Child-Robot Communication and Learning

Objectives

Develop and evaluate the communication and learning capabilities of the ZENO robot, as well as use the robot for enhancing the communication skills of TD children in an edutainment scenario. The design, development and evaluation of these capabilities will be grounded on child-robot interactive scenarios that constitute the second use case of BabyRobot. Long-term experiments (case study evaluations in schools) to verify the progress in the communicative/collaborative abilities of participants will be performed. In addition, the communicative capabilities of the robot will be enhanced via reinforcement learning and language learning from a minimal set of examples using the shared attention and common grounding modules.

Description of Work

  • Use Case 2 Specification and Data Collection Protocols: Working together with educators we will define the communication, collaboration and language learning tasks of use case 2. The main goal is to define scenarios that facilitate the development, demonstration and evaluation of communication capabilities of the robotic platform, as well as teach the children communication/collaboration skills. In this task we will also define the data collection protocols for this use case in order to efficiently evaluate the robot’s capabilities, the children’s communicative performance and the interaction.
  • Learning, Adaptation and Cognitive Development: In use case 2, an important goal is to allow the robot to learn from and adapt during the interaction with the children. The models developed for joint attention, common grounding and especially for shared intentionality will be adapted to the collaboration scenario in order to both predict and assess the collaborative skills of a child. Cognitive models for each individual child participant attention, common grounding and intentionality will also be built.
  • Development of the Communication Scenario: The communication scenario development mainly consists of software development realizing the scenario proper and designing the communication and collaboration games. In addition, we will investigate adaptive learning algorithms, learning by imitation and learning by association. Language learning from very few examples using concept networks will be investigated towards achieving the child-robot play scenario of use case 2.
  • Integration and Evaluation for Use Case 2: The algorithms developed in the previous tasks will be integrated in the ZENO and Furhat platform. An iterative design paradigm will be used to incorporate feedback from the used case 2 evaluation using the ZENO robot into the design and integration process. The robotic platform will be evaluated using objective and subjective metrics.