Mari Velonaki

Interpretation of the modality of touch on an artificial arm covered with an EIT-based sensitive skin

During social interaction humans extract important information from tactile stimuli that can improve their understanding of the interaction. The development of a similar capability in a robot will contribute to the future success of intuitive human–robot interaction. This paper presents a thin, flexible and stretchable artificial skin for robotics based on the principle of electrical impedance tomography. This skin, which can be used to extract information such as location, duration and intensity of touch, was used to cover the forearm and upper arm of a full-size mannequin. A classifier based on the ‘LogitBoost’ algorithm was used to classify the modality of eight different types of touch applied by humans to the mannequin arm. Experiments showed that the modality of touch was correctly classified in approximately 71% of the trials. This was shown to be comparable to the accuracy of humans when identifying touch. The classification accuracies obtained represent significant improvements over previous classification algorithms applied to artificial sensitive skins. It is shown that features based on touch duration and intensity are sufficient to provide a good classification of touch modality. Gender and cultural background were examined and found to have no statistically significant effect on the classification results.

Interpretation of Social Touch on an Artificial Arm Covered with an EIT-based Sensitive Skin

During social interaction humans extract important information from tactile stimuli that improves their understanding of the interaction. The development of a similar capacity in a robot will contribute to the future success of intuitive human–robot interactions. This paper presents experiments on the classification of social touch on a full-sized mannequin arm covered with touch-sensitive artificial skin. The flexible and stretchable sensitive skin was implemented using electrical impedance tomography. A classifier based on the LogitBoost algorithm was used to classify six emotions and six social messages transmitted by humans when touching the artificial arm. Experimental results show that classification of social touch can be achieved with accuracies comparable to those achieved by humans.

Improved Image Reconstruction for an EIT-Based Sensitive Skin With Multiple Internal Electrodes

Electrical impedance tomography (EIT) is a technique used to estimate the internal conductivity of an electrically conductive body by using measurements made only at its boundary. If this body is made of a thin, flexible, and stretchable material that responds to touch with local changes in conductivity, it can be used to create an artificial sensitive skin. Mathematically, the EIT reconstruction problem is an ill-posed nonlinear inverse problem in which it is commonly assumed that electrodes are located only on the surface of the body. In a thin sensitive skin, however, electrodes can readily be located within the 2-D conducting domain. This paper compares existing electrode-drive patterns with new patterns in which a number of reference electrodes are located inside of the sensitive skin. Simulation results and experimental data show improvements in both resolution and robustness to noise of the reconstructed image. These improvements are shown to be consistent for several commonly used regularization methods.

Touch modality interpretation for an EIT-based sensitive skin

During social interaction, humans extract important information from tactile stimuli that improves their understanding of the interaction. The development of a similar capacity in a robot will contribute to the future success of intuitive human-robot interaction. This paper presents a method of touch sensing based on the principle of electrical impedance tomography (EIT) that can be used to implement a large, flexible and stretchable artificial sensitive skin for robots. A classifier based on the “LogitBoost” algorithm is used to classify the modality of six different types of touch on an experimental EIT-based skin. Experiments showed that the modality of touch was correctly classified in approximately 80% of the trials. This is comparable with the experimental accuracy of a human touch recipient. The classification accuracies show significant improvements from previous classification algorithms applied to different artificial sensitive skins.

Electrical Impedance Tomography for Artificial Sensitive Robotic Skin: A Review

Electrical impedance tomography (EIT) is a nondestructive imaging technique used to estimate the internal conductivity distribution of a conductive domain by taking potential measurements only at the domain boundaries. If a thin electrically conductive material that responds to pressure with local changes in conductivity is used as a conductive domain, then EIT can be used to create a large-scale pressure-sensitive artificial skin for robotics applications. This paper presents a review of EIT and its application as a robotics sensitive skin, including EIT excitation and image reconstruction techniques, materials, and skin fabrication techniques. Touch interpretation via EIT-based artificial skins is also reviewed.

Perception of an android robot in Japan and Australia: A cross-cultural comparison

This paper reports the results from two experiments, conducted in Japan and Australia, to examine people’s perception and trust towards an android robot. Experimental results show that, in contrast to popular belief, Australian participants perceived the robot more positive than Japanese participants. This is the first study directly comparing human perception of a physically present android robot in two different countries.

Shared spaces: Media art, computing, and robotics

This article describes aspects of collaboration between a media artist (Velonaki) and robotics scientists (Scheding, Rye, Stefan Williams, and Durrant-Whyte) who have been working together over the last five years, leading to the formation of a center dedicated to cross-disciplinary research, called the Centre for Social Robotics. Both media arts and robotics have strong research directions in human-machine interaction, using computer technology as a tool to realize their visions. The article begins with a brief review of Velonakis earlier work in media art, followed by a description of the major interactive autokinetic artwork, Fish-Bird Circle B--Movement C, that was created by the team. The technological realization of the artwork is described, as are aspects of the teams model of collaboration. Finally, the article describes some of their current projects.

Perception of a humanoid robot: A cross-cultural comparison

This study focuses on differences and similarities of perception of a small humanoid robot between Japanese and Australian participants. Two conditions were investigated: participants actively interacting with the robot and bystanders observing the interaction. Experimental results suggested that, while the robot was perceived as highly likeable, Japanese participants rated the robot higher for animacy, intelligence and safety. Furthermore, passive observations of the interaction (rather than active interaction) resulted in higher ratings by Japanese participants for anthropomorphism, animacy, intelligence and safety. The findings are discussed in terms of cultural background and robot perception.

Group Comfortability When a Robot Approaches

This paper investigates the level of comfort in people with different robot approach paths. While engaged in a shared task, 45 pairs of participants were approached by a robot from eight different directions and asked to rate their level of comfort. Results show that comfortability patterns of individuals in pairs is different to lone individuals when they are approached by a robot. This in turn influences how comfortable a group is with different robot approach paths.

A comparison of unsupervised learning algorithms for gesture clustering

Gesture recognition is an important aspect of interpersonal social interaction. Developing a similar capacity in a robot will improve human-robot interaction. Various unsupervised clustering methods applied to clustering a set of dynamic human arm gestures are compared. Unsupervised clustering is important in gesture recognition as it imposes no a priori bound on the set of gestures. Results are compared using v-measure, a metric that allows differential weighting between clustering homogeneity and completeness. Experiments show that the best clustering method depends on the desired balance between homogeneity and completeness.