Towards Learning by Interacting Britta Wrede 1,2 , Katharina J. Rohlfing 1,2 , Marc Hanheide 1,2 , and Gerhard Sagerer 1,2 1 Bielefeld University, Applied Computer Science 2 Institute for Cognition and Robotics (CoR-Lab) 33501 Bielefeld, Germany Abstract. Traditional robotics has treated the question of learning as a one way process: learning algorithms, especially imitation learning ap- proaches, are based on observing and analysing the environment before carrying out the ‘learned’ action. In such scenarios the learning situation is restricted to uni-directional communication. However, insights into the process of infant learning more and more re- veal that interaction plays a major role in transferring relevant information to the learner. For example, in learning situations, the interactive situa- tion has the potential to highlight parts of an action by linguistic and non- linguistic features and thus to guide the attention of the learner to those aspects that the tutor deems relevant for her current state of mind. We argue that learning necessarily needs to be embedded in an in- teractive situation and that developmental robotics, in order to model engagement in interaction, needs to take the communicative context into account. We further propose that such an approach necessarily needs to take three aspects into account: (1) multi-modal integration at all pro- cessing levels (2) derivation of top-down strategies from bottom-up pro- cesses and (3) integration of single modules into an interactive system in order to facilite the first two desiderata. 1 Introduction For many years robotic research has aimed at developing robots that are able to learn from observation or interaction with their environment. In the domain of cognitive robotics it can be seen as an agreement that embodiment is a foun- dation for any kind of interactive or simply active learning [7,38]. Consequently, many approaches have thereby been motivated by findings from infant devel- opment, thus implicitly implying that their goal is to model human cognition. However, most approaches have either applied offline learning to simply enable online recognition or have treated learning and recognition as rather distinct processes. Other approaches exploit the embodiment of the system by enabling the robot to interact with the environment. However, only rarely has the social and cognitive knowledge of the tutor been taken into consideration, although it is widely accepted that a social learning situation itself comprises particular information facilitating the learning process and increase its effectivity. There- fore, we argue in this paper that learning – with a focus on the acquisition of B. Sendhoff et al. (Eds.): Creating Brain-Like Intelligence, LNAI 5436, pp. 139–150, 2009. c  Springer-Verlag Berlin Heidelberg 2009