Ingo Keller

Heriot-Watt University · Department of Computer Science

In this article, we evaluate the incremental object learning approach of the iCub humanoid robot which is directed towards long-term engagement. Affordable robot companion systems are currently entering the consumer market which highlights the importance in understanding environmental influences on robotic systems under real world conditions. If a...

In the field of human-robot interaction feedback from a robot is a vital to keep an interaction going. There are several ways to give appropriate feedback from a robots perspective, in this work we are focusing on lip synchronisation as this has shown to be important in conversations. According to the McGurk Effect, which described how the visual i...

In this paper, we will explore human movement using a tutoring spotter system which controls an iCub robot. We will present an evaluation based on the captured human movement from an experimental study, where our participants demonstrated a salt-shaker and a cup-stacking task to the iCub robot. We will use a method of action recognition, which will...

In this work, we introduce our model for activity recognition in assisted living environments. The proposed concept addresses the challenging trade-off in nowadays activity recognizers, between modeling knowledge at design time vs. machine learning approaches for runtime recognition. With our model, the system is able to recognize new activities du...

General Game Playing (GGP) is an active area of research concerned with the building of autonomous agents that are able to play arbitrary games. The AAAI GGP competition is probably the main driving force in this area. It provides a scientific framework for the development of those agents. During the competition the participating researchers are pr...

Cognitive load has been widely studied to help understand human performance. It is desirable to monitor user cognitive load in applications such as automation, robotics, and aerospace to achieve operational safety and to improve user experience. This can allow efficient workload management and can help to avoid or to reduce human error. However, tr...

We present an experiment investigating the relationships between different physiological measures, including Mean Pupil Diameter Change, Blinking-Rate, Heart-Rate, and Heart-Rate Variability to inform the development of a measure to estimate Cognitive Load. Our experiment involved participants performing a task to spot correct or incorrect words an...

Most collaborative tasks require interaction with everyday objects (e.g., utensils while cooking). Thus, robots must perceive everyday objects in an effective and efficient way. This highlights the necessity of understanding environmental factors and their impact on visual perception, such as illumination changes throughout the day on robotic syste...

This position paper describes an experiment conducted to understand the relationships between different physiological measures including pupil Diameter, Blinking Rate, Heart Rate, and Heart Rate Variability in order to develop an estimation of users' mental load in real-time (see Sidebar 1). Our experiment involved performing a task to spot a corre...

We focus on affective architecture issues relating to the generation of expressive facial behaviour, critique approaches that treat expressive behaviour as only a mirror of internal state rather than as also a social signal and discuss the advantages of combining the two approaches. Using the FAtiMA architecture, we analyse the requirements for gen...

In this paper we introduce a new model for conversational gaze control for robots with physical eyes. We describe our modeling approach and present the results of a set of exploratory experiments. The work illustrated here is a first step of a larger research program dedicated to the development of a conversational gaze controller (CGC) for Human-R...

In this paper, we will present a Human Robot Interaction (HRI) pilot study, that investigates the question, which impact the location of speech production has on a simple gesture interpretation game with the iCub robot. Participants where asked to communicate about different objects on a table by using a pointing gesture. As a feedback the robot wo...

In this work, the authors combine the field of cloud computing with assisted living to improve activity classifica- tion. The proposed system addresses the challenge of enabling heterogeneous, cloud-based sensors in domestic environments. With a semantic and model-based approach, the authors seamlessly integrate web services as virtual sensors and,...

In this work, we introduce our approach for detecting and presenting anomalies of daily routines in assisted living environments. The proposed concept addresses the challenges of detecting, deducing and presenting the provenance, if such anomalies occurs. With our assis- tive knowledge- and model-based approach, users reach higher levels of awarene...

Die allgegenwärtige Verfügbarkeit von Information, welche vor allem durch die zunehmende Verbreitung sozialer Medien einen neuen Stellenwert erfährt, erfordert eine neue Lernkultur. Insbesondere der kompetente und effiziente Umgang mit der vorherrschenden Informationsvielfalt stellt für Lernende eine große Herausforderung dar. Das Forschungsprojekt...

In this work, we introduce our interaction concept for efficient control of cyber-physical systems (CPS). The proposed concept addresses the challenges of the increased amount of smart/electronic devices along with increasingly complex user interfaces. With a dual reality approach, the user is able to perform the same action in the physical world a...

Der betriebliche Weiterbildungssektor ist einer der stark wachsenden Bildungssektoren. Jedoch zeigt sich, dass Ausbildungs- bzw. Studieninhalte den betrieblichen Spezifika kaum gerecht werden und bereits nach kurzen Tätigkeitsphasen Weiterbildungen in Anspruch genommen werden müssen. Dies geschieht oft in Form geplanter, formalisierter Personalentw...

The Game Description Language (GDL) is the language of choice for the annual AAAI General Game Playing Competition and therefore widely adopted by the scientific community. It is used to describe finite, discrete, deterministic multi-player games of complete information. During such a competition the player gets a scrambled description of a game, whi...

The clubroot disease of the family Brassicaceae is caused by the obligate biotrophic protist Plasmodiophora brassicae. Infected roots undergo a developmental switch that results in the formation of aberrant roots (clubs). To investigate host gene expression during the development of the disease, we have used the Arabidopsis ATH1 genome array. Two t...

The clubroot disease of the family Brassicaceae is caused by the obligate biotrophic protist Plasmodiophora brassicae. Infected roots undergo a developmental switch that results in the formation of aberrant roots (clubs). To investigate host gene expression during the development of the disease, we have used the Arabidopsis ATH1 genome array. Two t...

The clubroot disease of Brassicaceae is caused by the obligate biotrophic protist, Plasmodiophora brassicae. Infected roots undergo a developmental switch that results in the formation of aberrant roots (clubs). To investigate host gene expression during the development of the disease the Affymetrix 22k chip were used. Two time points were chosen,...

Animals and plants carry recognition systems to sense bacterial flagellin. Flagellin perception in Arabidopsis involves FLS2, a Leu-rich-repeat receptor kinase. We surveyed the early transcriptional response of Arabidopsis cell cultures and seedlings within 60 min of treatment with flg22, a peptide corresponding to the most conserved domain of flag...