Visually-Based Human-Machine-Interaction in a Neural Architecture

摘要

The article presents a neural architecture for gesture-based interaction between a mobile robot and its user. One of the main goals of our research is the greatest possible robustness of the intelligent interface under highly varying environmental conditions. After a short introduction of our mobile robot, a discussion of a reliable operation scenario and the motivation for a gesture-based dialogue in section 1, in section 2 we consider related approaches from the literature. Section 3 gives an overview over the whole neural architecture and outlines what we want, not taking into account the current implementation state. What we currently can is described in section 4. 1 Introduction and operation scenario Figure 1: Our mobile robot MILVA. Provided with highly developed on-board equipment (68040-VME-system, 2 PCsystems, CNAPS-board, framegrabber) and different sensors (3 cameras, laserscanner, ultrasound and infrared distance measures, bumpers) MILVA serves as the testbed for the gestu...