Maintaining Visibility of a Landmark using Optimal Sampling-based Path Planning

Abstract

An approach to extend sampling-based path planning algorithms to include visual  restrictions is presented. This approach imposes of visual constraints during  the sampling and optimization processes. Four visual constraints are imposed  during sampling: 1) keep the landmark within the sensor field of view, 2) avoid  landmark occlusions, 3) maintaining landmark features near the image center, and  4) limit changes in landmark view orientation. These last two are imposed during  path optimization. The robot task is to maintain these constraints, in an  environment with obstacles, while the robot changes configurations. The sampling-based motion planning algorithm imposes and  maintains both physical and visual restrictions. The process uses a collision checker to detect self-and obstacle-collisions, or landmark occlusions. To infer the landmark  visibility, the algorithm dynamically builds a 3D model of camera field  visibility as seen from the moving robot. To maintaining the landmark features  close to the image center, a distance parameter from the field of view boundary to the landmark is used and optimized. The camera roll angle was included as another element to be optimized, limiting changes in orientation. The algorithm  has been implemented, and both results in simulation and experiments using a real robot manipulator are presented.