Computer Science and Engineering

Mediating Shared Basis in Situated Human Robot Dialogue

Supported by National Science Foundation (10/1/2012 - Present), in collaboration with Professor Ning Xi (Co-PI) and The Robotics and Automation Laboratory at MSU.

Humans and robots have different representations of the shared environment. They also have different capabilities to attend and respond to the unexpected events in the environment, To support language based communication, humans and robots need to establish a shared basis and jointly handle exceptions. To address this issue, this work intends to develop a novel framework that tightly integrates high level language and dialogue processing with low level sensing and control systems and supports collaborative dialogue to mediate a shared basis between humans and robots.

A view graph

Related Videos:

The following video demonstrates the use of graph-based approach to keep track of collaborative dialogue discourse and to mediate shared perceptual basis between humans and robots.

The following video demonstrates that during nautral language interaction, exceptions occur and exception handling is seamlessly integrated with the lower-level control system.

The following video demonstrates teaching robots new actions through natural language dialogue.

Related Papers: