A decisional framework for autonomous robots interacting with humans

The presence of humans in its environment and the necessity to interact with them raise new challenges to the robot. Indeed, they require explicit reasoning on the human environment and on the robot capacities to achieve its tasks in a collaborative way with a human partner. This paper focuses on architectural aspects and more particularly on the organization of the robot decisional abilities for interacting with people. Indeed, our objective is to develop a management of human interaction that would be an integral part of a general robot control architecture. This should hopefully allow to come up with a principled way to deal with human-robot interaction for robot task achievement in presence of humans or in synergy with humans. Such an architecture should be the framework that would allow the robot to produce behaviors to accomplish its tasks but also produce behaviors that support its engagement vis-a-vis its human partner and interpret similar behaviors from him. We also intend to use the proposed approach as a framework in which we would develop and experiment various task planners and interaction schemes. Indeed, the robot should be able, for instance, to devise plans that allow it to execute its actions and to place itself to be seen by or to observe humans, according to the task.