Abstract — In this paper we present a new robot control and learning framework. By integrating previously presented as well as new methods, the robot is able to learn an invariant and generic movement representation from a human tutor. We argue that in order to apply such generic representations to new situations and thus create a flexible system, the use of interaction is beneficial. The interaction is based on a kinematically controlled model of a human tutor, which is used as a model-based filter and also for recognizing postures that influence the interaction. In addition, a new movement segmentation scheme is presented that is based on correlating movements by the tutor’s hand with the salient objects in the scene. The focus of this paper is on the interactive learning aspects of the system and particular emphasis is given to an experiment in which the humanoid robot ASIMO learns from a human tutor. The system includes extensive generalization capabilities that result from an online adaption of the robot’s body schema and the exploitation of inter-trial variance from multiple demonstrations. This enables the robot to reproduce the movement in new situations. For example, a stacking task that the tutor performed one-handed can be executed bimanually by the robot. I.

Abstract — This paper presents an architecture for learning and reproducing movements with a robot in interaction with a human teacher. We focus on the movement representation and propose three enhancements to increase generalization capabilities: Firstly, we introduce a flexible task-level movement representation that is based on neuropsychological findings. Movement is represented in task-oriented frames of reference, and generalizes to a variety of different situations. Secondly, we propose a mechanism to decouple the task descriptors from the perceived objects in the robot’s environment. This allows to formulate a set of generic controllers, and to interactively create associations with perceived objects. Thirdly, we introduce a method to dynamically modify the system’s body schema to account for structural changes such as having grasped a tool. The changes are consistently treated in the kinematics computations. This permits to generalize movements to be carried out in different ways, for instance with different hands or bi-manually. A set of experiments in an interactive imitation learning situation underline the capabilities of the proposed concepts. I.

Abstract — In this paper we present an approach to transfer human-like reflex behavior to robots by utilizing leaky integrate-and-fire neurons. For the acceptance of robots in general and humanoid robots, which are even closer to people’s daily life, in particular a main aspect is their appearance and how they act and move in human centered environments. Especially safety strategies are crucial for a widespread acceptance of these machines. In our work we target this safety aspect by approaching this issue from the direction how humans respond to external stimuli. To achieve such human-like reflexes a general reflex unit, based on special variants of the leaky integrate-and-fire neuron model has been built. Instances of this reflex unit are adapted to special reflex types and connected to form dependent reflex behaviors. The concept of these neural structures and its evaluation by means of several experiments are presented in this paper. The results are depicted in detail and future aspects of our ongoing work are addressed.