Narrow Results

We develop a collision-avoiding mechanism for a system of individual agents (pedestrians) that move in a crowd trying to reach their different goal points. The agents avoid collisions on the basis of a model of the other agents' behavior, a "theory of mind," which is realized at different levels through an iterative process (the first level, or level 0, corresponds to ignoring the other agents' behavior, level 1 to assuming that the other agents will ignore each other, and so on).

The model is conceived in order to perform an evolutionary simulation of some basic parameters that determine the agent's sensorial, cognitive and behavioral system (the perception of the agent's own size, the attraction to the goal, the radius and angle of the field of view and the level of the theory of mind).

In this preliminary work we present our model, show that it reproduces some of the simplest organized behaviors of a system of pedestrians, and focus on some features of the theory of mind, as the difference between odd and even levels.

This paper is concerned with the simulation of human-likess capabilities in synthetic characters within the domain of Personal and Social Education. Our aim was to achieve socially meaningful and engaging interactions with children in the 8–12 age group to enable an exploration of bullying and coping strategies. We consider the engagement between the interacting partners, focusing particularly on the affective and empathic aspects of this relationship. We have used Theory of Mind methods to enable us to evaluate children's understanding of social scenarios and the thinking of others. The results from this 345 children study highlight that children are able to recognize and interpret affect in synthetic characters and are empathically engaged with the characters in the scenarios.

We endow agents with the capability to open interactions based on their perception of the gaze and direction of attention of others in a virtual environment. The capability is geared towards the earliest part of interaction initiation, where agents may be at some distance from each other and may not initially have knowledge of each other's presence. An important idea in our work is that the start of interaction be initiated in a graceful manner involving exchanges of subtle cues before overt interaction commitments are made. Synthetic vision, attention and memory are used to implement the perceptually-based agent theory of mind. Theory of Mind is used to infer information about the intention of the other to interact based on their eye, head and body directions, locomotion and greeting gestures. An agent's interaction behavior is therefore driven not only by its interaction goal, but also by its theory of the goal of the other based on perception. We have implemented this system and used it to automate and evaluate social interaction behaviors between humans and agents in a virtual environment.

Understanding intent is an important aspect of communication among people and is an essential component of the human cognitive system. This capability is particularly relevant to situations that involve collaboration among multiple agents or detection of situations that can pose a particular threat. In this paper, we propose an approach that allows a physical robot to detect the intent of others based on experience acquired through its own sensory–motor capabilities, then use this experience while taking the perspective of the agent whose intent should be recognized. Our method uses a novel formulation of hidden Markov models (HMMs) designed to model a robot's experience and interaction with the world when performing various actions. The robot's capability to observe and analyze the current scene employs a novel vision-based technique for target detection and tracking, using a nonparametric recursive modeling approach. We validate this architecture with a physically embedded robot, detecting the intent of several people performing various activities.

Children with autism spectrum disorders have difficulties in identifying situation-based emotions, which is a fundamental ability for mind reading. Social robots received increased attention as assisting tools for improving the social and emotional skills of children with autism. This study investigates whether the social robot Probo can help children with autism spectrum disorders to enhance their performance in identifying situation-based emotions. Three participants (age between 5 and 6) diagnozed with autism spectrum disorders were included in a single case AB experimental design, with intersubjects replications. The results show that children's performance improved with moderate to large effect sizes in identifying both sadness and happiness. Based on these results, we intend to perform more extensive investigations regarding the effectiveness of robot assisted therapy in improving social-emotional abilities for children with autism spectrum disorders.

In recent years, a number of studies that have examined how social experiences are related to children's theory of mind development, have found that: (1) the frequency of mothers' mental state utterances used in mother-child picture-book reading, is correlated with children's theory of mind abilities; (2) mothers' use of cognitive terms is related more strongly to children's theory of mind performances than the mothers' references to other mental states, such as desires or emotions (Adrian, Clemente, Villanueva, Rieffe, 2005; Ruffman, Slade, Crowe, 2002; Taumoepeau, Ruffman, 2006; Dunn, 2002). Despite the evidence for the role of mothers' language, there is disagreement over how exactly it improves children's theory of mind development. In short, mentalistic comments contain distinctive words, grammatical constructions and pragmatic features. The question is, however, which factor is critical (de Rosnay, Pons, Harris, Morrell, 2004).

The present study addresses this issue and focuses on relationship between mothers' mental state terms and children's performances in theory of mind tasks (emotion understanding and false belief tasks).

Mothers were asked to read some pictures to 10 children between 3;0 and 5;0.

Among the different mental state references (perceptual, emotional, volitional, cognitive, moral and communicative), it was found that the frequency and variety of mothers' mental state words were significantly associated with children's mental lexicon. In addition, emotional terms correlated positively with children's false belief performance. Kind of emotional words that are used by the mothers with reference to the Italian language will be discussed.

We introduce a collision avoiding method for simulated agents based on recursive thinking, in order to understand if more developed "Theory of Mind" abilities (used to predict the motion of the others) can allow the agents to perform in a better way in a complex environment. Agents move in their environment trying to reach a goal while avoiding collisions with other agents. They try to predict the motion of the others taking in consideration also the others' prediction. This introduces a recursive process, that we stop at a given "recursion level". We study the evolution of this level, showing that there is a difference between even and odd levels, that leads to a correspondence with, the hawk-dove game, and that the collision avoiding abilities grow with the recursion level l, at least when the problem to be solved is complex enough. We also show that if the fitness function is properly chosen, the system converges to a stable state composed almost only of high level agents.