Voronoi-GRU-Based Multi-Robot Collaborative Exploration in Unknown Environments

In modern society, the autonomous exploration of unknown environments has attracted extensive attention due to its broad applications, such as in search and rescue operations, planetary exploration, and environmental monitoring. This paper proposes a novel collaborative exploration strategy for mult...

Full description

Saved in:
Bibliographic Details
Main Authors: Yang Lei, Jian Hou, Peixin Ma, Mingze Ma
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/6/3313
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850089827899277312
author Yang Lei
Jian Hou
Peixin Ma
Mingze Ma
author_facet Yang Lei
Jian Hou
Peixin Ma
Mingze Ma
author_sort Yang Lei
collection DOAJ
description In modern society, the autonomous exploration of unknown environments has attracted extensive attention due to its broad applications, such as in search and rescue operations, planetary exploration, and environmental monitoring. This paper proposes a novel collaborative exploration strategy for multiple mobile robots, aiming to quickly realize the exploration of entire unknown environments. Specifically, we investigate a hierarchical control architecture, comprising an upper decision-making layer and a lower planning and mapping layer. In the upper layer, the next frontier point for each robot is determined using Voronoi partitioning and the Multi-Agent Twin Delayed Deep Deterministic policy gradient (MATD3) deep reinforcement learning algorithm in a centralized training and decentralized execution framework. In the lower layer, navigation planning is achieved using A* and Timed Elastic Band (TEB) algorithms, while an improved Cartographer algorithm is used to construct a joint map for the multi-robot system. In addition, the improved Robot Operating System (ROS) and Gazebo simulation environments speed up simulation times, further alleviating the slow training of high-precision simulation engines. Finally, the simulation results demonstrate the superiority of the proposed strategy, which achieves over 90% exploration coverage in unknown environments with a significantly reduced exploration time. Compared to MATD3, Multi-Agent Proximal Policy Optimization (MAPPO), Rapidly-Exploring Random Tree (RRT), and Cost-based methods, our strategy reduces time consumption by 41.1%, 47.0%, 63.9%, and 74.9%, respectively.
format Article
id doaj-art-049c857eabaa4dd598f4101cd326c3c0
institution DOAJ
issn 2076-3417
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-049c857eabaa4dd598f4101cd326c3c02025-08-20T02:42:41ZengMDPI AGApplied Sciences2076-34172025-03-01156331310.3390/app15063313Voronoi-GRU-Based Multi-Robot Collaborative Exploration in Unknown EnvironmentsYang Lei0Jian Hou1Peixin Ma2Mingze Ma3School of Computer Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, ChinaSchool of Computer Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, ChinaBeijing Zhongke Huiling Robot Technology Co., Ltd., Beijing 100192, ChinaSchool of Information Engineering, Wenzhou Business College, Wenzhou 325035, ChinaIn modern society, the autonomous exploration of unknown environments has attracted extensive attention due to its broad applications, such as in search and rescue operations, planetary exploration, and environmental monitoring. This paper proposes a novel collaborative exploration strategy for multiple mobile robots, aiming to quickly realize the exploration of entire unknown environments. Specifically, we investigate a hierarchical control architecture, comprising an upper decision-making layer and a lower planning and mapping layer. In the upper layer, the next frontier point for each robot is determined using Voronoi partitioning and the Multi-Agent Twin Delayed Deep Deterministic policy gradient (MATD3) deep reinforcement learning algorithm in a centralized training and decentralized execution framework. In the lower layer, navigation planning is achieved using A* and Timed Elastic Band (TEB) algorithms, while an improved Cartographer algorithm is used to construct a joint map for the multi-robot system. In addition, the improved Robot Operating System (ROS) and Gazebo simulation environments speed up simulation times, further alleviating the slow training of high-precision simulation engines. Finally, the simulation results demonstrate the superiority of the proposed strategy, which achieves over 90% exploration coverage in unknown environments with a significantly reduced exploration time. Compared to MATD3, Multi-Agent Proximal Policy Optimization (MAPPO), Rapidly-Exploring Random Tree (RRT), and Cost-based methods, our strategy reduces time consumption by 41.1%, 47.0%, 63.9%, and 74.9%, respectively.https://www.mdpi.com/2076-3417/15/6/3313multiple mobile robotscollaborative explorationreinforcement learningvoronoi partitioningMATD3
spellingShingle Yang Lei
Jian Hou
Peixin Ma
Mingze Ma
Voronoi-GRU-Based Multi-Robot Collaborative Exploration in Unknown Environments
Applied Sciences
multiple mobile robots
collaborative exploration
reinforcement learning
voronoi partitioning
MATD3
title Voronoi-GRU-Based Multi-Robot Collaborative Exploration in Unknown Environments
title_full Voronoi-GRU-Based Multi-Robot Collaborative Exploration in Unknown Environments
title_fullStr Voronoi-GRU-Based Multi-Robot Collaborative Exploration in Unknown Environments
title_full_unstemmed Voronoi-GRU-Based Multi-Robot Collaborative Exploration in Unknown Environments
title_short Voronoi-GRU-Based Multi-Robot Collaborative Exploration in Unknown Environments
title_sort voronoi gru based multi robot collaborative exploration in unknown environments
topic multiple mobile robots
collaborative exploration
reinforcement learning
voronoi partitioning
MATD3
url https://www.mdpi.com/2076-3417/15/6/3313
work_keys_str_mv AT yanglei voronoigrubasedmultirobotcollaborativeexplorationinunknownenvironments
AT jianhou voronoigrubasedmultirobotcollaborativeexplorationinunknownenvironments
AT peixinma voronoigrubasedmultirobotcollaborativeexplorationinunknownenvironments
AT mingzema voronoigrubasedmultirobotcollaborativeexplorationinunknownenvironments