Particle swarm optimization for solving a scan-matching problem based on the normal distributions transform

Abstract

In this paper, an evolutionary scan-matching approach is proposed to solve an optimization issue in simultaneous localization and mapping (SLAM). A rich literature has been invested in this direction, however, most of the proposed approaches lack fast convergence and simplicity regarding the optimization process, which should directly affect the accuracy of the environment's map and the estimated pose. It is a line of research that is always active, offering various solutions to this issue. Among many SLAM methods, the normal distributions transform approach (NDT) has shown high performances, where numerous works have been published up to date and many studies demonstrate its efficiency wrt other methods. Nevertheless, few works have been interested to solve the optimization issue. The proposed solution is based on NDT scanmatching using particle swarm optimization (PSO) and it is dubbed NDT-PSO. The main contribution is to solve the pose estimation problem based on PSO and iterative NDT maps. The performances of the NDT-PSO approach have been proven in real experiments performed on a car-like mobile robot in both static and dynamic environments. NDT-PSO is tested for different swarm sizes, and the results show that 70 particles are more than enough to find the best particle while avoiding local minima even in loop closing. The algorithm is also suitable for real time applications, with an average runnnig time of 145ms for 70 particles and 70 iterations of the optimization process. This value can be further reduced using fewer particles and iterations. The accuracy of the proposed approach is also evaluated wrt other SLAM methods widely used among the robot operating system community and it has been shown that NDT-PSO outperforms these algorithms.

The Dissemination Mode of External Intelligence of Archery Culture Based on the Particle Swarm Algorithm

“…Bouraine et al believe that traditional culture, as the root of national cohesion, is a cultural concept that a nation has gradually created, developed and continued to the present in the long history, and will have an impact on the cultural construction of the nation in the future [4]. Wang and Tang believe that mining the modern value of traditional culture is a huge driving force for enhancing national cohesion and promoting national rejuvenation.…”

Extraction and Dyeing Techniques of Traditional Vegetable Dyestuffs

“…Therefore, Bouraine et al studied the application of BP neural network in product color matching and used the introduction of the neural network in color matching technology to verify the feasibility of the color matching aided design system established by the BP neural network. Based on this, a neural network computer intelligent color matching assistance system can be constructed [ 12 ].…”

Enhanced Indoor Localization Technique Based on Point Cloud Conversion Image Matching

“…Matching methods using point clouds mainly include the iterative closest point method (ICP) (12) and the normal distribution transformation method (NDT). (13) The basic principle of ICP is to determine the corresponding set of nearest points from the set of measured points as a measure of the distance from the set of points to another set of points. Then, a new set of nearest points is formed by calculation, after which an iterative calculation is performed to reduce the distance until a value of the residual sum of squares is satisfied.…”