Adaptive Occupancy Grid Mapping With Clusters

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 701
  • Download : 3
In this article, we describe an algorithm for acquiring occupancy grid maps with mobile robots. The standard occupancy grid mapping developed by Elfes and Moravec in the mid-1980s decomposes the high-dimensional mapping problem into many one-dimensional estimation problems, which are then tackled independently. Because of the independencies between neighboring grid cells, this often generates maps that are inconsistent with the sensor data. To overcome this, we propose a cluster that is a set of cells. The cells in the clusters are tackled dependently with another occupancy grid mapping with an expectation maximization (EM) algorithm. The occupancy grid mapping with an EM algorithm yields more consistent maps, especially in the cluster. As we use the mapping algorithm adaptively with clusters according to the sensor measurements, our mapping algorithm is faster and more accurate than previous mapping algorithms. Key words Occupancy grid - Mobile robotics - Mapping - Bayes rule - Cluster
Publisher
Springer Verlag (Germany)
Issue Date
2005-01
Keywords

Occupancy grid; Mobile robotics; Mapping; Bayes rule; Cluster

Citation

Artificial Life and Robotics, Volume 10, Number 2, pp. 162-165

ISSN
1433-5298
DOI
10.1007/s10015-005-0358-4
URI
http://hdl.handle.net/10203/8551
Appears in Collection
EE-Conference Papers(학술회의논문)

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0