Skip to main content
eScholarship
Open Access Publications from the University of California

Scholarly Works (3 results)

  • Thesis
  • Peer Reviewed
UC San Diego Electronic Theses and Dissertations (2017)

Social robots are becoming a part of everyday life, from household smart companions to education and healthcare assistants, assembly robots in factories and museum guide robots, they adapt different appearances and exhibit a range of capabilities and duties. These robots are benefiting from machine perception systems that automatically recognize people, recognize their facial expressions, and the surrounding environment. In this thesis, we focus on RUBI, a social robot designed to interact with toddlers in classroom and enrich the early childhood education environments. We develop perception algorithms for RUBI to recognize faces while interacting with toddlers in the classroom. We use facial recognition, along with facial expression recognition to analyze the social structure of the classroom and to monitor the emotional development of toddlers in the classroom. In the first two chapters of this thesis, we show that RUBI discovers useful aspects of the social structure of the toddler's group, as well as the children's preferences for different activities and toddler's preferences to play with or to avoid playing with other specific children. These studies illustrate that social robots may become a useful tool in early childhood education to discover socio-emotional patterns over time and to monitor toddlers development.

In the next chapters, we focus on active object recognition in RUBI. While interacting with children, RUBI can teach object names to children, to extend their vocabulary and monitor their learning skills. In chapter 3, we introduce GERMS, a dataset designed to accelerate progress on active object recognition in the context of human robot interaction. In chapter 4, a deep neural network is used for joint prediction of the object label and the action. A generative model of object similarities based on the Dirichlet distribution is proposed and embedded in the network for encoding the state of the system. In chapter 5, we propose a method for supervised learning of active object recognition, in which we train a Long Short Term Memory (LSTM) network to predict the best next action on the training set rollouts. We show improved recognition performance by optimizing the observation function and retraining the supervised LSTM network.

    Cover page: Perceptual Algorithms for Social Robots in Early Childhood Education
    • Article
    • Peer Reviewed
    UC San Diego Previously Published Works (2017)
    An active object recognition system has the advantage of acting in the environment to capture images that are more suited for training and lead to better performance at test time. In this paper, we utilize deep convolutional neural networks for active object recognition by simultaneously predicting the object label and the next action to be performed on the object with the aim of improving recognition performance. We treat active object recognition as a reinforcement learning problem and derive the cost function to train the network for joint prediction of the object label and the action. A generative model of object similarities based on the Dirichlet distribution is proposed and embedded in the network for encoding the state of the system. The training is carried out by simultaneously minimizing the label and action prediction errors using gradient descent. We empirically show that the proposed network is able to predict both the object label and the actions on GERMS, a dataset for active object recognition. We compare the test label prediction accuracy of the proposed model with Dirichlet and Naive Bayes state encoding. The results of experiments suggest that the proposed model equipped with Dirichlet state encoding is superior in performance, and selects images that lead to better training and higher accuracy of label prediction at test time.
      Cover page: Deep active object recognition by joint label and action prediction
      • Article
      • Peer Reviewed
      UC San Diego Previously Published Works (2021)
      Commensurate with constant technological advances, social robots are increasingly anticipated to enter homes and classrooms; however, little is known about the efficacy of social robots as teaching tools. To investigate children's learning from robots, 1- to 3-year-olds observed either a human or a robot demonstrate two goal-directed object manipulation tasks and were then given the opportunity to act on the objects. Children exhibited less imitation from robotic models that varied with task complexity and age, a phenomenon we term the "robot deficit." In addition, the more children engaged with the robot prior to administration of the imitation task, the more likely they were to replicate the robot's actions. These findings document how children are able to learn from robots but that ongoing design of robotic platforms needs to be oriented to developing more socially engaging means of interacting.
        Creative Commons 'BY-NC-SA' version 4.0 license
        Top