An unmanned forklift loading and unloading safety control system and method, and a storage medium

Abstract

The application provides an unmanned forklift taking and placing goods safety control system and method and a storage medium, wherein the method steps comprise: collecting the working task, driving speed information of the unmanned forklift and the goods distance information between the vehicle body and the goods detected by the depth camera; when it is judged that the working task is a goods taking task, the driving speed information is analyzed to calculate the real issuing speed of the forklift in the current frame; the real goods distance is calculated according to the real issuing speed and the goods distance information of the adjacent frame detected by the depth camera; when the depth camera cannot obtain the goods distance information, it is judged that the forklift enters the blind area of the depth camera, and the initial position is recorded, and the forklift drives according to the real issuing speed until the driving distance in the blind area exceeds the projection length of the blind area, and the forklift is stopped. Therefore, the relative state of the forklift and the goods can be monitored, and the problem that the forklift drives the goods when taking and placing the goods can be avoided.

Description

Technical Field

[0001] This invention relates to freight monitoring technology, and more particularly to a safety control system and method for unmanned forklifts to pick up and place goods, and a storage medium. Background Technology

[0002] The emergence of unmanned forklifts has greatly reduced human intervention in logistics and transportation processes, enabling them to perform handling tasks continuously and efficiently. They are also suitable for planning production tasks and are widely used in the daily industrial handling work of modern factories.

[0003] However, currently, there is a lack of reasonable monitoring and alarm methods for unmanned forklifts during operation. Moreover, most existing unmanned forklift safety systems focus on driving safety and lack real-time monitoring of the forklift's working status. For example, during the use of unmanned forklifts, due to the complex working environment of the forklift, there is a certain error between the actual driving speed and the planned speed. Therefore, it is difficult to grasp the true distance between the forklift and the goods, which can easily lead to collisions and damage to the goods when picking up or placing them.

[0004] On the other hand, even with depth cameras installed on forklifts to monitor the distance to goods, blind spots still commonly exist. In these blind spots, if the exact travel speed and relative position to the goods cannot be predicted, it's easy to collide with the goods or forks strike the pallet, causing the pallet to move and creating safety hazards. This frequently leads to accidents such as goods falling or impacting in blind spots, damaging factory goods and equipment, delaying work schedules, and in severe cases, even threatening the personal safety of nearby workers. Summary of the Invention

[0005] Therefore, the main objective of this invention is to provide a safety control system and method for unmanned forklifts to pick up and place goods, as well as a storage medium, so as to monitor the relative state between the forklift and the goods and avoid the problem of the forklift pulling the goods when picking up and placing goods.

[0006] To achieve the above objectives, according to one aspect of the present invention, a method for safe control of unmanned forklift loading and unloading is provided, comprising the following steps:

[0007] The system collects information on the unmanned forklift's work task, travel speed, and cargo distance between the forklift and the cargo detected by the depth camera. When the work task is determined to be a pickup task, the system parses the travel speed information to calculate the forklift's actual delivery speed in the current frame. Based on the actual delivery speed and cargo distance information in adjacent frames detected by the depth camera, the system calculates the actual cargo distance. When the depth camera cannot obtain cargo distance information, the system determines that the forklift has entered the depth camera's blind zone, records the initial position, and continues to travel according to the actual delivery speed until the distance traveled within the blind zone exceeds the blind zone's projection length, at which point the forklift is stopped.

[0008] In a possible preferred embodiment, the step of calculating the actual download speed of the forklift in the current frame includes:

[0009] Analyze the driving speed to obtain the current speed planning strategy information and the measured speed information; query the ideal transmission speed for the current frame under the current speed planning strategy. and ideal download speed of adjacent historical frames To match the measured speed information Calculate the speed gain coefficient k to estimate the forklift speed in the current frame. :

[0010]

[0011] Calculate the estimated speed of the forklift in the current frame. Ideal download speed for the current frame The error e is used to adjust the forklift PID control to obtain the actual frame download speed. .

[0012] In a possible preferred embodiment, the step of calculating the actual cargo distance includes:

[0013] Calculate the distance difference S1 between adjacent cargo frames captured by the depth camera and the interval time dt, and combine this with the actual data delivery speed. and position calculation gain coefficient Calculate the actual cargo distance S:

[0014] .

[0015] In a possible preferred embodiment, the step of calculating the blind zone projection length includes:

[0016] Obtain the blind zone distance parameter L1, the mounting angle Yaw, and the pitch parameter of the depth camera, and calculate the blind zone projection length D:

[0017] .

[0018] In a possible preferred embodiment, the unmanned forklift loading and unloading safety control method further includes the following steps:

[0019] Collect fork height information and fork sensor signals; when the work task is determined to be a loading task, monitor the fork sensor signals when the fork height of the forklift drops to the initial height at the loading point. If it is determined that the goods have not been removed, continue to slowly lower the fork until the goods are removed from the fork. At this time, record the forklift loading position, and retract the fork according to the actual loading speed until the travel distance in the blind zone exceeds the blind zone projection length, but still has not left the blind zone, and then stop the forklift.

[0020] To achieve the above objectives, corresponding to the above method, according to another aspect of the present invention, an unmanned forklift loading and unloading safety control system is also provided, comprising:

[0021] The forklift status monitoring module is used to monitor the forklift's work tasks and travel speed.

[0022] The cargo status monitoring module is used to detect the cargo distance information between the vehicle body and the cargo using a depth camera;

[0023] The central control unit is used to analyze the driving speed information when the work task is determined to be a picking task, to calculate the actual delivery speed of the forklift in the current frame, and to calculate the actual cargo distance by combining the cargo distance information of adjacent frames detected by the depth camera. When the depth camera cannot obtain cargo distance information, it is determined that the forklift has entered the depth camera blind zone, the initial position is recorded, and the forklift is driven according to the actual delivery speed until the distance traveled in the blind zone exceeds the projection length of the blind zone, at which point the forklift is stopped.

[0024] In a possible preferred embodiment, the unmanned forklift loading and unloading safety control system further includes:

[0025] The cargo detachment monitoring module is used to monitor whether the cargo has detached from the forks based on the fork sensors;

[0026] The forklift status monitoring module is also used to monitor the forklift fork height information;

[0027] The central control unit is also used to monitor the fork sensor signal when the fork height of the forklift drops to the initial height at the loading point when the work task is determined to be a loading task. If it is determined that the goods have not been removed, the forklift continues to slowly drop until the goods are removed from the forklift. At this time, the loading position of the forklift is recorded, and the forklift is retracted according to the actual loading speed until the distance traveled in the blind zone exceeds the projected length of the blind zone, but the forklift still has not left the blind zone, at which point the forklift is stopped.

[0028] To achieve the above objectives, in accordance with another aspect of the present invention, a computer-readable storage medium is also provided, corresponding to the above-described method, the computer-readable storage medium storing a computer program, wherein when the computer program is executed, it implements the steps of the unmanned forklift loading and unloading safety control method as described above.

[0029] The unmanned forklift loading and unloading safety control system and method, along with the storage medium provided by this invention, cleverly calculates the actual forklift loading speed in the current frame based on the collected forklift speed information, and estimates the actual cargo distance based on this and the cargo distance information collected by the depth camera. Thus, whether in the camera monitoring area or the camera blind spot, the relative position between the forklift and the cargo can be accurately predicted, effectively avoiding collisions between the forklift forks and the pallet or rack, thereby reducing the occurrence of cargo falling safety problems. Attached Figure Description

[0030] The accompanying drawings, which form part of this application, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings:

[0031] Figure 1 This is a schematic diagram illustrating the steps of the unmanned forklift loading and unloading safety control method of the present invention;

[0032] Figure 2 This is a schematic diagram of the cargo retrieval task flow logic in the unmanned forklift cargo retrieval and placement safety control method of the present invention;

[0033] Figure 3 This is a schematic diagram illustrating the determination of safe distance within the blind zone of the picking task in the unmanned forklift picking and placing safety control method of the present invention.

[0034] Figure 4 This is a schematic diagram illustrating the projection of the blind spot length to calculate the blind spot projection length in the unmanned forklift loading and unloading safety control method of the present invention.

[0035] Figure 5 This is a schematic diagram illustrating the relationship between the forklift's blind spot travel distance and the blind spot projection length in the unmanned forklift loading and unloading safety control method of the present invention.

[0036] Figure 6 This is a schematic diagram of the loading and unloading task flow logic in the unmanned forklift loading and unloading safety control method of the present invention;

[0037] Figure 7 This is a schematic diagram of the fork descent control in the unmanned forklift loading and unloading safety control method of the present invention;

[0038] Figure 8 This is a schematic diagram of the unmanned forklift loading and unloading safety control system of the present invention. Detailed Implementation

[0039] To enable those skilled in the art to better understand the technical solutions of the present invention, the specific technical solutions of the present invention will be clearly and completely described below in conjunction with embodiments, so as to help those skilled in the art further understand the present invention. Obviously, the embodiments described in this application are merely some embodiments of the present invention, and not all embodiments. It should be noted that, for those skilled in the art, the embodiments and features in the embodiments of this application can be combined with each other without departing from the concept of the present invention and without conflict. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the disclosure and protection scope of the present invention.

[0040] Furthermore, the terms "first," "second," "S100," "S200," etc., used in the specification, claims, and drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such features can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those described herein. At the same time, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. Unless otherwise expressly specified and limited, the terms "set," "arranged," "installed," "connected," and "linked" should be interpreted broadly, for example, as a fixed connection, a detachable connection, or an integral connection; a mechanical connection or an electrical connection; a direct connection or an indirect connection through an intermediate medium; or a connection within two elements. Those skilled in the art can understand the specific meaning of the above terms in this case based on the specific circumstances and in conjunction with existing technology.

[0041] To monitor the relative status of the forklift and the goods, and to prevent the forklift from moving the goods when picking up or placing them, such as... Figures 1 to 7 As shown, the present invention provides a safety control method for unmanned forklift loading and unloading, the steps of which include:

[0042] Step S100 collects information on the unmanned forklift's work tasks, driving speed, and cargo distance between the forklift and the cargo detected by the depth camera.

[0043] In step S200, when the work task is determined to be a pickup task, the driving speed information is parsed to calculate the actual dispatch speed of the forklift in the current frame; based on the actual dispatch speed and the cargo distance information of adjacent frames detected by the depth camera, the actual cargo distance is calculated.

[0044] Specifically, in the process of forklift freight, the work tasks are mainly divided into two types: picking up and placing goods. Different safety control strategies will be involved for different types of work tasks.

[0045] like Figure 2 The workflow for a pickup task is shown below. When the unmanned forklift starts operating, it first needs to determine the task information. If it is determined to be a pickup task, it needs to acquire images of the goods at the target point in real time using a depth camera to determine the distance between the forklift and the goods, and thus know the relative positional changes between the forklift and the goods.

[0046] When determining the relative position of goods, considering the complex working environment of forklifts, which can easily lead to false alarms due to excessive camera noise or abnormal forklift positioning, the following processing was performed to ensure the stability and reliability of the actual position data.

[0047] On the one hand, considering that unmanned forklifts typically carry heavy loads, which can affect the motor's tracking performance, in order to avoid poor motor tracking performance leading to abnormal acquisition of the forklift status, the ideal download speed of the previous frame under the speed planning can be obtained by looking up a table. The download speed of the current frame is then adjusted based on the speed planning of the previous frame, thereby ensuring accurate estimation of the forklift status.

[0048] For example, in this example, the steps for calculating the actual download speed of the forklift in the current frame include:

[0049] Step S210 analyzes the driving speed, obtains the current speed planning strategy information, and the measured speed information reported by the forklift odometer;

[0050] Step S220: Query the ideal transmission speed of the current frame under the current speed planning strategy. and ideal download speed of adjacent historical frames To match the measured speed information Calculate the speed gain coefficient k to estimate the forklift speed in the current frame. :

[0051]

[0052] Then, calculate the estimated speed of the forklift in the current frame. Ideal download speed for the current frame The following speed error e is used to adjust the forklift's PID control to obtain the actual download speed of the current frame. .

[0053] On the other hand, to eliminate the influence of camera noise and calculate the actual cargo distance, this example includes the following steps:

[0054] Step S230 performs data filtering on the cargo distance value returned by the camera to obtain the difference in cargo distance between the two frames at this time, S1, and the interval time dt. Then, based on the actual transmission speed of the current frame obtained in the previous step... Calculate the actual cargo distance S:

[0055]

[0056] in, This is the gain coefficient when calculating the actual cargo distance.

[0057] By following the steps above, the forklift's own position and the relative position of the forklift and the goods can be accurately calculated, thus providing a basis for controlling the positional relationship between the forklift and the goods, and thereby avoiding safety issues such as forklift collisions causing damage to the goods.

[0058] Furthermore, considering the existing blind spots of depth cameras installed on forklifts, this invention aims to prevent the forklift from losing control of its relative position to the goods within these blind spots, thus avoiding collisions and damage. The invention calculates the projected distance of the camera's blind spot length along the forklift's longitudinal direction, based on the camera's mounting position on the forklift. This blind spot projection length is the actual distance between the forklift and the goods when the forklift enters the blind spot, providing a basis for evaluating the forklift's position within the blind spot.

[0059] In step S300, when the depth camera cannot obtain the distance information of the goods, it is determined that the forklift has entered the blind zone of the depth camera, and the initial position is recorded. The forklift is driven according to the actual speed until the distance traveled in the blind zone exceeds the projected length of the blind zone, at which point the forklift is stopped.

[0060] Specifically, when the camera detects that it cannot return valid cargo distance information between the forklift and the cargo, it means that the forklift has entered the camera's blind zone. In order to determine the safe distance between the forklift and the cargo in the blind zone, the blind zone projection length needs to be calculated first.

[0061] For example, in this example, the steps for calculating the blind zone projection length include:

[0062] Obtain the blind zone distance parameter L1, the mounting angle Yaw, and the pitch parameter of the depth camera, and calculate the blind zone projection length D:

[0063]

[0064] In real-world conditions, the camera blind spot distance is one of the camera's parameters, which can be obtained by consulting the product manual, while the camera mounting angle parameter can be obtained by manual measurement.

[0065] When the forklift enters the camera's blind spot, its position is recorded as its initial position. The forklift continues to travel at the previously calculated actual speed. When the forklift travels a distance greater than or equal to the depth camera's blind spot projection length, it is considered that the forklift and the goods are extremely close. If the forklift moves forward further, it may cause the forks to hit the pallet, potentially dragging the pallet and goods. In this case, the forklift should be stopped and all subsequent tasks ceased, and an alarm should be issued.

[0066] For example, to more intuitively illustrate the calculation process, assume the forklift is located at the pickup point A1, ready to execute the pickup task to the goods point G. Assume the forklift's loading trigger monitoring speed is 0.1 m / s, the camera's blind spot distance is 0.3 m, the camera's yaw angle is 170°, and the pitch is 10°. Also assume the gain coefficient is used to calculate the actual goods distance. It is 0.8.

[0067] like Figure 3 As shown, when the forklift starts performing the picking task, the relative distance S1 between the camera and the target point, captured by the first depth camera, is 1m. The second return shows a cargo distance S2 of 0.9m. The actual download speed of the current frame is then obtained. The speed is 0.125 m / s, and the time interval is 1 second. The actual distance S between the goods and the forklift can be obtained as:

[0068] .

[0069] When the camera fails to return valid cargo distance information, indicating the forklift has entered the camera's blind spot, the forklift's current position A3 is recorded. Due to variations in camera mounting positions, to obtain accurate projection lengths of the camera's blind spot along the vehicle's travel direction, such as... Figure 4 As shown, the length of the blind spot is projected to obtain its length in the forklift's travel direction.

[0070]

[0071] like Figure 5 As shown, the forklift's positioning position in the next control cycle is A4. If the distance L between points A3 and A4 in the blind zone is greater than 0.29m before the forklift reaches the picking task, it will be determined that the forks will move the target goods, and an alarm message will be given immediately, and the forklift will stop its task in place.

[0072] Furthermore, in an optional embodiment, the steps of the unmanned forklift loading and unloading safety control method further include:

[0073] Step S110: Collect fork height information and fork sensor signals.

[0074] Step S310: When the work task is determined to be a cargo handling task, monitor the fork sensor signal when the fork height of the forklift drops to the initial height at the loading point. If it is determined that the cargo has not been removed, continue to slowly lower the fork until the cargo is removed from the fork. At this time, record the loading position of the forklift and retract the fork according to the actual loading speed until the distance traveled in the blind zone exceeds the projected length of the blind zone, but the forklift still has not left the blind zone, and then stop the forklift.

[0075] Specifically, such as Figure 6As shown, when the work task is determined to be a pickup task, the forklift will pick up the goods and place them at the delivery point. When the forklift arrives at the delivery point and adjusts the fork height to place the goods, the fork sensors installed at the root of the fork teeth can determine whether the goods have detached from the forks. If the fork height drops to the initial preset height and the signal indicating that the goods have detached from the forks has not yet disappeared, to avoid the forklift directly retracting and rubbing against the upper surface of the pallet holes, causing the pallet to tilt, the forks can be controlled to continue descending at a low speed until all the fork sensor signals disappear, that is, when the goods have completely detached from the forks, before the subsequent retraction action is performed.

[0076] When performing a loading / unloading operation, the depth camera is very close to the goods, which means the camera is in a blind spot. At this point, a blind spot detection logic, similar to that used for retrieval tasks, is applied. If the forklift travels a distance greater than the blind spot projection length of the depth camera, an alarm is triggered, and the forklift is stopped in place.

[0077] For example Figure 7 As shown, after the forklift picks up the goods, it proceeds to the placement point A1 to perform the placement task. Assume the current height H1 of the goods is 0.5m and the target height H2 is 0.2m. The forklift then begins its lifting motion, lowering the forks from the current height of 0.5m to the target height of 0.2m. The forklift sensor signal is acquired in real time. When the forks reach the preset height of 0.2m, if the sensor signal has not yet disappeared, it is considered that the goods have not been removed. The forklift mechanism then continues to issue a lowering command until the sensor signal disappears. Only then can the forklift safely perform the subsequent fork retraction action.

[0078] Similar to blind spot detection during pickup, if the forklift travels more than 0.29m within the blind spot, it is determined that the forks will move the target goods when releasing them, and the forklift will immediately stop its operation and issue an alarm.

[0079] Furthermore, since the distance between the goods and the camera is small at this time, the goods are located within the camera's blind spot. To avoid potential camera jitter when the starting speed is low, in an optional implementation, goods status monitoring is only activated when the detected speed sent to the forklift is greater than 0.1 m / s, so as to return the relative goods distance information between the forklift and the goods at the target point in real time.

[0080] On the other hand, corresponding to the above methods, such as Figure 8 The present invention also provides a safety control system for unmanned forklifts for picking and placing goods, comprising:

[0081] The forklift status monitoring module is used to monitor the forklift's work tasks and travel speed.

[0082] The cargo status monitoring module is used to detect the cargo distance information between the vehicle body and the cargo using a depth camera;

[0083] The central control unit is used to analyze the driving speed information when the work task is determined to be a picking task, to calculate the actual delivery speed of the forklift in the current frame, and to calculate the actual cargo distance by combining the cargo distance information of adjacent frames detected by the depth camera. When the depth camera cannot obtain cargo distance information, it is determined that the forklift has entered the depth camera blind zone, the initial position is recorded, and the forklift is driven according to the actual delivery speed until the distance traveled in the blind zone exceeds the projection length of the blind zone, at which point the forklift is stopped.

[0084] Furthermore, in an optional embodiment, the unmanned forklift loading and unloading safety control system further includes:

[0085] The cargo detachment monitoring module is used to monitor whether the cargo has detached from the forks based on the fork sensors;

[0086] The forklift status monitoring module is also used to monitor the forklift fork height information;

[0087] The central control unit is also used to monitor the fork sensor signal when the fork height of the forklift drops to the initial height at the loading point when the work task is determined to be a loading task. If it is determined that the goods have not been removed, the forklift continues to slowly drop until the goods are removed from the forklift. At this time, the loading position of the forklift is recorded, and the forklift is retracted according to the actual loading speed until the distance traveled in the blind zone exceeds the projected length of the blind zone, but the forklift still has not left the blind zone, at which point the forklift is stopped.

[0088] On the other hand, in accordance with the above methods, the present invention also provides a computer-readable storage medium storing a computer program, wherein when the computer program is executed, it implements the steps of the unmanned forklift loading and unloading safety control method as described above.

[0089] In summary, the unmanned forklift loading and unloading safety control system and method, along with the storage medium provided by this invention, cleverly calculates the actual forklift loading speed in the current frame based on the collected forklift speed information, and estimates the actual cargo distance based on this and the cargo distance information collected by the depth camera. Thus, whether in the camera monitoring area or the camera blind spot, the relative position between the forklift and the cargo can be accurately predicted, effectively avoiding collisions between the forklift forks and the pallet or rack, thereby reducing the occurrence of cargo falling safety problems.

[0090] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The present invention is limited only by the claims and their full scope and equivalents. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the invention should be included within the protection scope of the invention.

[0091] Those skilled in the art will understand that, besides implementing the system, apparatus, unit, and its modules provided by this invention in purely computer-readable program code, the same program can be implemented in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, the system, apparatus, and its modules provided by this invention can be considered a hardware component, and the modules included therein for implementing various programs can also be considered structures within the hardware component; alternatively, modules for implementing various functions can be considered both software programs implementing the method and structures within the hardware component.

[0092] Furthermore, all or part of the steps in the methods of the above embodiments can be implemented by a program instructing related hardware. This program is stored in a storage medium and includes several instructions to cause a microcontroller, chip, or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0093] Furthermore, various different implementations of the present invention can be combined arbitrarily, as long as they do not violate the spirit of the present invention, they should also be regarded as the content disclosed in the present invention.

Claims

1. A safety control method for unmanned forklifts to pick up and place goods, comprising the following steps: Collect information on the unmanned forklift's work tasks, driving speed, and the distance between the forklift and the goods detected by the depth camera; When the task is determined to be a pickup task, the driving speed information is parsed to calculate the actual dispatch speed of the forklift in the current frame; The actual cargo distance is calculated based on the actual delivery speed and the cargo distance information of adjacent frames detected by the depth camera. When the depth camera cannot obtain the distance information of the goods, it is determined that the forklift has entered the blind zone of the depth camera, and the initial position is recorded. The forklift is driven according to the actual speed until the distance traveled in the blind zone exceeds the projected length of the blind zone, at which point the forklift is stopped.

2. The unmanned forklift loading and unloading safety control method according to claim 1, wherein the step of calculating the actual frame transmission speed of the forklift in the current frame includes: Analyze the driving speed to obtain current speed planning strategy information and measured speed information; Query the ideal download speed for the current frame under the current speed planning strategy. and ideal download speed of adjacent historical frames To match the measured speed information Calculate the speed gain coefficient k to estimate the forklift speed in the current frame. : Calculate the estimated speed of the forklift in the current frame. Ideal download speed for the current frame The error e is used to adjust the forklift PID control to obtain the actual frame download speed. .

3. The unmanned forklift loading and unloading safety control method according to claim 1, wherein the step of calculating the actual cargo distance includes: Calculate the distance difference S1 between adjacent cargo frames captured by the depth camera and the interval time dt, and combine this with the actual data delivery speed. and position calculation gain coefficient Calculate the actual cargo distance S: 。 4. The unmanned forklift loading and unloading safety control method according to claim 1, wherein the step of calculating the blind spot projection length includes: Obtain the blind zone distance parameter L1, the mounting angle Yaw, and the pitch parameter of the depth camera, and calculate the blind zone projection length D: 。 5. The unmanned forklift loading and unloading safety control method according to claim 1, wherein the method steps further include: Collect fork height information and fork sensor signals; When the task is determined to be a cargo handling task, monitor the forklift fork height at the loading point when it descends to the initial height. If it is determined that the cargo has not been removed, continue to slowly lower the fork until the cargo is removed from the fork. At this time, record the loading position of the forklift and retract the fork according to the actual loading speed until the forklift travels a distance in the blind zone that exceeds the projected length of the blind zone, but still has not left the blind zone, then stop the forklift.

6. A safety control system for unmanned forklifts for picking and placing goods, comprising: The forklift status monitoring module is used to monitor the forklift's work tasks and travel speed. The cargo status monitoring module is used to detect the cargo distance information between the vehicle body and the cargo using a depth camera; The central control unit is used to analyze the driving speed information when the work task is determined to be a picking task, to calculate the actual delivery speed of the forklift in the current frame, and to calculate the actual cargo distance by combining the cargo distance information of adjacent frames detected by the depth camera. When the depth camera cannot obtain cargo distance information, it is determined that the forklift has entered the depth camera blind zone, the initial position is recorded, and the forklift is driven according to the actual delivery speed until the distance traveled in the blind zone exceeds the projection length of the blind zone, at which point the forklift is stopped.

7. The unmanned forklift loading and unloading safety control system according to claim 6 further includes: The cargo detachment monitoring module is used to monitor whether the cargo has detached from the forks based on the fork sensors; The forklift status monitoring module is also used to monitor the forklift fork height information; The central control unit is also used to monitor the fork sensor signal when the fork height of the forklift drops to the initial height at the loading point when the work task is determined to be a loading task. If it is determined that the goods have not been removed, the forklift continues to slowly drop until the goods are removed from the forklift. At this time, the loading position of the forklift is recorded, and the forklift is retracted according to the actual loading speed until the distance traveled in the blind zone exceeds the projected length of the blind zone, but the forklift still has not left the blind zone, at which point the forklift is stopped.

8. A computer-readable storage medium storing a computer program, wherein when the computer program is executed, it implements the steps of the unmanned forklift loading and unloading safety control method as described in any one of claims 1 to 5.

Images