scholarly journals An Improved DSA-Based Approach for Multi-AUV Cooperative Search

2018 ◽  
Vol 2018 ◽  
pp. 1-13 ◽  
Author(s):  
Jianjun Ni ◽  
Liu Yang ◽  
Pengfei Shi ◽  
Chengming Luo
Keyword(s):  
Search Task ◽  
Autonomous Underwater Vehicle ◽  
Hot Spot ◽  
Search Problem ◽  
Self Organizing Map ◽  
Target Search ◽  
Dynamic Alliance ◽  
Underwater Environment ◽  
Three Stages ◽  
Som Neural Network

Multi-AUV cooperative target search problem in unknown 3D underwater environment is not only a research hot spot but also a challenging task. To complete this task, each autonomous underwater vehicle (AUV) needs to move quickly without collision and cooperate with other AUVs to find the target. In this paper, an improved dolphin swarm algorithm- (DSA-) based approach is proposed, and the search problem is divided into three stages, namely, random cruise, dynamic alliance, and team search. In the proposed approach, the Levy flight method is used to provide a random walk for AUV to detect the target information in the random cruise stage. Then the self-organizing map (SOM) neural network is used to build dynamic alliances in real time. Finally, an improved DSA algorithm is presented to realize the team search. Furthermore, some simulations are conducted, and the results show that the proposed approach is capable of guiding multi-AUVs to achieve the target search task in unknown 3D underwater environment efficiently.

Multi-autonomous underwater vehicles collaboratively search for intelligent targets in an unknown environment in the presence of interception

2020 ◽  
pp. 095440622094362
Author(s):  
Xi-wen Ma ◽  
Yan-li Chen ◽  
Gui-qiang Bai ◽  
Yong-bai Sha ◽  
Jun Liu
Keyword(s):  
Autonomous Underwater Vehicle ◽  
Autonomous Underwater Vehicles ◽  
Full Range ◽  
Underwater Vehicle ◽  
Underwater Vehicles ◽  
Layer By Layer ◽  
Self Organizing Map ◽  
Unknown Environment ◽  
Underwater Environment ◽  
Wave Diffusion

We present a bionic neural wave network that uses multiple autonomous underwater vehicles to search and acquire intelligent targets in an unknown underwater environment. The neuron pheromone content is arranged according to neural wave diffusion and layer-by-layer energy attenuation, when underwater mesh space based on neural wave diffusion theory was established that the neuron nodes in the neural network structure correspond to obstacles, autonomous underwater vehicles, and targets in the environment. In order to solve the problems of over-allocation and under-allocation of the multi-autonomous underwater vehicles system during the cooperative capture of targets, a redistribution mechanism based on the improved self-organizing map algorithm is implemented and directed to rationalize task distribution. Two different taboo search methods are employed to update the autonomous underwater vehicle path in real time, and the polynomial coefficient solution method is used to fit partial path data. So that the autonomous underwater vehicle trajectory can be obtained and an interceptor position coordinate can be predicted. An auxiliary autonomous underwater vehicle is aimed to replace the intercepted autonomous underwater vehicle and the matching capture points are tracked to ensure the completion of the task so that the full range of hunting targets is identified. In order to simulate an unknown complex underwater environment, obstacles are randomly arranged around the target, the location information of the obstacle, and the target is unknown and unpredictable. Four simulation experiments were performed to verify the accuracy and efficiency of the algorithm under unknown environment. The results show that this algorithm can improve the path update average efficiency by 66% compared with other algorithms. Obviously, this algorithm is reasonable and effective.

Multi-AUV Cooperative Target Search Algorithm in 3-D Underwater Workspace

2017 ◽  
Vol 70 (6) ◽  
pp. 1293-1311 ◽  
Author(s):  
Xiang Cao ◽  
A-long Yu
Keyword(s):  
Neural Network ◽  
Search Task ◽  
Search Algorithm ◽  
Autonomous Underwater Vehicles ◽  
Three Dimensional ◽  
Target Search ◽  
Team Members ◽  
Neural Network Algorithm ◽  
Som Neural Network ◽  
Self Organising Map

To improve the efficiency of multiple Autonomous Underwater Vehicles (multi-AUV) cooperative target search in a Three-Dimensional (3D) underwater workspace, an integrated algorithm is proposed by combining a Self-Organising Map (SOM), neural network and Glasius Bioinspired Neural Network (GBNN). With this integrated algorithm, the 3D underwater workspace is first divided into subspaces dependent on the abilities of the AUV team members. After that, tasks are allocated to each subspace for an AUV by SOM. Finally, AUVs move to the assigned subspace in the shortest way and start their search task by GBNN. This integrated algorithm, by avoiding overlapping search paths and raising the coverage rate, can reduce energy consumption of the whole multi-AUV system. The simulation results show that the proposed algorithm is capable of guiding multi-AUV to achieve a multiple target search task with higher efficiency and adaptability compared with a more traditional bioinspired neural network algorithm.

scholarly journals Toward target search approach of swarm robotics in limited communication environment based on robot chains with elimination mechanism

2020 ◽  
Vol 17 (3) ◽  
pp. 172988142091995
Author(s):  
Yandong Luo ◽  
Jianwen Guo ◽  
Guoliang Ye ◽  
Yan Wang ◽  
Li Xie ◽  
...  
Keyword(s):  
Swarm Robotics ◽  
Search Task ◽  
Search Problem ◽  
Chain Model ◽  
Target Search ◽  
Limited Communication ◽  
Communication Environments ◽  
Search Speed ◽  
Elimination Mechanism ◽  
Search Approach

Swarm robotics refers to artificial swarm systems composed of a large number of autonomous mobile robots with relatively simple structures and functions. One of the basic problems of swarm robotics involves the target search process, which entails a cooperative search using limited perception and local interaction of robots under a self-organizing mechanism. When communication is limited, the connectivity of swarm robotics may decrease, leading to the failure of the target search task. This article describes a new target search method based on the robot chain model and the elimination mechanism. The proposed method allows the target search task to be completed efficiently and reliably while maintaining the connectivity of the robots. Experimental results show that the proposed algorithm offers better performance than conventional techniques in terms of search speed and success rate, and provides an effective method for solving the target search problem using swarm robotics in limited-communication environments.

scholarly journals Complete Coverage Path Planning in an Unknown Underwater Environment Based on D-S Data Fusion Real-Time Map Building

2012 ◽  
Vol 8 (10) ◽  
pp. 567959 ◽  
Author(s):  
Mingzhong Yan ◽  
Daqi Zhu ◽  
Simon X. Yang
Keyword(s):  
Path Planning ◽  
Real Time ◽  
Autonomous Underwater Vehicle ◽  
Evidence Theory ◽  
Sensor Data ◽  
Map Building ◽  
Complete Coverage ◽  
Coverage Path Planning ◽  
Underwater Environment ◽  
Time Map

A real-time map-building system is proposed for an autonomous underwater vehicle (AUV) to build a map of an unknown underwater environment. The system, using the AUV's onboard sensor information, includes a neurodynamics model proposed for complete coverage path planning and an evidence theoretic method proposed for map building. The complete coverage of the environment guarantees that the AUV can acquire adequate environment information. The evidence theory is used to handle the noise and uncertainty of the sensor data. The AUV dynamically plans its path with obstacle avoidance through the landscape of neural activity. Concurrently, real-time sensor data are “fused” into a two-dimensional (2D) occupancy grid map of the environment using evidence inference rule based on the Dempster-Shafer theory. Simulation results show a good quality of map-building capabilities and path-planning behaviors of the AUV.

scholarly journals An Improved SOM-Based Method for Multi-Robot Task Assignment and Cooperative Search in Unknown Dynamic Environments

Energies ◽  
2020 ◽  
Vol 13 (12) ◽  
pp. 3296
Author(s):  
Hongwei Tang ◽  
Anping Lin ◽  
Wei Sun ◽  
Shuqi Shi
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Task Assignment ◽  
Dynamic Environments ◽  
Self Organizing Map ◽  
Cooperative Search ◽  
Dynamic Task ◽  
Locking Mechanism ◽  
Som Neural Network ◽  
Multi Robot

The methods of task assignment and path planning have been reported by many researchers, but they are mainly focused on environments with prior information. In unknown dynamic environments, in which the real-time acquisition of the location information of obstacles is required, an integrated multi-robot dynamic task assignment and cooperative search method is proposed by combining an improved self-organizing map (SOM) neural network and the adaptive dynamic window approach (DWA). To avoid the robot oscillation and hovering issue that occurs with the SOM-based algorithm, an SOM neural network with a locking mechanism is developed to better realize task assignment. Then, in order to solve the obstacle avoidance problem and the speed jump problem, the weights of the winner of the SOM are updated by using an adaptive DWA. In addition, the proposed method can search dynamic multi-target in unknown dynamic environment, it can reassign tasks and re-plan searching paths in real time when the location of the targets and obstacle changes. The simulation results and comparative testing demonstrate the effectiveness and efficiency of the proposed method.

scholarly journals Directional-Sensor Network Deployment Planning for Mobile-Target Search

Robotics ◽  
2020 ◽  
Vol 9 (4) ◽  
pp. 82
Author(s):  
Shiraz Wasim ◽  
Zendai Kashino ◽  
Goldie Nejat ◽  
Beno Benhabib
Keyword(s):  
Sensor Network ◽  
Search Algorithm ◽  
Search Problem ◽  
Target Search ◽  
Physical Constraints ◽  
Sensing Model ◽  
Mobile Target ◽  
Deployment Planning ◽  
Directional Sensor Network ◽  
Directional Sensor

In this paper, a novel time-phased directional-sensor network deployment strategy is presented for the mobile-target search problem, e.g., wilderness search and rescue (WiSAR). The proposed strategy uses probabilistic target-motion models combined with a variation of a standard direct search algorithm to plan the optimal locations of directional-sensors which maximize the likelihood of target detection. A linear sensing model is employed as a simplification for directional-sensor network deployment planning, while considering physical constraints, such as on-time sensor deliverability. Extensive statistical simulations validated our method. One such illustrative experiment is included herein to demonstrate the method’s operation. A comparative study was also carried out, whose summary is included in this paper, to highlight the tangible improvement of our approach versus three traditional deployment strategies: a uniform, a random, and a ring-of-fire type deployment, respectively.

scholarly journals Music Waveform Analysis Based on SOM Neural Network and Big Data

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Xinmei Zhang
Keyword(s):  
Neural Network ◽  
Big Data ◽  
Audio Signal ◽  
The Self ◽  
Waveform Analysis ◽  
Self Organizing Map ◽  
Matching Method ◽  
Emotion Model ◽  
Som Neural Network ◽  
First Time

Music is an indispensable part of our life and study and is one of the most important forms of multimedia applications. With the development of deep learning and neural network in recent years, how to use cutting-edge technology to study and apply music has become a research hotspot. Music waveform is not only the main form of music frequency but also the basis of music feature extraction. This paper first designs a method of note extraction based on the fast Fourier transform principle of the audio signal packet route under the self-organizing map (SOM neural network) which can accurately extract the musical features of the note, such as amplitude, loudness, period, and so on. Secondly, the audio segments are divided into summary by adding window moving matching method, and the music features such as amplitude, loudness, and period of each bar are obtained according to the performance of audio signal in each bar. Finally, according to the similarity of the audio music theory of the adjacent summary of each bar, the audio segments are divided, and the music features of each segment are obtained. The traditional recurrent neural network (RNN) is improved, and the SOM neural network is used to recognize the audio emotion features. The final experimental results show that the proposed method based on SOM neural network and big data can effectively extract and analyze music waveform features. Compared with previous studies, this paper creatively proposed a new algorithm, which can more accurately and quickly extract and analyze the data sound waveform, and used SOM neural network to analyze the emotion model contained in music for the first time.

Determining the Number of Distinct Solutions in Planar Mechanism Design

2019 ◽  
Author(s):  
Lawrence Funke ◽  
Jonathan Raney ◽  
Cyler Caldwell
Keyword(s):  
Mechanism Design ◽  
General Mechanism ◽  
Compact Set ◽  
Self Organizing Map ◽  
Mechanism Synthesis ◽  
Modal Assurance Criterion ◽  
Planar Mechanism ◽  
Starting Point ◽  
Distinct Solution ◽  
Som Neural Network

Abstract This work investigates two novel approaches to sorting solutions to planar-mechanism-synthesis problems. The examples contained herein are specific to planar morphing mechanisms, but the procedure is general and can easily be extended to any planar-mechanism-synthesis problem. The results indicate that the two approaches, namely self-organizing map (SOM) neural network and modal assurance criterion (MAC), can be used to sort a set of solution mechanisms into a reduced set of distinct solution groups. Additionally two sorting approaches (inclusive and exclusive) were investigated. This process can be used to take the initial set of solution mechanisms, often numbering in the hundreds, and pare it down to a significantly smaller set of substantially different designs. For the two case studies presented herein, one set was reduced by a factor of ten and the other by a factor of five. This means that a designer has fewer mechanisms to look through and that the differences in these mechanisms are clearer so that considerations such as size and joint locations may more easily be considered. It was found that the MAC method with inclusive sorting is generally a better starting point because it runs quickly and gives a more compact set of distinct solution mechanisms. The paper concludes with some recommendations for best practices for sorting solutions for a general mechanism-design problem.

Sign in / Sign up

Export Citation Format

Share Document