Path Planning in Narrow Road Scenarios Based on Four-Layer Network Cost Structure Map.

Aiming at the problems of poor flexibility, complicated path maintenance and poor positioning performance in the current guidance technology of AGV, this paper designs and implements a new navigation system of automated guided vehicle (AGV) based on AprilTags2 auxiliary positioning. The system uses the Robot Operating System (ROS) as a platform to develop AGV navigation functions. The navigation system comprises two parts: the hardware and software layers. Firstly, hardware selection is performed after considering the actual requirements, performance, cost, and other factors in the hardware layer. Simultaneously, the AGV chassis and single-steering wheel walking mechanism are built to provide a stable and flexible operating platform for the software layer. Secondly, the software layer design includes two parts, namely the ROS navigation planning end and AprilTags2 detection. The ROS planning navigation end performs the design of four functional modules (i.e., AGV map construction, autonomous positioning, path planning, and path tracking), while the AprilTags2 detection part obtains the visual positioning pose of AGV by setting the AprilTags2 on each site and using the Kinect1 camera to detect. A more accurate AGV pose can be obtained by merging the former pose with the kinematic estimated pose. Finally, the two groups of positioning errors of the system before and after adding the AprilTags2 auxiliary positioning are tested and compared. The experimental results show that the navigation accuracy of the proposed system with AprilTags2 auxiliary positioning is significantly improved.

A motion planning method that integrates global planning and local control is proposed in this paper, aiming to enable Automated Guided Vehicle (AGV) to navigate automatically in two-dimensional environment. The layered cost maps are utilized and divided into global cost map and local cost map to respectively provide environment information for the global planning and local control. Specifically, the global planning is based on the path planning algorithm to establish a global optimal path on the global cost map. Under the guidance of global path, local control generates an optimal collision free trajectory with temporal information on the local cost map, which can avoid contact with surrounding obstacles. The local control operates in real-time and consider temporal information, thereby it can directly generate commands for the underlying robot motion controller. Both the simulation and experimental results are presented in support of the feasibility and effectiveness of the proposed motion planning.

Intelligent logistics is an important part of intelligent manufacturing, and Automated Guided vehicle (AGV), as a part of seamless enterprise production system and storage system, is an important technical equipment to achieve intelligent logistics, and has been widely used in factories, warehousing and logistics environment such as automatic handling scenarios. Since a single AGV in the same site can no longer meet the trend of automated factory, it is important to effectively schedule and plan paths for multiple AGVs in limited space. Aiming at multi-AGV system, this paper analyzes and organizes the common path planning algorithms in the market, in order to improve the effectiveness and safety of AGVs. The A* algorithm and the ant colony algorithm's principles will be analyzed in the first part of the paper. Then describe the research status of the two respectively and summarize the advantages and defects respectively. Finally, prospect the development progress of AGV coordinated scheduling and path planning.

Efficient path planning for Automated Guided Vehicles (AGVs) in warehouse automation is crucial yet challenging, particularly in environments with irregular structures and constrained spaces. This study addresses these challenges by focusing on AGVs without rotary platforms, which require the rotation of the entire robot-rack assembly for directional changes, demanding additional space and complex path planning. We have developed dedicated algorithms that integrate robotics and optimization principles to tackle these issues. Our methods take into account the spatial requirements for rack rotation, navigating through limited inter-rack clearance, and adapting to irregular warehouse layouts. Extensive simulations and real-world applications validate the proposed solutions, demonstrating significant improvements in traversal efficiency and collision risk mitigation. The results indicate that our algorithms effectively enhance the operational efficiency and reliability of AGV systems in complex warehouse environments. This research adapts AGV path planning by providing robust strategies to optimize navigation in challenging settings, ultimately improving warehouse productivity.

Path planning is one of the most important fields of research in the area of robotics. In this paper, a path planning method for a certain type of wheeled mobile robots called automated guided vehicles (AGVs) is proposed. The proposed model applies fuzzy control techniques to navigate the AGV in an unknown environment to reach a certain destination. In addition, a new method for escaping local minimums, which may be very critical issue faced by an AGV in an unknown environment, is introduced. Simulation results show satisfactory performance of the proposed method

In order to solve the path planning problem of Automated Guided Vehicle (AGV) transporting goods and packages in warehouse logistics, this paper studies the Algorithm of the path planning problem, an improved adaptive genetic algorithm is presented to solve the path optimization problem. In order to avoid falling into local optimum, an improved self-adaptive crossover method is proposed. In order to avoid the conflict of AGV in the process of path planning, the concept of Congestion Coefficient is introduced into the design of fitness function, reduce the AGV in the path optimization process of conflict. The mathematical model of AGV to accomplish multi-task is established, and the comparative experiment is set up. The experimental results show that the improved adaptive genetic algorithm can improve the optimization performance by 4.2% in solving the optimal path problem, and improve the convergence speed by 4.2%, the improved algorithm has obvious advantages.

The most fundamental requirements for achieving accurate navigation of mobile robots are localization, map building and path planning. Currently, the mainstream methods include magnetic peg navigation, laser navigation, and 2D code navigation, etc. SLAM technology has the advantages of automation, intelligence, environmental adaptability, and low cost, and AGVs using this algorithm have been widely used in indoor applications and logistics transportation. Therefore, the SLAM (Simultaneous Localization and Mapping) algorithm based Automated Guided Vehicle (AGV) has become a hot research topic at home and abroad. In this paper, we investigate the SLAM algorithm in AGV system, and build indoor and logistics simulation environment maps based on 2D laser SLAM technology of Hector, Cartographer, Gmapping and Karto algorithms, and compare them by building accuracy index. The results show that the Hector algorithm has faster map building speed and accuracy, and is more suitable for indoor and logistics AGV systems.

Automated Guided Vehicles (AGV) with magnetic navigation and electromagnetic navigation have lower path flexibility due to the need to lay the path ahead of time. The Simultaneous Localization and Mapping (SLAM) is mature in technology theory, so that this technique is applied to the AGV navigation. The laser sensor is used to acquire the information in the location environment for immediate location and mapping, so that carry out the path planning and complete the AGV autonomous navigation. Extended Kalman Filter (EKF) is the most common solution for laser SLAM. Firstly, this paper analyzes the research results of EKF-SLAM at this stage and its limitations. Secondly, it discusses the application of EKF-SLAM in AGV and the development direction in the next stage. By comparative analysis shows that laser EKF-SLAM can meet the requirements of AGV navigation. The development of EKF-SLAM algorithm in positioning, mapping accuracy and the ability to solve interferences in dynamic environment has an important reference for the reliability of AGV navigation.

AGV (Automated Guided Vehicle) technology has attracted increasing attention. Precise control of AGV position and attitude information in complex operating environment is a key part of smart factories. With outdoor AGV as a platform, this study uses BDS/INS combined navigation system combining Beidou positioning system and inertial navigation system and takes the velocity and position difference between BDS and INS as a model. An integrated navigation method is proposed to improve bee colony algorithm and optimize the BP neural network-assisted Kalman filtering to achieve accurate positioning. Moreover, the optimization of BP neural network navigation using INS navigation, network-assisted navigation and bee colony algorithm is simulated. Results demonstrate that the integrated navigation algorithm has effectiveness and feasibility, and can solve the problems of BDS misalignment and large INS navigation error in complex environments.

Intelligent warehouse becomes a key component of logistics process automation, which essentially promotes the productivity and cost reduction. This paper presents a novel design solution of an Automated Guided Vehicles (AGVs) system for intelligent warehouse. An improved version of classical Dijkstra shortest-path algorithm is proposed for efficient global path planning. In the case of multi-AGV, the time windows method is used to address the issue of conflict and deadlock. In addition, the local path planning and auto-localization is addressed by using a heuristics-based algorithm and Monte Carlo Localization algorithm respectively. Extensive numerical experiments based on Player/Stage simulator are carried out to assess the suggested algorithms, for a range of scenarios and the result well validates its effectiveness. Currently the proposed design solution is adopted in developing the prototype of AGVs to be deployed in practice.

The Automated Guided Vehicle (AGV) is a device that uses various sensor technologies, automation, and multiple control systems. AGVs have many navigation methods, of which the magnetic stripe navigation system is well developed. The magnetic stripe navigation AGV positioning is carried out precisely and at a lower cost level. However, the magnetic stripe is prone to breakage, and the AGV can only travel according to the magnetic stripe and cannot be intelligently avoided or the task changed in real-time by the control system. This paper draws on magnetic stripe navigation tracking principles, using grey-scale sensors for stable path tracking; distance sensors are combined for timely obstacle avoidance; Bluetooth is used to obtain approximate indoor locations for path planning. The navigation system simultaneously combines multi-sensor information for navigation, ultimately enabling the AGV to be quickly positioned accurately along the prescribed path and return to the route in time to avoid obstacles.

With the booming development of logistics, manufacturing and warehousing fields, the autonomous navigation and intelligent obstacle avoidance technology of automated guided vehicles (AGVs) has become the focus of scientific research. In this paper, an enhanced deep reinforcement learning (DRL) framework is proposed, aiming to empower AGVs with the ability of autonomous navigation and obstacle avoidance in the unknown and variable complex environment. To address the problems of time‐consuming training and limited generalisation ability of traditional DRL, we refine the twin delayed deep deterministic policy gradient algorithm by integrating adaptive noise attenuation and dynamic delayed updating, optimising both training efficiency and model robustness. In order to further strengthen the AGV's ability to perceive and respond to changes of a dynamic environment, we introduce a distance‐based obstacle penalty term in the designed composite reward function, which ensures that the AGV is capable of predicting and avoiding obstacles effectively in dynamic scenarios. Experiments indicate that the AGV model trained by this algorithm presents excellent autonomous navigation capability in both static and dynamic environments, with a high task completion rate, stable and reliable operation, which fully proves the high efficiency and robustness of this method and its practical value.

Robot path planning is a cornerstone of precision agriculture, enabling safe and efficient operations for agricultural robots. However, complex field environments—characterized by static and dynamic obstacles, dense vegetation, and unstructured terrain—pose significant challenges to effective path planning. Conventional methods, such as A*, Dijkstra, and rapidly exploring random tree (RRT), exhibit limitations in efficiency and adaptability to dynamic conditions. To address these challenges, this study introduces AgriPath, a robust multi-objective path planning framework that integrates an improved convolutional neural network (CNN), an improved A* algorithm, and an improved whale optimization algorithm (IWOA) to optimize pathfinding, convergence efficiency, and obstacle avoidance in complex agricultural settings. Key innovations include an improved CNN leveraging causal convolution and multi-head self-attention mechanisms to improve temporal modeling for short-term trajectory prediction, augmented by Gaussian perturbations to enhance initial solution diversity; an improved A* algorithm incorporating dynamic heuristic functions based on Normalized Difference Vegetation Index (NDVI), combined with Kalman filtering, to bolster global path adaptability; IWOA employing non-linear convergence factors and differential evolution mechanisms to dynamically balance path length, smoothness, and planning time; and an improved Douglas–Peucker algorithm paired with cubic B-spline smoothing and navigation command modules to ensure path simplification and real-time execution. Experiments conducted in the Modern Agricultural Demonstration Zone at Chengdu, Sichuan Province, China, across simple, moderate, and complex scenarios, demonstrate that AgriPath outperforms advanced algorithms—SBREA*, Ant Colony A*, Orchard A*, and Greedy A*—in path length, smoothness, planning time, and dynamic obstacle avoidance success rate, indicative of superior multi-objective optimization balance. This study significantly enhances the efficiency and robustness of agricultural robot path planning, offering a more adaptive solution for autonomous navigation in precision agriculture while providing new theoretical and practical directions for the field of path planning.

This paper presents a new approach for kinodynamic online motion planning for Automated Guided Vehicles (AGVs) in industrial environments. AGVs normally transport large and heavy transport units such as Euro-pallets or mesh pallets. Nowadays just-in-time inventory management and lean production requires the transport of small transportation units. Thus a flexible material flow is needed that can not be fulfilled by continuous material handling devices like belt or roll conveyors. Our approach uses small holonomic AGVs that are equipped with safety laser range finders for our semi autonomous motion and path planning system. This system plans trajectories with respect to the kinodynamic constraints of the AGVs and the environment. The operator retains as much control as necessary and the vehicle can react online on course deviations and unforeseen changes in the environment.

In order to solve the problem that the traditional automated guided vehicle (AGV) path planning algorithm has slow convergence speed and is easy to fall into local optimal solution, an improved D*lite algorithm is being presented by combining Dijkstra algorithm and D*lite algorithm. Firstly, the topological map is generated with grid graph. Then, AGV path planning is divided into two stages: pre-planning and real-time planning. In the pre-planning stage, the local shortest path can be achieved through forward searching with Dijkstra algorithm from start vertex to the goal vertex. In the real-time planning stage, the total shortest path can be computed through backward searching with improved D*lite algorithm which searches from the goal vertex to the start vertex and uses heuristics to focus the search, and uses similar ways to minimize having to reorder the priority queue. Finally, the simulation results indicate that the convergence speed and path distance of AGV are optimized by using the improved D*lite algorithm.KeywordsAGVImproved D*lite algorithmPath planningSimulation