Chaotic artificial bee colony approach to Uninhabited Combat Air Vehicle (UCAV) path planning

https://doi.org/10.1016/j.ast.2010.04.008Get rights and content

Abstract

Path planning of Uninhabited Combat Air Vehicle (UCAV) is a rather complicated global optimum problem which is about seeking a superior flight route considering the different kinds of constrains under complex combat field environment. Artificial Bee Colony (ABC) algorithm is a new optimization method motivated by the intelligent behavior of honey bees. In this paper, we propose an improved ABC optimization algorithm based on chaos theory for solving the UCAV path planning in various combat field environments, and the implementation procedure of our proposed chaotic ABC approach is also described in detail. Series of experimental comparison results are presented to show the feasibility, effectiveness and robustness of our proposed method.

Introduction

Uninhabited Combat Aerial Vehicle (UCAV) is one of the inevitable trends of the modern aerial weapon equipments owing to its potential to perform dangerous, repetitive tasks in remote and hazardous environments [12]. Research on UCAV can directly affect battle effectiveness of the air force, therefore is crucial to safeness of a nation. Path planning is an imperative task required in the design of UCAV, which is to search out an optimal or near-optimal flight path between an initial location and the desired destination under specific constraint conditions. Series of algorithms have been proposed to solve this complicated optimization problem, including the A* algorithm, evolutionary computation [12], particle swarm optimization [2], genetic algorithm (GA) [9] and ant colony algorithm [11]. However, those methods can be easily trapped into the local best, hence would probably end up without finding a satisfying path. In our paper, we mainly focus on UCAV path planning in two dimensions.

Artificial Bee Colony (ABC) algorithm was originally presented by Dervis Karaboga in 2007 [5], under the inspiration of collective behavior on honey bees, and it has been proved to possess a better performance in function optimization problem, compared with genetic algorithm, differential evolution (DE) algorithm and particle swarm optimization (PSO) algorithm [5], [6]. As we know, usual optimization algorithms conduct only one search operation in one iteration, for example the PSO algorithm carries out global search at the beginning and local search in the later stage. Compared with the usual algorithms, the major advantage of ABC algorithm lies in that it conducts both global search and local search in each iteration, and as a result the probability of finding the optimal parameters is significantly increased, which efficiently avoid local optimum to a large extent. Although the ABC algorithm has rarely been used in path planning field before, yet due to the above advantages we described, we adopted this algorithm to figure out the flight path. What is more, considering the outstanding performance of chaos theory in jumping out of stagnation, we introduced it to improve the robustness of basic ABC algorithm, and the comparative experimental results testified that our proposed method manifests better performance than the original ABC algorithm.

The remainder of this paper is organized as follows. Section 2 introduces the threat resource and objective function in UCAV path planning. Section 3 described the principle of basic ABC algorithm, while Section 4 specified implementation procedure of our proposed chaotic ABC algorithm. Then, in Section 5, series of comparison experiments are conducted. Our concluding remarks are contained in the final section.

Section snippets

Threat resource model in UCAV path planning

Modeling of the threat sources is the key task in UCAV optimal path planning. In our model, define the starting point as S and the target point as T, as is shown in Fig. 1. There are some threatening areas in the task region, such as radars, missiles, and artillery, which all are presented in the form of a circle, inside of which will be vulnerable to the threat with a certain probability proportional to the distance away from the threat center, while out of which will not be attacked. The

Principles of the basic ABC algorithm

Karlvon Frisch, a famous Nobel Prize winner, found that in nature, although each bee only performs one single task, yet through a variety of information communication ways between bees such as waggle dance and special odor, the entire colony can always easily find food resources that produce relative high amount nectar, hence realize its self-organizing behavior [4].

In order to introduce the self-organization model of forage selection that leads to the emergence of collective intelligence of

Introduction to chaos theory

Chaos is the highly unstable motion of deterministic systems in finite phase space which often exists in nonlinear systems. Chaos theory is epitomized by the so-called ‘butterfly effect’ detailed by Lorenz [8]. Attempting to simulate numerically a global weather system, Lorenz discovered that minute changes in initial conditions steered subsequent simulations towards radically different final stales, rendering long-term prediction impossible in general. Until now, chaotic behavior has already

Experimental results

In order to investigate the feasibility and effectiveness of the proposed method in this work, series of experiments are conducted, and further comparative experimental results with the standard ABC algorithm are also given.

Set the coordinates of the starting point as (11,11), and the target point as (75,75), while the initial parameters of ABC algorithm were set as: Ns=60, Ne=30, Nu=30, Tmax=100, Limit=30.

Respectively assume D as 10, 20 and 30 to carry our experiments, the results of which are

Concluding remarks

This paper presents a novel chaotic ABC approach for UCAV path planning problem in complicated combat field environment. Utilizing the ergodicity and irregularity of the chaotic variable to help the basic ABC algorithm to jump out of the local optimum as well as speeding up the process of finding the optimal parameters. The simulation experiments show that our proposed method is a feasible and effective way in UCAV path planning, and it is also flexible, in that dynamic environments and pop-up

Acknowledgements

This work was partially supported by the National Natural Science Foundation of China (Grant Nos. 60975072 and 60604009), the Program for New Century Excellent Talents in University of China (Grant No. NCET-10-0021), Aeronautical Science Foundation of China, and the Beijing NOVA Program Foundation of China (Grant No. 2007A0017), Graduate Innovation Practice Foundation of Beihang University, China, and the Fundamental Research Funds for the Central Universities (Grant No. YWF-10-01-A18).

References (12)

There are more references available in the full text version of this article.

Cited by (261)

View all citing articles on Scopus
View full text