The near future will see an increasing demand of elder care and a shortage of professional and informal caregivers. In this context, ageing societies would benefit from the design of intelligent homes that provide assistance. The choice of interfaces between the assistive environment and the user is of great importance and determines the degree of user acceptance of this technology. Socially assistive robots are one of the most promising interfaces. Their embodiment and multimodal communication channels could potentially provide a large number of services that otherwise would have to be carried out by a variety of dedicated systems. Furthermore, evidence suggests that people perceive robots more as companions and social actors than tools and this is likely to steer user acceptance positively. This paper presents the authors' work related to the EU-FP7 project KSERA, a project that aims at introducing a socially assistive robot that acts as a proactive communication interface in smart home environments. In particular, it gives an overview of (1) human--robot interaction studies conducted in Eindhoven (The Netherlands) whose general aim was to preliminary assess the added value of socially assistive robots in intelligent homes and (2) the KSERA project field trials in Schwechat (Vienna) and Tel Aviv (Israel) that tested an integrated smart-home/robot system with real end users (N=16) in three real-world scenarios. Overall, results show that socially assistive robots positively affect user experience and motivation compared to standard smart environment interfaces such as touch screens. However, people still tend to prefer conventional interfaces for receiving information.

Gaze direction is an important communicative cue. In order to use this cue for human-robot interaction, software needs to be developed that enables the estimation of head pose. We began by designing an application that is able to make a good estimate of the head pose, and, contrary to earlier head pose estimation approaches, that works for non-optimal lighting conditions. Initial results show that our approach using multiple networks trained with differing datasets, gives a good estimate of head pose, and it works well in poor lighting conditions and with low-resolution images. We validated our head pose estimation method using a custom built database of images of human heads. The actual head poses were measured using a trakStar (Ascension Technologies) six-degrees-of-freedom sensor. The head pose estimation algorithm allows us to assess a person's focus of attention, which allows robots to react in a timely fashion to dynamic human communicative cues.

Embodied nonverbal cues are fundamental for regulating human-human social iteractions. The physical embodiment of robots makes it likely that they will have to exhibit appropriate nonverbal interactive behaviors. In this paper we propose a model of the user's proximity based on a superposition of quasi-Gaussian probability distributions which allows to express findings from HRI trials regarding distances and direction of approach in a human-robot interaction scenario. The way the model is formulated is suitable for well-established Bayesian filtering techniques, and thus the inference of the preferred distance and direction of approach in a human robot interaction scenario can be regarded as a state estimation problem. Results derived from simulations show the effectiveness of the inference process.

An experiment was designed to determine whether speech input is a valuable alternative or addition to manual input. Subjects used both speech and mouse input for control purposes in a document-annotation system. Speech recognition was realized by a speaker-dependent speech-recognition board. In separate sessions, subjects used either a mouse or speech interface, and comparisons were made between the two media in performance speed, number of commands, and number of errors. In a third session, subjects were free to use either input medium, and measures included both objective (usage) and subjective (questionnaire) preferences for the two media. The main results were that: (1)9 out of 24 subjects used speech more than the mouse when they were free to use both; (2) 21% of the subjects preferred speech control, because it allowed other devices to be operated manually; and (3) 37% of the subjects preferred to control the system with both input devices available. Speech can be a valuable addition to other input media enabling users to adapt their choice of media to specific task situations.