Abstract
In this paper, an adaptive improved ant colony algorithm based on population information entropy(AIACSE) is proposed to improve the optimization ability of the algorithm. The diversity of the population in the iterative process is described by the information entropy. The non-uniform distribution initial pheromone is constructed to reduce the blindness of the search at the starting phase. The pheromone diffusion model is used to enhance the exploration and collaboration capacity between ants. The adaptive parameter adjusting strategy and the novel pheromone updating mechanism based on the evolutionary characteristics of the population are designed to achieve a better balance between exploration of the search space and exploitation of the knowledge during the optimization progress. The performance of AIACSE is evaluated on the path planning of mobile robots. Friedman's test is further conducted to check the significant difference in performance between AIACSE and the other selected algorithms. The experimental results and statistical tests demonstrate that the presented approach significantly improves the performance of the ant colony system (ACS) and outperforms the other algorithms used in the experiments.
Highlights
Nowadays, the research of mobile robots has expanded widely, due to their effective use in repetitive and unattainable environments for humans [1]
SIMULATIONS IN VARIOUS ENVIRONMENTS To evaluate the performance and adaptability of the AIACSE algorithm in the path planning of the robot, the third experiment is conducted under four different size environments, It can be seen from Table 6 that Rank-based Ant System (RAS), ant colony system (ACS), multi-role adaptive collaborative ant colony optimization (MRCACO) and AIACSE can find the optimal path for all runs in case of small-scale environments, such as map5 and map6
WORK In the present paper, an adaptive improved ant colony algorithm based on the non-uniform distribution initial pheromone, the pheromone diffusion model, the adaptive parameter adjusting strategy, and the novel pheromone updating mechanism are proposed to enhance the optimization ability and efficiency of the ACS algorithm
Summary
The research of mobile robots has expanded widely, due to their effective use in repetitive and unattainable environments for humans [1]. The above proposed works have been focused on some variants of basic ACO, the hybridization of ACO algorithms with other algorithms and multi ant colony optimization algorithms, at the same time, a variety of improved techniques, such as search strategy [35], pheromone initialization [30] and update strategy [4], state transition rules [36] and heuristic information [37], have been delivered by many scholars to effectively enhance the performance of the ant colony algorithm. The studies mentioned above can achieve high algorithmic performances, there are still some inherent shortcomings that have not been effectively solved, such as low search efficiency, the problems of local optimum, and the contradiction between convergence speed and diversity loss For this reason, the pheromone initialization strategy based on A* algorithm, pheromone diffusion mechanism, adaptive adjustment strategies of the parameter q0, and dynamic pheromone updating mechanism, are introduced into the ACS to develop an adaptive improved ant colony system algorithm based on population information entropy(AIACSE). The global update rule gives the edges belonging to the best solution found so far higher probabilities of being selected in the subsequent iterations which is helpful to speed up convergence to the optimal solution
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
