Map Building for Mobile Robots using a SOKUIKI Sensor -Robust Scan Matching using Laser Reflection Intensity
Yoshitaka Hara, Hirohiko Kawata, Akihisa Ohya, Shin’ichi Yuta
- Year
- 2006
- Citations
- 12
Abstract
This paper describes map building using a new scan matching method, Intensity-ICP. The method uses laser reflection intensity of a laser range scanner named "SOKUIKI sensor". So compared with conventional scan matching methods which are effective just in geometric featured environments, Intensity-ICP is effective in both geometric featured and non geometric featured environments. We also propose two methods to remove outliers in scan matching. Laser reflection intensity and geometric constraint are used in these methods. As the result of using Intensity-ICP scan matching and outlier removing methods, an accurate map can be built. In addition, the map has abundant information; not only geometric data but also Laser reflection intensity, and it is useful for robust localization
Keywords
Related papers
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Fractional Differential Equations
Igor Podlubný
2025
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991