Research

The INSIDE initiative is driven by the following key research goals:

  • Explore the scientific and technological challenges involved in developing symbiotic human-robot interactions in the context of a physical game involving children. We investigate how to extend adhoc teamwork and approaches on multiagent planning under uncertainty to cooperative scenarios involving human and robot agents.
  • Explore the scientific and technological challenges involved in developing robust forms of natural interaction (including spoken interactions) and how contextual and environment information (collected by a sensor network) can improve the communication between robot and human agents during joint collaborative tasks involving activities in a physical environment.

Broadly speaking, INSIDE explores the benefits that the interaction with a heterogeneous network of intelligent devices can bring to the therapy of children with Autism Spectrum Disorder (ASD).

In INSIDE we also investigate both novel hardware (such as biometric sensors) and processing algorithms (for example, for natural language-based interaction) that enable the system as a whole to infer the user’s behavior and goals and act upon these, facilitating a natural and cooperative interaction between the system and the human users in the context of joint human-robot cooperative tasks.

INSIDE is organized around 6 tasks:

  • Task 1 investigates multi-agent planning for symbiotic interaction. This task looks into new models and algorithms for decentralized decision-making under uncertainty in scenarios with human and artificial agents involved in symbiotic interaction.
  • Task 2 investigates how natural interaction (including natural language communication) can be established between human and robotic agents during joint execution of a collaborative spacial task. In particular, we investigate new algorithms that enable the use of task, contextual and environment information provided by a sensor network deployed in the environment (including cameras and biometric sensors) to attain richer and more natural interactions between the human and robotic agents.
  • Task 3 focuses on the design of the interaction scenarios. Preliminary studies used to inform the refinement of the scenario and the design of the system architecture are also be conducted in the context of this task.
  • Task 4 is oriented toward technology development and integration. Closely following the scenario design in Task 3, it is in the context of Task 4 that the design of the sensor network architecture, and the perception and control requirements for the system as a whole are defined.
  • Task 5 evaluates of the outcomes of the project in terms of therapeutical impact.
  • Task 6 is concerned with dissemination and technology transfer.

task-diagram