RESEARCH ARTICLE
A search and rescue robot search method
based on flower pollination algorithm and Q-
learning fusion algorithm
Bing Hao
ID
1☯
*, Jianshuo Zhao
ID
1☯
, He Du
1
, Qi Wang
1
, Qi Yuan
2
, Shuo Zhao
2
1 College of Computer and Control Engineering, Qiqihar University, Qiqihar, China, 2 College of
Telecommunication and Electronic Engineering, Qiqihar University, Qiqihar, China
☯ These authors contributed equally to this work.
* 01522@qqhru.edu.cn
Abstract
Search algorithm plays an important role in the motion planning of the robot, it determines
whether the mobile robot complete the task. To solve the search task in complex environ-
ments, a fusion algorithm based on the Flower Pollination algorithm and Q-learning is pro-
posed. To improve the accuracy, an improved grid map is used in the section of
environment modeling to change the original static grid to a combination of static and
dynamic grids. Secondly, a combination of Q-learning and Flower Pollination algorithm is
used to complete the initialization of the Q-table and accelerate the efficiency of the search
and rescue robot path search. A combination of static and dynamic reward function is pro-
posed for the different situations encountered by the search and rescue robot during the
search process, as a way to allow the search and rescue robot to get better different feed-
back results in each specific situation. The experiments are divided into two parts: typical
and improved grid map path planning. Experiments show that the improved grid map can
increase the success rate and the FIQL can be used by the search and rescue robot to
accomplish the task in a complex environment. Compared with other algorithms, FIQL can
reduce the number of iterations, improve the adaptability of the search and rescue robot to
complex environments, and have the advantages of short convergence time and small
computational effort.
Introduction
With the rapid development of artificial intelligence and sensors, search and rescue robots
(SAR robots) are no longer far away, and SAR robots can help humans to complete search and
rescue tasks, especially in the era of prevalent epidemics and frequent natural disasters. As
technology advances, the functions, movements, and responses of SAR robots are becoming
more and more mature, bringing hope to people in deep water. Compared to real humans,
SAR robots can not only detect the target that needed to be searched and rescued but can also
do things that humans cannot do, such as snake-like robots that can complete the search task
PLOS ONE | https://doi.org/10.1371/journal.pone.0283751 March 30, 2023 1 / 22
a1111111111
a1111111111
a1111111111
a1111111111
a1111111111
OPEN ACCESS
Citation: Hao B, Zhao J, Du H, Wang Q, Yuan Q,
Zhao S (2023) A search and rescue robot search
method based on flower pollination algorithm and
Q-learning fusion algorithm. PLoS ONE 18(3):
e0283751. https://doi.org/10.1371/journal.
pone.0283751
Editor: Aytac¸ Altan, Zonguldak Bu¨lent Ecevit
University: Zonguldak Bulent Ecevit Universitesi,
TURKEY
Received: September 25, 2022
Accepted: March 15, 2023
Published: March 30, 2023
Copyright: © 2023 Hao et al. This is an open
access article distributed under the terms of the
Creative Commons Attribution License, which
permits unrestricted use, distribution, and
reproduction in any medium, provided the original
author and source are credited.
Data Availability Statement: Data, analysis code
and images are available from GitHub at https://
github.com/466331315/Data-Availability-
Statement.
Funding: Basic scientific research business cost
scientific research project of Heilongjiang
Provincial University (135509114) The Funder is
Bing Hao, the funder had a role in
conceptualization, methodology project
administration and supervision. Natural Science
