Human-robot interaction requires the robot to explicitly reason on human environments and on its own capacities to achieve tasks in a collaborative way with a human partner. We have devised a decisional framework for human-robot interactive task achievement, embedded in a cognitive architecture, and that is aimed to allow the robot not only to accomplish its tasks but also to produce behaviours that support its commitment vis-a-vis its human partner and to interpret human behaviours and intentions. Together and in coherence with this framework, we develop and experiment various task planners and interaction schemes that allow the robot to select and perform its tasks while taking into account explicitly the human abilities as well as the constraints imposed by the presence of humans, their needs and preferences. We present the first results obtained by our "human-aware" task and motion planners and discuss how they can be extended.
展开▼
