Route following based on visual landmark matching may require many models to cover all different situations. This paper describes a system that JLs able to adapt template's modelling parameters to environmental conditions (lighting, shadows, etc.) by a genetic learning technique. In addition, the mobile robot self-localisation is obtained by a stereo approach that uses the centres of matching in the two images to solve in a simple way the correspondence problem in the 3D position estimation. The experimental results show that the tracking robustness is improved, while using a small set of templates.
Route following based on adaptive visual landmark matching / Zingaretti, Primo; Carbonaro, A.. - In: ROBOTICS AND AUTONOMOUS SYSTEMS. - ISSN 0921-8890. - 25:(1998), pp. 177-184. [10.1016/S0921-8890(98)00047-5]
Route following based on adaptive visual landmark matching
ZINGARETTI, PRIMO;
1998-01-01
Abstract
Route following based on visual landmark matching may require many models to cover all different situations. This paper describes a system that JLs able to adapt template's modelling parameters to environmental conditions (lighting, shadows, etc.) by a genetic learning technique. In addition, the mobile robot self-localisation is obtained by a stereo approach that uses the centres of matching in the two images to solve in a simple way the correspondence problem in the 3D position estimation. The experimental results show that the tracking robustness is improved, while using a small set of templates.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.