The focus of this research is on designing and developing interfaces for human-robot interaction through which non-expert users can specify a task to a robot. Specifically, we are studying methods to better understand human-robot interaction through a collaborative robotic interface for humanoid domestic service robots, where the user can interact with the robot intuitively using multimodal cues of language, gestures and gaze. We are applying a user-centric approach by conducting user studies to model how a human uses speech, gestures, and gaze naturally to collaborate with a robot, and then using these models to design intuitive human-robot interaction interfaces.
This research is being funded by the Opus-LAP program of NCN, and we have collaborating partners at the Technical University, Vienna (TUW), and Czech Technical University, Prague (CTU).
The focus of this research is to study how children interact with robots, and to develop guidelines for designing social robots for children. We follow in-the-wild methodology where we conduct in-situ workshops involving robots and children in naturalistic settings such as schools, day-care centers, or museums. The activities include book reading, dancing, creating an animation, and so on. We have conducted such workshops in Poland, Japan, and Turkey, and are studying cultural aspects of child-robot interaction as well. We have studied the effect of emotional feedback on robot-assisted learning. We are collaborating with Hosei University to design a Robot-assisted Learning intervention system for detecting potentially risky behaviors during laboratory experiments.
In order to deploy robots in unstructured environments such as homes, hospitals or shops robots must be able to cope with environment changes without the need for re-programming or re-learning their skills. The line of research of robot skill adaptation aims to find the right knowledge representations and algorithms that will enable robots to use their existing skills and knowledge and adapt them autonomously to previously unseen situations and settings.
