Learning Occupancy Grid Maps with Forward Sensor Models

Abstract¶

This article describes a new algorithm for acquiring occupancy grid maps with mobile robots. Existing occupancy grid mapping algorithms decompose the high-dimensional mapping problem into a collection of one-dimensional problems, where the occupancy of each grid cell is estimated independently. This induces conflicts that may lead to inconsistent maps, even for noise-free sensors. This article shows how to solve the mapping problem in the original, high-dimensional space, thereby maintaining all dependencies between neighboring cells. As a result, maps generated by our approach are often more accurate than those generated using traditional techniques. Our approach relies on a statistical formulation of the mapping problem using forward models. It employs the expectation maximization algorithm for searching maps that maximize the likelihood of the sensor measurements.

Summary¶

Proposes learning occupancy grid maps with forward sensor models rather than independent inverse updates for each grid cell. By optimizing the likelihood of measurements in the full high-dimensional map space with expectation maximization, the method preserves dependencies between neighboring cells and can produce more consistent maps.

Links¶

Tags¶

Similar Papers¶