Vol.:(0123456789)
1 3
Journal of Ambient Intelligence and Humanized Computing
https://doi.org/10.1007/s12652-019-01531-8
ORIGINAL RESEARCH
An improved ant colony optimization algorithm based onparticle
swarm optimization algorithm forpath planning ofautonomous
underwater vehicle
GaofengChe
1
· LijunLiu
1
· ZhenYu
1
Received: 19 December 2018 / Accepted: 27 September 2019
© Springer-Verlag GmbH Germany, part of Springer Nature 2019
Abstract
The motion control of autonomous underwater vehicle (AUV) has got more and more attention because AUV has been used
in many applications in recent years. In order to find the optimal path for AUV to reach the specified destination in complex
undersea environment, an improved ant colony optimization (ACO) algorithm based on particle swarm optimization (PSO)
algorithm is proposed. Due to the various constraints, such as the limited energy and limited visual distance, the improved
ACO algorithm uses improved pheromone update rule and heuristic function based on PSO algorithm to make AUV find
the optimal path by connecting the chosen nodes of the undersea environment while avoiding the collision with the complex
undersea terrain (static obstacles). The improved ACO algorithm based on PSO algorithm can overcome disadvantages of
the traditional ACO algorithm, such as falling into local extremum, poor quality, and low accuracy. Experiment results dem-
onstrate that improved ACO algorithm is more effective and feasible in path planning for autonomous underwater vehicle
than the traditional ant colony algorithm.
Keywords AUV· Path planning· ACO algorithm· PSO algorithm· Pheromone· Path point
1 Introduction
Due to the potential technical superiority, AUV has been
widely used in commercial, scientific and military applica-
tions, such as offshore oil and obviating torpedoes and so
on(Yuh 2000; Xiang etal. 2015; Santhakumar and Aso-
kan 2013). In these applications, high precision is usually
required to accomplish the specific tasks. The problem of
path planning in completely unknown undersea environ-
ment is an important branch of AUV research. An obstacle-
avoided optimal path is required for AUV from start point
to goal point in the complex undersea environment to solve
the path planning problems.
All the existing path planning methods are mostly in
two-dimensional plane(Chen etal. 2013b; Ghoseiri and
Nadjari 2013; Mousavi etal. 2017; Tan etal. 2007). The
design of path planning algorithm in three-dimensional
plane is difficult due to its complicated calculation process,
large amount of stored information, difficulty in directly
performing global planning, and other issues. Many algo-
rithms have been proposed to solve the path planning prob-
lems in three-dimensional space and get some good results,
such as artificial potential field algorithm(Sun etal. 1993),
A* algorithm(Carroll etal. 1992), genetic algorithm(Hao
and Zhang 2003), and PSO algorithm(Chen etal. 2013a).
However, they have some limitations. The artificial potential
field algorithm can be trapped in local optimal path easily
with the complicated optimization. The A* algorithm can
not meet the space-time requirement when the dimension
increases. When the environment is complex, the genetic
algorithm is difficult to find a feasible path. The PSO algo-
rithm is quasi three-dimensional planning algorithm.
ACO algorithm is a new intelligent optimization algo-
rithm(Blum 2005; Narasimha etal. 2013; Reed etal.
2014; Arora etal. 2019). ACO algorithm has many char-
acteristics, such as swarm intelligence, positive feedback
mechanism and distributed computing. It can be used two-
dimensional or three-dimensional path planning. However,
the traditional ACO algorithm falls into local extremum
* Zhen Yu
yuzhen20@xmu.edu.cn
1
Department ofAutomation, Xiamen University, Xiamen,
China