The Spatial Semantic Hierarchy

This paper reports the new steps undertaken in our work aimed to demonstrate the effectiveness of an omnidirectional vision sensor when conjugated with the Spatial Semantic Hierarchy. The Spatial Semantic Hierarchy was proposed by Benjamin Kuipers as a method for map building with robots. In our work, a robot builds a topological map of an unknown environment, using the Spatial Semantic Hierarchy and an omnidirectional vision system as the only sensor. In the paper, we present the new omnidirectional mirror and the new robot. The new mirror was expressly designed for this application, the robot's chassis was designed to create a synergy with the omnidirectional vision sensor. A complete description of our project is reported, underlying the strict link it is possible to create between omnidirectional vision and the Spatial Semantic Hierarchy. Experiments in simulated environments and in real environments produced positive results.

• Type: Journal
• Year: 2000
• Where: AI
• Authors: Benjamin Kuipers
• Keywords: AI 2000, Artificial Intelligence, Omnidirectional Vision, Omnidirectional Vision Sensor, Spatial Semantic Hierarchy