Unmanned driving path planning system based on machine learning

By introducing vehicle-road comparison module and vehicle protection module in the unmanned driving path planning system, the problem that the existing system cannot consider vehicle height and width information and cargo manned quality inspection is solved, and more accurate path planning and safety are achieved Drive.

CN119088000APending Publication Date: 2024-12-06JIANGSU HAILANJU SMART CITY TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410979353.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-22
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The existing unmanned driving path planning system based on machine learning cannot take into account vehicle height and width information, resulting in invalid path generation and inability to detect cargo or manned mass, posing safety hazards.

Method used

A system including map construction module, vehicle management module, vehicle road matching module, path planning module, vehicle road comparison module, vehicle protection module, obstacle avoidance module and deviation processing module was designed. The path height limit is limited to the width through the vehicle road comparison module. Comparing with vehicle information, the vehicle protection module uses pressure sensors to detect the mass of manned or loaded items, and alarms or adjusts the path if the conditions do not meet the conditions.

Benefits of technology

It improves the accuracy of path generation, ensures that the vehicle can pass the height and width limit conditions safely, and alarms when cargo or manned overweight, avoid safety hazards, and ensures that the vehicle can drive within a safe range.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119088000A_ABST
    Figure CN119088000A_ABST
Patent Text Reader

Abstract

The invention discloses an unmanned driving path planning system based on machine learning, and belongs to the technical field of unmanned driving, and the system comprises a main control center which comprises a map construction module, a vehicle management module, a vehicle-road matching module, a path planning module, a vehicle-road comparison module, a vehicle protection module, an obstacle avoidance module and a deviation processing module. The path generation module sends the generated path to the main control center, the main control center compares height limit or width limit conditions and the like on the generated path with information such as the height and the width of the vehicle, a feasible path is generated when the comparison is passed, and the path generation module generates a path again for comparison when the comparison is not passed until the path is generated when the comparison is passed; after the vehicle carries people or objects, a pressure sensor and the like on the vehicle send the mass of the carried people or the objects to the main control center, and when the weight of the carried people or the objects exceeds the maximum cargo capacity of the vehicle, a vehicle alarm gives an alarm.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of unmanned driving, and in particular relates to an unmanned driving path planning system based on machine learning. Background Art

[0002] An unmanned vehicle is a smart car that relies mainly on an intelligent driving system based on a computer system in the car to achieve unmanned driving. Unmanned vehicles integrate many artificial intelligence technologies such as automatic control, environmental interaction, and visual recognition. They are the product of the high development of computer science, pattern recognition, and intelligent control technology. They are also an important symbol of a country's scientific research strength and industrial level. They have broad application prospects in the fields of national defense and national economy. Unmanned vehicles are smart cars that sense the road environment through on-board sensor systems, automatically plan driving routes, and control vehicles to reach predetermined targets. It uses on-board sensors to sense the environment around the vehicle, and controls the steering and speed of the vehicle based on the road, vehicle position, and obstacle information obtained through perception, so that the vehicle can drive safely and reliably on the road.

[0003] The existing technology has the following problems:

[0004] 1. After planning a route, the existing unmanned driving path planning system based on machine learning cannot compare the planned route with information such as vehicle height and width. When a vehicle with height or width restrictions cannot pass on the planned route, the generated path will be invalid.

[0005] 2. The existing unmanned driving path planning system based on machine learning cannot detect the mass of the vehicle's cargo or passengers, which poses a safety hazard when the mass of the cargo or passengers exceeds the vehicle's maximum load capacity; Summary of the invention

[0006] In order to solve the problems raised in the above background technology, the present invention provides an unmanned driving path planning system based on machine learning, which has the characteristics of being able to compare and confirm the generated path with vehicle information and having a high path accuracy.

[0007] To achieve the above object, the present invention provides the following technical solutions: an unmanned driving path planning system based on machine learning, comprising a main control center, wherein the main control center comprises a map construction module, a vehicle management module, a vehicle-road matching module, a path planning module, a vehicle-road comparison module, a vehicle protection module, an obstacle avoidance module and a deviation processing module;

[0008] The map construction module uses GIS technology to construct a virtual map of the park;

[0009] The vehicle management module visualizes vehicle information and vehicle driving status;

[0010] The vehicle-route matching module is used to divide the vehicle paths and match the vehicle sub-paths with the delivery vehicles;

[0011] The path planning module obtains the shortest travel path based on vehicles and delivery points;

[0012] The vehicle-road comparison module is used by the path generation module to send the generated path to the main control center. The main control center compares the height or width limit conditions on the generated path with the vehicle height and width information. If the comparison passes, a feasible path is generated. If the comparison fails, the path generation module generates a path again for comparison until the comparison passes and a path is generated.

[0013] The vehicle protection module is used when the vehicle is loaded with people or cargo. The pressure sensor on the vehicle sends the weight of the people or cargo to the main control center. When the weight of the people or cargo exceeds the maximum cargo capacity of the vehicle, the vehicle alarm sounds. When the weight of the people or cargo does not exceed the maximum cargo capacity of the vehicle, the vehicle is locked and driven.

[0014] The obstacle avoidance module is used to obtain the path video and avoid the path obstacles according to the path video;

[0015] The deviation processing module determines whether the vehicle has deviated from the path and processes the path deviation.

[0016] Furthermore, the main control center stores information such as the width and height of the vehicle.

[0017] Furthermore, the vehicle is in an engine-off and powered-on state when the vehicle-road comparison is performed.

[0018] Furthermore, when the quality comparison is performed, the vehicle will not be locked if the comparison fails.

[0019] Furthermore, when the vehicle alarm sounds, after the cargo is unloaded, when the load is less than the maximum load of the vehicle, the vehicle alarm automatically turns off.

[0020] Compared with the prior art, the present invention has the following beneficial effects:

[0021] 1. The present invention sets a vehicle-road comparison module. The path generation module sends the generated path to the main control center. The main control center compares the height limit or width limit conditions on the generated path with the vehicle height and width information. When the comparison passes, a feasible path is generated. When the comparison fails, the path generation module generates a path again for comparison until the comparison passes and a path is generated.

[0022] 2. The present invention sets a vehicle protection module. After the vehicle is loaded with people or cargo, the pressure sensor on the vehicle sends the mass of the people or cargo to the main control center. When the weight of the people or cargo exceeds the maximum cargo capacity of the vehicle, the vehicle alarm sounds. When the weight of the people or cargo does not exceed the maximum cargo capacity of the vehicle, the vehicle is locked and driven. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a flowchart of the workflow of the present invention;

[0024] Figure 2 This is a flowchart of the vehicle-road comparison module of the present invention;

[0025] Figure 3 The flowchart of the vehicle protection module of the present invention is as follows; DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] See also Figure 1-3 , the present invention provides the following technical solutions: an unmanned driving path planning system based on machine learning, comprising a main control center, the main control center comprising a map construction module, a vehicle management module, a vehicle-road matching module, a path planning module, a vehicle-road comparison module, a vehicle protection module, an obstacle avoidance module and a deviation processing module;

[0028] The map construction module uses GIS technology to construct a virtual map of the park;

[0029] The vehicle management module visualizes vehicle information and vehicle driving status;

[0030] The vehicle-route matching module is used to divide the vehicle paths and match the vehicle sub-paths with the delivery vehicles;

[0031] The path planning module obtains the shortest travel path based on vehicles and delivery points;

[0032] The vehicle-road comparison module is used by the path generation module to send the generated path to the main control center. The main control center compares the height or width limit conditions on the generated path with the vehicle height and width information. If the comparison passes, a feasible path is generated. If the comparison fails, the path generation module generates a path again for comparison until the comparison passes and a path is generated.

[0033] The vehicle protection module is used when the vehicle is loaded with people or cargo. The pressure sensor on the vehicle sends the weight of the people or cargo to the main control center. When the weight of the people or cargo exceeds the maximum cargo capacity of the vehicle, the vehicle alarm sounds. When the weight of the people or cargo does not exceed the maximum cargo capacity of the vehicle, the vehicle is locked and driven.

[0034] The obstacle avoidance module is used to obtain the path video and avoid the path obstacles according to the path video;

[0035] The deviation processing module determines whether the vehicle has deviated from the path and processes the path deviation.

[0036] Furthermore, in the present invention, information such as the width and height of the vehicle is stored in the main control center.

[0037] By adopting the above technical solution, the main control center can easily compare information such as the width and height of the vehicle with the height and width limits on the generated path.

[0038] Furthermore, in the present invention, the vehicle is in a powered-on and ignition-off state when performing the vehicle-road comparison.

[0039] By adopting the above technical solution, the vehicle can supply power to the main control center when it is powered on, and at the same time avoid the vehicle from driving randomly on unknown paths during vehicle-road comparison.

[0040] Furthermore, in the present invention, when the quality comparison is performed, the vehicle will not be locked if the comparison fails.

[0041] By adopting the above technical solution, it is avoided that the personnel or goods are inconvenient to get off or unload due to overweight.

[0042] Furthermore, in the present invention, when the vehicle alarm sounds, after the cargo is unloaded, when the load is less than the maximum load of the vehicle, the vehicle alarm automatically turns off the alarm.

[0043] By adopting the above technical solution, it is avoided that the alarm is always on when the weight is not overloaded and causes sound and light pollution.

[0044] The working principle and usage process of the present invention: When the unmanned driving path planning system based on machine learning is used, the device is installed in a suitable position. The path generation module sends the path to the main control center after generation. The main control center compares the height limit or width limit conditions on the generated path with the vehicle height and width information. When the comparison passes, a feasible path is generated. When the comparison fails, the path generation module generates the path again for comparison until the comparison passes and the path is generated. After the vehicle is loaded with people or cargo, the pressure sensors on the vehicle send the mass of the people or cargo to the main control center. When the weight of the people or cargo exceeds the maximum cargo capacity of the vehicle, the vehicle alarm sounds. When the weight of the people or cargo does not exceed the maximum cargo capacity of the vehicle, the vehicle is locked and driven.

[0045] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An unmanned driving path planning system based on machine learning, comprising a main control center, characterized in that: The main control center includes a map construction module, a vehicle management module, a vehicle-road matching module, a path planning module, a vehicle-road comparison module, a vehicle protection module, an obstacle avoidance module and a deviation processing module; The map construction module uses GIS technology to construct a virtual map of the park; The vehicle management module visualizes vehicle information and vehicle driving status; The vehicle-route matching module is used to divide the vehicle paths and match the vehicle sub-paths with the delivery vehicles; The path planning module obtains the shortest travel path based on vehicles and delivery points; The vehicle-road comparison module is used by the path generation module to send the generated path to the main control center. The main control center compares the height or width limit conditions on the generated path with the vehicle height and width information. If the comparison passes, a feasible path is generated. If the comparison fails, the path generation module generates a path again for comparison until the comparison passes and a path is generated. The vehicle protection module is used when the vehicle is loaded with people or cargo. The pressure sensor on the vehicle sends the weight of the people or cargo to the main control center. When the weight of the people or cargo exceeds the maximum cargo capacity of the vehicle, the vehicle alarm sounds. When the weight of the people or cargo does not exceed the maximum cargo capacity of the vehicle, the vehicle is locked and driven. The obstacle avoidance module is used to obtain the path video and avoid the path obstacles according to the path video; The deviation processing module determines whether the vehicle has deviated from the path and processes the path deviation.

2. The unmanned driving path planning system based on machine learning according to claim 1, characterized in that: The main control center stores information such as the width and height of the vehicle.

3. The unmanned driving path planning system based on machine learning according to claim 1, characterized in that: The vehicle is in a powered-on state while performing the vehicle-road comparison.

4. The unmanned driving path planning system based on machine learning according to claim 1, characterized in that: When the quality comparison is performed, the vehicle will not be locked if the comparison fails.

5. The unmanned driving path planning system based on machine learning according to claim 1, characterized in that: When the vehicle alarm is triggered, the vehicle alarm automatically turns off when the load is less than the maximum load of the vehicle after the cargo is unloaded.