Future Work

Needless to say, much work remains to be done. Future work will concentrate on four major aspects:

1. Improve the computational performance of the system to improve robot/environment interaction.
2. Generate high level descriptions and semantic maps including the 3D information, e.g., in XML format. The semantic maps will contain spatial 3D data with descriptions and labels.
3. Integrate a camera and enhance the semantic interpretation by fusing color images with range data. The aperture angle of the camera will be enlarged using a pan and tilt unit to acquire color information for all measured range points.
4. Enlarge the database with more objects of an indoor and outdoor environment and build an explicit knowledge base, i.e., specifying a semantic net containing general object relations as well as links to the object database [14].

The final goal of object detection and localization is to develop unrestricted, automatic and highly reliable algorithms that could be used in scenarios like RoboCup Rescue.