Emergency control method and device for automatic guided vehicle and automatic guided vehicle

Abstract

The invention relates to the technical field of vehicle control, and discloses an emergency control method and device for an automatic guided vehicle and the automatic guided vehicle, and the method comprises the steps: obtaining a first position of the automatic guided vehicle, and determining a region type of a road network region where the automatic guided vehicle is located according to the first position; selecting a target sensor according to the region type, and obtaining sensing data of the target sensor; and determining whether an obstacle exists based on the sensing data, and if yes, judging whether emergency control needs to be performed according to the sensing data and the obstacle. According to the invention, the proper sensor can be selected according to the current area of the automatic guided vehicle, and the recognition accuracy of the obstacle is improved, so that the automatic guided vehicle is flexibly and emergently controlled according to the obstacle, and the safety and operation reliability of the automatic guided vehicle are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle control, and in particular to an emergency control method and device for an automatic guided vehicle and the automatic guided vehicle. Background Art

[0002] As the core equipment in automated logistics and manufacturing systems, the safety of Automated Guided Vehicles (AGVs) is of vital importance. In complex environments such as high-density logistics warehouses and production workshops, AGVs share channels with people, other vehicles and equipment, which poses a potential risk of collision. Therefore, enhancing the safety system of AGVs to ensure their stability and safety during operation has become an important research topic.

[0003] The current AGV safety system mainly relies on a single sensor technology (such as lidar, camera) and preset collision detection logic. However, in a dynamically changing and complex environment, the existing safety system is prone to misjudgment or delayed response, and cannot perform flexible emergency control of the AGV, resulting in the inability to effectively avoid accidents. Summary of the invention

[0004] In view of this, the present invention provides an emergency control method and device for an automated guided vehicle and an automated guided vehicle to solve the problem that the AGV cannot be flexibly and urgently controlled.

[0005] In a first aspect, the present invention provides an emergency control method for an automated guided vehicle, the method comprising:

[0006] Obtaining a first position of the automatic guided vehicle, and determining an area type of a road network area where the automatic guided vehicle is located according to the first position;

[0007] Select a target sensor according to the area type and obtain the perception data of the target sensor;

[0008] Determine whether there is an obstacle based on the perception data. If there is an obstacle, determine whether emergency control is required based on the perception data and the obstacle.

[0009] The emergency control method of the automatic guided vehicle provided by the present invention determines the area type of the road network area where the first position of the automatic guided vehicle is located, selects a target sensor according to the area type, and determines whether there is an obstacle based on the sensing data of the target sensor. If there is, it determines whether emergency control is required based on the sensing data and the obstacle. The present invention can select a suitable sensor according to the area where the automatic guided vehicle is currently located, improve the accuracy of obstacle recognition, and thus flexibly perform emergency control on the automatic guided vehicle according to the obstacle, thereby improving the safety and operational reliability of the automatic guided vehicle.

[0010] In an optional embodiment, the area types include: a mixed pedestrian and vehicle area and a material storage area. The area type of the road network area is determined according to the first position, including: obtaining a first area range corresponding to the mixed pedestrian and vehicle area and a second area range corresponding to the material storage area; determining whether the first position is within the first area range or the second area range; if the first position is within the first area range, determining that the automatic guided vehicle is in the mixed pedestrian and vehicle area, and if the first position is within the second area range, determining that the automatic guided vehicle is in the material storage area.

[0011] By classifying the road network areas, the present invention can distinguish the obstacles that the automatic guided vehicle may encounter during movement, so as to subsequently select appropriate sensors to ensure the accuracy of obstacle recognition in the current area.

[0012] In an optional embodiment, the target sensor is selected according to the area type, including: if it is in a mixed pedestrian and vehicle traffic area, the lidar is used as the first target sensor and the visual camera is used as the second target sensor; if it is in a material warehouse area, the ultrasonic sensor is used as the first target sensor and the infrared sensor is used as the second target sensor.

[0013] By selecting appropriate sensors in different areas, the present invention can fuse different sensors according to sensor characteristics and obstacle types, thereby improving the perception of the surrounding environment, ensuring accurate detection of obstacles and dangerous situations under various working conditions, and improving the accuracy and real-time performance of obstacle detection.

[0014] In an optional embodiment, judging whether emergency control is needed based on the perception data and the obstacle includes: determining the distance interval between the obstacle and the automated guided vehicle based on the perception data; determining the emergency control stage based on the distance interval, and the emergency control stage includes: a warning stage, a preventive parking stage, an emergency stop stage, and a recovery stage; if it is in the warning stage, the preventive parking stage, or the emergency stop stage, determining the relative angle between the obstacle and the automated guided vehicle, the moving speed and the moving direction of the obstacle based on the perception data; adjusting the running speed and / or running trajectory of the automated guided vehicle based on the distance interval, the relative angle, the moving speed, and the moving direction, and controlling the automated guided vehicle to move according to the adjusted running speed and / or running trajectory; if it is determined based on the perception data that the obstacle does not exist, or after the emergency control is completed, determining that it is in the recovery stage, and moving according to the running speed and / or running trajectory before adjustment.

[0015] By dividing emergency control into multiple stages, the present invention can automatically adjust the armband strategy according to the real-time detected obstacle position and speed, etc., adaptively adjust the motion trajectory of the automatic guided vehicle or trigger an emergency stop to avoid collision with obstacles, thereby improving the safety and reliability of the automatic guided vehicle in complex environments.

[0016] In an optional embodiment, determining whether emergency control is needed based on the perception data and obstacles also includes: determining the second position of the obstacle based on the first position, distance interval and relative angle, and sending the second position, moving speed and moving direction of the obstacle to the scheduling system, so that the scheduling system plans the path of the automatic guided vehicle based on the second position and moving speed.

[0017] The present invention uploads the obstacle situation currently encountered by the adaptive guided vehicle to the scheduling system, and can flexibly plan the paths of the automatic guided vehicles under the jurisdiction of the scheduling system based on the obstacle situation, so as to adjust the paths in advance before other automatic guided vehicles reach the obstacles, thereby realizing coordinated control between different automatic guided vehicles and avoiding collisions or path conflicts between automatic guided vehicles.

[0018] In a second aspect, the present invention provides a control device for an automatic guided vehicle, the device comprising:

[0019] An area determination module is used to obtain a first position of the automatic guided vehicle and determine the area type of the road network area where the automatic guided vehicle is located according to the first position;

[0020] A sensor selection module is used to select a target sensor according to the area type and obtain the perception data of the target sensor;

[0021] The emergency control module is used to determine whether there is an obstacle based on the perception data. If there is an obstacle, it is used to determine whether emergency control is required based on the perception data and the obstacle.

[0022] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the control method of an automatic guided vehicle according to the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0023] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the control method for an automated guided vehicle according to the first aspect or any corresponding embodiment thereof.

[0024] In a fifth aspect, the present invention provides a computer program product, comprising computer instructions for causing a computer to execute the method for controlling an automatic guided vehicle according to the first aspect or any corresponding embodiment thereof.

[0025] In a sixth aspect, the present invention provides an automatic guided vehicle, comprising:

[0026] Sensors, including lidar, visual cameras, ultrasonic sensors, and infrared sensors, are used to obtain perception data of the road network area;

[0027] The controller is connected to the sensor and is used to execute the control method of the automatic guided vehicle of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0029] Figure 1 is a flow chart of an emergency control method for an automatic guided vehicle according to an embodiment of the present invention;

[0030] Figure 2 is a schematic diagram of sensor installation positions according to an emergency control method for an automatic guided vehicle according to an embodiment of the present invention;

[0031] Figure 3 is a flow chart of another emergency control method for an automatic guided vehicle according to an embodiment of the present invention;

[0032] Figure 4 is a schematic diagram of area classification of another emergency control method for an automatic guided vehicle according to an embodiment of the present invention;

[0033] Figure 5 is a flow chart of another emergency control method for an automatic guided vehicle according to an embodiment of the present invention;

[0034] Figure 6 is an emergency control schematic diagram of another emergency control method of an automatic guided vehicle according to an embodiment of the present invention;

[0035] Figure 7 is a structural block diagram of an emergency control device for an automatic guided vehicle according to an embodiment of the present invention;

[0036] Figure 8 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0037] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0038] The embodiment of the present invention is applicable to application scenarios of flexibly controlling an automated guided vehicle in complex environments such as high-density logistics warehouses and production workshops. The embodiment of the present invention provides an emergency control method for an automated guided vehicle, which achieves the effect of flexibly controlling the automated guided vehicle by selecting appropriate sensors.

[0039] According to an embodiment of the present invention, an embodiment of an emergency control method for an automated guided vehicle is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0040] In this embodiment, an emergency control method for an automated guided vehicle is provided, which can be used for the above-mentioned automated guided vehicle or the dispatching system of the automated guided vehicle. Figure 1 : is a flow chart of an emergency control method for an automatic guided vehicle according to an embodiment of the present invention, such as Figure 1 As shown, the process includes the following steps:

[0041] Step S101, obtaining a first position of an automated guided vehicle, and determining an area type of a road network area where the automated guided vehicle is located according to the first position.

[0042] Specifically, in an embodiment of the present invention, the dispatching system pre-classifies the road network areas of the current complex environment according to the scene, including mixed pedestrian and vehicle areas and material storage areas, and determines the area range of each area according to the area division. In the mixed pedestrian and vehicle area, the probability of staff appearing is relatively high, and the location of appearance is relatively flexible, so the mixed pedestrian and vehicle area is relatively spacious; in the material storage area, the probability of staff appearing is relatively low, and generally there will be goods stacked or suddenly dropped, so the material storage area is usually a relatively narrow passage. The automatic guided vehicle is pre-installed with a positioning system and a sensor, which can determine its own real-time position based on the positioning data and the sensor data. The specific positioning method is a conventional technical means in this field and will not be repeated here. After the dispatching system obtains the position information of the automatic guided vehicle, it determines the area type of the road network area where the current automatic guided vehicle is located based on the position information and the range of each area.

[0043] Step S102: select a target sensor according to the area type, and obtain perception data of the target sensor.

[0044] Specifically, in the embodiment of the present invention, the automatic guided vehicle is equipped with various types of sensors, including laser radar, ultrasonic sensor, infrared sensor and 3D visual camera, which are only taken as examples and are not limited thereto. In the embodiment of the present invention, in order to achieve the best perception of the surrounding environment, the installation positions of various sensors on the automatic guided vehicle are as follows: Figure 2 As shown. Among them, LiDAR (Light Laser Detection and Ranging) is a device that emits laser beams to detect the position, speed and other characteristic quantities of surrounding targets. It emits detection signals (lasers) to surrounding targets, and then compares the received signals reflected from the targets (target echoes) with the transmitted signals to obtain relevant information such as the distance, direction, and speed of the targets. Ultrasonic sensors emit ultrasonic waves, which will return when encountering obstacles. Ultrasonic sensors determine the actual distance from the emission point to the obstacle based on the time difference between the transmitted wave and the echo. Infrared cameras are mainly based on the emission and reception of infrared rays, and usually include an infrared transmitter and an infrared receiver. The transmitter emits infrared light. When this beam of light encounters an object, part of the light will be reflected back. After the receiver receives the reflected infrared light, it converts it into an electrical signal, and then performs data processing and analysis. Visual cameras shoot the scene around the vehicle and identify vehicles, staff, obstacles, etc. through image recognition technology. Three-dimensional visual cameras can also perform 3D modeling, which can further improve the accuracy of obstacle recognition. It can be seen that different types of sensors have different working characteristics. Therefore, the embodiment of the present invention selects a suitable target sensor according to the type of area where the automatic guided vehicle is located, and obtains the perception data of each target sensor.

[0045] Step S103, determining whether there is an obstacle based on the perception data, and if there is an obstacle, determining whether emergency control is required based on the perception data and the obstacle.

[0046] Specifically, in an embodiment of the present invention, the perception data is fused by a fusion algorithm such as Kalman filtering or Bayesian estimation to obtain fused perception data. The fusion process includes: (1) Perception data preprocessing: the perception data of all sensors need to be preprocessed by filtering, denoising and other processes to ensure data quality; (2) Feature extraction: For LiDAR and camera, first extract environmental feature points to establish pose estimation. For infrared and ultrasonic waves, obtain distance information and simple obstacle information; (3) Data time synchronization: align the timestamps of different sensors to ensure data consistency; (4) Data weighted fusion: use extended Kalman filter (EKF) or particle filter to perform data fusion according to the accuracy and reliability of various sensors. In certain cases (such as too strong light or too dynamic environment), shield the data of some sensors and rely on the information of other sensors. The embodiment of the present invention analyzes the fused perception data to determine whether there is an obstacle within the perception range. If so, relative state information such as the distance interval and relative angle between the obstacle and the automatic guided vehicle is determined based on the perception data, and target state information such as the moving speed and moving direction of the obstacle is determined. Therefore, based on the relative state information and the target state information, it is determined whether emergency control of the automatic guided vehicle is required, including controlling the running speed or adjusting the running trajectory, so as to avoid collision between the automatic guided vehicle and the obstacle.

[0047] In some optional embodiments, the automated guided vehicle obtains its own position information and sensor perception data, can implement emergency control through a controller deployed by itself, and can also upload the data to a dispatching system, which will make emergency control judgments, receive speed control instructions or path planning results from the dispatching system, and execute according to the speed control instructions or path planning results, thereby avoiding collisions between the automated guided vehicle and obstacles.

[0048] In some optional implementations, data communication is performed between the automated guided vehicle and the dispatching system based on a secure communication protocol, specifically including: data encryption, using the AES-256-bit encryption protocol to ensure the security of communication data between the AGV and the dispatching system, and to prevent data leakage or tampering; identity authentication, through a key-based identity authentication mechanism, to ensure that only authorized devices and systems can communicate with the AGV, to prevent illegal devices from controlling the AGV; real-time communication mechanism (low-latency communication): using 5G communication technology or high-frequency Wi-Fi to ensure that the communication delay between the AGV and the dispatching system is minimized, and to ensure secure information transmission in high-speed movement or complex environments. In this case, all AGVs controlled by the dispatching system can upload relevant operating data to the dispatching system, and the dispatching system can uniformly plan paths for all AGVs to ensure that each AGV can move on the optimal path without path conflicts. The embodiment of the present invention ensures secure and real-time communication between the AGV and the control system and other devices through a reliable communication protocol, thereby realizing information sharing and collaborative security control.

[0049] The emergency control method of the automatic guided vehicle provided by the present invention determines the area type of the road network area where the first position of the automatic guided vehicle is located, selects a target sensor according to the area type, and determines whether there is an obstacle based on the sensing data of the target sensor. If there is, it determines whether emergency control is required based on the sensing data and the obstacle. The present invention can select a suitable sensor according to the area where the automatic guided vehicle is currently located, improve the accuracy of obstacle recognition, and thus flexibly perform emergency control on the automatic guided vehicle according to the obstacle, thereby improving the safety and operational reliability of the automatic guided vehicle.

[0050] In this embodiment, an emergency control method for an automated guided vehicle is provided, which can be used for the above-mentioned automated guided vehicle or the dispatching system of the automated guided vehicle. Figure 3 : is a flow chart of an emergency control method for an automatic guided vehicle according to an embodiment of the present invention, such as Figure 3 As shown, the process includes the following steps:

[0051] Step S301, obtaining a first position of an automated guided vehicle, and determining an area type of a road network area where the automated guided vehicle is located according to the first position.

[0052] Specifically, the above step S301 includes:

[0053] Step S3011, obtaining a first area range corresponding to the mixed traffic area for pedestrians and vehicles and a second area range corresponding to the material storage area.

[0054] Step S3012: Determine whether the first location is within the first area or within the second area.

[0055] Step S3013: if the first position is within the first area, it is determined that the automatic guided vehicle is in a mixed pedestrian and vehicle area; if the first position is within the second area, it is determined that the automatic guided vehicle is in a material storage area.

[0056] Specifically, in an embodiment of the present invention, the scheduling system of the host computer pre-divides the road network area into a mixed traffic area for people and vehicles and a material storage area, and determines the area range of each area according to the current complex environment, and the area range can be represented by local coordinate information. During the movement, the AGV can directly determine its own real-time position according to the positioning system, or estimate the relative position according to the sensor's perception data. For example, AGV is usually equipped with positioning devices, such as the Global Positioning System (GPS), Inertial Measurement Unit (IMU) and encoders, which can provide accurate position and posture information to help AGV determine its own position; AGV can use sensor data, such as lidar, camera or infrared sensor, to perceive and analyze the surrounding environment, so as to estimate its own position by the relative position relationship with known landmarks or obstacles.

[0057] In some optional embodiments, after determining the real-time position of the AGV itself, coordinate comparison is used to determine whether the current position is in the mixed pedestrian and vehicle area or in the material storage area, thereby determining whether the current AGV is in the mixed pedestrian and vehicle area or the material storage area.

[0058] Step S302: select a target sensor according to the area type, and obtain perception data of the target sensor.

[0059] Specifically, the above step S302 includes:

[0060] Step S3021: If the vehicle is in a mixed traffic area, the laser radar is used as the first target sensor and the visual camera is used as the second target sensor.

[0061] Specifically, in the embodiment of the present invention, Figure 4 As shown in the figure, if the AGV is in a mixed traffic area, the site is relatively spacious and there are relatively many workers, who may enter the planned route of the AGV from any direction. Therefore, it is necessary to obtain environmental information in a larger range to control the AGV. At this time, the vision and laser positioning method is selected to determine whether there are obstacles around, that is, the laser radar and camera are selected. Figure 2 As shown, a three-dimensional visual camera and a lidar are installed in front of the automated guided vehicle, so it can accurately determine whether there are obstacles in the direction of travel.

[0062] Step S3022: If the device is in the material warehouse area, the ultrasonic sensor is used as the first target sensor and the infrared sensor is used as the second target sensor.

[0063] Specifically, in the embodiment of the present invention, Figure 4 As shown in the figure, if the AGV is in the material warehouse area, it will move forward in a narrow passage, and workers may appear occasionally. Therefore, it is necessary to obtain environmental information within a small range to control the AGV. At this time, infrared and ultrasonic positioning methods are selected to determine whether there are obstacles around, that is, infrared sensors and ultrasonic sensors are selected. Figure 2 As shown, the automatic guided vehicle is equipped with an ultrasonic sensor in the front and an infrared sensor on the side, which can determine whether there are obstacles around in narrow passages.

[0064] Step S303: Determine whether there is an obstacle based on the sensing data. If there is an obstacle, determine whether emergency control is required based on the sensing data and the obstacle. Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.

[0065] The emergency control method of the automatic guided vehicle provided by the present invention determines the area type of the road network area where the first position of the automatic guided vehicle is located, selects a target sensor according to the area type, and determines whether there is an obstacle based on the sensing data of the target sensor. If there is, it determines whether emergency control is required based on the sensing data and the obstacle. The present invention can select a suitable sensor according to the area where the automatic guided vehicle is currently located, improve the accuracy of obstacle recognition, and thus flexibly perform emergency control on the automatic guided vehicle according to the obstacle, thereby improving the safety and operational reliability of the automatic guided vehicle.

[0066] In this embodiment, an emergency control method for an automated guided vehicle is provided, which can be used for the above-mentioned automated guided vehicle or the dispatching system of the automated guided vehicle. Figure 5 : is a flow chart of an emergency control method for an automatic guided vehicle according to an embodiment of the present invention, such as Figure 5 As shown, the process includes the following steps:

[0067] Step S501, obtaining a first position of the automated guided vehicle, and determining the area type of the road network area where the automated guided vehicle is located according to the first position. Figure 3 Step S301 of the illustrated embodiment will not be described in detail here.

[0068] Step S502: Select a target sensor according to the area type and obtain the sensing data of the target sensor. Figure 3 Step S302 of the illustrated embodiment will not be described in detail here.

[0069] Step S503, determining whether there is an obstacle based on the perception data, and if there is an obstacle, determining whether emergency control is required based on the perception data and the obstacle.

[0070] Specifically, the above step S503 includes:

[0071] Step S5031, determining the distance interval between the obstacle and the automatic guided vehicle based on the perception data.

[0072] Step S5032, determining the emergency control stage according to the distance interval, the emergency control stage includes: warning stage, preventive parking stage, emergency stop stage and recovery stage.

[0073] Specifically, in the embodiment of the present invention, the dispatching system performs data fusion on the perception data of different sensors, and calculates the distance interval between the AGV and the obstacle based on the integrated perception data, and determines the current emergency control stage based on the different distance intervals. The present invention divides the emergency control stage into four stages according to the degree of danger brought by different distance intervals, including three levels of emergency control response: warning stage, preventive parking stage, emergency stop stage, and recovery stage. The smaller the distance interval between the AGV and the obstacle, the greater the degree of emergency control. Figure 6 As shown, if the distance interval is within the warning distance range of about 1.5 meters, it is determined to be in the warning stage; if the distance interval reaches the dangerous range of 1 meter to 0.5 meters, it is determined to be in the preventive parking stage; if the distance interval is less than the dangerous distance of 0.5 meters, it is determined to be in the economic stop stage, but in the emergency control process, if it is detected that the obstacle is removed or enters the safe area, it enters the recovery stage.

[0074] In some optional implementations, the distance interval between the obstacle and the AGV can be directly determined through sensing data, or the position information of the obstacle can be determined first, and then the distance between the AGV position and the obstacle distance can be calculated.

[0075] Step S5033: If the vehicle is in the warning stage, the preventive stop stage or the emergency stop stage, the relative angle between the obstacle and the automated guided vehicle, the moving speed and the moving direction of the obstacle are determined based on the perception data.

[0076] Step S5034, adjusting the running speed and / or running track of the automatic guided vehicle based on the distance interval, relative angle, moving speed and moving direction, and controlling the automatic guided vehicle to move according to the adjusted running speed and / or running track.

[0077] Specifically, in the embodiment of the present invention, in the warning stage, the preventive parking stage or the emergency stop stage, the running speed or running track of the AGV needs to be adjusted. Figure 6As shown in the figure, in the warning stage, the obstacle is within the warning distance, at which point the AGV sends out an alarm signal and begins to decelerate; in the preventive parking stage, the obstacle approaches the danger range, at which point the AGV stops slowly; in the emergency stop stage, the obstacle is equivalent to suddenly appearing within the danger distance, and the AGV immediately stops at full speed to prevent a collision. Furthermore, if the obstacle persists during the deceleration process, the AGV's running trajectory needs to be adjusted so that the AGV can bypass the obstacle and continue to move forward. At this point, it is necessary to determine the relative angle between the obstacle and the AGV based on the perception data, and it is also necessary to determine the obstacle's moving speed and direction, and adjust the AGV's path based on the relative angle, moving speed, and moving direction.

[0078] In some optional implementations, the scheduling system plans the driving path of the AGV based on the A* algorithm and the Dynamic Window Approach (DWA), thereby ensuring that the AGV can smoothly bypass after detecting an obstacle and avoid delays caused by sudden stops. Among them, the A* algorithm (A star algorithm) is a heuristic search algorithm used to find the path with the lowest passing cost among multiple nodes on a graphic plane, and evaluates the distance from the current node to the end point by introducing global information, so as to perform a heuristic search in the search process; the DWA algorithm is an algorithm for robot obstacle avoidance planning, which is mainly used to implement the local path planning of the robot in ROS (Robot Operating System), by sampling multiple groups of speeds in the speed space, simulating the motion trajectory of these speeds within a certain time, and evaluating these trajectories through evaluation functions, and finally selecting the optimal trajectory and speed to control the movement of the robot. In an embodiment of the present invention, the A* algorithm is used to plan the optimal path from the starting point to the target point on the global map of the environment. This path is the reference route of the AGV. If the environment is complex or there are dynamic obstacles, the A* path may not be used directly, but it can provide a global navigation target. During the driving process of the AGV, DWA will perform real-time obstacle avoidance based on the AGV's current state, speed, and dynamic obstacles in the environment. DWA continuously adjusts the AGV's speed and direction based on the AGV's current position and the target point provided by A* to ensure that the AGV safely bypasses obstacles.

[0079] In some optional embodiments, during the dynamic obstacle avoidance process, if the obstacle only exists at a certain position, when adjusting the driving path, only the pre-planned path is locally adjusted or avoided, which can adapt to environmental changes to a certain extent, quickly respond to the appearance of obstacles, and ensure the safety of the AGV and the reliability of path completion. However, if a large environmental change occurs, such as the path is completely blocked, or a new target point appears, if local obstacle avoidance causes the AGV to deviate too far from the global path, the scheduling system can re-run the A* algorithm, correct the global path or generate a new path, which can be processed in the scheduling system or the AGV's own algorithm, re-plan the path according to the new environmental map and target point, and send the new path to the AGV to ensure that the AGV can reach the target according to the optimized path. Further, if the obstacle changes in the environment (such as adding or moving an obstacle), the scheduling system will dynamically update the global map and re-plan the global path. By periodically running A* and continuous DWA obstacle avoidance, the AGV can make adaptive adjustments in a dynamic environment.

[0080] Step S5035: If it is determined based on the perception data that the obstacle does not exist, or after the emergency control is completed, it is determined that it is in the recovery stage and moves according to the operating speed and / or operating trajectory before adjustment.

[0081] Specifically, in an embodiment of the present invention, if the obstacle is removed during the obstacle avoidance process, or after emergency control is completed according to the local adjustment path, the scheduling system restarts the AGV and resumes the task from the interrupted position, moving according to the operating speed and trajectory before the adjustment.

[0082] In some optional implementations, during the AGV's dynamic obstacle avoidance process, the obstacle location information, moving speed, and moving direction determined based on the perception data will also be sent to the dispatching system. When the dispatching system plans the paths for all AGVs, it can plan the travel paths of other AGVs in advance based on the relevant information of the obstacles. Or it can be sent directly to other AGVs through a distributed communication protocol, so that the AGVs can share information such as location, speed, task, and obstacles. The AGVs share obstacle information and path planning results, which can achieve collaborative obstacle avoidance, avoid multiple AGVs from making emergency stops in front of the same obstacle at the same time, and avoid collisions or path conflicts between AGVs, thereby improving the throughput of the entire system.

[0083] In some optional implementations, an application scenario in which an AGV is running in a warehouse environment with a large number of workers and equipment activities is used as an example: in the scheduling system, the AGV's driving path and driving area have been planned. In densely populated scenes, the navigation and obstacle avoidance system is mainly based on cameras and laser radars. Through fusion algorithms such as Kalman filtering or Bayesian estimation, the extracted sensor data is screened to increase the data share of cameras and laser radars. During the operation of the AGV, the laser radar scans in real time and compares it with the map point cloud to determine whether there is an obstacle in front. If the obstacle is within the warning distance range, the AGV sends an alarm signal and starts to slow down. When the obstacle approaches the danger range, the AGV stops slowly. If the obstacle is stationary, it is bypassed through the camera. If the obstacle is dynamic, for example, the laser radar detects that the worker is 2 meters ahead of the AGV's driving direction. The data fusion algorithm confirms that the worker is moving through the joint detection of the laser radar, camera and ultrasonic sensor, and predicts that the worker may enter the AGV's driving path. The scheduling system starts the dynamic obstacle avoidance algorithm, slows down in advance, waits for the worker to leave the danger area, and the AGV resumes normal speed.

[0084] In some optional implementations, an application scenario where an AGV is traveling in a narrow passage and an obstacle (such as fallen goods) suddenly appears is used as an example: in the dispatching system, the AGV's travel path and travel area have been planned. In narrow passages, ultrasonic sensors are used first for precise obstacle avoidance. When an obstacle suddenly appears within a dangerous distance, the AGV immediately stops at full speed to prevent a collision. For example, the ultrasonic sensor emits sound waves in real time, and when the sound waves rebound, the obstacle is detected. For example, when the AGV is traveling, a piece of cargo suddenly falls 0.4 meters in front of it. The system triggers the emergency stop mechanism, and the AGV stops immediately, waiting for the obstacle to be removed and alarming through the speaker and reporting system. When the obstacle is removed, the dispatching system confirms that the front is safe and the AGV resumes driving.

[0085] The emergency control method of the automatic guided vehicle provided by the present invention determines the area type of the road network area where the first position of the automatic guided vehicle is located, selects a target sensor according to the area type, and determines whether there is an obstacle based on the sensing data of the target sensor. If there is, it determines whether emergency control is required based on the sensing data and the obstacle. The present invention can select a suitable sensor according to the area where the automatic guided vehicle is currently located, improve the accuracy of obstacle recognition, and thus flexibly perform emergency control on the automatic guided vehicle according to the obstacle, thereby improving the safety and operational reliability of the automatic guided vehicle.

[0086] In the present embodiment, an emergency control device for an automated guided vehicle is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0087] This embodiment provides an emergency control device for an automatic guided vehicle, such as Figure 7 As shown, including:

[0088] The area determination module 701 is used to obtain a first position of the automatic guided vehicle and determine the area type of the road network area where the automatic guided vehicle is located according to the first position.

[0089] The sensor selection module 702 is used to select a target sensor according to the area type and obtain the sensing data of the target sensor.

[0090] The emergency control module 703 is used to determine whether there is an obstacle based on the perception data. If there is an obstacle, it is determined whether emergency control is required based on the perception data and the obstacle.

[0091] In some optional implementations, the region determination module 701 includes:

[0092] The range acquisition unit is used to acquire a first area range corresponding to the mixed pedestrian and vehicle traffic area and a second area range corresponding to the material storage area.

[0093] The range comparison unit is used to determine whether the first position is within the first area or within the second area.

[0094] The area determination unit is used to determine that the automatic guided vehicle is in a mixed pedestrian and vehicle traffic area if the first position is within the first area, and to determine that the automatic guided vehicle is in a material storage area if the first position is within the second area.

[0095] In some optional implementations, the sensor selection module 702 includes:

[0096] The first selection unit is used to use the laser radar as the first target sensor and the visual camera as the second target sensor if the area is in a mixed traffic area of ​​people and vehicles.

[0097] The second selection unit is used to use the ultrasonic sensor as the first target sensor and the infrared sensor as the second target sensor if the device is in the material warehouse area.

[0098] In some optional implementations, the emergency control module 703 includes:

[0099] The distance calculation unit is used to determine the distance interval between the obstacle and the automatic guided vehicle based on the perception data.

[0100] The stage judgment unit is used to determine the emergency control stage according to the distance interval. The emergency control stages include: warning stage, preventive parking stage, emergency stop stage and recovery stage.

[0101] The state determination unit is used to determine the relative angle between the obstacle and the automatic guided vehicle, the moving speed and moving direction of the obstacle based on the perception data if it is in the warning stage, the preventive parking stage or the emergency stop stage.

[0102] The dynamic adjustment unit is used to adjust the running speed and / or running track of the automatic guided vehicle based on the distance interval, relative angle, moving speed and moving direction, and control the automatic guided vehicle to move according to the adjusted running speed and / or running track.

[0103] The operation recovery unit is used to determine that it is in the recovery stage if it is determined based on the perception data that an obstacle does not exist, or after the emergency control is completed, and move according to the operating speed and / or operating trajectory before adjustment.

[0104] In some optional implementations, the emergency control module 703 further includes:

[0105] The collaborative obstacle avoidance unit is used to determine the second position of the obstacle based on the first position, distance interval and relative angle, and send the second position, moving speed and moving direction of the obstacle to the scheduling system, so that the scheduling system plans the path of the automatic guided vehicle according to the second position and moving speed.

[0106] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0107] The control device of the automatic guided vehicle in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0108] The embodiment of the present invention also provides a computer device having the above Figure 7 The control device of the automated guided vehicle is shown.

[0109] See also Figure 8 , Figure 8 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 8As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 8 A processor 10 is taken as an example.

[0110] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0111] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0112] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0113] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0114] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0115] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0116] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0117] The embodiment of the present invention also provides an automatic guided vehicle, such as Figure 2 As shown, it includes: sensors, including: laser radar, visual camera, ultrasonic sensor and infrared sensor, used to obtain perception data of the road network area; a controller connected to the sensor to execute the above Figure 1 , Figure 3 or Figure 5 The emergency control method of the automatic guided vehicle is shown.

[0118] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. An emergency control method for an automatic guided vehicle, characterized in that: The method comprises: Acquire a first position of an automated guided vehicle, and determine an area type of a road network area where the automated guided vehicle is located according to the first position; Selecting a target sensor according to the area type, and acquiring sensing data of the target sensor; Determine whether there is an obstacle based on the perception data, and if the obstacle exists, determine whether emergency control is required based on the perception data and the obstacle.

2. The method according to claim 1, characterized in that The area types include: mixed pedestrian and vehicle traffic areas and material storage areas. The area type of the road network area determined according to the first position includes: Acquire a first area range corresponding to the mixed pedestrian and vehicle traffic area and a second area range corresponding to the material storage area; Determining whether the first location is within the first area or within the second area; If the first position is within the first area, it is determined that the automatic guided vehicle is in the mixed pedestrian and vehicle area; if the first position is within the second area, it is determined that the automatic guided vehicle is in the material storage area.

3. The method according to claim 2, characterized in that The selecting a target sensor according to the area type comprises: If the vehicle is in the mixed traffic area, the laser radar is used as the first target sensor and the visual camera is used as the second target sensor; If it is in the material warehouse area, the ultrasonic sensor is used as the first target sensor and the infrared sensor is used as the second target sensor.

4. The method according to claim 1, characterized in that: The determining whether emergency control is required according to the sensing data and the obstacle includes: Determine the distance interval between the obstacle and the automatic guided vehicle according to the sensing data; Determine the emergency control stage according to the distance interval, the emergency control stage includes: a warning stage, a preventive parking stage, an emergency stop stage and a recovery stage; If the vehicle is in the warning stage, the preventive parking stage or the emergency stop stage, determining the relative angle between the obstacle and the automated guided vehicle, the moving speed and the moving direction of the obstacle according to the sensing data; Adjusting the running speed and / or running track of the automatic guided vehicle based on the distance interval, the relative angle, the moving speed and the moving direction, and controlling the automatic guided vehicle to move according to the adjusted running speed and / or running track; If it is determined based on the perception data that the obstacle does not exist, or after the emergency control is completed, it is determined that it is in the recovery stage, and moves according to the operating speed and / or the operating trajectory before adjustment.

5. The method according to claim 4, characterized in that The determining whether emergency control is required according to the sensing data and the obstacle further includes: The second position of the obstacle is determined according to the first position, the distance interval and the relative angle, and the second position of the obstacle, the moving speed and the moving direction are sent to the scheduling system, so that the scheduling system plans the path of the automatic guided vehicle according to the second position and the moving speed.

6. A control device for an automatic guided vehicle, characterized in that: The device comprises: An area determination module is used to obtain a first position of the automatic guided vehicle and determine the area type of the road network area where the automatic guided vehicle is located according to the first position; A sensor selection module, used to select a target sensor according to the area type and obtain sensing data of the target sensor; The emergency control module is used to determine whether there is an obstacle based on the perception data, and if there is an obstacle, determine whether emergency control is required based on the perception data and the obstacle.

7. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the emergency control method for an automatic guided vehicle according to any one of claims 1 to 5 by executing the computer instructions.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the emergency control method for an automated guided vehicle according to any one of claims 1 to 5.

9. A computer program product, characterized in that The method comprises computer instructions for causing a computer to execute the emergency control method for an automated guided vehicle according to any one of claims 1 to 5.

10. An automatic guided vehicle, characterized in that: include: Sensors, including lidar, visual cameras, ultrasonic sensors, and infrared sensors, are used to obtain perception data of the road network area; A controller is connected to the sensor and is used to execute the emergency control method of the automatic guided vehicle according to any one of claims 1 to 5.

Images