Outdoor visual localization with a hand-drawn line drawing map using FastSLAM with PSO-based mapping

Abstract

This paper deals with a navigation of a mobile robot in a campus environment using a hand-drawn line drawing building map. Hand-drawn maps often include various types of uncertainty such as incorrect size/position and missing objects, thereby making it difficult to establish correspondence between objects in the map and sensory data. We solve this problem using a SLAM approach with an input hand-drawn map being an initial estimate. The proposed method combines a FastSLAM with a particle swarm optimization for map refinement. The method has been successfully applied to a stereo-based localization in a real scene.

Monte Carlo localization in hand-drawn maps

“…They then use particle swarm optimization (PSO) techniques to compute the alignment and the sketch deformation. Matsuo and Miura [13] extended the previous work in a simultaneous localization and mapping (SLAM) framework. They assume, however that the sketch map is composed of rectangles corresponding to building in the scene.…”

Modern Art Interactive Design Relying on Neural Network Intelligent Algorithms

“…where sgn () is a symbolic function. e exact linear separability of the sample can be processed according to formulas (1)- (5). rough the three steps of artificial intelligence technology symmetry feature, interactive definition algorithm feature and automatic creation of algorithm feature tree are shown in Figure 1; the advanced design knowledge of modern art model can be obtained to design and evaluate the searched modern art model.…”

“…Among them, x is the decision vector, ξ is the random vector parameter, η is the artificial intelligence technology vector parameter, f(x, ξ, n) is the objective function, and Advances in Multimedia g j (x, ξ, n) is the constraint function. Due to the emergence of artificial intelligence technical parameters η and random parameters ξ, the symbols max x and constraints in the model (1) lack clear meaning [5,6]. In order to solve this problem, the artificial intelligence technology and random elements appearing in the model simultaneously are regarded as the coexistence of artificial intelligence technology and random chance for further consideration.…”

Sketched Floor plans versus SLAM maps: A Comparison

“…Researchers have also aimed to automate matching of a hand-drawn map to a SLAM or other automatically generated map for the purposes of navigation [4,11,12]. In the first case, the robot simultaneously locates itself on both the SLAM map and the sketch, including a scale factor for the sketch map to account for inaccuracies in the sketch.…”