Towards 3D object maps for autonomous household robots

• Published in: 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems pp. 3191 - 3198
• Main Authors: Rusu, R.B., Blodow, N., Marton, Z., Soos, A., Beetz, M.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.10.2007
• Subjects: Clouds; Cognitive robotics; Context modeling; Inference algorithms; Intelligent robots; Libraries; Orbital robotics; Robot sensing systems; Robotics and automation; Robustness
• ISBN: 9781424409112; 142440911X
• ISSN: 2153-0858
• DOI: 10.1109/IROS.2007.4399309

This paper describes a mapping system that acquires 3D object models of man-made indoor environments such as kitchens. The system segments and geometrically reconstructs cabinets with doors, tables, drawers, and shelves, objects that are important for robots retrieving and manipulating objects in these environments. The system also acquires models of objects of daily use such glasses, plates, and ingredients. The models enable the recognition of the objects in cluttered scenes and the classification of newly encountered objects. Key technical contributions include (1) a robust, accurate, and efficient algorithm for constructing complete object models from 3D point clouds constituting partial object views, (2) feature-based recognition procedures for cabinets, tables, and other task-relevant furniture objects, and (3) automatic inference of object instance and class signatures for objects of daily use that enable robots to reliably recognize the objects in cluttered and real task contexts. We present results from the sensor-based mapping of a real kitchen.