An unmanned truck neutral steering intelligent adjustment system and control method

Abstract

The application discloses an unmanned truck neutral steering intelligent adjusting system, which comprises a truck box and a neutral steering control system; the truck box comprises a box plate, a load box tray, a load box and a moving device, the moving device is in transmission connection with the load box tray so as to move the load box tray and the load box together; the neutral steering control system comprises a sensor and a whole vehicle controller, the whole vehicle controller comprises a neural network model, the neural network model is used for comparing data measured by the sensor with judgment data after calculation, and outputting an expected position of the load box meeting a neutral steering condition, and the moving device moves the load box to the expected position according to the received expected data. When the truck is steering, the front and back positions of the load box can be automatically adjusted according to the weight of the goods and the driver and passengers, so that the truck meets the neutral steering condition.

Description

Technical Field

[0001] This invention belongs to the field of autonomous driving technology, and in particular relates to an intelligent neutral steering adjustment system and control method for autonomous trucks. Background Technology

[0002] The steering characteristics of a vehicle have a significant impact on its handling stability, ride comfort, and safety. Based on the vehicle's steady-state steering response characteristics, vehicle steering can be categorized into understeer, neutral steering, and oversteer, and its characteristics are related to the vehicle's center of gravity position. The point of application of the lateral force that causes the front and rear wheels to produce the same slip angle is called the neutral steering point. When the vehicle's center of gravity coincides with the neutral steering point, the vehicle meets the neutral steering condition, and its turning radius is independent of the vehicle's speed. This represents an ideal state of vehicle steering characteristics, which can greatly improve the vehicle's handling stability, ride comfort, and safety.

[0003] The center of gravity of a truck is affected by the vehicle structure, cargo weight, and driver weight and number of passengers. Traditional trucks have a fixed and non-adjustable structure; when the cargo weight and driver conditions change, the truck's center of gravity shifts. Therefore, traditional trucks cannot guarantee that their steering characteristics remain neutral throughout operation.

[0004] The invention patent with authorization publication number CN107380273B, entitled "A Neutral Steering-Based Electric Vehicle Center of Gravity Adjustment Device and Method," proposes a neutral steering-based electric vehicle center of gravity adjustment device. This device adjusts the position of the electric vehicle's power motor, thereby changing the vehicle's center of gravity position and achieving neutral steering. However, because trucks have a large cargo weight, their center of gravity position is primarily affected by the position of the cargo; therefore, trucks cannot achieve neutral steering by adjusting the position of the vehicle's power source. Summary of the Invention

[0005] The purpose of this invention is to provide an intelligent control method for neutral steering of unmanned trucks, which solves the problems mentioned in the background art.

[0006] To achieve the above objectives, the technical solution adopted by the present invention is: an intelligent control method for neutral steering of an unmanned truck, comprising a truck cargo box and a neutral steering control system;

[0007] The truck cargo box includes a cargo box panel, a cargo box pallet, a cargo box, and a moving device. The cargo box panel is fixedly installed. The cargo box pallet is movably connected to the cargo box panel along the length of the truck. The cargo box is fixedly connected to the cargo box pallet. The moving device is throttle-connected to the cargo box pallet so that the cargo box pallet and the cargo box move together.

[0008] The neutral steering control system includes sensors and a vehicle controller. The sensors detect current vehicle information and transmit it to the vehicle controller. The vehicle controller includes a neural network model, which is configured with desired positions and decision data for the cargo box under various conditions. The neural network model calculates the data measured by the sensors, compares it with the decision data, and outputs the desired position of the cargo box that meets the neutral steering conditions. The moving device moves the cargo box to the desired position based on the received desired data.

[0009] Based on the above scheme and as a preferred embodiment of the above scheme, the mobile device further includes a drive motor, a drive wheel, a drive locking mechanism, and a microcontroller. The drive locking mechanism is disposed on the drive wheel to control the locking of the drive wheel, and the drive locking mechanism is connected to the microcontroller for control.

[0010] Based on the above scheme and as a preferred embodiment of the above scheme, the sensors include a cargo box pressure sensor, a cargo box position sensor, a tire pressure sensor, a seat pressure sensor, and a slope sensor.

[0011] Based on the above scheme and as a preferred embodiment of the above scheme, the determination data includes the tire pressure ratio of the left front wheel to the right front wheel, the tire pressure ratio of the left rear wheel to the right rear wheel, the tire pressure ratio of the left front wheel to the left rear wheel, and the tire pressure ratio of the right front wheel to the right rear wheel.

[0012] Based on the above scheme and as a preferred embodiment of the above scheme, the tire pressure ratio of the left front wheel to the right front wheel and the tire pressure ratio of the left rear wheel to the right rear wheel at the desired position is 1, and the tire pressure ratio of the left front wheel to the left rear wheel is equal to the tire pressure ratio of the right front wheel to the right rear wheel.

[0013] Based on the above scheme and as a preferred embodiment of the above scheme, the tire pressure ratio of the left front wheel to the left rear wheel and the tire pressure ratio of the right front wheel to the right rear wheel are equal to the sum of the lateral stiffness of the tires on both sides of the front axle divided by the sum of the lateral stiffness of the tires on both sides of the rear axle.

[0014] Based on the above scheme and as a preferred embodiment of the above scheme, the determination data also includes the weight of the goods and / or the weight of the driver and passengers.

[0015] Based on the above scheme and as a preferred embodiment of the above scheme, the slope sensor is an inertial measurement unit (IMU).

[0016] Based on the above scheme and as a preferred embodiment of the above scheme, the cargo box panel is provided with guide rails, and the cargo box tray is movably connected to the guide rails.

[0017] Another objective of this invention is to provide an intelligent control method for neutral steering of an unmanned truck, comprising the following steps:

[0018] S1. Activate the neutral steering control system when the truck turns;

[0019] S2. The sensor monitors the current information of the vehicle and transmits the information to the vehicle controller. The vehicle controller includes a neural network model, in which the desired position of the cargo box under various conditions is set.

[0020] S3. The neural network model compares the collected sensor information with the set judgment data and outputs the expected position of the cargo box that meets the neutral steering condition. The neural network model is connected to the power unit control to send control commands to the moving device.

[0021] S4. The mobile device receives control commands and controls the cargo container to move to the desired location.

[0022] S5. The neutral steering control system conditions are met, and the vehicle has met the neutral steering conditions.

[0023] The beneficial effects of this invention are as follows:

[0024] 1. When a truck is turning, the present invention can automatically adjust the front and rear position of the cargo box according to the weight of the cargo and the driver and passengers, so that the truck meets the neutral steering conditions, realizes the neutral steering of the truck under different cargo and driver conditions, and improves the handling stability, comfort and safety of the truck.

[0025] 2. This invention determines the desired position of the cargo box by the tire pressure ratio between the tires. While adjusting the position of the truck's center of gravity, it makes the load distribution of each tire and the front and rear axles of the truck more reasonable, thereby improving the service life of the truck.

[0026] 3. This invention only requires adjusting the position of the cargo to achieve neutral steering of the truck, without changing the vehicle chassis structure, thus improving production efficiency. Attached Figure Description

[0027] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0028] Figure 1 This is a schematic diagram of the structural composition of the present invention.

[0029] Figure 2 This is a flowchart of the control method of the present invention.

[0030] Figure 3 Flowchart of data acquisition for a 2D neural network model. Detailed Implementation

[0031] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0032] In the description of this invention, it should be understood that the terms "upper", "lower", "front", "rear", "left", "right", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0033] As attached Figure 1 To be continued Figure 3 As shown, an intelligent neutral steering adjustment system for an unmanned truck includes a truck cargo box and a neutral steering control system.

[0034] The truck cargo box includes a cargo box panel, a cargo box pallet, a cargo box, and a moving device. The cargo box panel is fixedly installed. The cargo box pallet is movably connected to the cargo box panel along the length of the truck. The cargo box is fixedly connected to the cargo box pallet. The moving device is throttle-connected to the cargo box pallet so that the cargo box pallet and the cargo box move together. In this way, the truck cargo box can change the center of gravity of the entire truck by moving the cargo box.

[0035] The neutral steering control system includes sensors and a vehicle controller. The sensors detect current vehicle information and transmit it to the vehicle controller. The vehicle controller includes a neural network model, which is configured with desired positions and decision data for the cargo box under various conditions. The neural network model calculates the data measured by the sensors, compares it with the decision data, and outputs the desired position of the cargo box that meets the neutral steering conditions. The moving device moves the cargo box to the desired position based on the received desired data.

[0036] The neural network model can be a three-layer BP neural network structure, consisting of an input layer, a hidden layer, and an output layer. The neural network model compares the truck's current information during turning with pre-set decision data and controls the moving device to move the cargo box to the desired position. During truck turning, the fore-and-aft position of the cargo box can be automatically adjusted according to the weight of the cargo and passengers, thus enabling the truck to meet neutral turning conditions. This achieves neutral turning for trucks under different cargo and driver conditions, improving the truck's handling stability, comfort, and safety.

[0037] The mobile device also includes a drive motor, a drive wheel, a drive locking mechanism, and a microcontroller. The drive locking mechanism is located on the drive wheel to control the locking of the drive wheel, and the drive locking mechanism is connected to the microcontroller for control.

[0038] The sensors include a cargo box pressure sensor, a cargo box position sensor, a tire pressure sensor, a seat pressure sensor, and a slope sensor.

[0039] The determination data includes the tire pressure ratios of the left front tire to the right front tire, the left rear tire to the right rear tire, the left front tire to the left rear tire, and the right front tire to the right rear tire. The desired tire pressure ratios for the left front tire to the right front tire and the left rear tire to the right rear tire are 1, and the left front tire to the left rear tire ratio is equal to the right front tire to the right rear tire ratio. The left front tire to the left rear tire ratio and the right front tire to the right rear tire ratio are equal to the sum of the lateral stiffness of the tires on both sides of the front axle divided by the sum of the lateral stiffness of the tires on both sides of the rear axle. Determining the desired position of the cargo box by adjusting the tire pressure ratios between the tires allows for a more reasonable distribution of load on the tires and front and rear axles, while simultaneously adjusting the truck's center of gravity, thus improving the truck's service life.

[0040] The determination data also includes the weight of the cargo and / or the weight of the driver and passengers, which can more accurately determine the desired location. The slope sensor is an inertial measurement unit (IMU). The cargo box is equipped with guide rails, and the cargo box is movably connected to the guide rails, which ensure that the cargo box can only move along the length of the truck.

[0041] This invention also provides an intelligent control method for neutral steering of an unmanned truck, comprising the following steps:

[0042] S1. Activate the neutral steering control system when the truck turns;

[0043] S2. The sensor monitors the current information of the vehicle and transmits the information to the vehicle controller. The vehicle controller includes a neural network model, in which the desired position of the cargo box under various conditions is set.

[0044] S3. The neural network model compares the collected sensor information with the set judgment data and outputs the expected position of the cargo box that meets the neutral steering condition. The neural network model is connected to the power unit control to send control commands to the moving device.

[0045] S4. The mobile device receives control commands and controls the cargo container to move to the desired location.

[0046] S5. The neutral steering control system conditions are met, and the vehicle has met the neutral steering conditions.

[0047] The desired positions of cargo containers under various conditions set in the neural network model can be obtained through the following methods:

[0048] S301: Start collecting data.

[0049] S302: Loading cargo.

[0050] S303: The vehicle controller sends control commands to the microcontroller inside the cargo box pallet to move the cargo box to a designated position for data acquisition.

[0051] S304: The system receives information from each sensor, calculates and obtains a set of training data.

[0052] After completing the above calculations, a set of training data is obtained, and its input layer data is as follows:

[0053] The expected tire pressure ratio of each wheel of the vehicle, the mass of each driver, and the mass of each cargo box plus the cargo inside; its output layer data is:

[0054] The actual location of each cargo container.

[0055] S305: Determine whether the data collection for the currently loaded goods has been completed. If it has been completed, proceed to step S306; otherwise, proceed to step S303.

[0056] The criteria for judgment are as follows: if the number of data sets corresponding to different cargo container positions for the current quality of goods exceeds M, then the data collection of the currently loaded goods has been completed; otherwise, it has not been completed, where M is a positive integer.

[0057] S306: Determine whether all data collection has been completed. If it has been completed, proceed to step S308; otherwise, proceed to step S307.

[0058] The criteria for judgment are as follows: if more than N sets of data on goods of different qualities have been collected, then all data collection has been completed; otherwise, it is considered incomplete.

[0059] S307: Reloading cargo of different weights.

[0060] S308: Data collection complete.

[0061] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An intelligent neutral steering adjustment system for an unmanned truck, characterized in that: Including the truck bed and neutral steering control system; The truck cargo box includes a cargo box panel, a cargo box pallet, a cargo box, and a moving device. The cargo box panel is fixedly installed. The cargo box pallet is movably connected to the cargo box panel along the length of the truck. The cargo box is fixedly connected to the cargo box pallet. The moving device is throttle-connected to the cargo box pallet so that the cargo box pallet and the cargo box move together. The neutral steering control system includes sensors and a vehicle controller. The sensors are used to detect current vehicle information and transmit the information to the vehicle controller. The vehicle controller includes a neural network model, which is configured with the desired position and judgment data of the cargo box under various conditions. The neural network model is used to calculate the data measured by the sensors, compare it with the judgment data, and output the desired position of the cargo box that meets the neutral steering conditions. The moving device moves the cargo box to the desired position according to the received desired data. The determination data includes the tire pressure ratio of the left front tire to the right front tire, the tire pressure ratio of the left rear tire to the right rear tire, the tire pressure ratio of the left front tire to the left rear tire, and the tire pressure ratio of the right front tire to the right rear tire. The tire pressure ratios of the left front wheel to the right front wheel and the left rear wheel to the right rear wheel at the desired position are 1, and the tire pressure ratio of the left front wheel to the left rear wheel is equal to the tire pressure ratio of the right front wheel to the right rear wheel. The tire pressure ratio of the left front wheel to the left rear wheel and the tire pressure ratio of the right front wheel to the right rear wheel are equal to the sum of the lateral stiffness of the tires on both sides of the front axle divided by the sum of the lateral stiffness of the tires on both sides of the rear axle.

2. The unmanned truck neutral steering intelligent adjustment system as described in claim 1, characterized in that: The mobile device also includes a drive motor, a drive wheel, a drive locking mechanism, and a microcontroller. The drive locking mechanism is located on the drive wheel to control the locking of the drive wheel, and the drive locking mechanism is connected to the microcontroller for control.

3. The unmanned truck neutral steering intelligent adjustment system as described in claim 1, characterized in that: The sensors include a cargo box pressure sensor, a cargo box position sensor, a tire pressure sensor, a seat pressure sensor, and a slope sensor.

4. The unmanned truck neutral steering intelligent adjustment system as described in claim 1, characterized in that: The determination data also includes the weight of the goods and / or the weight of the drivers and passengers.

5. The intelligent neutral steering adjustment system for an unmanned truck as described in claim 3, characterized in that: The slope sensor is an inertial measurement unit.

6. The unmanned truck neutral steering intelligent adjustment system as described in claim 1, characterized in that: The cargo box panel is equipped with guide rails, and the cargo box tray is movably connected to the guide rails.

7. A neutral steering intelligent control method for an unmanned truck, comprising the neutral steering intelligent adjustment system for an unmanned truck as described in any one of claims 1 to 6, characterized in that, Includes the following steps: S1. Activate the neutral steering control system when the truck turns; S2. The sensor monitors the current information of the vehicle and transmits the information to the vehicle controller. The vehicle controller includes a neural network model, in which the desired position of the cargo box under various conditions is set. S3. The neural network model compares the collected sensor information with the set judgment data and outputs the expected position of the cargo box that meets the neutral steering condition. The neural network model is connected to the power unit control to send control commands to the moving device. S4. The mobile device receives control commands and controls the cargo container to move to the desired location. S5. The neutral steering control system conditions are met, and the vehicle has met the neutral steering conditions.

Images