Autonomous navigation based on unscented-FastSLAM using particle swarm optimization for autonomous underwater vehicles

Ying, Lulu; Zhang, Shujing; Feng, Xiaoxiao; Yan, Tianhong; Nian, Rui; Shen, Yue

doi:10.1016/j.measurement.2015.02.026

Cited by 38 publications

(26 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The work of [44] tried to extract point features from the sonar images with the artificial sonar targets being deployed at the field test site a prior. On the other hand, point feature extracted from MSS image was used to describe natural bay environment in [11]. One main drawback of feature based approaches is that loop closure detection relies on the dead reckoning estimate because of that features are distinguishable only by their global or relative locations.…”

Section: Loop Closure Detectionmentioning

confidence: 99%

A Survey of Underwater Acoustic SLAM System

Jiang

Song

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Due to the unavailability of GPS signal, it is more urgent to develop the autonomous navigation capability for the underwater vehicles. In this paper, we summarize the development status of underwater SLAM (simultaneous localization and mapping) system. Different from the terrestrial or aerial SLAM that largely depends on the optical sensors, the underwater SLAM system mainly uses the acoustic sensors, i.e., sonars, to watch the environment. With respect to the general SLAM system, which is mainly composed of the front-end local dataassociation and the back-end global error adjustment, we briefly survey recent progress in sonar image registration and the loop closure detection. Furthermore, some heuristic problems are posed in the conclusion.

show abstract

Section: Loop Closure Detectionmentioning

confidence: 99%

A Survey of Underwater Acoustic SLAM System

Jiang

Song

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Several SLAM applications such as, automatic car piloting [16], rescue tasks for high-risk environments [1] and planetary exploration [2] have difficulties to use the map generated by the monocular-SLAM systems as 3D reference. Typically, 3D reconstruction algorithms carry out the 3D map estimation [17]. In recent years, the increase of computing power and a better SLAM algorithms understanding, allowed to increase the point clouds density.…”

Section: Motivation and Scopementioning

confidence: 99%

Dense mapping for monocular-SLAM

Aguilar-González¹,

Arias-Estrada²

2016

2016 International Conference on Indoor Positioning and Indoor Navigation (IPIN)

View full text Add to dashboard Cite

Abstract-Simultaneous Localization and Mapping (SLAM) is the problem of constructing a 3D map while simultaneously keeping track of an agent location within the map. In recent years, work has focused in systems that use a single camera as the only sensing mechanism (monocular-SLAM). 3D reconstruction (map) by monocular-SLAM systems is a point cloud where all points preserve high accuracy and can deliver visual environmental information. However, the maximum number of points in the cloud is limited by the tracked features, this is named "sparse cloud problem". In this work, we propose a new SLAM framework that is robust enough for indoor/outdoor SLAM applications, and at the same time increases the 3D map density. The point cloud density is increased by applying a new feature-tracking/densetracking algorithm in the SLAM formulation. In order to achieve real-time processing, the algorithm is formulated to facilitate a parallel FPGA implementation. Preliminary results show that it is possible to obtain dense mapping (superior to previous work) and accurate camera pose estimation (localization) under several real-world conditions.

show abstract

“…Many path planning algorithms are proposed [4][5][6][7], including grid methods, which include the A* algorithm based on an exact grid [8], and the probability grid method, based on an approximate grid [9,10]. Intelligent optimization algorithms, which are based on natural heuristics, are as follows: Neural network algorithms [11], genetic algorithms [12], ant colony algorithms [13], particle swarm optimization (PSO) [14][15][16], artificial bee colony algorithms [17,18], artificial potential field (APF) algorithms based on the virtual force field [19], the Voronoi graph method, and the tangent graph method, based on a cell structure [20,21]. Each of these algorithms has its own advantages and disadvantages.…”

Section: Introductionmentioning

confidence: 99%

“…In this method, a geometric free configuration space of the robot was established by using the triangular decomposition method, and a non-collision path, as the input reference for the next level and was found by using the Dijkstra algorithm. Study [15] presents a type of motion path planning for an underwater robot, based on PSO. Since the local minimum value problem and inefficient path planning are easily caused by APFs, study [16] proposes an improved APF (PSO-TVAPF) based on the tangent vector method and PSO.…”

Section: Introductionmentioning

confidence: 99%

A Heuristic Elastic Particle Swarm Optimization Algorithm for Robot Path Planning

Wang

Zhou

2019

Information

View full text Add to dashboard Cite

Path planning, as the core of navigation control for mobile robots, has become the focus of research in the field of mobile robots. Various path planning algorithms have been recently proposed. In this paper, in view of the advantages and disadvantages of different path planning algorithms, a heuristic elastic particle swarm algorithm is proposed. Using the path planned by the A* algorithm in a large-scale grid for global guidance, the elastic particle swarm optimization algorithm uses a shrinking operation to determine the globally optimal path formed by locally optimal nodes so that the particles can converge to it rapidly. Furthermore, in the iterative process, the diversity of the particles is ensured by a rebound operation. Computer simulation and real experimental results show that the proposed algorithm not only overcomes the shortcomings of the A* algorithm, which cannot yield the shortest path, but also avoids the problem of failure to converge to the globally optimal path, owing to a lack of heuristic information. Additionally, the proposed algorithm maintains the simplicity and high efficiency of both the algorithms.

show abstract

Autonomous navigation based on unscented-FastSLAM using particle swarm optimization for autonomous underwater vehicles

Cited by 38 publications

References 32 publications

A Survey of Underwater Acoustic SLAM System

A Survey of Underwater Acoustic SLAM System

Dense mapping for monocular-SLAM

A Heuristic Elastic Particle Swarm Optimization Algorithm for Robot Path Planning

Contact Info

Product

Resources

About