K. E. Bekris, A. A. Argyros, and L. E. Kavraki, “Exploiting Panoramic Vision for Angle-Based Robot Navigation,” in Lecture Notes in Computer Science, Vol. 33, Springer, 2006, pp. 229–251.
Omni-directional vision allows for the development of techniques for mobile robot navigation that have minimum perceptual requirements. In this work, we focus on robot navigation algorithms that do not require range information or metric maps of the environment. More specifically, we present a homing strategy that enables a robot to return to its home position after executing a long path. The proposed strategy relies on measuring the angle between pairs of features extracted from panoramic images, which can be achieved accurately and robustly. In the heart of the proposed homing strategy lies a novel, local control law that enables a robot to reach any position on the plane by exploiting the bearings of at least three landmarks of unknown position, without making assumptions regarding the robot’s orientation and without making use of a compass. This control law is the result of the unification of two other local control laws which guide the robot by monitoring the bearing of landmarks and which are able to reach complementary sets of goal positions on the plane. Long-range homing is then realized through the systematic application of the unified control law between automatically extracted milestone positions connecting the robot’s current position to the home position. Experimental results, conducted both in a simulated environment and on a robotic platform equipped with a panoramic camera validate the employed local control laws as well as the overall homing strategy. Moreover, they show that panoramic vision can assist in simplifying the perceptual processes required to support robust and accurate homing behaviors.