Shengxuan Dong, Xiongwei Li^*

CMC-Computers, Materials & Continua, Vol.89, No.2, 2026, DOI:10.32604/cmc.2026.086535 - 15 September 2026

Abstract To address the conflict between navigation performance and safety constraints in safe reinforcement learning, this paper proposes Dual Stream-Analytic Hierarchy Process-Safe Soft Actor (DS-AHP-SAC), a safe soft actor-critic algorithm based on a dual-stream Q-network and dynamic Analytic Hierarchy Process (AHP) stratified experience replay. The algorithm achieves a balance between reward maximization and constraint satisfaction through three synergistic designs: (1) decoupling the Q-network into independent navigation and safety value streams to eliminate gradient interference at the Critic level and mitigate gradient competition at the Actor level; (2) constructing a three-criterion dynamic sampling strategy based on AHP, More >

Ao Nie¹, Wei Zhou¹, Yi Yu¹, Wan Xu^1,2,*

CMC-Computers, Materials & Continua, Vol.89, No.2, 2026, DOI:10.32604/cmc.2026.083871 - 15 September 2026

Abstract Currently, mobile robot path planning in unstructured forest environments remains a hot research topic in the robotics field. Studies applying the Greylag Goose Optimization (GGO) algorithm to multi-robot path planning under such scenarios are limited, and these approaches still face significant challenges, such as insufficient trajectory smoothness, frequent coordination conflicts, and relatively slow convergence to optimal solutions. To address these issues, this paper proposes an Evolutionary Game-Theoretic Improved GGO algorithm (EG-IGGO), designed to optimize path quality while ensuring robust obstacle avoidance capabilities. Specifically, two novel strategies—the population alignment strategy and the dual-source adaptive guidance strategy—are… More >

Qiwu Wu¹, Tao Yang^2,*, Yunchen Su², Lingzhi Jiang³, Tao Tong²

CMC-Computers, Materials & Continua, Vol.88, No.3, 2026, DOI:10.32604/cmc.2026.082757 - 23 July 2026

Abstract Deep reinforcement learning (DRL) has become an important method in Unmanned Aerial Vehicle(UAV) path planning, but the field still lacks a dedicated bibliometric review that summarizes its publication patterns, intellectual structure, and thematic evolution. This study analyzes 1402 Web of Science publications from 2010 to 2025 using CiteSpace, VOSviewer, and the Bibliometrix R package. Three main findings are reported. First, the bibliometric evidence suggests a four-phase evolution of the field—foundational exploration (2015–2016), continuous-control breakthrough (2017–2019), multi-agent collaborative coordination (2020–2022), and complex-scenario integration (2023–2025)—as reflected in publication trends, keyword bursts, and co-citation clusters. Second, co-citation and keyword More >

Zhengshun Fei^1,*, Qiao Sun¹, Chuang Yang², Siranee Nuchitprasitchai³, Yongping Zheng¹, Xinjian Xiang^1,*

CMC-Computers, Materials & Continua, Vol.88, No.3, 2026, DOI:10.32604/cmc.2026.078696 - 23 July 2026

Abstract Path planning is a critical component for enabling autonomous navigation in mobile robots. Sampling-based planners are widely adopted due to their strong generality, yet they rely heavily on uniform sampling, which often leads to unstable performance and high computational cost in complex environments. To address this issue, recent studies feed free-space point clouds into neural networks to infer a set of guidance states near the optimal path, thereby enabling non-uniform sampling; however, the accuracy of the guidance set becomes a key bottleneck for further improvement. In this paper, we propose an improved point-cloud neural RRT*… More >

Rubina Castro^1,2, Bruno Silva^1,3, Luiz Guerreiro Lopes^1,4, Fábio Mendonça^1,2,*

CMC-Computers, Materials & Continua, Vol.88, No.2, 2026, DOI:10.32604/cmc.2026.079979 - 15 June 2026

Abstract Path planning for autonomous underwater vehicles requires reliable and computationally efficient methods, particularly in cluttered environments. This work presents a comparative evaluation of representative approaches, including metaheuristic optimization methods (continuous genetic algorithm, particle swarm optimization, gray wolf optimizer, and Jaya), a sampling-based method (probabilistic roadmap with genetic refinement), a reactive strategy (artificial potential fields), and a control-based approach (model predictive control with control barrier functions). The algorithms are assessed in a controlled two-dimensional simulated workspace with randomly generated obstacles and systematically increasing obstacle density. Each configuration is evaluated across multiple independent trials using metrics such… More >

Qianshu Yang, Shuangxi Liu^*, Xianyu Wu, Wei Zhao

CMC-Computers, Materials & Continua, Vol.88, No.1, 2026, DOI:10.32604/cmc.2026.079895 - 08 May 2026

Abstract Path planning for unmanned systems in complex environments must simultaneously satisfy safety, kinematic feasibility, and real-time performance requirements. Monte Carlo Tree Search (MCTS) offers advantages such as model-free operation, strong interpretability, and anytime planning capability, but it suffers from large branching factors, excessive search depths, and poor convergence under sparse reward conditions in high-dimensional state spaces. To address these challenges, this paper proposes a Heuristic Rolling Monte Carlo Tree Search (HRMCTS) framework. First, the path planning problem is formulated as a constrained Markov decision process, where the state consists of position and heading, and actions… More >

A. Sivasangari^1,*, V. J. K. Kishor Sonti¹, J. Cruz Antony¹, E. Murali¹, D. Deepa¹, A. Happonen²

CMC-Computers, Materials & Continua, Vol.87, No.3, 2026, DOI:10.32604/cmc.2026.074429 - 09 April 2026

Abstract In the past two decades, Precision Agriculture has received research attention since the development of robotics. Agricultural robotic equipment and drones, which can be operated by farmers, are appearing more frequently and being used to make the process of farming easier and more productive. This paper attempts to develop a modified Q-learning algorithm. A reinforcement learning algorithm called Q-learning has Q-values that are updated in order to find the best routes for the robotic devices to follow while avoiding any obstacles. Different types of terrain and other factors that influence the development of good routes… More >

Yanping Chen¹, Zhengxin Zhan¹, Xiaohui Yan¹, Le Zou^1,*, Yucheng Zhong¹, Hailei Wang²

CMC-Computers, Materials & Continua, Vol.87, No.2, 2026, DOI:10.32604/cmc.2026.075459 - 12 March 2026

Abstract With the increasing complexity of substation inspection tasks, achieving efficient and safe path planning for Unmanned Aerial Vehicles in densely populated and structurally complex three-dimensional (3D) environments remains a critical challenge. To address this problem, this paper proposes an improved path planning algorithm—Random Geometric Graph (RGG)-guided Rapidly-exploring Random Tree (R-RRT)—based on the classical Rapidly-exploring Random Tree (RRT) framework. First, a refined 3D occupancy grid map is constructed from Light Detection and Ranging point cloud data through ground filtering, noise removal, coordinate transformation, and obstacle inflation using spherical structuring elements. During the planning stage, a dynamic… More >

Rui Yao^1,2, Yuye Wang^1,2,*, Fei Yu^1,2,3,*, Hongrun Wu^1,2, Zhenya Diao^1,2

CMC-Computers, Materials & Continua, Vol.87, No.2, 2026, DOI:10.32604/cmc.2026.073861 - 12 March 2026

Abstract Path planning for Unmanned Aerial Vehicles (UAVs) in complex environments presents several challenges. Traditional algorithms often struggle with the complexity of high-dimensional search spaces, leading to inefficiencies. Additionally, the non-linear nature of cost functions can cause algorithms to become trapped in local optima. Furthermore, there is often a lack of adequate consideration for real-world constraints, for example, due to the necessity for obstacle avoidance or because of the restrictions of flight safety. To address the aforementioned issues, this paper proposes a dynamic weighted spherical particle swarm optimization (DW-SPSO) algorithm. The algorithm adopts a dual Sigmoid-based More >

Md. Faishal Rahaman¹, Xueyuan Li^1,*, Muhammad Amjad¹, Ibrahim Gasimov², Md. Shariful Islam², S. M. Abul Bashar³

CMES-Computer Modeling in Engineering & Sciences, Vol.146, No.2, 2026, DOI:10.32604/cmes.2026.078206 - 26 February 2026

Abstract Researchers are increasingly focused on enabling groups of multiple unmanned vehicles to operate cohesively in complex, real-world environments, where coordinated formation control and obstacle avoidance are essential for executing sophisticated collective tasks. This paper presents a Distributed Formation Control and Obstacle Avoidance (DFCOA) framework for multi-unmanned ground vehicles (UGV). DFCOA integrates a virtual leader structure for global guidance, an improved A* path planning algorithm with an advanced cost function for efficient path planning, and a repulsive-force- based improved vector field histogram star(VFH*) technique for collision avoidance. The virtual leader generates a reference trajectory while enabling… More >