spontaneously considered for the task segmentation and for those moments in the interaction which are viewed as most important.

Issues in Human/Robot Task Structuring and Teaching

Teaching a robot new skills may require that the teacher scaffolds the teaching experience appropriately. However, due to inherent assumptions made by a human teacher the scaffolding process may in some circumstances fail to effectively teach the robot. Here we illustrate this issue in two simple robot teaching exploratory studies and examine the assumptions made by the teacher when teaching the robot. In the first study the human teacher had to reason about robot perceived states in order to provide suitable teaching. In the second study the human teachers had to understand the perceptual constraints of the robot based on the instructions given beforehand by the experimenter and subsequently adapt the guidance given. The results suggest that although the two tasks are quite distinct in their level of complexity a common thread can be observed: people tend to underspecify their teaching. It seems that steps of the explanation are assumed to be known and skipped or not even considered at all. We reflect on the possibility that one of the major challenges in designing robots that are capable interaction partners in these teaching situations is to be able to make them communicate their internal state and current capabilities effectively. Furthermore, we also reflect on designing appropriate behavioral primitives for the robot, corresponding implications on the level of task description and for benefiting from human teaching.

Relational Properties in Interaction Aesthetics: The Ubiquitous Music Turn

Taking as a point of departure recent theoretical advances in Interaction Design and Human-Computer Interaction (Lowgren 2009), we discuss a body of knowledge gathered in Ubiquitous Music practices (Keller et al. 2011a) during the last six years. New concepts and methods have been proposed to describe aspects of the ideation and materialisation of experiences with technology. Pliability (Lowgren 2007) and anchoring (Keller et al. 2010) are two of the multiple design qualities that surfaced in interaction design that impact information technology creative practices. We present results of experiments addressing creativity support for ubiquitous music making through the time tagging metaphor (Radanovitsck et al. 2011). The studies serve to exemplify how relational properties can be integrated within creativity-centred design. Our research indicates that sonic relational properties may provide affordances for proto-musical phenomena. We discuss the theoretical and methodological implications of this proposal highlighting its impact on everyday musical creativity.

Tangible and wearable user interfaces for supporting collaboration among emergency workers

Ensuring a constant flow of information is essential for offering quick help in different types of disasters. In the following, we report on a work-in-progress distributed, collaborative and tangible system for supporting crisis management. On one hand, field operators need devices that collect information--personal notes and sensor data--without interrupting their work. On the other hand, a disaster management system must operate in different scenarios and be available to people with different preferences, backgrounds and roles. Our work addresses these issues by introducing a multi-level collaborative system that manages real-time data flow and analysis for various rescue operators.

Exploring human mental models of robots through explicitation interviews

This paper presents the findings of a qualitative study exploring how mental models of a mechanoid robot using dog-inspired affective cues behaviour emerges and impacts the evaluation of the robot after the viewing of a video of an assistive robotics scenario interaction with the robot. It discusses this using contrasting case studies based on the analysis of explicitation interviews with three participants. The analysis suggests that while for some users zoomorphic cues may aid in initial interactions, they need to be framed in an authentic interaction, highlighting the actual capabilities of the robot as a technological artifact, and how these impact the everyday life and interests of the potential user.

Interactive Public Digital Displays: Investigating Its Use in a High School Context

This paper presents a longitudinal user study that investigated the adoption of some Bluetooth based functionalities for a public digital display in a high school. More specifically, the utilization of Bluetooth device naming extended beyond social identity representation and introduced the use of a simple interaction mechanism. The interaction mechanism involves recognizing parts of the Bluetooth device name as explicit instructions to trigger the generation of content on an interactive public display. Together with representatives of the teachers’ community, the design team defined some social rules concerning usage in order to account for the specificities of the place. In the user study, three fully functional prototypes were deployed at the school hall of the high school. The functionalities introduced with the different prototypes were: the visualization on the display of the Bluetooth device names, the possibility to contribute to tag clouds and the possibility to choose icons from a given set for self-expression. The results suggest that people appropriated some but not all of the functionalities employed. Implications of our findings to the design of interactive digital displays are pointed out.