Control method and system for realizing anti-collision port machine of L4-level container truck and medium

Abstract

The invention relates to a control method and system for realizing an anti-collision port machine of an L4-level container truck and a medium, and the method comprises the steps: S1, enabling a vehicle to run on a road, obtaining the image data information of the road in real time based on a vehicle-mounted camera, obtaining the point cloud data information of the road in real time based on a vehicle-mounted laser radar, and obtaining the point cloud data information of the road; distance data information of an obstacle is acquired in real time based on a vehicle-mounted millimeter wave radar; and S2, on the basis of the distance data information of the obstacle and the image data information of the road, representing the probability distribution of the pixel points of the obstacle by adopting an image pixel point probability distribution algorithm based on Gaussian distribution to obtain the probability distribution data information of the pixel points of the obstacle. Through a high-precision environment sensing system and an advanced decision algorithm, the container truck can monitor the surrounding environment in real time, recognize potential obstacles in time and make a response, the cargo turnover speed is increased, the operation cost is reduced, and the overall operation efficiency of a port is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned container trucks, and in particular to a control method, system and medium for realizing L4 level container truck anti-collision port machinery. Background Art

[0002] With the continuous development of autonomous driving technology, it is constantly affecting the development of various industries. Among them, port transportation is constantly realizing automated management, and the application of unmanned container trucks in the transportation process is becoming more and more extensive. However, facing the complex environment of the port, unmanned container trucks need to perform precise operations in complex spaces, including loading and unloading and steering. Due to the large size and high speed of unmanned container trucks, coupled with the dynamic interference of other process equipment in the port, collision accidents are prone to occur. This not only affects the operating efficiency, but may also cause equipment damage and casualties. Summary of the invention

[0003] In view of the above problems, the present invention provides a control method, system and medium for realizing L4 level container truck anti-collision port machinery. Not only through the high-precision environmental perception system and advanced decision-making algorithm, the container truck can monitor the surrounding environment in real time, identify potential obstacles in time and respond, but also speed up the cargo turnover speed, reduce operating costs, and improve the overall operation efficiency of the port.

[0004] In order to achieve the above-mentioned purpose and other related purposes, the technical solution provided by the present invention is as follows: a control method for realizing L4 level container truck anti-collision port machinery, the method comprising:

[0005] S1. The vehicle is driving on the road, and the image data information of the road is obtained in real time based on the vehicle-mounted camera, the point cloud data information of the road is obtained in real time based on the vehicle-mounted laser radar, and the distance data information of the obstacle is obtained in real time based on the vehicle-mounted millimeter wave radar;

[0006] S2. Based on the distance data information of the obstacle and the image data information of the road, the probability distribution of the obstacle pixels is characterized by using an image pixel probability distribution algorithm based on Gaussian distribution to obtain probability distribution data information of the obstacle pixels;

[0007] S3. Based on the probability distribution data information of the obstacle pixel points and the point cloud data information of the road, a point cloud-based 3D obstacle detection model is constructed to characterize the obstacle detection points to obtain the obstacle detection point matrix data information;

[0008] S4. Based on the detection point matrix data information of the obstacle, establish the anti-collision control function F of the unmanned container truck, control the motion state of the unmanned container truck, and output the anti-collision control data information of the unmanned container truck.

[0009] Furthermore, in step S2, characterizing the probability distribution of obstacle pixels using an image pixel probability distribution algorithm based on Gaussian distribution includes:

[0010] S21. Based on the image data information of the road and the distance data information of the obstacle, a road image pixel feature extraction function Q is established.

[0011]

[0012] Wherein, x is the image data information of the road, y is the distance data information of the obstacle, α1, α2 and α3 are the feature extraction factors of the obstacle image of the road, the feature points of the obstacle image of the road are extracted and the feature matrix of the pixel points of the obstacle image of the road is constructed to obtain the feature matrix data information of the pixel points of the obstacle image of the road;

[0013] S22. Based on the characteristic matrix data information of the pixel points of the obstacle image of the road, a probability distribution function W of the obstacle pixel points is established.

[0014]

[0015] Among them, z is the characteristic matrix data information of the pixel points of the road obstacle image, β1, β2 and β3 are the probability distribution difference factors of the obstacles;

[0016] S23. Based on the probability distribution function W of the obstacle pixel point, the probability distribution of the obstacle pixel point is characterized to obtain probability distribution data information of the obstacle pixel point.

[0017] Furthermore, the constraints of the road obstacle image feature extraction factors α1, α2 and α3 are:

[0018]

[0019] Furthermore, the probability distribution difference factors β1, β2 and β3 of the obstacle are:

[0020]

[0021] Among them, z is the feature matrix data information of the pixel points of the road obstacle image.

[0022] Furthermore, the constraint function f of the probability distribution difference factors β1, β2 and β3 of the obstacle is,

[0023]

[0024] The value range of the constraint function f is (1,2).

[0025] Furthermore, in step S3, the step of constructing a point cloud-based 3D obstacle detection model and characterizing the obstacle detection points includes:

[0026] S31. Based on the probability distribution data information of the obstacle pixel points and the point cloud data information of the road, a mapping function R between the obstacle pixel points and the point cloud of the road is established.

[0027]

[0028] Among them, a is the probability distribution data information of the obstacle pixel point, b is the point cloud data information of the road, δ1, δ2 and δ3 are the constant parameters of the relationship between the obstacle pixel point and the road point cloud. The obstacle pixel point and the road point cloud are fused to obtain the fused 3D data information of the obstacle;

[0029] S32. Based on the fused 3D data information of the obstacle, construct a detection point function P of the obstacle,

[0030]

[0031] Among them, c is the fused 3D data information of the obstacle, γ1, γ2 and γ3 are the detection factors of the obstacle;

[0032] S33. Based on the monitoring point function P of the obstacle, the detection points of the obstacle are characterized to obtain the detection point matrix data information of the obstacle.

[0033] Furthermore, the constraint function g of the relationship constant parameters δ1, δ2 and δ3 between the obstacle pixel point and the road point cloud is,

[0034]

[0035] Among them, the value range of the constraint function g is (2,3);

[0036] The constraint function h of the obstacle detection factors γ1, γ2 and γ3 is,

[0037]

[0038] Among them, the value range of the constraint function h is (1,2).

[0039] Furthermore, the anti-collision control function F of the unmanned container truck is:

[0040]

[0041] Among them, m is the detection point matrix data information of the obstacle, and η1, η2 and η3 are the self-adaptive adjustment factors for unmanned container truck anti-collision.

[0042] In order to achieve the above-mentioned purpose and other related purposes, the present invention also provides a control system for implementing L4 level container truck anti-collision port crane, including a computer device, which is programmed or configured to execute any one of the steps of the control method for implementing L4 level container truck anti-collision port crane.

[0043] In order to achieve the above-mentioned purpose and other related purposes, the present invention also provides a computer-readable storage medium, which stores a computer program programmed or configured to execute any one of the control methods for realizing L4 level container truck anti-collision port machinery.

[0044] The present invention has the following positive effects:

[0045] 1. The present invention characterizes the probability distribution of obstacle pixels by adopting an image pixel probability distribution algorithm based on Gaussian distribution, and characterizes the detection points of obstacles by building a 3D obstacle detection model based on point cloud. Not only can the container truck monitor the surrounding environment in real time, identify potential obstacles in time and respond through a high-precision environmental perception system and advanced decision-making algorithms, but it also speeds up cargo turnover, reduces operating costs, and improves the overall operating efficiency of the port.

[0046] 2. The present invention controls the motion state of unmanned container trucks by establishing an anti-collision control function F of the unmanned container trucks, which not only reduces safety accidents caused by human factors and ensures the safety of port operations, but also improves the maturity of the product, promotes the progress and innovation of related technologies, and lays a good foundation for subsequent technological development. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0048] Figure 2 Schematic diagram of the process of the image pixel probability distribution algorithm based on Gaussian distribution of the present invention;

[0049] Figure 3 The figure is a schematic diagram of the process of constructing a point cloud-based 3D obstacle detection model according to the present invention. DETAILED DESCRIPTION

[0050] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0051] Example 1: Figure 1 As shown, a control method for realizing L4 level container truck anti-collision port machinery, the method comprising:

[0052] S1. The vehicle is driving on the road, and the image data information of the road is obtained in real time based on the vehicle-mounted camera, the point cloud data information of the road is obtained in real time based on the vehicle-mounted laser radar, and the distance data information of the obstacle is obtained in real time based on the vehicle-mounted millimeter wave radar;

[0053] S2. Based on the distance data information of the obstacle and the image data information of the road, the probability distribution of the obstacle pixels is characterized by using an image pixel probability distribution algorithm based on Gaussian distribution to obtain probability distribution data information of the obstacle pixels;

[0054] S3. Based on the probability distribution data information of the obstacle pixel points and the point cloud data information of the road, a point cloud-based 3D obstacle detection model is constructed to characterize the obstacle detection points to obtain the obstacle detection point matrix data information;

[0055] S4. Based on the detection point matrix data information of the obstacle, establish the anti-collision control function F of the unmanned container truck, control the motion state of the unmanned container truck, and output the anti-collision control data information of the unmanned container truck.

[0056] In this embodiment, if Figure 2 As shown, in step S2, the characterization of the probability distribution of obstacle pixels by using the image pixel probability distribution algorithm based on Gaussian distribution includes:

[0057] S21. Based on the image data information of the road and the distance data information of the obstacle, a road image pixel feature extraction function Q is established.

[0058]

[0059] Wherein, x is the image data information of the road, y is the distance data information of the obstacle, α1, α2 and α3 are the feature extraction factors of the obstacle image of the road, the feature points of the obstacle image of the road are extracted and the feature matrix of the pixel points of the obstacle image of the road is constructed to obtain the feature matrix data information of the pixel points of the obstacle image of the road;

[0060] S22. Based on the characteristic matrix data information of the pixel points of the obstacle image of the road, a probability distribution function W of the obstacle pixel points is established.

[0061]

[0062] Among them, z is the characteristic matrix data information of the pixel points of the road obstacle image, β1, β2 and β3 are the probability distribution difference factors of the obstacles;

[0063] S23. Based on the probability distribution function W of the obstacle pixel point, the probability distribution of the obstacle pixel point is characterized to obtain probability distribution data information of the obstacle pixel point.

[0064] In this embodiment, the constraints of the road obstacle image feature extraction factors α1, α2 and α3 are:

[0065]

[0066] In this embodiment, the probability distribution difference factors β1, β2 and β3 of the obstacles are:

[0067]

[0068] Among them, z is the feature matrix data information of the pixel points of the road obstacle image.

[0069] In this embodiment, the constraint function f of the probability distribution difference factors β1, β2 and β3 of the obstacle is,

[0070]

[0071]

[0072] The value range of the constraint function f is (1,2).

[0073] In this embodiment, if Figure 3 As shown, in step S3, the construction of a point cloud-based 3D obstacle detection model and characterization of obstacle detection points include:

[0074] S31. Based on the probability distribution data information of the obstacle pixel points and the point cloud data information of the road, a mapping function R between the obstacle pixel points and the point cloud of the road is established.

[0075]

[0076] Among them, a is the probability distribution data information of the obstacle pixel point, b is the point cloud data information of the road, δ1, δ2 and δ3 are the constant parameters of the relationship between the obstacle pixel point and the road point cloud. The obstacle pixel point and the road point cloud are fused to obtain the fused 3D data information of the obstacle;

[0077] S32. Based on the fused 3D data information of the obstacle, construct a detection point function P of the obstacle,

[0078]

[0079] Among them, c is the fused 3D data information of the obstacle, γ1, γ2 and γ3 are the detection factors of the obstacle;

[0080] S33. Based on the monitoring point function P of the obstacle, the detection points of the obstacle are characterized to obtain the detection point matrix data information of the obstacle.

[0081] In this embodiment, the constraint function g of the relationship constant parameters δ1, δ2 and δ3 between the obstacle pixel point and the road point cloud is:

[0082]

[0083] Among them, the value range of the constraint function g is (2,3);

[0084] The constraint function h of the obstacle detection factors γ1, γ2 and γ3 is,

[0085]

[0086] Among them, the value range of the constraint function h is (1,2).

[0087] First, safety is significantly improved. L4-level autonomous trucks are designed to achieve fully autonomous driving in specific environments, avoiding collision risks caused by human error. Through high-precision environmental perception systems and advanced decision-making algorithms, trucks can monitor the surrounding environment in real time, identify potential obstacles in a timely manner and respond. This technology reduces safety accidents caused by human factors and ensures the safety of port operations. Secondly, operating efficiency is greatly improved. Traditional truck operations rely on manual driving, which has problems of low efficiency and uncertain operation time. Through the introduction of automation technology, trucks can optimize routes based on real-time data and planning algorithms, reduce transportation time and waiting time. This efficiency improvement not only speeds up cargo turnover, but also reduces operating costs and improves the overall operating efficiency of ports. Furthermore, environmental adaptability is enhanced. The autonomous driving system that realizes L4-level trucks has strong environmental adaptability and can operate stably in various complex weather conditions and port environments. Through sensor fusion and machine learning technology, the system can continuously learn and adapt to new environmental changes, improving the flexibility and reliability of trucks in actual operations. In addition, the introduction of the test system promotes technological iteration and innovation. Through virtual simulation and field testing, deficiencies in the system can be effectively identified and improved in a timely manner. This continuous feedback mechanism not only improves the maturity of the product, but also promotes the progress and innovation of related technologies, laying a good foundation for subsequent technological development. Finally, the impact on the environment is reduced. The efficient operation of automated container trucks helps to reduce energy consumption caused by traffic congestion and operation delays, thereby reducing carbon emissions. Through precise scheduling and operation control, the transportation process can be planned more reasonably, energy efficiency can be improved, and the port can be transformed into green and sustainable development.

[0088] Embodiment 2: Based on the control method for realizing L4 level container truck anti-collision port machinery in Embodiment 1, the present invention is further illustrated and described below.

[0089] like Figure 1 As shown, a control method for realizing L4 level container truck anti-collision port machinery, the method comprising:

[0090] S1. The vehicle is driving on the road, and the image data information of the road is obtained in real time based on the vehicle-mounted camera, the point cloud data information of the road is obtained in real time based on the vehicle-mounted laser radar, and the distance data information of the obstacle is obtained in real time based on the vehicle-mounted millimeter wave radar;

[0091] S2. Based on the distance data information of the obstacle and the image data information of the road, the probability distribution of the obstacle pixels is characterized by using an image pixel probability distribution algorithm based on Gaussian distribution to obtain probability distribution data information of the obstacle pixels;

[0092] S3. Based on the probability distribution data information of the obstacle pixel points and the point cloud data information of the road, a point cloud-based 3D obstacle detection model is constructed to characterize the obstacle detection points to obtain the obstacle detection point matrix data information;

[0093] S4. Based on the detection point matrix data information of the obstacle, establish the anti-collision control function F of the unmanned container truck, control the motion state of the unmanned container truck, and output the anti-collision control data information of the unmanned container truck.

[0094] In this embodiment, the anti-collision control function F of the unmanned container truck is:

[0095]

[0096] Among them, m is the detection point matrix data information of the obstacle, and η1, η2 and η3 are the self-adaptive adjustment factors for unmanned container truck anti-collision.

[0097] In this embodiment, the present invention provides a control system for implementing L4 level container truck anti-collision port machinery, including a computer device, which is programmed or configured to execute any one of the steps of the control method for implementing L4 level container truck anti-collision port machinery.

[0098] First, a comprehensive simulation platform is established. By building a virtual port environment and integrating different sensor models, traffic flow models, and container truck behavior models, large-scale simulation experiments can be carried out on computers. This platform can simulate various complex operating scenarios, such as different weather conditions, traffic density, and emergencies. Simulation can be quickly iterated, reducing the risks and costs in actual testing. At the same time, researchers can verify the effectiveness of the anti-collision algorithm in a safe virtual environment and analyze its performance in real time under different conditions. Secondly, a hierarchical testing method is used. The testing process is divided into three levels: functional testing, integration testing, and system testing. Functional testing focuses on verifying the performance of individual sensors and algorithms, such as the detection accuracy and response time of radar, lidar, and camera. Integration testing focuses on the data fusion capabilities of multiple sensors and the accuracy of the decision-making system to ensure the efficient transmission of information between different modules. Finally, the system test is carried out on the entire container truck's autonomous driving system, simulating real operating scenarios and verifying the system's anti-collision capabilities in complex environments. In addition, actual data sets are used for testing. By collecting data from actual port operations, including traffic flow, collision events, and environmental changes, these data are used for model training and verification. The introduction of real data can improve the accuracy of the model and make it better adapt to actual application scenarios. In addition, machine learning and deep learning technologies are introduced. By training the performance of container trucks in different situations, the decision-making ability of the algorithm is optimized. The reinforcement learning method is adopted to enable the system to learn in continuous simulation and feedback, and gradually improve the intelligence level of the anti-collision strategy. Finally, a multi-party collaborative verification mechanism is developed. Invite port operators, equipment manufacturers and academia to participate in the design and verification of test plans to form an effective feedback loop and continuously improve and optimize the test process. In summary, by establishing a comprehensive simulation platform, implementing a layered testing method, using actual data, introducing intelligent algorithms and multi-party collaborative verification, the test goals of L4-level container truck anti-collision port machinery can be effectively achieved, and the further development of port automation technology can be promoted.

[0099] Aims to ensure the efficiency and safety of the product. In terms of hardware design, container truck anti-collision port machinery needs to integrate a variety of sensors, such as lidar, cameras, ultrasonic sensors, etc. The layout of these sensors needs to be carefully designed to ensure 360-degree environmental perception without blind spots. During the manufacturing process, the selection of sensors should take into account their accuracy, response time and environmental resistance, especially reliability under severe weather conditions. The installation process of the sensor should ensure its stability and seismic resistance to avoid loosening or damage in the complex operating environment of the port. The design of the data processing unit is also key. The container truck needs to be equipped with a powerful computing platform for real-time processing of sensor data and decision-making. This part can use high-performance embedded computing modules combined with GPU acceleration to improve the efficiency of image processing and deep learning algorithms. During the manufacturing process, the design of the circuit board should ensure high signal integrity and low latency to avoid information loss during data transmission. In terms of software development, the implementation of the anti-collision algorithm needs to consider a variety of traffic scenarios. The use of machine learning-based algorithms can improve the adaptability of the system in dynamic environments. The software development process should include multiple rounds of testing and verification to ensure the stability and accuracy of the algorithm under different conditions. In order to support subsequent system updates and maintenance, the software architecture should have a good modular design to facilitate functional expansion and iteration. During the system integration and testing phase, the assembly of the entire system should follow a strict quality control process. After integration, comprehensive functional testing and system testing, including stress testing and fault simulation testing, are carried out to ensure the coordination between various modules. The test should cover a variety of scenarios, such as high-density traffic, complex weather, etc., to ensure the reliability of the system. Environmental protection and safety considerations in the production and manufacturing process are equally important. In terms of material selection, recyclable and environmentally friendly materials are given priority to meet the sustainable development requirements of modern manufacturing. At the same time, the production process should follow relevant safety standards to ensure the safety of workers during the manufacturing process.

[0100] In this embodiment, the present invention further provides a computer-readable storage medium storing a computer program programmed or configured to execute any one of the control methods for realizing L4 level container truck anti-collision port machinery.

[0101] Any reference to memory, storage, database or other media used in the embodiments provided in the present application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM) and memory bus dynamic RAM (RDRAM).

[0102] In summary, the present invention not only enables container trucks to monitor the surrounding environment in real time, identify potential obstacles in a timely manner and respond through a high-precision environmental perception system and advanced decision-making algorithms, but also speeds up cargo turnover, reduces operating costs, and improves the overall operating efficiency of the port.

[0103] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A control method for realizing L4 level container truck anti-collision port machinery, characterized in that: The method comprises: S1. The vehicle is driving on the road, and the image data information of the road is obtained in real time based on the vehicle-mounted camera, the point cloud data information of the road is obtained in real time based on the vehicle-mounted laser radar, and the distance data information of the obstacle is obtained in real time based on the vehicle-mounted millimeter wave radar; S2. Based on the distance data information of the obstacle and the image data information of the road, the probability distribution of the obstacle pixels is characterized by using an image pixel probability distribution algorithm based on Gaussian distribution to obtain probability distribution data information of the obstacle pixels; S3. Based on the probability distribution data information of the obstacle pixel points and the point cloud data information of the road, a point cloud-based 3D obstacle detection model is constructed to characterize the obstacle detection points to obtain the obstacle detection point matrix data information; S4. Based on the detection point matrix data information of the obstacle, establish the anti-collision control function F of the unmanned container truck, control the motion state of the unmanned container truck, and output the anti-collision control data information of the unmanned container truck.

2. The control method for realizing L4 level container truck anti-collision port machinery according to claim 1 is characterized in that: In step S2, characterizing the probability distribution of obstacle pixels by using an image pixel probability distribution algorithm based on Gaussian distribution includes: S21. Based on the image data information of the road and the distance data information of the obstacle, a road image pixel feature extraction function Q is established. Wherein, x is the image data information of the road, y is the distance data information of the obstacle, α1, α2 and α3 are the feature extraction factors of the obstacle image of the road, the feature points of the obstacle image of the road are extracted and the feature matrix of the pixel points of the obstacle image of the road is constructed to obtain the feature matrix data information of the pixel points of the obstacle image of the road; S22. Based on the characteristic matrix data information of the pixel points of the obstacle image of the road, a probability distribution function W of the obstacle pixel points is established. Among them, z is the characteristic matrix data information of the pixel points of the road obstacle image, β1, β2 and β3 are the probability distribution difference factors of the obstacles; S23. Based on the probability distribution function W of the obstacle pixel point, the probability distribution of the obstacle pixel point is characterized to obtain probability distribution data information of the obstacle pixel point.

3. The control method for realizing L4 level container truck anti-collision port machinery according to claim 2 is characterized in that: The constraints of the road obstacle image feature extraction factors α1, α2 and α3 are:

4. The control method for realizing L4 level container truck anti-collision port machinery according to claim 2 is characterized in that: The probability distribution difference factors β1, β2 and β3 of the obstacles are: Among them, z is the feature matrix data information of the pixel points of the road obstacle image.

5. The control method for realizing L4 level container truck anti-collision port machinery according to claim 2 is characterized in that: The constraint function f of the probability distribution difference factors β1, β2 and β3 of the obstacle is, The value range of the constraint function f is (1,2).

6. The control method for realizing L4 level container truck anti-collision port machinery according to claim 1 is characterized in that: In step S3, the step of constructing a point cloud-based 3D obstacle detection model and characterizing the obstacle detection points includes: S31. Based on the probability distribution data information of the obstacle pixel points and the point cloud data information of the road, a mapping function R between the obstacle pixel points and the point cloud of the road is established. Among them, a is the probability distribution data information of the obstacle pixel point, b is the point cloud data information of the road, δ1, δ2 and δ3 are the constant parameters of the relationship between the obstacle pixel point and the road point cloud. The obstacle pixel point and the road point cloud are fused to obtain the fused 3D data information of the obstacle; S32. Based on the fused 3D data information of the obstacle, construct a detection point function P of the obstacle, Among them, c is the fused 3D data information of the obstacle, γ1, γ2 and γ3 are the detection factors of the obstacle; S33. Based on the monitoring point function P of the obstacle, the detection points of the obstacle are characterized to obtain the detection point matrix data information of the obstacle.

7. The control method for realizing L4 level container truck anti-collision port machinery according to claim 6 is characterized in that: The constraint function g of the relationship constant parameters δ1, δ2 and δ3 between the obstacle pixel point and the road point cloud is: Among them, the value range of the constraint function g is (2,3); The constraint function h of the obstacle detection factors γ1, γ2 and γ3 is, Among them, the value range of the constraint function h is (1,2).

8. The control method for realizing L4 level container truck anti-collision port machinery according to claim 1, characterized in that: The anti-collision control function F of the unmanned container truck is: Among them, m is the detection point matrix data information of the obstacle, and η1, η2 and η3 are the self-adaptive adjustment factors for unmanned container truck anti-collision.

9. A control system for realizing L4 level container truck anti-collision port machinery, including computer equipment, characterized in that: The computer device is programmed or configured to execute the steps of the control method for realizing L4 level container truck anti-collision port machinery as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer readable storage medium stores a computer program programmed or configured to execute the control method for realizing L4 level container truck anti-collision port machinery according to any one of claims 1 to 8.

Images