Abstract
This paper presents an octree-based map building algorithm for mobile home-service robots. The robot is equipped with a time-of-flight camera, which produces point clouds of the environment surfaces. Given the successive input of point clouds, a 3D map is incrementally computed in real time. The map is accurate and memory-efficient because the octree nodes containing points on a plane are merged and represented simply by an index to the plane. The real-time performance is achieved largely due to the parallel processing capability of the many-core Graphics Processing Unit used for plane extraction.
Original language | English |
---|---|
Pages (from-to) | 301-308 |
Number of pages | 8 |
Journal | Advanced Robotics |
Volume | 27 |
Issue number | 4 |
DOIs | |
Publication status | Published - 2013 Mar 1 |
Keywords
- GPU
- home-service robot
- map building
- octree
ASJC Scopus subject areas
- Software
- Control and Systems Engineering
- Human-Computer Interaction
- Hardware and Architecture
- Computer Science Applications