P. Ravindra De Silva

Modeling human affective postures: an information theoretic characterization of posture features

One of the challenging issues in affective computing is to give a machine the ability to recognize the mood of a person. Efforts in that direction have mainly focused on facial and oral cues. Gestures have been recently considered as well, but with less success. Our aim is to fill this gap by identifying and measuring the saliency of posture features that play a role in affective expression. As a case study, we collected affective gestures from human subjects using a motion capture system. We first described these gestures with spatial features, as suggested in studies on dance. Through standard statistical techniques, we verified that there was a statistically significant correlation between the emotion intended by the acting subjects, and the emotion perceived by the observers. We used Discriminant Analysis to build affective posture predictive models and to measure the saliency of the proposed set of posture features in discriminating between 4 basic emotional states: angry, fear, happy, and sad. An information theoretic characterization of the models shows that the set of features discriminates well between emotions, and also that the models built over‐perform the human observers. Copyright

STB: Child-Dependent Sociable Trash Box

In this paper, we explore the effective social cues, behaviors, and potential interactive spaces (the proxemics) in the approach of a child-dependent robot. The proposed social trash box (STB) robot uses the above interactive social cues and vocal interactions to build a social coupling with children in order to induce their assistance in the collection of trash. We discuss the minimalist design of mechanism for the STB, as well as the effectiveness of the above factors, through an experiment which is conducted in a child-centric environment. A model-based unsupervised approach is proposed to elicit the proxemic information (interactive spaces) by considering the dynamic (i.e., the interactive distance and duration of interactions) interaction of the children.

Grounding affective dimensions into posture features

Many areas of today’s society are seeing an increased importance in the creation of systems capable of interacting with users on an affective level through a variety of modalities. Our focus has been on affective posture recognition. However, a deeper understanding of the relationship between emotions in terms of postural expressions is required. The goal of this study was to identify affective dimensions that human observers use when discriminating between postures, and to investigate the possibility of grounding this affective space into a set of posture features. Using multidimensional scaling, arousal, valence, and action tendency were identified as the main factors in the evaluation process. Our results showed that, indeed, low-level posture features could effectively discriminate between the affective dimensions.

STB: human-dependent sociable trash box

We developed a Sociable Trash Box (STB) as a children-assisted robot able to collect the trash in order to convey its intentional stance to children. The STB is capable of engaging manifold affiliation behaviors to build a social rapport with children by collecting the trash around their environment. In particular, the STB is a child-dependent robot that walks alone in a public space for tracing humans and trash for the purpose of collecting the trash. The robot is incapable of collecting the trash by itself, and it engages by using interactive behaviors and vocalizations to make a social coupling with children based on the robots anticipation to accomplish its goal. The present experiment investigates how STB behaviors are effective in conveying intentions to evoke childrens social interactions and to assist in collecting the trash in their environment.

A Computational Model for Recognizing Emotion with Intensity for Machine Vision Applications

One of the challenging issues in affective computing is to give a machine the ability to recognize the affective states with intensity of a person. Few studies are directed toward this goal by categorizing affective behavior of the person into a set of discrete categories. But still two problems exist: gesture is not yet a concern as a channel of affective communication in interactive technology, and existing systems only model discrete categories but not affective dimensions, e.g., intensity. Modeling the intensity of emotion has been well addressed in synthetic autonomous agent and virtual environment literature, but there is an evident lack of attention in other important research areas such as affective computing, machine vision, and robotic. In this work, we propose an affective gesture recognition system that can recognize the emotion of a child and the intensity of the emotion states in a scenario of game playing. We used levels of cognitive and non-cognitive appraisal factors to estimate intensity of emotion. System has an intelligent agent (called Mix) that takes these factors into consideration and adapt the game state to create a more positive interactive environment for the child.

MAWARI: a social interface to reduce the workload of the conversation

In this paper, we propose a MAWARI-based social interface as an interactive social medium to broadcast information (e.g. news, etc.). The interface consists of three sociable creatures (MAWARIs) and is designed with minimalism designing concepts. MAWARI is a small scale robot that has only body gestures to express (or interact) its attractive social cues. This helps to reduce the observing workload of the user, because during the conversation the creature just uses vocal interactions mixed with attractive body gestures. The proposed interface is capable of behaving in two kinds of states: behavior as a passive social interface and also as an interactive social interface in order to reduce the conversation workload of the participant.

Therapeutic Tool for Develop Child Nonverbal Communication Skills through Interactive Game

In this paper, an interactive multi-agent based system that recognizes childs emotions and the intensity of emotions to build systems for therapeutic purposes (developed childs non-verbal communication skills) is presented. It introduces the development of an arousal perception agent that uses a novel emotion intensity estimation model. The arousal perception agent uses cognitive and non-cognitive factors to estimate a childs intensity of emotions in real time. Flexible and a novel adaptation model based on emotional intensity is developed for the proposed situational control agent. The situational control agent tries to adjust the intensity of negative and positive emotions by changing the status of the game to encourage children to express natural emotions. This situational control agent reacts as therapy (adjusting motivational and encouragement support) for developing childrens emotional expression through affective body gestures. An animated pedagogical agent gives motivational help with instructions (like therapy) as a means of encouragement to naturally express emotions by adapting the system in an interactive manner.

STB: intentional stance grounded child-dependent robot

This paper reports on a children-dependent robotic approach to establish asynchronous child assistance with a social rapport network for the purpose of collecting trash from a public space. Our sociable trash box robot (STB) was unable to collect trash by itself. However, it did succeed in conveying its intentions to collect the trash from children. The main purpose of this study is to investigate the effective social cues, behaviors, and other essential factors to facilitate children in their anticipation of the behavior of a sociable trash box robot. The STB engages by using interactive social cues and vocal interactions to build a social coupling with children in order to induce their assistance in collecting trash. We discuss the minimalism designing mechanism of the STB, as well as the effectiveness of the above factors through an experiment which is conducted in a child-centric environment.

Sociable trash box

The STB is capable of engaging manifold affiliation behaviors to build a social rapport toward the goal of collecting trash around an environment. In particular, STB is a child-dependent robot that walks alone in a public space for the purpose of tracing humans and trash and to collect the trash. In a crowded space, STBs move toward the trash by engaging with an attractive twisting motion (behaviors) and vocal interaction to convey STBs intention to children. Our STB robot is incapable of collecting the trash by itself. In this sense, children have to infer a robots intentional stance or expectation for interaction with the STB. To collect trash while creating social rapport with children is a novel concept. The STB engages with twisting and bowing motions when children put trash into an STB container (figure 1).

Designing Sociable CULOT as a Playground Character

CULOT is designed as a playground character with the aim of grounding the playground language (verbal, non-verbal, playing-rules, etc) between children through play-routing while experiencing the pleasure of play. A robot establishes ”persuasiveness” activities inside the playground, through the process of generating play rules/contexts and executive social interactions and engagement toward the intention of ”attachment” of the children to the robot through interaction and activities. The behavior of the robot plays a significant role in executing the above playground activities (or interaction). As a primary study, our focus is to explore how robot behaviors (cues) are capable of generating the playground rules, social interaction and engagement in order to convey its intention to children and extract the potential dimensions in order to design CULOT behaviors as a playground character by considering the above factors.