AGV scheduling management system based on multi-line sensing

Abstract

The invention discloses an AGV scheduling management system based on multi-line sensing, which belongs to the technical field of artificial intelligence systems, is used for AGV scheduling management, and comprises a control module, a scheduling module, a storage module and a vision module, when an automatic task is started, a full barrel or an empty barrel is found through the vision module, and when a proper position is found, the storage module generates an automatic task, and the automatic task is sent to the control module; and the scheduling plate plans a walking route, distributes vehicles and notifies the control plate, and the control program and the vehicles interact to complete a command issued by scheduling. An internal thread of the control plate comprises a vehicle data connection and a vehicle dispatcher; the scheduling plate performs real-time positioning and updating; an internal thread of the storage module comprises a task planner and a storage service; the internal thread of the visual module comprises reasoning and data synchronization, the reasoning is real-time camera recognition, and the data synchronization is recognition state updating. Compared with the prior art, the AGV operation efficiency is improved, task allocation is reasonably regulated and controlled, and an efficient, intelligent and flexible modern AGV system is constructed.

Description

Technical Field

[0001] This invention discloses an AGV scheduling and management system based on multi-line sensing, belonging to the field of artificial intelligence system technology. Background Technology

[0002] As the manufacturing industry continues to evolve towards intelligence and flexibility, automated logistics systems, as an important component of modern factories and warehousing systems, are increasingly becoming a key link in improving production efficiency and reducing operating costs. Automated Guided Vehicles (AGVs), as core equipment for realizing automated material handling, have been widely used in various industries such as automotive, electronics, pharmaceuticals, and e-commerce due to their flexible path planning capabilities and efficient scheduling and execution mechanisms.

[0003] However, with the increasing number of AGVs and the increasing complexity of operating environments, traditional scheduling methods based on fixed paths or simple rules are no longer sufficient to meet the demands for efficient, safe, and flexible logistics. Multi-AGV systems commonly suffer from problems such as path conflicts, resource contention, and uneven task allocation, severely impacting the overall operational efficiency and stability of the system. Therefore, how to achieve efficient collaborative scheduling of multi-AGV systems has become one of the key scientific problems urgently needing to be solved in the field of intelligent logistics and automation. Summary of the Invention

[0004] The purpose of this invention is to provide an AGV scheduling and management system based on multi-line sensing to solve the problems of path conflict, resource contention, and uneven task allocation in existing AGV systems.

[0005] An AGV scheduling and management system based on multi-line sensing includes four modules: control, scheduling, storage, and vision. When an automatic task is started, the vision module searches for full or empty buckets. When a suitable location is found, the storage module generates an automatic task. The scheduling module plans the travel route, allocates vehicles, and notifies the control module. The control program and the vehicle interact to complete the scheduling commands.

[0006] The AGV scheduling and management system includes modules for system management, log query, control system, scheduling, vision, and warehouse management.

[0007] The system management module includes a system operation status module, which controls the on / off switching of control, scheduling, storage, and visual module threads; The internal threads of the control module include vehicle data connection and vehicle dispatcher; The internal threads of the scheduling module include a vehicle dispatcher, a scheduling system API server, and a location monitoring system. The vehicle dispatcher plans routes and dispatches vehicles, the scheduling system API server displays the AGV's path, provides a scheduling map and scheduling status interface, and the location monitoring system updates the location in real time. The internal threads of the warehousing module include a task scheduler and warehousing services; The internal threads of the vision module include inference and data synchronization. Inference is for real-time camera recognition, and data synchronization is for updating the recognition status.

[0008] The log query module includes system logs and task log queries. The system logs record the system's running status.

[0009] The control system module includes AGV operating status, records and updates the status of each sensor of the AGV, and controls the AGV's repositioning, enabling or disabling, and canceling of tasks.

[0010] The control system module page includes a system information bar and a robot status bar; The system information bar displays the information interaction status of each AGV in the system. The information interaction status includes activation status, robot ID, IP, status, reason for status change, time of last operation, last operation, and obstacle avoidance range mode. The robot status bar displays the status of each AGV. Once the AGV starts successfully and the update thread is open, the correct content is displayed. The AGV status includes robot ID, battery, depth camera, PLC, radar, AGV X coordinate, AGV Y coordinate, positioning point, system startup, IMU status, driver Odom status, task status, positioning quality, task ID, and update time.

[0011] The scheduling module includes a scheduling map, which displays the scheduling routes and the operating status of the AGVs.

[0012] The vision module includes drawing, creating visual recognition boxes, and observing the visual recognition effect.

[0013] The warehouse management module includes task management and location map. The task management page displays currently generated tasks, manual operations for picking up and placing goods, and standby tasks. The location map displays the location and trigger column.

[0014] The task management information bar displays the task number, signal point, pickup station, pickup status, delivery station, pickup / delivery status, standby station, standby status, assigned vehicle, and task creation time.

[0015] Compared with existing technologies, the present invention has the following advantages: it improves the operating efficiency of AGVs, rationally controls task allocation, and builds an efficient, intelligent, and flexible modern AGV system. Attached Figure Description

[0016] Figure 1 This is a flowchart of the AGV scheduling and management system of the present invention. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention are described clearly and completely below. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0018] An AGV scheduling and management system based on multi-line sensing includes four modules: control, scheduling, storage, and vision. When an automatic task is started, the vision module searches for full or empty buckets. When a suitable location is found, the storage module generates an automatic task. The scheduling module plans the travel route, allocates vehicles, and notifies the control module. The control program and the vehicle interact to complete the scheduling commands.

[0019] The AGV scheduling and management system includes modules for system management, log query, control system, scheduling, vision, and warehouse management, such as... Figure 1 As shown, the system management module includes system running status, the log query module includes system logs and task flow query, the control system module includes AGV running status, the scheduling module includes scheduling map, the vision module includes drawing, and the warehouse management includes task management and storage location map.

[0020] The system management module includes a system operation status module, which controls the on / off switching of control, scheduling, storage, and visual module threads; The internal threads of the control module include vehicle data connection and vehicle dispatcher; The internal threads of the scheduling module include a vehicle dispatcher, a scheduling system API server, and a location monitoring system. The vehicle dispatcher plans routes and dispatches vehicles, the scheduling system API server displays the AGV's path, provides a scheduling map and scheduling status interface, and the location monitoring system updates the location in real time. The internal threads of the warehousing module include a task scheduler and warehousing services; The internal threads of the vision module include inference and data synchronization. Inference is for real-time camera recognition, and data synchronization is for updating the recognition status.

[0021] The log query module includes system logs and task log queries. The system logs record the system's running status.

[0022] The control system module includes AGV operating status, records and updates the status of each sensor of the AGV, and controls the AGV's repositioning, enabling or disabling, and canceling of tasks.

[0023] The control system module page includes a system information bar and a robot status bar; The system information bar displays the information interaction status of each AGV in the system. The information interaction status includes activation status, robot ID, IP, status, reason for status change, time of last operation, last operation, and obstacle avoidance range mode. The robot status bar displays the status of each AGV. Once the AGV starts successfully and the update thread is open, the correct content is displayed. The AGV status includes robot ID, battery, depth camera, PLC, radar, AGV X coordinate, AGV Y coordinate, positioning point, system startup, IMU status, driver Odom status, task status, positioning quality, task ID, and update time.

[0024] The scheduling module includes a scheduling map, which displays the scheduling routes and the operating status of the AGVs.

[0025] The vision module includes drawing, creating visual recognition boxes, and observing the visual recognition effect.

[0026] The warehouse management module includes task management and location map. The task management page displays currently generated tasks, manual operations for picking up and placing goods, and standby tasks. The location map displays the location and trigger column.

[0027] The task management information bar displays the task number, signal point, pickup station, pickup status, delivery station, pickup / delivery status, standby station, standby status, assigned vehicle, and task creation time.

[0028] This invention uses a particle swarm optimization algorithm to optimize the AGV scheduling path. This includes initializing parameters for a swarm of m particles, including random position and velocity; evaluating the fitness of each particle; comparing its fitness value with its best previously experienced position (pbest); and updating the velocity and position of the particle if the fitness is better than the best previously experienced position (gbest). If the termination condition is not met (usually a sufficiently good fitness value or reaching a preset maximum number of generations Gmax), the process returns to evaluate the fitness of each particle.

[0029] In particle swarm optimization, the following methods are used: ; ; ; ; ; In the formula, The node number selected for the particle in the j-th column. Returns the argument when the function is at its maximum. For the encoding disk The pheromone concentration at a given location, where t represents the current iteration time. For the selected node number, This is a random function that returns a random number in the range (0, 1). For selection function, Returns a vector of element-wise sums; The probability function for selecting the next column node for a particle. For heuristic functions, This is the AGV scheduling path obtained after selecting k nodes.

[0030] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. An AGV scheduling and management system based on multi-line sensing, characterized in that, It includes four modules: control, scheduling, storage, and vision. When an automatic task is started, the vision module finds full or empty buckets. When a suitable location is found, the storage module generates an automatic task. The scheduling module plans the travel route, allocates vehicles, and notifies the control module. The control program and the vehicle interact to complete the command issued by the scheduling module.

2. The AGV scheduling and management system based on multi-line sensing according to claim 1, characterized in that, The AGV scheduling and management system includes modules for system management, log query, control system, scheduling, vision, and warehouse management.

3. The AGV scheduling and management system based on multi-line sensing according to claim 2, characterized in that, The system management module includes a system operation status module, which controls the on / off switching of control, scheduling, storage, and visual module threads; The internal threads of the control module include vehicle data connection and vehicle dispatcher; The internal threads of the scheduling module include a vehicle dispatcher, a scheduling system API server, and a location monitoring system. The vehicle dispatcher plans routes and dispatches vehicles, the scheduling system API server displays the AGV's path, provides a scheduling map and scheduling status interface, and the location monitoring system updates the location in real time. The internal threads of the warehousing module include a task scheduler and warehousing services; The internal threads of the vision module include inference and data synchronization. Inference is for real-time camera recognition, and data synchronization is for updating the recognition status.

4. The AGV scheduling and management system based on multi-line sensing according to claim 3, characterized in that, The log query module includes system logs and task log queries. The system logs record the system's running status.

5. The AGV scheduling and management system based on multi-line sensing according to claim 4, characterized in that, The control system module includes AGV operating status, records and updates the status of each sensor of the AGV, and controls the AGV's repositioning, enabling or disabling, and canceling of tasks.

6. The AGV scheduling and management system based on multi-line sensing according to claim 5, characterized in that, The control system module page includes a system information bar and a robot status bar; The system information bar displays the information interaction status of each AGV in the system. The information interaction status includes activation status, robot ID, IP, status, reason for status change, time of last operation, last operation, and obstacle avoidance range mode. The robot status bar displays the status of each AGV. Once the AGV starts successfully and the update thread is open, the correct content is displayed. The AGV status includes robot ID, battery, depth camera, PLC, radar, AGV X coordinate, AGV Y coordinate, positioning point, system startup, IMU status, driver Odom status, task status, positioning quality, task ID, and update time.

7. The AGV scheduling and management system based on multi-line sensing according to claim 6, characterized in that, The scheduling module includes a scheduling map, which displays the scheduling routes and the operating status of the AGVs.

8. The AGV scheduling and management system based on multi-line sensing according to claim 7, characterized in that, The vision module includes drawing, creating visual recognition boxes, and observing the visual recognition effect.

9. The AGV scheduling and management system based on multi-line sensing according to claim 8, characterized in that, The warehouse management module includes task management and location map. The task management page displays currently generated tasks, manual operations for picking up and placing goods, and standby tasks. The location map displays the location and trigger column.

10. An AGV scheduling and management system based on multi-line sensing according to claim 9, characterized in that, The task management information bar displays the task number, signal point, pickup station, pickup status, delivery station, pickup / delivery status, standby station, standby status, assigned vehicle, and task creation time.

Images