Building environmental models of man-made environments by panoramic sensing

Building environmental models by a vision-guided mobile robot is a key problem in robotics. This paper presents a new strategy of the vision-guided mobile robot for building models of an unknown environment by panoramic sensing. The mobile robot perceives with two types of panoramic sensing: one is for acquiring omnidirectional visual information at an observation point to find the outline structure of the local environment and the other is for acquiring visual information along a route to build local environmental models. Before exploring the environment, the robot looks around and finds the outline structure of the local environment as a reference frame for acquiring the local models. Then the robot builds the local models while moving along the directions of the outline structure (the outline structure is represented by a simple convex polygon, each side of which has a direction). We have implemented the above-mentioned robot behaviors into a mobile robot which has multiple vision agents. The multiple vision agents can simultaneously execute different vision tasks needed for panoramic sensing.

[1]  Alberto Elfes,et al.  Sonar-based real-world mapping and navigation , 1987, IEEE J. Robotics Autom..

[2]  Hiroshi Ishiguro,et al.  Multiple vision agents navigating a mobile robot in a real world , 1993, [1993] Proceedings IEEE International Conference on Robotics and Automation.