A control method and system for realizing L4-level cluster anti-collision port machines and a medium

Abstract

The application relates to a control method and system for realizing L4-level container truck anti-collision port machines and a medium, the method comprising the following steps: S1. A vehicle travels on a road, real-time image data information of the road is acquired based on a vehicle-mounted camera, real-time point cloud data information of the road is acquired based on a vehicle-mounted laser radar, and distance data information of an obstacle is acquired in real time based on a vehicle-mounted millimeter wave radar; S2. Based on the distance data information of the obstacle and the image data information of the road, a Gaussian distribution-based image pixel point probability distribution algorithm is used to represent the probability distribution of obstacle pixel points, and probability distribution data information of the obstacle pixel points is obtained. The application not only realizes real-time monitoring of the surrounding environment, timely identification of potential obstacles and reaction of the container truck through a high-precision environment perception system and an advanced decision algorithm, but also accelerates the cargo turnover speed, reduces the operation cost, and improves the overall operation efficiency of the port.

Description

Technical Field

[0001] This invention relates to the field of unmanned container truck technology, and in particular to a control method, system and medium for realizing L4 level container truck collision avoidance port machinery. Background Technology

[0002] With the continuous development of autonomous driving technology, various industries are being impacted. Port transportation is increasingly achieving automated management, and the application of unmanned trucks is becoming more widespread. However, given the complex port environment, unmanned trucks need to perform precise operations within these confined spaces, including loading, unloading, and turning. Due to their large size and high speed, coupled with dynamic interference from other port equipment, collisions are prone to occur. This not only affects operational efficiency but can also cause equipment damage and personnel injuries. 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 anti-collision port machinery for container trucks. Through a high-precision environmental perception system and advanced decision-making algorithms, the container truck can monitor the surrounding environment in real time, identify potential obstacles in a timely manner and react accordingly. In addition, it can speed up cargo turnover, reduce operating costs and improve the overall operational efficiency of the port.

[0004] To achieve the above and other related objectives, the present invention provides the following technical solution: a control method for implementing L4 level anti-collision port cranes for container trucks, the method comprising:

[0005] S1. As the vehicle travels on the road, it acquires real-time image data of the road based on the onboard camera, real-time point cloud data of the road based on the onboard lidar, and real-time distance data of obstacles based on the onboard millimeter-wave radar.

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

[0007] S3. Based on the probability distribution data of the obstacle pixels and the point cloud data of the road, construct a 3D obstacle detection model based on the point cloud, characterize the detection points of the obstacles, and obtain the obstacle detection point matrix data information;

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

[0009] Furthermore, in step S2, the characterization of 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 of the road and the distance data of the obstacles, establish a feature extraction function Q for road image pixels.

[0011]

[0012] Where x represents the image data of the road, y represents the distance data of the obstacle, and 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 obstacle image pixels of the road is constructed to obtain the feature matrix data information of the obstacle image pixels of the road.

[0013] S22. Based on the feature matrix data of the obstacle image pixels of the road, establish the probability distribution function W of the obstacle pixels.

[0014]

[0015] Where z represents the feature matrix data of the road obstacle image pixels, and 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 pixels, the probability distribution of the obstacle pixels is characterized to obtain the probability distribution data information of the obstacle pixels.

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

[0018]

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

[0020]

[0021] Where z represents the feature matrix data of the road obstacle image pixels.

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

[0023]

[0024] The constraint function f takes values ​​in the range (1,2).

[0025] Furthermore, in step S3, the construction of the point cloud-based 3D obstacle detection model and the characterization of the obstacle detection points include:

[0026] S31. Based on the probability distribution data of the obstacle pixels and the point cloud data of the road, establish a mapping function R between the obstacle pixels and the point cloud of the road.

[0027]

[0028] Where a represents the probability distribution data of obstacle pixels, b represents the point cloud data of the road, and δ1, δ2 and δ3 are constant parameters relating obstacle pixels to the point cloud of the road. The obstacle pixels and the point cloud of the road are fused to obtain the fused 3D data of the obstacle.

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

[0030]

[0031] Where c represents the fused 3D data information of the obstacle, and 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 for the relationship between the obstacle pixels and the road point cloud constant parameters δ1, δ2, and δ3 is,

[0034]

[0035] The constraint function g takes values ​​in the range of (2,3);

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

[0037]

[0038] The constraint function h takes values ​​in the range of (1,2).

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

[0040]

[0041] Where m is the obstacle detection point matrix data information, and η1, η2 and η3 are the anti-collision adaptive adjustment factors of unmanned trucks.

[0042] To achieve the above and other related objectives, the present invention also provides a control system for implementing a Level 4 truck collision avoidance port crane, including a computer device programmed or configured to perform the steps of any of the control methods for implementing a Level 4 truck collision avoidance port crane.

[0043] To achieve the above and other related objectives, the present invention also provides a computer-readable storage medium storing a computer program programmed or configured to perform any of the control methods for implementing L4 level truck collision avoidance port machinery as described in the present invention.

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

[0045] 1. This invention uses a Gaussian distribution-based image pixel probability distribution algorithm to characterize the probability distribution of obstacle pixels, and combines it with a point cloud-based 3D obstacle detection model to characterize the detection points of obstacles. Through a high-precision environmental perception system and advanced decision-making algorithms, container trucks can monitor the surrounding environment in real time, identify potential obstacles in a timely manner and react accordingly. This also speeds up cargo turnover, reduces operating costs, and improves the overall operational efficiency of ports.

[0046] 2. This invention controls the motion state of unmanned container trucks by establishing a collision avoidance control function F, 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 and promotes the progress and innovation of related technologies, laying a good foundation for subsequent technological development. Attached Figure Description

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

[0048] Figure 2 This is a flowchart illustrating the image pixel probability distribution algorithm based on Gaussian distribution of the present invention.

[0049] Figure 3 This is a schematic diagram illustrating the process of constructing a point cloud-based 3D obstacle detection model according to the present invention. Detailed Implementation

[0050] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0051] Example 1: As Figure 1 As shown, a control method for implementing L4 level anti-collision port cranes for container trucks is described, the method comprising:

[0052] S1. As the vehicle travels on the road, it acquires real-time image data of the road based on the onboard camera, real-time point cloud data of the road based on the onboard lidar, and real-time distance data of obstacles based on the onboard millimeter-wave radar.

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

[0054] S3. Based on the probability distribution data of the obstacle pixels and the point cloud data of the road, construct a 3D obstacle detection model based on the point cloud, characterize the detection points of the obstacles, and obtain the obstacle detection point matrix data information;

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

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

[0057] S21. Based on the image data of the road and the distance data of the obstacles, establish a feature extraction function Q for road image pixels.

[0058]

[0059] Where x represents the image data of the road, y represents the distance data of the obstacle, and 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 obstacle image pixels of the road is constructed to obtain the feature matrix data information of the obstacle image pixels of the road.

[0060] S22. Based on the feature matrix data of the obstacle image pixels of the road, establish the probability distribution function W of the obstacle pixels.

[0061]

[0062] Where z represents the feature matrix data of the road obstacle image pixels, and 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 pixels, the probability distribution of the obstacle pixels is characterized to obtain the probability distribution data information of the obstacle pixels.

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

[0065]

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

[0067]

[0068] Where z represents the feature matrix data of the road obstacle image pixels.

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

[0070]

[0071]

[0072] The constraint function f takes values ​​in the range (1,2).

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

[0074] S31. Based on the probability distribution data of the obstacle pixels and the point cloud data of the road, establish a mapping function R between the obstacle pixels and the point cloud of the road.

[0075]

[0076] Where a represents the probability distribution data of obstacle pixels, b represents the point cloud data of the road, and δ1, δ2 and δ3 are constant parameters relating obstacle pixels to the point cloud of the road. The obstacle pixels and the point cloud of the road are fused to obtain the fused 3D data of the obstacle.

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

[0078]

[0079] Where c represents the fused 3D data information of the obstacle, and 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 for the constant parameters δ1, δ2, and δ3 relating the obstacle pixels to the road point cloud is:

[0082]

[0083] The constraint function g takes values ​​in the range of (2,3);

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

[0085]

[0086] The constraint function h takes values ​​in the range of (1,2).

[0087] First, safety is significantly improved. Level 4 autonomous trucks are designed to achieve fully autonomous driving in specific environments, avoiding the risk of collisions caused by human error. Through a high-precision environmental perception system and advanced decision-making algorithms, the truck can monitor its surroundings in real time, promptly identify potential obstacles, and react accordingly. This technology reduces safety accidents caused by human factors, ensuring the safety of port operations. Second, operational efficiency is greatly improved. Traditional truck operation relies on manual driving, resulting in low efficiency and uncertain operation times. With the introduction of automation technology, the truck can optimize routes based on real-time data and planning algorithms, reducing transportation and waiting times. This efficiency improvement not only speeds up cargo turnover but also reduces operating costs and improves the overall operational efficiency of the port. Third, environmental adaptability is enhanced. The autonomous driving system of Level 4 trucks has strong environmental adaptability and can operate stably in various complex weather conditions and port environments. Through sensor fusion and machine learning technologies, the system can continuously learn and adapt to new environmental changes, improving the flexibility and reliability of the truck in actual operation. In addition, the introduction of testing systems promotes technological iteration and innovation. Through virtual simulation and field testing, shortcomings in the system can be effectively identified and improved in a timely manner. This continuous feedback mechanism not only improves product maturity but also drives technological advancement and innovation, laying a solid foundation for future technological development. Finally, it reduces environmental impact. The efficient operation of automated trucks helps reduce energy consumption caused by traffic congestion and operational delays, thereby lowering carbon emissions. Precise scheduling and operational control enable more rational planning of transportation processes, improving energy efficiency and facilitating the port's transformation towards green and sustainable development.

[0088] Example 2: Based on the control method for implementing L4 level container truck anti-collision port crane in Example 1, the present invention will be further explained and described below.

[0089] like Figure 1 As shown, a control method for implementing L4 level anti-collision port cranes for container trucks is described, the method comprising:

[0090] S1. As the vehicle travels on the road, it acquires real-time image data of the road based on the onboard camera, real-time point cloud data of the road based on the onboard lidar, and real-time distance data of obstacles based on the onboard millimeter-wave radar.

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

[0092] S3. Based on the probability distribution data of the obstacle pixels and the point cloud data of the road, construct a 3D obstacle detection model based on the point cloud, characterize the detection points of the obstacles, and obtain the obstacle detection point matrix data information;

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

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

[0095]

[0096] Where m is the obstacle detection point matrix data information, and η1, η2 and η3 are the anti-collision adaptive adjustment factors of unmanned trucks.

[0097] In this embodiment, the present invention provides a control system for implementing L4 level truck collision avoidance port cranes, including a computer device that is programmed or configured to perform the steps of any of the control methods for implementing L4 level truck collision avoidance port cranes.

[0098] First, a comprehensive simulation platform was established. By constructing a virtual port environment and integrating different sensor models, traffic flow models, and truck behavior models, large-scale simulation experiments could be conducted on a computer. This platform can simulate various complex operational scenarios, such as different weather conditions, traffic density, and emergencies. Simulation allows for rapid iteration, reducing the risks and costs in actual testing. Simultaneously, researchers can verify the effectiveness of collision avoidance algorithms in a safe virtual environment and analyze their performance under different conditions in real time. Second, a layered testing approach was adopted. The testing process was divided into three levels: functional testing, integration testing, and system testing. Functional testing focused on verifying the performance of individual sensors and algorithms, such as the detection accuracy and response time of radar, lidar, and cameras. Integration testing focused on the data fusion capabilities of multiple sensors and the accuracy of the decision-making system, ensuring efficient information transfer between different modules. Finally, system testing was conducted on the entire truck's autonomous driving system, simulating real-world operational scenarios and verifying the system's collision avoidance capabilities in complex environments. Furthermore, real-world datasets were used for testing. By collecting data from actual port operations, including traffic flow, collision events, and environmental changes, this data was used for model training and validation. The introduction of real-world data improved the model's accuracy, making it better suited to real-world application scenarios. Furthermore, machine learning and deep learning technologies are introduced. By training the trucks to perform under different conditions, the algorithm's decision-making ability is optimized. Reinforcement learning methods are employed to allow the system to learn through continuous simulation and feedback, gradually improving the intelligence level of the collision avoidance strategy. Finally, a multi-party collaborative verification mechanism is implemented. Port operators, equipment manufacturers, and academia are invited to participate in the design and verification of the test scheme, forming an effective feedback loop to continuously improve and optimize the test process. In summary, by establishing a comprehensive simulation platform, implementing a hierarchical testing method, utilizing real-world data, introducing intelligent algorithms, and conducting multi-party collaborative verification, the testing objectives for L4-level truck collision avoidance port machinery can be effectively achieved, promoting the further development of port automation technology.

[0099] The aim is to ensure the product's efficiency and safety. In terms of hardware design, the anti-collision port crane for container trucks needs to integrate multiple sensors, such as LiDAR, cameras, and ultrasonic sensors. The layout of these sensors requires careful design to ensure 360-degree blind-spot-free environmental perception. During manufacturing, sensor selection should consider their accuracy, response time, and environmental resistance, especially reliability under harsh weather conditions. The sensor installation process should ensure their stability and shock resistance to prevent loosening or damage in the complex port operating environment. The design of the data processing unit is also crucial; 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 utilize high-performance embedded computing modules combined with GPU acceleration to improve the efficiency of image processing and deep learning algorithms. During manufacturing, the circuit board design 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 various traffic scenarios. Employing machine learning-based algorithms can improve the system's adaptability 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. To support subsequent system updates and maintenance, the software architecture should feature a robust modular design, facilitating functional expansion and iteration. During the system integration and testing phases, the assembly of the entire system should adhere to rigorous quality control procedures. After integration, comprehensive functional and system testing, including stress testing and fault simulation testing, should be conducted to ensure the interoperability of each module. Testing should cover various scenarios, such as high-density traffic and complex weather conditions, to ensure system reliability. Environmental and safety considerations during production and manufacturing are equally important. In material selection, priority should be given to recyclable and environmentally friendly materials to meet the sustainable development requirements of modern manufacturing. Simultaneously, production processes should comply with relevant safety standards to ensure worker safety during manufacturing.

[0100] In this embodiment, the present invention also provides a computer-readable storage medium storing a computer program programmed or configured to perform any of the control methods for implementing L4 level truck collision avoidance port cranes.

[0101] Any references to memory, storage, database, or other media used in the embodiments provided in this 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. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0102] In summary, this invention not only enables container trucks to monitor their surroundings in real time, identify potential obstacles, and react promptly through a high-precision environmental perception system and advanced decision-making algorithms, but also accelerates cargo turnover, reduces operating costs, and improves the overall operational efficiency of ports.

[0103] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A control method for implementing L4 level collision avoidance port cranes for container trucks, characterized in that, The method includes: S1. As the vehicle travels on the road, it acquires real-time image data of the road based on the onboard camera, real-time point cloud data of the road based on the onboard lidar, and real-time distance data of obstacles based on the onboard millimeter-wave radar. S2. Based on the distance data of the obstacle and the image data of the road, the probability distribution of the obstacle pixels is characterized by an image pixel probability distribution algorithm based on Gaussian distribution, and the probability distribution data of the obstacle pixels is obtained. S3. Based on the probability distribution data of the obstacle pixels and the point cloud data of the road, construct a 3D obstacle detection model based on the point cloud, characterize the detection points of the obstacles, and obtain the obstacle detection point matrix data information; S4. Based on the detection point matrix data information of the obstacles, establish the anti-collision control function F of the unmanned truck, control the motion state of the unmanned truck, and output the anti-collision control data information of the unmanned truck.

2. The control method for implementing L4 level anti-collision port cranes for container trucks according to claim 1, characterized in that, In step S2, the process of characterizing the probability distribution of obstacle pixels using an image pixel probability distribution algorithm based on Gaussian distribution includes: S21. Based on the image data of the road and the distance data of the obstacles, establish a feature extraction function Q for road image pixels. Where x represents the image data of the road, y represents the distance data of the obstacle, and 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 obstacle image pixels of the road is constructed to obtain the feature matrix data information of the obstacle image pixels of the road. S22. Based on the feature matrix data of the obstacle image pixels of the road, establish the probability distribution function W of the obstacle pixels. Where z represents the feature matrix data of the road obstacle image pixels, and β1, β2 and β3 are the probability distribution difference factors of the obstacles; S23. Based on the probability distribution function W of the obstacle pixels, the probability distribution of the obstacle pixels is characterized to obtain the probability distribution data information of the obstacle pixels.

3. The control method for achieving L4 level anti-collision port cranes according to claim 2, characterized in that: The constraints for the obstacle image feature extraction factors α1, α2, and α3 of the road are as follows:

4. The control method for achieving L4 level anti-collision port cranes for container trucks according to claim 2, characterized in that: The probability distribution difference factors β1, β2, and β3 of the obstacle are, Where z represents the feature matrix data of the road obstacle image pixels.

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

6. The control method for implementing L4 level anti-collision port cranes for container trucks according to claim 1, characterized in that, In step S3, constructing a 3D obstacle detection model based on point clouds and characterizing the detection points of obstacles includes: S31. Based on the probability distribution data of the obstacle pixels and the point cloud data of the road, establish a mapping function R between the obstacle pixels and the point cloud of the road. Where a represents the probability distribution data of obstacle pixels, b represents the point cloud data of the road, and δ1, δ2 and δ3 are constant parameters relating obstacle pixels to the point cloud of the road. The obstacle pixels and the point cloud of the road are fused to obtain the fused 3D data of the obstacle. S32. Based on the fused 3D data information of the obstacles, construct the obstacle detection point function P. Where c represents the fused 3D data information of the obstacle, and 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 collision avoidance port crane according to claim 6, characterized in that: The constraint function g for the relationship between the obstacle pixels and the point cloud of the road, using constant parameters δ1, δ2, and δ3, is: The constraint function g takes values ​​in the range of (2,3); The constraint function h for the detection factors γ1, γ2, and γ3 of the obstacle is, The constraint function h takes values ​​in the range of (1,2).

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

9. A control system for implementing L4 level collision avoidance port cranes for container trucks, comprising computer equipment, characterized in that, The computer device is programmed or configured to perform the steps of the control method for implementing L4 level truck collision avoidance 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 that is programmed or configured to perform the control method for implementing L4 level truck collision avoidance port machinery as described in any one of claims 1 to 8.

Images