Towards Identification of Best Practice Algorithms in 3D Perception and Modeling
Robots need a representation of their environment to reason about and to interact with it. Different 3D perception and modeling approaches exist to create such a representation, but they are not yet easily comparable. This work tries to identify best practice algorithms in the domain of 3D perception and modeling with a focus on environment reconstruction for robotic applications. The goal is to have a collection of refactored algorithms that are easily measurable and comparable. The realization follows a methodology consisting of five steps. After a survey of relevant algorithms and libraries, common representations for the core data-types Cartesian point, Cartesian point cloud and triangle mesh are identified for use in harmonized interfaces. Atomic algorithms are encapsulated into four software components: the Octree component, the Iterative Closest Point component, the k-Nearest Neighbors search component and the Delaunay triangulation component. A sample experiment demonstrates how the component structure can be used to deduce best practice.
Sebastian Blumenthal Erwin Prassler Jan Fischer Walter Nowak
GPS GmbH,Nobelstr. 12,70569 Stuttgart,Germany University of Applied Sciences Bonn-Rhein-Sieg,Grantham-Allee 20,53757 Sankt Augustin,Germany Fraunhofer IPA,Nobelstr. 12,70569 Stuttgart,Germany
国际会议
2011 IEEE International Conference on Robotics and Automation(2011年IEEE世界机器人与自动化大会 ICRA 2011)
上海
英文
3554-3561
2011-05-09（万方平台首次上网日期，不代表论文的发表时间）