Anti-collision early warning method and anti-collision system suitable for forklift operation vehicle

Abstract

The invention discloses an anti-collision early warning method and an anti-collision system suitable for a forklift operation vehicle, belongs to the technical field of anti-collision, and particularly relates to anti-collision of the forklift operation vehicle. The problems that an existing forklift anti-collision system cannot deal with flexible obstacles, is prone to being interfered by severe weather and environments, cannot adapt to all-weather working environments, needs additional RFID tags or special equipment and is low in universality are solved. The system comprises an information acquisition module, a central control system, a sound-light alarm device and an execution control system. The AI camera submodule comprises a detection unit and a deep learning unit. The anti-collision early warning method and the anti-collision system suitable for the forklift operation vehicle are suitable for reducing the accident rate during operation of the special vehicle and improving the operation efficiency of the forklift when the special vehicle, especially the forklift executes tasks of loading, unloading, stacking, carrying and the like, so that the special vehicle can adapt to the all-weather working environment.

Description

Technical Field

[0001] The invention relates to the technical field of anti-collision, and in particular to the anti-collision of a forklift operating vehicle. Background Art

[0002] As a kind of special operation vehicle, forklifts play an important role in the field of logistics and warehousing. They undertake tasks such as cargo loading and unloading, stacking, and handling, and are one of the key equipment for achieving efficient logistics. Forklifts are widely used in ports, stations, airports, cargo yards, factory workshops, warehouses, circulation centers, and distribution centers, etc., to load, unload, and carry out pallet cargo handling operations in cabins, carriages, and containers. However, there are always safety hazards in the operation of forklifts, among which the problem of visual blind spots is particularly prominent. The problem of visual blind spots will not only cause collisions and scratches between forklifts and cargo, but may also lead to more serious casualties. Therefore, when the forklift is working, it is of great significance to prevent obstacles such as cargo and people from colliding with the forklift, which is of great significance to the safety of forklift operations.

[0003] At present, the collision avoidance of forklifts during operation still mainly relies on the empirical judgment of forklift drivers. This collision avoidance method is highly correlated with the driver's personal factors and is strictly limited by the driver's personal experience. For people with less driving experience, it is relatively difficult to avoid obstacles based on experience.

[0004] In order to reduce the economic losses or casualties caused by collisions between forklifts and cargo, technicians in this field have developed forklift anti-collision systems. Existing forklift anti-collision systems are mainly divided into two types: one is to install physical barriers and devices, one is to use warning and reminder devices, and the other is to install an anti-collision detection system on the forklift vehicle to detect obstacles.

[0005] The installation of physical barriers and devices, such as guardrails, anti-collision bars, corner guards, etc. before the protected (fixed) goods, can reduce the degree of damage caused by collision accidents. However, it is difficult to prevent collisions with some flexible obstacles that suddenly appear in the forklift workplace (such as people, fallen small boxes, etc.), and it is not suitable for scenes that require forklifts to work flexibly.

[0006] As for the use of warning and reminder devices, reflective signs are set on the protected goods, or warning devices (such as warning lights, sound alarms, etc.) are set within a certain range of the goods to increase the operator's vigilance. However, in some cases, even if a collision warning is made, a collision accident may still occur due to improper operation of the driver. This anti-collision method has the risk of environmental interference, reliance on subjective reactions of personnel, and increased maintenance and management costs.

[0007] Regarding the method of installing an anti-collision detection system on a forklift vehicle to detect obstacles, the anti-collision detection system currently installed on the vehicle has a limited detection range and can only detect dangerous obstacles within the line of sight (i.e., the area visible to the forklift driver). Detection in areas outside the line of sight is limited, and the forklift is easily affected by bad weather and environment when operating outdoors, and cannot adapt to an all-weather working environment. Summary of the invention

[0008] The present invention proposes an anti-collision warning method and an anti-collision system suitable for forklift operating vehicles, which solves the problems of the existing forklift anti-collision system that it cannot cope with flexible obstacles, is easily disturbed by bad weather and environment, cannot adapt to all-weather working environment, requires additional RFID tags or special equipment, and has low versatility.

[0009] The anti-collision warning method applicable to a forklift operation vehicle of the present invention comprises the following steps:

[0010] Step S1: Acquire forklift position information, forklift status information, forklift surrounding environment information and forklift driver driving status information; the forklift status information includes the speed, acceleration and heading angle information of the forklift; the forklift surrounding environment information includes the status information of obstacle targets;

[0011] Step S2: converting the acquired forklift position information from longitude and latitude coordinates into XY coordinates in a rectangular coordinate system;

[0012] Step S3: Calculate the relative position relationship between the forklift and the obstacle target;

[0013] Step S4: Calculate the distance, relative speed and relative acceleration between the forklift and the obstacle target that meets the triggering conditions of the early warning algorithm as collision trend judgment information;

[0014] Step S5: judging whether the forklift has a tendency to collide with an obstacle target according to the collision tendency judgment information:

[0015] If it is determined that the forklift has a tendency to collide with the obstacle target, step S6 is executed;

[0016] Otherwise, there is no potential collision risk and the method ends;

[0017] Step S6: Calculate the collision time required for the forklift to collide with the obstacle target;

[0018] Step S7: Calculate the collision time threshold according to the forklift speed;

[0019] Step S8: Determine whether the collision time required for the forklift to collide with the obstacle target is less than the collision time threshold:

[0020] If it is less than the collision time threshold, there is a potential collision risk, and the type of collision is identified, and a warning signal is output according to the type of collision, and the method ends;

[0021] Otherwise, there is no potential collision risk and the method ends.

[0022] Further, a preferred embodiment is provided, wherein step S2 is as follows:

[0023] The obtained forklift location information is converted from the longitude and latitude coordinates to obtain the X coordinate in the rectangular coordinate system:

[0024]

[0025] The Y coordinate in the rectangular coordinate system obtained by converting the obtained forklift position information from the longitude and latitude coordinates:

[0026]

[0027] Among them, the parameters x, N, B0, l, t, g are obtained by the following formula:

[0028] x=C(B1B0+sinB0(B2cosB0+B3cos 3 B0+B4cos 5 B0+B5cos 7 B0))

[0029]

[0030] t=tanB0

[0031] g=e1cosB0

[0032] Among them, π=3.14159, L0=120, W0=0; parameters C, B1, B2, B3, B4, B5, e, e1 are obtained by the following formula:

[0033]

[0034] B2=B1-1

[0035]

[0036] Among them, a=6378137, b=6356752; x is the arc length of the meridian measured from the equator to the known point; N is the radius of the meridian circle; B0 is the geodetic latitude; l is the central meridian longitude difference in the projection band, in radians; L0 is the geodetic latitude; all physical quantities represented by B1, B2, B3, B4 and B5 are the base latitudes, and are functions of the first eccentricity of the ellipsoid; e is the first eccentricity of the ellipsoid; e1 is the second eccentricity of the ellipsoid; a is the equatorial radius of the earth, in meters; b is the polar radius of the earth, in meters; t, g, W0, L, B, f, C are intermediate parameters used for calculation.

[0037] Further, a preferred embodiment is provided, in step S7, the collision time is:

[0038]

[0039] Among them, ΔD is the distance between the forklift and the obstacle target; v1 is the relative speed between the forklift and the obstacle target; α1 is the relative acceleration of the forklift relative to the obstacle, α1=0 means that the obstacle target is stationary, and α1≠0 means that the obstacle target is moving.

[0040] Further, a preferred embodiment is provided, in step S8, the collision time threshold is:

[0041]

[0042] Where v2 is the speed of the forklift.

[0043] The present invention also proposes an anti-collision system suitable for a forklift operation vehicle, the system comprising an information collection module, a central control system, an audible and visual alarm device and an execution control system;

[0044] The information acquisition module includes multiple forklift sensors, a GPS submodule, a CAN submodule and an AI camera submodule:

[0045] The GPS submodule is used to collect forklift location information;

[0046] The CAN submodule is connected to a plurality of forklift sensor signals for collecting forklift status information; the forklift status information includes the speed, acceleration and heading angle information of the forklift;

[0047] The AI ​​camera submodule includes a detection unit and a deep learning unit; the detection unit includes a radio detection device and a visual detection device, which are used to collect information about the surrounding environment of the forklift and the driving status information of the forklift driver; the information about the surrounding environment of the forklift includes status information of obstacle targets; the deep learning unit is used to execute any one of the above-mentioned anti-collision warning methods applicable to forklift operating vehicles, determine whether there is a potential collision risk, and when there is a potential collision risk, output a warning signal according to the type of collision:

[0048] The central control system includes an alarm submodule, a pre-pressurization submodule and an emergency brake submodule:

[0049] The alarm submodule is used to send an alarm control signal to the sound and light alarm device according to the early warning signal; the sound and light alarm device is used to send an sound and light alarm according to the alarm control signal;

[0050] The pre-pressurization submodule is used to pre-increase the oil pressure of the brake master cylinder according to the early warning signal, so as to obtain a greater deceleration in a shorter time during braking;

[0051] The emergency brake submodule is used to determine whether the forklift driver takes correct collision avoidance operations within a given time according to the warning signal and the forklift driver's driving state information, and when the forklift driver does not take correct collision avoidance operations, calculate the emergency brake control amount and send it to the execution control system, and the emergency brake control amount includes throttle opening and brake pressure;

[0052] The execution control system is used to adjust the opening of the throttle of the forklift engine and the brake pressure of the forklift brake system according to the emergency brake control amount to execute the emergency brake operation.

[0053] Further, a preferred embodiment is provided, wherein the system further comprises a user terminal module;

[0054] The user terminal module is used to display the real-time status of the forklift itself, the real-time status of the forklift's surrounding environment and the real-time driving status of the forklift driver based on the forklift's position information, forklift status information, forklift surrounding environment information and forklift driver's driving status information; and is also used to display the real-time status of the warning based on the warning signal.

[0055] The present invention also proposes an anti-collision warning device suitable for a forklift operation vehicle, the device comprising the following modules:

[0056] Module S1: Acquire forklift position information, forklift status information, forklift surrounding environment information and forklift driver driving status information; the forklift status information includes the speed, acceleration and heading angle information of the forklift; the forklift surrounding environment information includes the status information of obstacle targets;

[0057] Module S2: converting the acquired forklift position information from longitude and latitude coordinates into XY coordinates in a rectangular coordinate system;

[0058] Module S3: Calculate the relative position relationship between the forklift and the obstacle target;

[0059] Module S4: Calculate the distance, relative speed and relative acceleration between the forklift and the obstacle target that meets the triggering conditions of the early warning algorithm as the collision trend judgment information;

[0060] Module S5: Determine whether the forklift has a tendency to collide with an obstacle target based on the collision tendency judgment information:

[0061] If it is determined that the forklift has a tendency to collide with the obstacle target, the process goes to module S6;

[0062] Otherwise, there is no potential collision risk and the process ends;

[0063] Module S6: Calculate the collision time required for the forklift to collide with the obstacle target;

[0064] Module S7: Calculate the collision time threshold according to the forklift speed;

[0065] Module S8: Determine whether the collision time required for the forklift to collide with the obstacle target is less than the collision time threshold:

[0066] If it is less than the collision time threshold, there is a potential collision risk, a warning signal is output, and the process ends;

[0067] Otherwise, there is no potential collision risk and the process ends.

[0068] The present invention also proposes a computer device, comprising: a processor and a memory, wherein the memory is used to store executable instructions of the processor, and the processor is configured to execute any one of the above-mentioned anti-collision warning methods applicable to forklift operating vehicles by executing the executable instructions.

[0069] The present invention further proposes a computer storage medium, in which a computer program is stored. When the computer program is run, any one of the above-mentioned anti-collision warning methods applicable to forklift operating vehicles is executed.

[0070] The present invention also proposes a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of any one of the above-mentioned anti-collision warning methods applicable to forklift operating vehicles.

[0071] The present invention has the following beneficial effects:

[0072] 1. The anti-collision system for forklift operating vehicles described in the present invention is equipped with a radar system in the AI ​​camera submodule, which can use millimeter wave reflection to detect the distance, speed and direction of objects (obstacles). In addition, this radar system has a strong ability to penetrate rain, fog and dust and is suitable for bad weather. It solves the problem that the anti-collision measures of forklifts are easily affected by bad weather and environment when operating outdoors and cannot adapt to all-weather working environments.

[0073] 2. The anti-collision system for forklift operating vehicles described in the present invention can detect obstacle targets in areas outside the line of sight through a camera (AI camera) installed at the front end of the forklift, and can perform all-round obstacle detection and identification around the forklift.

[0074] 3. The anti-collision system for forklift vehicles described in the present invention uses deep learning technology in the AI ​​camera submodule to distinguish pedestrians and obstacles through training models. It does not require any RFID tags or special equipment to detect people, which greatly improves the versatility and ease of use of the system.

[0075] 4. The anti-collision system for forklift operating vehicles described in the present invention has an emergency braking function. If the driver still does not take correct collision avoidance operations after the alarm signal is issued, the system will take over the control of the vehicle on behalf of the driver and perform emergency braking on the vehicle to avoid collision or reduce the speed of the vehicle at the time of collision, thereby minimizing the damage to the driver and pedestrians.

[0076] 5. The anti-collision system for forklift operation vehicles described in the present invention can continuously monitor the area around the forklift in real time to detect any potential obstacles; when an object or person enters a preset safety distance, the system will immediately issue an audible and visual alarm to notify the forklift driver to pay attention to avoid it.

[0077] 6. The anti-collision system for forklift operating vehicles described in the present invention has a high degree of accuracy and can accurately identify and distinguish different objects and personnel. It is an easy-to-operate, safe, reliable and humanized safety warning system.

[0078] The anti-collision warning method and anti-collision system for forklift operating vehicles described in the present invention are suitable for special vehicles, especially forklifts, when performing tasks such as loading and unloading, stacking, and transportation. They can reduce the accident rate during the operation of special vehicles, improve the operating efficiency of forklifts, and enable special vehicles to adapt to all-weather working environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0080] Figure 1 A schematic flow chart of an anti-collision warning method applicable to a forklift operation vehicle in one embodiment of the present invention;

[0081] Figure 2 A schematic diagram of a structure of an anti-collision system applicable to a forklift operation vehicle in one embodiment of the present invention;

[0082] Figure 3 A schematic diagram of a control flow of a collision avoidance system applicable to a forklift operation vehicle in one embodiment of the present invention;

[0083] Figure 4 FIG. 1 is a schematic diagram of dynamic detection of obstacle targets in one embodiment of the present invention. DETAILED DESCRIPTION

[0084] In order to make the technical solutions and advantages of the present invention more clearly described, the specific implementation methods of the present invention will be further described in detail and completely in conjunction with the accompanying drawings. The various implementation methods described below are only part of the preferred solutions of the present invention, rather than all implementation methods; the various implementation methods described below are intended to explain the present invention and cannot be understood as limitations on the present invention; the reasonable combination of technical features defined in the various implementation methods of the present invention, and all other implementation methods obtained by ordinary technicians in the field without creative work based on the implementation methods of the present invention, are within the scope of protection of the present invention.

[0085] In one embodiment, a collision avoidance warning method applicable to a forklift operation vehicle is provided, the method comprising the following steps:

[0086] Step S1: Acquire forklift position information, forklift status information, forklift surrounding environment information and forklift driver driving status information; the forklift status information includes the speed, acceleration and heading angle information of the forklift; the forklift surrounding environment information includes the status information of obstacle targets;

[0087] Step S2: converting the acquired forklift position information from longitude and latitude coordinates into XY coordinates in a rectangular coordinate system;

[0088] Step S3: Calculate the relative position relationship between the forklift and the obstacle target;

[0089] Step S4: Calculate the distance, relative speed and relative acceleration between the forklift and the obstacle target that meets the triggering conditions of the early warning algorithm as collision trend judgment information;

[0090] Step S5: judging whether the forklift has a tendency to collide with an obstacle target according to the collision tendency judgment information:

[0091] If it is determined that the forklift has a tendency to collide with the obstacle target, step S6 is executed;

[0092] Otherwise, there is no potential collision risk and the method ends;

[0093] Step S6: Calculate the collision time required for the forklift to collide with the obstacle target;

[0094] Step S7: Calculate the collision time threshold according to the forklift speed;

[0095] Step S8: Determine whether the collision time required for the forklift to collide with the obstacle target is less than the collision time threshold:

[0096] If it is less than the collision time threshold, there is a potential collision risk, and the type of collision is identified, and a warning signal is output according to the type of collision, and the method ends;

[0097] Otherwise, there is no potential collision risk and the method ends.

[0098] In this embodiment, the steps of calculating the relative position relationship between the forklift and the obstacle target, calculating the distance, relative speed and relative acceleration between the forklift and the obstacle target that meets the triggering conditions of the early warning algorithm, judging whether the forklift has a tendency to collide with the obstacle target based on the collision trend judgment information, and identifying the collision type are implemented using a deep learning-based method.

[0099] In this embodiment, the collision types include a collision between a forklift and a fixed obstacle and a collision between a forklift and a moving obstacle.

[0100] In addition, in one embodiment, step S2 is as follows:

[0101] The obtained forklift location information is converted from the longitude and latitude coordinates to obtain the X coordinate in the rectangular coordinate system:

[0102]

[0103] The Y coordinate in the rectangular coordinate system obtained by converting the obtained forklift position information from the longitude and latitude coordinates:

[0104]

[0105] Among them, the parameters x, N, B0, l, t, g are obtained by the following formula:

[0106] x=C(B1B0+sinB0(B2cosB0+B3cos 3 B0+B4cos 5 B0+B5cos 7 B0))

[0107]

[0108] t=tanB0

[0109] g=e1cosB0

[0110] Among them, π=3.14159, L0=120, W0=0; parameters C, B1, B2, B3, B4, B5, e, e1 are obtained by the following formula:

[0111]

[0112] B2=B1-1

[0113]

[0114] Among them, a=6378137, b=6356752.

[0115] In this implementation, x is the arc length of the meridian from the equator to the known point; N is the radius of the equator; B0 is the geodetic latitude; l is the central meridian longitude difference in the projection band, in radians; L0 is the geodetic latitude; all physical quantities represented by B1, B2, B3, B4 and B5 are the base latitudes, and are functions of the first eccentricity of the ellipsoid; e is the first eccentricity of the ellipsoid; e1 is the second eccentricity of the ellipsoid; a is the equatorial radius of the earth, in meters; b is the polar radius of the earth, in meters; t, g, W0, L, B, f, and C are intermediate parameters used for calculation and have no practical significance.

[0116] In addition, in one embodiment, in step S7, the collision time is:

[0117]

[0118] Among them, ΔD is the distance between the forklift and the obstacle target; v1 is the relative speed between the forklift and the obstacle target; α1 is the relative acceleration of the forklift relative to the obstacle, α1=0 means that the obstacle target is stationary, and α1≠0 means that the obstacle target is moving.

[0119] In addition, in one embodiment, in step S8, the collision time threshold is:

[0120]

[0121] Where v2 is the speed of the forklift.

[0122] In one embodiment, a collision avoidance system applicable to a forklift operation vehicle is provided, the system comprising an information collection module, a central control system, an audible and visual alarm device, and an execution control system;

[0123] The information acquisition module includes multiple forklift sensors, a GPS submodule, a CAN submodule and an AI camera submodule:

[0124] The GPS submodule is used to collect forklift location information;

[0125] The CAN submodule is connected to a plurality of forklift sensor signals for collecting forklift status information; the forklift status information includes the speed, acceleration and heading angle information of the forklift;

[0126] The AI ​​camera submodule includes a detection unit and a deep learning unit; the detection unit includes a radio detection device and a visual detection device, which are used to collect information about the surrounding environment of the forklift and the driving status information of the forklift driver; the information about the surrounding environment of the forklift includes status information of obstacle targets; the deep learning unit is used to execute any one of the above-mentioned anti-collision warning methods applicable to forklift operating vehicles, determine whether there is a potential collision risk, and when there is a potential collision risk, output a warning signal according to the type of collision:

[0127] The central control system includes an alarm submodule, a pre-pressurization submodule and an emergency brake submodule:

[0128] The alarm submodule is used to send an alarm control signal to the sound and light alarm device according to the early warning signal; the sound and light alarm device is used to send an sound and light alarm according to the alarm control signal;

[0129] The pre-pressurization submodule is used to pre-increase the oil pressure of the brake master cylinder according to the early warning signal, so as to obtain a greater deceleration in a shorter time during braking;

[0130] The emergency brake submodule is used to determine whether the forklift driver takes correct collision avoidance operations within a given time according to the warning signal and the forklift driver's driving state information, and when the forklift driver does not take correct collision avoidance operations, calculate the emergency brake control amount and send it to the execution control system, and the emergency brake control amount includes throttle opening and brake pressure;

[0131] The execution control system is used to adjust the opening of the throttle of the forklift engine and the brake pressure of the forklift brake system according to the emergency brake control amount to execute the emergency brake operation.

[0132] It should be noted that for forklift collision accidents, investigation and analysis show that about 80% of collision accidents are caused by the driver not having enough time to respond; if a warning of potential collision can be issued 0.5 seconds in advance, the driver can reduce collision accidents by 60% after taking anti-collision measures; if the warning time is advanced by 1 second, 90% of forklift collision accidents can be reduced. Therefore, for the anti-collision of forklift operating vehicles, if the driver can be warned (i.e. anti-collision warning) or intervene in the control of the vehicle in the early stage of the forklift accident, it plays an important role in avoiding accidents and ensuring the safety of drivers.

[0133] In this embodiment, the radio detection device is a radar system, and the visual detection device is a camera (AI camera).

[0134] Among them, the radar system can use millimeter wave reflection to detect the distance, speed and direction of objects (obstacles). This radar system has a strong ability to penetrate rain, fog and dust and is suitable for bad weather. It solves the problem that forklift anti-collision measures are easily affected by bad weather and environment when operating outdoors and cannot adapt to all-weather working environments.

[0135] For the "area outside the visual range", that is, the area that the forklift driver cannot see, the camera installed at the front end of the forklift (i.e., the AI ​​camera) can detect obstacles and perform all-round obstacle detection and identification around the forklift.

[0136] In this implementation, the deep learning unit includes a data processing subunit and an anti-collision warning algorithm processing subunit:

[0137] The data processing subunit is used to perform the following steps:

[0138] The acquired forklift position information is converted from longitude and latitude coordinates to XY coordinates in a rectangular coordinate system; the relative position relationship between the forklift and the obstacle target is calculated; the distance, relative speed and relative acceleration between the forklift and the obstacle target that meets the triggering conditions of the early warning algorithm are calculated as the collision trend judgment information.

[0139] The anti-collision warning algorithm processing subunit is used to perform the following steps:

[0140] Determine whether the forklift has a tendency to collide with the obstacle target based on the collision trend judgment information; calculate the collision time required for the forklift to collide with the obstacle target; calculate the collision time threshold based on the forklift speed; and determine whether the collision time required for the forklift to collide with the obstacle target is less than the collision time threshold.

[0141] In this embodiment, the AI ​​camera submodule uses deep learning technology to distinguish pedestrians and obstacles through training models. It does not require any RFID tags or special equipment to detect people, which greatly improves the versatility and ease of use of the system.

[0142] In this embodiment, the system can continuously monitor the area around the forklift in real time to detect any potential obstacles; when an object or person enters the preset safety distance, the system will immediately issue an audible and visual alarm to notify the forklift driver to pay attention and avoid it.

[0143] In this embodiment, the system also has a high degree of accuracy and can accurately identify and distinguish different objects and people. It is an easy-to-operate, safe, reliable, and humanized safety warning system.

[0144] It should be noted that simply using warning and reminder devices to avoid collisions has the following disadvantages:

[0145] The first is the risk of environmental interference. For example, noise masking: in noisy environments such as factories and warehouses (such as multiple forklifts working at the same time, the sound of machinery running), the sound alarm may be masked by background noise, resulting in the failure of the warning. For example, visual interference: reflective signs or warning lights may lose their warning effect due to excessive reflection or blur in strong light, haze, and dusty environments, and even interfere with vision (for example, glaring reflections lead to misjudgment of distance).

[0146] Second, it relies on the subjective response of personnel. For example, human factors dominate, such as habitual neglect: long-term exposure to alarm sounds or lights may cause personnel to become numb to warnings. Operational distraction. For example, distraction: If the operator needs to handle multiple tasks at the same time (such as observing goods, controlling forklifts, and avoiding obstacles), he may not be able to respond to warnings in time.

[0147] Third, the maintenance and management costs increase. For example, the limitations of reflective signs: they are easily affected by pollution (oil, dust), and need to be cleaned or replaced regularly, otherwise the reflective performance will decrease. For example, the complexity of electronic equipment maintenance: electronic equipment such as warning lights and sound alarms need to regularly check circuits, batteries, sensors, etc., and may be aged faster due to environmental factors such as humidity and vibration.

[0148] In this embodiment, through the emergency braking function, if the driver still does not take correct collision avoidance operations after the alarm signal is issued, the system will take over the control of the vehicle on behalf of the driver and perform emergency braking on the vehicle to avoid collision or reduce the speed of the vehicle at the time of collision, thereby minimizing the damage to the driver and pedestrians.

[0149] In addition, in one embodiment, the system further comprises a user terminal module;

[0150] The user terminal module is used to display the real-time status of the forklift itself, the real-time status of the forklift's surrounding environment and the real-time driving status of the forklift driver based on the forklift's position information, forklift status information, forklift surrounding environment information and forklift driver's driving status information; and is also used to display the real-time status of the warning based on the warning signal.

[0151] In this embodiment, if Figure 3 As shown, it is a schematic diagram of the control process of the anti-collision system applicable to forklift operation vehicles, including a perception stage, a decision stage, an execution stage and a display stage.

[0152] The perception stage uses computer technology, information fusion technology, radar technology and sensor technology to perceive the environment around the forklift to assist the driver in controlling the movement state of the forklift, thereby avoiding vehicle collisions. Radar and AI cameras are mainly used to detect the surroundings of the forklift and the driver's status information in real time, and the forklift (its own) status information collected by the on-board sensors is sent to the central control system.

[0153] The decision-making stage uses sensor data to determine the current dangerous state of driving. When it is determined that there is a potential collision risk, two functions are performed respectively:

[0154] ① Early warning function:

[0155] On the one hand, an alarm signal is issued, such as flashing lights (on the human-machine interface) and / or using a buzzer to sound, to remind the driver that danger is about to occur and that he needs to take collision avoidance measures;

[0156] On the other hand, the oil pressure of the brake master cylinder is increased in advance at the same time to obtain a greater deceleration in a shorter time.

[0157] ② Emergency brake function:

[0158] If the driver still does not take correct collision avoidance measures after the alarm signal is issued, the system will take over control of the vehicle and perform emergency braking on the vehicle to avoid collision or reduce the speed at the time of collision, thereby minimizing damage to drivers, passengers and pedestrians.

[0159] The execution stage receives a signal from the central control system, and the execution control system adjusts the engine throttle opening and the brake system brake pressure, so that the forklift vehicle performs the automatic emergency braking function and the engine and the brake system switch smoothly between the normal working state and the emergency braking state.

[0160] The display stage includes a safety management status display and a real-time monitoring status display, which displays the state of the forklift's surrounding environment, the forklift's own state, the driver's driving state and the forklift's warning state information.

[0161] In this embodiment, if Figure 4 As shown, this is a schematic diagram of dynamic detection of obstacle targets:

[0162] The AI ​​camera submodule includes 2 AI cameras:

[0163] AI camera 1 is located at the front end of the forklift and is used to detect the surrounding environment (i.e. obstacles) of the forklift;

[0164] AI camera 2 is located inside the forklift cab and is used to detect the driving status information of the forklift driver;

[0165] The GPS submodule includes the GPS locator:

[0166] The GPS locator is located at the rear of the forklift and is used to locate the forklift's location information, including longitude, latitude and altitude.

[0167] In one embodiment, a collision avoidance warning device applicable to a forklift operation vehicle is provided, the device comprising the following modules:

[0168] Module S1: Acquire forklift position information, forklift status information, forklift surrounding environment information and forklift driver driving status information; the forklift status information includes the speed, acceleration and heading angle information of the forklift; the forklift surrounding environment information includes the status information of obstacle targets;

[0169] Module S2: converting the acquired forklift position information from longitude and latitude coordinates into XY coordinates in a rectangular coordinate system;

[0170] Module S3: Calculate the relative position relationship between the forklift and the obstacle target;

[0171] Module S4: Calculate the distance, relative speed and relative acceleration between the forklift and the obstacle target that meets the triggering conditions of the early warning algorithm as the collision trend judgment information;

[0172] Module S5: Determine whether the forklift has a tendency to collide with an obstacle target based on the collision tendency judgment information:

[0173] If it is determined that the forklift has a tendency to collide with the obstacle target, the process goes to module S6;

[0174] Otherwise, there is no potential collision risk and the process ends;

[0175] Module S6: Calculate the collision time required for the forklift to collide with the obstacle target;

[0176] Module S7: Calculate the collision time threshold according to the forklift speed;

[0177] Module S8: Determine whether the collision time required for the forklift to collide with the obstacle target is less than the collision time threshold:

[0178] If it is less than the collision time threshold, there is a potential collision risk, a warning signal is output, and the process ends;

[0179] Otherwise, there is no potential collision risk and the process ends.

[0180] In one embodiment, a computer device is provided, comprising: a processor and a memory, wherein the memory is used to store executable instructions of the processor, and the processor is configured to execute any one of the above-mentioned anti-collision warning methods applicable to forklift operating vehicles by executing the executable instructions.

[0181] In one embodiment, a computer storage medium is provided, wherein a computer program is stored in the storage medium, and when the computer program is run, any one of the above-mentioned anti-collision warning methods applicable to forklift operation vehicles is executed.

[0182] In one embodiment, a computer program product is provided, including a computer program / instruction, which, when executed by a processor, implements the steps of any one of the above-mentioned anti-collision warning methods applicable to forklift operating vehicles.

[0183] A computer device or system is provided in this embodiment. The hardware device of this part is a general model and is not shown in the form of a diagram. The system includes a processor and a memory, wherein the processor and the memory can be connected via a bus or other means. The memory is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer executable programs and modules, and corresponding program instructions / modules. The processor executes various functional applications and data processing of the processor by running the non-volatile software programs, instructions and modules stored in the memory, so as to realize the data space entity resolution data quality enhancement method in the above method embodiment.

[0184] The memory may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required by at least one function; the data storage area may store data created by the processor, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, an intranet, a mobile communication network, and combinations thereof.

[0185] One or more modules are stored in the memory, and when the processor executes, the method steps in the embodiment are executed. In this way, the purpose of the invention can be achieved through the method, device and process of the present invention. The specific details of the above-mentioned computer device can be understood by referring to the corresponding related descriptions and effects in the embodiment, and will not be repeated here.

[0186] Those skilled in the art can understand that the implementation of all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program. The program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memory.

[0187] The technical solution provided by the present invention is further described in detail above through several specific implementation modes in order to highlight the advantages and benefits of the technical solution provided by the present invention. However, the several specific implementation modes described above are not intended to be used as limitations on the present invention. Any reasonable changes and improvements to the present invention, reasonable combinations of implementation modes and equivalent substitutions based on the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An anti-collision warning method applicable to a forklift operation vehicle, characterized in that: The method comprises the following steps: Step S1: Acquire forklift position information, forklift status information, forklift surrounding environment information and forklift driver driving status information; the forklift status information includes the speed, acceleration and heading angle information of the forklift; the forklift surrounding environment information includes the status information of obstacle targets; Step S2: converting the acquired forklift position information from longitude and latitude coordinates into XY coordinates in a rectangular coordinate system; Step S3: Calculate the relative position relationship between the forklift and the obstacle target; Step S4: Calculate the distance, relative speed and relative acceleration between the forklift and the obstacle target that meets the triggering conditions of the early warning algorithm as collision trend judgment information; Step S5: judging whether the forklift has a tendency to collide with an obstacle target according to the collision tendency judgment information: If it is determined that the forklift has a tendency to collide with the obstacle target, step S6 is executed; Otherwise, there is no potential collision risk and the method ends; Step S6: Calculate the collision time required for the forklift to collide with the obstacle target; Step S7: Calculate the collision time threshold according to the forklift speed; Step S8: Determine whether the collision time required for the forklift to collide with the obstacle target is less than the collision time threshold: If it is less than the collision time threshold, there is a potential collision risk, and the type of collision is identified, and a warning signal is output according to the type of collision, and the method ends; Otherwise, there is no potential collision risk and the method ends.

2. The anti-collision warning method for a forklift vehicle according to claim 1, characterized in that: The step S2 is as follows: The obtained forklift location information is converted from the longitude and latitude coordinates to obtain the X coordinate in the rectangular coordinate system: The Y coordinate in the rectangular coordinate system obtained by converting the obtained forklift position information from the longitude and latitude coordinates: Among them, the parameters x, N, B0, l, t, g are obtained by the following formula: x=C(B1B0+sinB0(B2cosB0+B3cos 3 B0+B4cos 5 B0+B5cos 7 B0)) t=tanB0 g=e1cosB0 Among them, π=3.14159, L0=120, W0=0; parameters C, B1, B2, B3, B4, B5, e, e1 are obtained by the following formula: Among them, a=6378137, b=6356752; x is the arc length of the meridian measured from the equator to the known point; N is the radius of the meridian circle; B0 is the geodetic latitude; l is the central meridian longitude difference in the projection band, in radians; L0 is the geodetic latitude; all physical quantities represented by B1, B2, B3, B4 and B5 are the base latitudes, and are functions of the first eccentricity of the ellipsoid; e is the first eccentricity of the ellipsoid; e1 is the second eccentricity of the ellipsoid; a is the equatorial radius of the earth, in meters; b is the polar radius of the earth, in meters; t, g, W0, L, B, f, C are intermediate parameters used for calculation.

3. The anti-collision warning method for a forklift vehicle according to claim 1, characterized in that: In step S7, the collision time is: Among them, ΔD is the distance between the forklift and the obstacle target; v1 is the relative speed between the forklift and the obstacle target; α1 is the relative acceleration of the forklift relative to the obstacle, α1=0 means that the obstacle target is stationary, and α1≠0 means that the obstacle target is moving.

4. The anti-collision warning method for a forklift vehicle according to claim 1, characterized in that: In step S8, the collision time threshold is: Where v2 is the speed of the forklift. 5.An anti-collision system for forklift vehicles, characterized in that: The system includes an information collection module, a central control system, an audible and visual alarm device, and an execution control system; The information acquisition module includes multiple forklift sensors, a GPS submodule, a CAN submodule and an AI camera submodule: The GPS submodule is used to collect forklift location information; The CAN submodule is connected to a plurality of forklift sensor signals for collecting forklift status information; the forklift status information includes the speed, acceleration and heading angle information of the forklift; The AI ​​camera submodule includes a detection unit and a deep learning unit; the detection unit includes a radio detection device and a visual detection device, which are used to collect information about the surrounding environment of the forklift and the driving status information of the forklift driver; the information about the surrounding environment of the forklift includes status information of obstacle targets; the deep learning unit is used to execute the anti-collision warning method applicable to forklift operation vehicles according to any one of claims 1 to 4, determine whether there is a potential collision risk, and when there is a potential collision risk, output a warning signal according to the type of collision: The central control system includes an alarm submodule, a pre-pressurization submodule and an emergency brake submodule: The alarm submodule is used to send an alarm control signal to the sound and light alarm device according to the early warning signal; the sound and light alarm device is used to send an sound and light alarm according to the alarm control signal; The pre-pressurization submodule is used to pre-increase the oil pressure of the brake master cylinder according to the early warning signal, so as to obtain a greater deceleration in a shorter time during braking; The emergency brake submodule is used to determine whether the forklift driver takes correct collision avoidance operations within a given time according to the warning signal and the forklift driver's driving state information, and when the forklift driver does not take correct collision avoidance operations, calculate the emergency brake control amount and send it to the execution control system, and the emergency brake control amount includes throttle opening and brake pressure; The execution control system is used to adjust the opening of the throttle of the forklift engine and the brake pressure of the forklift brake system according to the emergency brake control amount to execute the emergency brake operation.

6. The anti-collision system for a forklift vehicle according to claim 5, characterized in that: The system also includes a user terminal module; The user terminal module is used to display the real-time status of the forklift itself, the real-time status of the forklift's surrounding environment and the real-time driving status of the forklift driver based on the forklift's position information, forklift status information, forklift surrounding environment information and forklift driver's driving status information; and is also used to display the real-time status of the warning based on the warning signal. 7.Anti-collision warning device for forklift operation vehicles, characterized in that: The device comprises the following modules: Module S1: Acquire forklift position information, forklift status information, forklift surrounding environment information and forklift driver driving status information; the forklift status information includes the speed, acceleration and heading angle information of the forklift; the forklift surrounding environment information includes the status information of obstacle targets; Module S2: converting the acquired forklift position information from longitude and latitude coordinates into XY coordinates in a rectangular coordinate system; Module S3: Calculate the relative position relationship between the forklift and the obstacle target; Module S4: Calculate the distance, relative speed and relative acceleration between the forklift and the obstacle target that meets the triggering conditions of the early warning algorithm as the collision trend judgment information; Module S5: Determine whether the forklift has a tendency to collide with an obstacle target based on the collision tendency judgment information: If it is determined that the forklift has a tendency to collide with the obstacle target, the process goes to module S6; Otherwise, there is no potential collision risk and the process ends; Module S6: Calculate the collision time required for the forklift to collide with the obstacle target; Module S7: Calculate the collision time threshold according to the forklift speed; Module S8: Determine whether the collision time required for the forklift to collide with the obstacle target is less than the collision time threshold: If it is less than the collision time threshold, there is a potential collision risk, a warning signal is output, and the process ends; Otherwise, there is no potential collision risk and the process ends.

8. A computer device comprising: A processor and a memory, characterized in that the memory is used to store executable instructions of the processor, and the processor is configured to execute the anti-collision warning method applicable to a forklift operating vehicle as described in any one of claims 1-4 by executing the executable instructions.

9. A computer storage medium, characterized in that The storage medium stores a computer program, and when the computer program is run, the anti-collision warning method applicable to a forklift operating vehicle according to any one of claims 1 to 4 is executed.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction is executed by a processor, the steps of the anti-collision warning method applicable to a forklift operating vehicle as described in any one of claims 1 to 4 are implemented.

Images