Water wave optimization algorithm for autonomous underwater vehicle path planning problem

2021 ◽  
pp. 1-15
Author(s):  
Zheping Yan ◽  
Jinzhong Zhang ◽  
Jia Zeng ◽  
Jialing Tang
Keyword(s):  
Path Planning ◽  
Water Wave ◽  
Autonomous Underwater Vehicle ◽  
Optimal Path ◽  
Wave Theory ◽  
Underwater Vehicle ◽  
Local Optimum ◽  
Planning Problem ◽  
Vehicle Path ◽  
Path Planning Problem

In this paper, a water wave optimization (WWO) algorithm is proposed to solve the autonomous underwater vehicle (AUV) path planning problem to obtain an optimal or near-optimal path in the marine environment. Path planning is a prerequisite for the realization of submarine reconnaissance, surveillance, combat and other underwater tasks. The WWO algorithm based on shallow wave theory is a novel evolutionary algorithm that mimics wave motions containing propagation, refraction and breaking to obtain the global optimization solution. The WWO algorithm not only avoids jumps out of the local optimum and premature convergence but also has a faster convergence speed and higher calculation accuracy. To verify the effectiveness and feasibility, the WWO algorithm is applied to solve the randomly generated threat areas and generated fixed threat areas. Compared with other algorithms, the WWO algorithm can effectively balance exploration and exploitation to avoid threat areas and reach the intended target with minimum fuel costs. The experimental results demonstrate that the WWO algorithm has better optimization performance and is robust.

scholarly journals Proposed Smooth-STC Algorithm for Enhanced Coverage Path Planning Performance in Mobile Robot Applications

Robotics ◽  
2019 ◽  
Vol 8 (2) ◽  
pp. 44 ◽  
Author(s):  
Hai Van Pham ◽  
Philip Moore ◽  
Dinh Xuan Truong
Keyword(s):  
Path Planning ◽  
Optimal Path ◽  
Forest Monitoring ◽  
Planning Problem ◽  
Operational Environment ◽  
Uncertain Environments ◽  
Coverage Path Planning ◽  
Agricultural Robots ◽  
Cleaning Robots ◽  
Path Planning Problem

Robotic path planning is a field of research which is gaining traction given the broad domains of interest to which path planning is an important systemic requirement. The aim of path planning is to optimise the efficacy of robotic movement in a defined operational environment. For example, robots have been employed in many domains including: Cleaning robots (such as vacuum cleaners), automated paint spraying robots, window cleaning robots, forest monitoring robots, and agricultural robots (often driven using satellite and geostationary positional satellite data). Additionally, mobile robotic systems have been utilised in disaster areas and locations hazardous to humans (such as war zones in mine clearance). The coverage path planning problem describes an approach which is designed to determine the path that traverses all points in a defined operational environment while avoiding static and dynamic (moving) obstacles. In this paper we present our proposed Smooth-STC model, the aim of the model being to identify an optimal path, avoid all obstacles, prevent (or at least minimise) backtracking, and maximise the coverage in any defined operational environment. The experimental results in a simulation show that, in uncertain environments, our proposed smooth STC method achieves an almost absolute coverage rate and demonstrates improvement when measured against alternative conventional algorithms.

Autonomous underwater vehicle optimal path planning method for seabed terrain matching navigation

2017 ◽  
Vol 133 ◽  
pp. 107-115 ◽  
Author(s):  
Ye Li ◽  
Teng Ma ◽  
Pengyun Chen ◽  
Yanqing Jiang ◽  
Rupeng Wang ◽  
...  
Keyword(s):  
Path Planning ◽  
Autonomous Underwater Vehicle ◽  
Optimal Path ◽  
Underwater Vehicle ◽  
Planning Method ◽  
Optimal Path Planning ◽  
Terrain Matching

Path planning of a mobile robot using genetic heuristics

Robotica ◽  
1998 ◽  
Vol 16 (5) ◽  
pp. 575-588 ◽  
Author(s):  
Andreas C. Nearchou
Keyword(s):  
Genetic Algorithm ◽  
Path Planning ◽  
Mobile Robot ◽  
Optimal Path ◽  
Hill Climbing ◽  
Planning Problem ◽  
Well Performance ◽  
Simulation Results ◽  
Task Oriented ◽  
Path Planning Problem

A genetic algorithm for the path planning problem of a mobile robot which is moving and picking up loads on its way is presented. Assuming a findpath problem in a graph, the proposed algorithm determines a near-optimal path solution using a bit-string encoding of selected graph vertices. Several simulation results of specific task-oriented variants of the basic path planning problem using the proposed genetic algorithm are provided. The results obtained are compared with ones yielded by hill-climbing and simulated annealing techniques, showing a higher or at least equally well performance for the genetic algorithm.

Autonomous underwater vehicle path planning based on actor-multi-critic reinforcement learning

2020 ◽  
pp. 095965182093708
Author(s):  
Zhuo Wang ◽  
Shiwei Zhang ◽  
Xiaoning Feng ◽  
Yancheng Sui
Keyword(s):  
Reinforcement Learning ◽  
Path Planning ◽  
Value Function ◽  
Autonomous Underwater Vehicle ◽  
Autonomous Underwater Vehicles ◽  
Underwater Vehicle ◽  
Learning Efficiency ◽  
Environmental Adaptability ◽  
Vehicle Path ◽  
The Value Function

The environmental adaptability of autonomous underwater vehicles is always a problem for its path planning. Although reinforcement learning can improve the environmental adaptability, the slow convergence of reinforcement learning is caused by multi-behavior coupling, so it is difficult for autonomous underwater vehicle to avoid moving obstacles. This article proposes a multi-behavior critic reinforcement learning algorithm applied to autonomous underwater vehicle path planning to overcome problems associated with oscillating amplitudes and low learning efficiency in the early stages of training which are common in traditional actor–critic algorithms. Behavior critic reinforcement learning assesses the actions of the actor from perspectives such as energy saving and security, combining these aspects into a whole evaluation of the actor. In this article, the policy gradient method is selected as the actor part, and the value function method is selected as the critic part. The strategy gradient and the value function methods for actor and critic, respectively, are approximated by a backpropagation neural network, the parameters of which are updated using the gradient descent method. The simulation results show that the method has the ability of optimizing learning in the environment and can improve learning efficiency, which meets the needs of real time and adaptability for autonomous underwater vehicle dynamic obstacle avoidance.

Two novel approaches for unmanned underwater vehicle path planning: constrained optimisation and semi-infinite constrained optimisation

Robotica ◽  
2000 ◽  
Vol 18 (2) ◽  
pp. 123-142 ◽  
Author(s):  
Yongji Wang ◽  
David M. Lane ◽  
Gavin J. Falconer
Keyword(s):  
Path Planning ◽  
Underwater Vehicle ◽  
Planning Problem ◽  
Robot Path Planning ◽  
Approximation Techniques ◽  
Constrained Optimisation ◽  
Unmanned Underwater Vehicle ◽  
Novel Approaches ◽  
Vehicle Path ◽  
Robot Path

In this paper, two novel approaches to unmanned underwater vehicle path planning are presented. The main idea of the first approach, referred to as Constrained Optimisation (CO) is to represent the free space of the workspace as a set of inequality constraints using vehicle configuration variables. The second approach converts robot path planning into a Semi-infinite Constrained Optimisation (SCO) problem. The function interpolation technique is adopted to satisfy the start and goal configuration requirements. Mathematical foundations for Constructive Solid Geometry (CSG), Boolean operations and approximation techniques are also presented to reduce the number of constraints, and to avoid local minima. The advantages of these approaches are that the mature techniques developed in optimisation theory which guarantee convergence, efficiency and numerical robustness can be directly applied to the robot path planning problem. Simulation results have been presented.

Sign in / Sign up

Export Citation Format

Share Document