Dataset Information

Robots Learn to Recognize Individuals from Imitative Encounters with People and Avatars.

ABSTRACT: Prior to language, human infants are prolific imitators. Developmental science grounds infant imitation in the neural coding of actions, and highlights the use of imitation for learning from and about people. Here, we used computational modeling and a robot implementation to explore the functional value of action imitation. We report 3 experiments using a mutual imitation task between robots, adults, typically developing children, and children with Autism Spectrum Disorder. We show that a particular learning architecture--specifically one combining artificial neural nets for (i) extraction of visual features, (ii) the robot's motor internal state, (iii) posture recognition, and (iv) novelty detection--is able to learn from an interactive experience involving mutual imitation. This mutual imitation experience allowed the robot to recognize the interactive agent in a subsequent encounter. These experiments using robots as tools for modeling human cognitive development, based on developmental theory, confirm the promise of developmental robotics. Additionally, findings illustrate how person recognition may emerge through imitative experience, intercorporeal mapping, and statistical learning.

SUBMITTER: Boucenna S

PROVIDER: S-EPMC4741103 | biostudies-literature | 2016 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Robots Learn to Recognize Individuals from Imitative Encounters with People and Avatars.

Boucenna Sofiane S Cohen David D Meltzoff Andrew N AN Gaussier Philippe P Chetouani Mohamed M

Scientific reports 20160204

Prior to language, human infants are prolific imitators. Developmental science grounds infant imitation in the neural coding of actions, and highlights the use of imitation for learning from and about people. Here, we used computational modeling and a robot implementation to explore the functional value of action imitation. We report 3 experiments using a mutual imitation task between robots, adults, typically developing children, and children with Autism Spectrum Disorder. We show that a partic ...[more]

PMID: 26844862

Similar Datasets

Project description:IntroductionSocial skills training (SST) is used to help individuals with autism spectrum conditions (ASC) better understand the perspectives of others and social interactions, develop empathy skills, and learn how to engage with others socially. However, many individuals with ASC cannot easily sustain high motivation and concentration during such an intervention when it is administered by humans. We developed a social skills training program using multiple humanoid robots (STUH), including an android robot, that aimed to enable individuals with ASC to become familiar with the perspectives of others and improve their sociability and empathy skills. The objective of the present study was to investigate the effectiveness of STUH for these individuals.MethodsIn STUH, we prepared 50 social exercises that consisted of conversations and behavioral interactions between an android robot and a simple humanoid robot. We prepared another humanoid robot that featured a cartoon-like and mechanical design, which played the role of host. In the first half-session of STUH, participants worked on the exercise from the perspective of an outsider. In the second half-session of STUH, they simulated experience by using robots as their avatars. The intervention associated with STUH was conducted for five days in total. We conducted an analysis of variance (ANOVA) featuring the intervention time point as the independent variable to examine changes in each score on the sociability index items.ResultsIn total, 14 individuals with ASC participated in the study. The results of multiple comparison tests using the Bonferroni method indicated that all sociability index items improved between preintervention and follow-up. Our program enabled the participants to become familiar with the perspectives of others and improve their sociability.DiscussionGiven the promising results of this study, future studies featuring long-term follow-up should be conducted to draw definitive conclusions about the efficacy of our training system.

Dataset Information

Robots Learn to Recognize Individuals from Imitative Encounters with People and Avatars.

Publications

Robots Learn to Recognize Individuals from Imitative Encounters with People and Avatars.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets