作者: J.-S. Gutmann , M. Fukuchi , M. Fujita
DOI: 10.1109/ROBOT.2005.1570257
关键词:
摘要: With the development of biped robots, systems became able to navigate in a 3 dimensional world, walking up and down stairs, or climbing over small obstacles. We present method for obtaining labeled 2.5D grid map robot's surroundings. Each cell is marked either as floor obstacle contains value telling height obstacle. Such maps are useful path planning collision avoidance. The uses novel combination 3D occupancy robust sensor data interpretation fine resolution values. evaluate our approach using stereo vision on humanoid robot QRIO show advantages previous methods. Experimental results from navigation runs an course demonstrate ability generate detailed autonomous navigation.