Options
2010
Conference Paper
Titel
Hierarchical, knowledge-oriented opto-acoustic scene analysis for humanoid robots and man-machine interaction
Abstract
The opto-acoustic scene analysis is an extremely important as well as a challenging task for a humanoid robot. By the opto-acoustic scene analysis, the guided and autonomous exploration of the environment by means of acoustic and/or visual perception is meant. On the one hand, the perception ability is necessary to interact with humans in a humanoid way. On the other hand, the proximity of the robot has to be analyzed continuously, in order to enable the robot to fulfill its everyday tasks. Thereby, the greatest challenge lies in the wide variety of different perception tasks, e.g. detection, tracking, and identification of persons and different types of objects. This leads to the need of adapted, both, task- and context-dependent perception modules with specific requirements and abilities. Taking these considerations into account, the paper presents a hierarchical, knowledge-oriented concept of a framework for the opto-acoustic scene analysis. The focus of the work is put on formal conditions on one side and the practical realization of a real-time system on the other side. The proposed framework is modular structured and consists of a number of specialized perception modules. To reflect the knowledge-based structure of the framework, an object-oriented environment model is used for continuous inserting, updating and removing the information about the proximity of the robot. Besides the task of analyzing the scene with the reference to already known objects (and persons1), the proposed concept enables the robot to explore a (partially) unknown environment, with the focus on the creation of multimodal signatures for unknown objects and persons. These signatures are used to build an unique representation of the explored objects and enable the robot to recognize them at a later time.