A system to navigate a robot into a ship structure

Abstract

Abstract. A prototype system has been built to navigate a walking robot into a ship structure. The 8-legged robot is equipped with an active stereo head. From the CAD-model of the ship good view points are selected, such that the head can look at locations with sufficient edge features, which are extracted automatically for each view. The pose of the robot is estimated from the features detected by two vision approaches. One approach searches in stereo images for junctions and measures the 3-D position. The other method uses monocular image and tracks 2-D edge features. Robust tracking is achieved with a method of edge projected integration of cues (EPIC). Two inclinometres are used to stabilise the head while the robot moves. The results of the final demonstration to navigate the robot within centimetre accuracy are given.

Factors Affecting the Accuracy of an Active Vision Head

“…The head. The head has been utilized as an accurate measuring device for the purpose of ROVISION project [11,12]. More specifically, it has been mounted on a walking/climbing and the measurements obtained by it have been used for self-localization of the robot.…”

Edge-Projected Integration of Image and Model Cues for Robust Model-Based Object Tracking

“…Cues other than intensity, color, and texture have been tested (Zelenka 1998;Vincze et al 2001), for example, the maximum gradient, the type of transition at the edge location, and the distance to the previous edge location. However, these cues did not improve robustness.…”

“…Within RobVision, the capacity of two vision systems (Pronto and V4R) is used to extract redundant features from the images. All features extracted by these two vision systems are used to estimate the robot pose in V4R (for more details about this project, see Vincze et al 2001).…”