检索结果-内蒙古大学图书馆

Hybrid path planning for USV with kinematic constraints and COLREGS based on APF-RRT and DWA

OCEAN ENGINEERING 2025年 318卷

作者： Wang, Yuchao Li, Jialing Zhao, Shiquan Su, Peng Fu, Huixuan Niu, Hongmin Harbin Engn Univ Coll Intelligent Syst Sci & Engn Harbin 150001 Peoples R China China Ship Res & Design Ctr Wuhan 430060 Peoples R China Changan Univ Sch Elect & Control Engn Xian 710064 Peoples R China

Intelligent algorithms are increasingly employed to optimize the ship path planning, ensuring safe navigation and preventing potential collisions. This paper proposes a hybrid path planning approach that incorporates kinematic constraints, which includes both global and local path planning. Firstly, the Artificial Potential Field (APF) is utilized to guide node growth, allowing the Rapidly-exploring Random Tree (RRT) to more efficiently navigate through multi-obstacle areas. To enhance the robustness of the algorithm, the gravitational coefficient optimization method and dynamic step-size strategy are introduced. Additionally, a novel RRT termination method is proposed to accelerate search speed by either using the node that satisfies the termination criteria as the last path point or by inserting anew node to fulfill all constraints. Furthermore, building upon the dynamic window algorithm (DWA), a turning function based on maritime rules and the Collision Risk Index (CRI) are incorporated. New cost functions are established accordingly for different types of obstacles. The results from simulation experiments demonstrate the superior performance of the proposed method. The enhanced global path planning algorithm improves the efficiency of global path acquisition in diverse environments. Moreover, the proposed local path planning algorithm can accurately assess and respond to different scenarios and performs better than the traditional method in collision avoidance.

关键词： Unmanned surface vehicle Rapidly-exploring random tree Artificial potential field algorithm dynamic window algorithm Collision avoidance COLREGS

来源：评论

学校读者我要写书评

暂无评论

Obstacle Avoidance Strategy and Path Planning of Medical Automated Guided Vehicles Based on the Bionic Characteristics of Antelope Migration

引用

BIOMIMETICS 2025年第3期10卷 142-142页

作者： Hu, Jing Niu, Junchao Zhang, Bangcheng Gao, Xiang Zhang, Xinming Huang, Sa Changchun Univ Sci & Technol Sch Mechatron Engn Changchun 130022 Peoples R China Changchun Inst Technol Changchun 130103 Peoples R China Foshan Univ Sch Mechatron Engn & Automat Foshan 528225 Peoples R China Guangdong Educ Dept Precis Machining & Special Machining Innovat Team Foshan 528225 Peoples R China Jilin Univ Bethune Clin Sch Med 2 Changchun 130015 Peoples R China

Automated Guided Vehicles (AGVs) face dynamic and static obstacles in the process of transporting patients in medical environments, and they need to avoid these obstacles in real time. This paper proposes a bionic obstacle avoidance strategy based on the adaptive behavior of antelopes, aiming to address this problem. Firstly, the traditional artificial potential field and dynamic window algorithm are improved by using the bionic characteristics of antelope migration. Secondly, the success rate and prediction range of AGV navigation are improved by adding new potential field force points and increasing the window size. Simulation experiments were carried out on a numerical simulation platform, and the verification results showed that the bionic obstacle avoidance strategy proposed in this paper can avoid dynamic and static obstacles at the same time. In the example, the success rate of path planning is increased by 34%, the running time is reduced by 33%, and the average path length is reduced by 1%. The proposed method can help realize the integration of "dynamic and static" avoidance in the process of transporting patients and effectively save time by using AGVs to transport patients. It provides a theoretical basis for realizing obstacle avoidance and rapidly loading AGVs in medical environments.

关键词： medical AGV bionic strategy artificial potential field algorithm dynamic window algorithm path planning

来源：评论

学校读者我要写书评

暂无评论

A hybrid path planning strategy unified with COLREGS for the unmanned surface vehicle

引用

SHIPS AND OFFSHORE STRUCTURES 2025年

作者： Wan, Lili Li, Jing Zhou, Mi Wuhan Polytech Univ Sch Elect & Elect Engn Wuhan 430023 Peoples R China

The applications of the Unmanned Surface Vehicle (USV) are widely distributed in various fields. This paper proposes a new path planning method that combines A* algorithm with an adaptive dynamic window algorithm (DWA), which can simultaneously achieve static and dynamic obstacle avoidance. For ADWA, the adaptive factor is introduced in adjust the prediction time of DWA, and the time evaluation factor is introduced in the DWA evaluation function to evaluate the prediction time. The global path planning of the USV is realised by A* algorithm and smooth processed by spline interpolation method based on B-spline, then the local path planning of the USV is realised by the adaptive DWA. Furthermore, the Convention on the International Regulations for Preventing Collisions at Sea (COLREGS) is integrated and a hybrid path planning strategy is emerged to guarantee the collision avoidance safety in multi-ships encounter. Simulation experiments show that the proposed hybrid path planning strategy can realise flexible obstacle avoidance by adjusting the prediction time, and the USV can follow COLREGS for safe avoidance when encountering other vehicles.

关键词： Unmanned surface vehicle path planning COLREGS dynamic window algorithm A* algorithm

来源：评论

学校读者我要写书评

暂无评论

A Balanced Collision Avoidance algorithm for USVs in Complex Environment: A Deep Reinforcement Learning Approach

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2024年第12期25卷 21404-21415页

作者： Lou, Mengmeng Yang, Xiaofei Hu, Jiabao Zhu, Zhiyu Shen, Hao Xiang, Zhengrong Zhang, Bin Jiangsu Univ Sci & Technol Sch Automat Zhenjiang 212100 Jiangsu Peoples R China Anhui Univ Technol Sch Elect & Informat Engn Maanshan 242032 Anhui Peoples R China Nanjing Univ Sci & Technol Sch Automat Nanjing 210094 Peoples R China Univ South Carolina Dept Elect Engn Columbia SC 29208 USA

The collision avoidance in real-time is crucial for unmanned surface vehicles (USVs) in a complex environment. Traditional methods make it hard to ensure the balance of control decisions. To balance safety and practicality, a collision avoidance algorithm based on deep reinforcement learning (DRL) and a two-level incentive reward based on the principle of complementarity is proposed. To address the vital sparse reward problem of Deep Deterministic Policy Gradient (DDPG), the trajectory evaluation function of the dynamic window algorithm (DWA) is referred to construct the primary reward strategy, and a secondary incentive reward is constructed based on velocity obstacle (VO) to eliminate potential collision risks. To improve the efficiency of training, the electronic chart (EC) and Unity3D are used to build an immersive simulation platform. Based on it, simulations are made to verify the performance. In addition, field experiments are first conducted in various encounter scenarios to verify the effectiveness. The results show that it can take safe collision avoidance actions and get practical paths in various situations.

关键词： Unmanned surface vehicles obstacle avoidance deep deterministic policy gradient dynamic window algorithm velocity obstacle

来源：评论

学校读者我要写书评

暂无评论

A Real-time Path Planning algorithm for Mobile Robots Based on Safety Distance Matrix and Adaptive Weight Adjustment Strategy

引用

INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS 2024年第4期22卷 1385-1399页

作者： Zhai, Xinpeng Tian, Jianyan Li, Jifu Taiyuan Univ Technol Coll Elect & Power Engn Taiyuan 030024 Peoples R China

The fusion of the A* and the dynamic windowing algorithm is commonly used for the path planning of mobile robots in dynamic environments. However, the planned path has the problems of redundancy and low security. This paper proposes a path planning algorithm based on the safety distance matrix and adaptive weight adjustment strategy to address the above problems. Firstly, the safety distance matrix and new heuristic function are added to the traditional A* algorithm to improve the safety of global path. Secondly, the weight of the evaluation sub-function in the dynamic window algorithm is adjusted through an adaptive weight adjustment strategy to solve the problem of path redundancy. Then, the above two improved algorithms are fused to make the mobile robot have dynamic obstacle avoidance capability by constructing a new global path evaluation function. Finally, simulations are performed on grid maps, and the fusion algorithm is applied to the actual mobile robot path planning based on the ROS. Simulation and experimental results show that the fusion algorithm achieves optimization of path safety and length, enabling the robot to reach the end point safely with real-time dynamic obstacle avoidance capability.

关键词： Adaptive weight A* algorithm dynamic window algorithm path planning safety distance matrix

来源：评论

学校读者我要写书评

暂无评论

Hybrid path planning method for USV using bidirectional A* and improved DWA considering the manoeuvrability and COLREGs

引用

OCEAN ENGINEERING 2024年 298卷

作者： Xu, Donghao Yang, Jie Zhou, Xueqian Xu, Haitong Harbin Univ Sci & Technol Coll Automat Harbin 150080 Peoples R China Harbin Engn Univ Coll Shipbuilding Engn Harbin 150001 Peoples R China Univ Lisbon Ctr Marine Technol & Ocean Engn CENTEC Inst Super Tecn Lisbon Portugal Univ Lisbon Int Joint Lab Naval Architecture Offshore Technol Harbin 150001 Peoples R China

This paper proposes a hybrid dynamic path planning algorithm that integrates global path planning (GPP) and local path planning (LPP). The objective is to effectively address the challenges associated with path planning and collision avoidance for unmanned surface vehicles (USV) in complex environments. The bidirectional A* algorithm is used to search the optimized strategy based on the actual geographical information map for the navigation routes of USV. The dynamic window algorithm (DWA) is employed, and a novel cost function is formulated considering the USV's manoeuvring characteristics, dynamic constraints, and environmental information. The primary purpose is to ensure the compliance of the USV with COLREGs during dynamic obstacle avoidance. It accomplishes this by providing positive reinforcement for achieving the correct turning speed when the USV determines the orientation of an approaching ship. Another evaluation function is introduced to mitigate the problem of local optima in complex environments that the LPP may encounter. The actual work map is used to model the application scenario with the obstacles in the presence of incoming ships, the simulation results show that the proposed algorithm is capable of generating adaptive, collision-free routes while adhering to COLREGs rules.

关键词： Bidirectional A* algorithm dynamic window algorithm Unmanned surface vessel COLREGs Manoeuvrability

来源：评论

学校读者我要写书评

暂无评论

Research on Path Planning of Family Nursing Robot Based on Robot Operating System

Research on Path Planning of Family Nursing Robot Based on R...

引用

International Conference on Advanced Robotics and Mechatronics (ICARM)

作者： Zheng, Wenlei Cheng, Lei Huang, Jian Dai, Yating Shang, Chuang Peng, Rui He, Zhihua Wuhan Univ Sci & Technol Minist Educ Engn Res Ctr Met Automat & Measurement Technol Wuhan 430081 Peoples R China Hangzhou Dianzi Univ Sch Automat Hangzhou 310018 Zhejiang Peoples R China Huhzhong Univ Sci & Technol Sch Automat Wuhan 430074 Peoples R China Wuhan Univ Sci & Technol Wuhan Hubei Peoples R China

ISBN: (纸本)9781509033645

Aiming at the problem of indoor navigation of family nursing robot, this paper proposes a dynamic window algorithm that the service robot could plan the optimal path autonomously and realize the obstacle avoidance quickly in the indoor dynamic environment. Firstly, the basic principle of the dynamic window method is introduced, and then the navigation system of the service robot's indoor dynamic environment is built in the robot operating system framework by this algorithm. According to the established map of indoor grid environment, the system collects information about the destination that the user inputs, then using the dynamic window algorithm, service robot could avoid dynamic obstacles accurately in dynamic indoor environment and independently arrive the destination quickly through the optimal path of autonomous planning. Finally, the effectiveness of the proposed method is verified by experiments.

关键词： dynamic environment dynamic window algorithm Family nursing robot robot operating system

来源：评论

学校读者我要写书评

暂无评论

Hybrid Collision Avoidance for Autonomous Surface Vehicles

Hybrid Collision Avoidance for Autonomous Surface Vehicles

引用

11th IFAC Conference on Control Applications in Marine Systems, Robotics, and Vehicles (CAMS)

作者： Serigstad, Einvald Eriksen, Bjorn-Olav H. Breivik, Morten Norwegian Univ Sci & Technol NTNU Ctr Autonomous Marine Operat & Syst Dept Engn Cybernet Trondheim Norway

Autonomous vehicles and collision avoidance (COLAV) systems are advancing rapidly. However, the majority of the COLAV methods developed are not designed for vehicles with second-order nonholonomic constraints, such as autonomous surface vehicles (ASVs). This paper proposes the hybrid dynamic window (HDW) algorithm, which in addition to acting as a reactive COLAV method, functions as a trajectory tracker in a hybrid COLAV architecture. The algorithm serves as an interface to any deliberate COLAV method which generates time parameterized trajectories, enabling vehicles to avoid local minima and track optimal trajectories towards the goal. Furthermore, a new distance function is developed for the dynamic window (DW) algorithm, improving the algorithm trajectory planning when operating close to obstacles. A case study is done for an ASV model using the HDW algorithm and the rapidly-exploring random tree (RRT) algorithm, which together form a hybrid COLAV system. The performance is evaluated through simulations using a defined set of performance metrics. (C) 2018, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.

关键词： Hybrid collision avoidance trajectory planning dynamic window algorithm autonomous surface vehicles

来源：评论

学校读者我要写书评

暂无评论

Multi -robot flocking path planning based on fusion of APF and Improved DWA algorithms 39

Multi -robot flocking path planning based on fusion of APF a...

引用

39th Youth Academic Annual Conference of Chinese-Association-of-Automation (YAC)

作者： Zhang, Jin Shao, Shiliang Wang, Ting Shi, Xianyu Zhao, Xianzhe Zhao, Hai Northeastern Univ Sch Comp Sci & Engn Shenyang Peoples R China Chinese Acad Sci State Key Lab Robot Shenyang Inst Automat Shenyang Peoples R China Chinese Acad Sci Inst Robot & Intelligent Mfg Shenyang Peoples R China Univ Chinese Acad Sci Beijing Peoples R China

ISBN: (纸本)9798350390780;9798350379228

Robot flocking systems in unknown environments have higher adaptability, higher efficiency and stronger robustness compared to single robots. In this paper, a control algorithm based on the fusion of the artificial potential field algorithm and the improved dynamic window algorithm is proposed for the path planning in the multi-robot flocking control process. In the free space, the multi -robot flocking will obtain the velocity control input based on the artificial potential field algorithm, and go to the target point quickly with the "quasi -lattice" formation structure;when the robots senses obstacles, control algorithm switches to the dynamic window algorithm, and obtains the control input that can maintain the flocking state and realize the obstacle avoidance at the same time, according to the evaluation function. In this paper, the orientation evaluation function is improved, and a new evaluation functions are added to form an evaluation function with four evaluation indexes, which solves the robot local optimization problem and ensures the formation state of the robots, and improves the excellent trajectory score. The validity and advantages of the proposed algorithm are verified through theoretical analysis and simulation experiments.

关键词： mufti-robot flocking path planning artificial potential field dynamic window algorithm

来源：评论

学校读者我要写书评

暂无评论

Enhanced USV path planning through integrated Bi-RRT and DWA algorithms considering environmental factors

引用

JOURNAL OF MARINE ENGINEERING AND TECHNOLOGY 2024年

作者： Zhou, Yanghua Li, Weifeng Cheng, Ke Schonfeld, Paul Dalian Maritime Univ Nav Coll Dalian 116026 Peoples R China Univ Maryland Dept Civil & Environm Engn College Pk MD USA

This paper presents a novel hybrid dynamic path planning algorithm termed GIBi-RRT-IDWA, which enhances global path planning by amalgamating the Bi-RRT algorithm with the local path planning capabilities of the refined DWA algorithm. Through enhancements in node expansion techniques, Improvements in Tree Expansion to eliminate redundancy, and improvements in Sample Point Generation to augment the Bi-RRT algorithm, the algorithm achieves heightened search efficiency and path security, ultimately leading to the derivation of globally optimal trajectories. The motion model for USV is refined to encompass environmental factors such as winds and currents, pertinent to marine contexts. Furthermore, the evaluation function of the DWA algorithm undergoes enhancements, incorporating elements from heuristic functions within the A* algorithm and radar-based assessment of search range. These improvements facilitate expedited Goal point tracking and fortify the USV's capability to navigate around hazards. Experimental findings corroborate the efficacy of the GIBi-RRT-IDWA algorithm, showcasing its superiority over conventional DWA algorithm and IDWA algorithm. Notably, the algorithm demonstrates prowess in generating shorter and safer trajectories, adeptly navigating through intricate and dynamic waterside environments. Consequently, it improves path planning strategies' adaptability and resilience, allowing USVs to navigate more safely and efficiently.

关键词： Bidirectional RRT algorithm dynamic window algorithm path planning Unmanned surface vessel

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：