A trolley straight driving control method and system

Abstract

The application provides a trolley straight driving control method and system, acquires sensing images at left and right ends of a trolley advancing direction; based on the sensing images at left and right ends of the trolley advancing direction, left straight line endpoint coordinates and right straight line endpoint coordinates are acquired; based on the left straight line endpoint coordinates and the right straight line endpoint coordinates, a deviation pixel value is calculated; when the displacement deviation value does not satisfy a preset deviation requirement, the deviation pixel value is corrected through a preset pixel control algorithm to obtain deviation correction data; based on the deviation correction data, a trolley driving posture is controlled in real time. The application solves the problem that the prior art is prone to yaw in a complex work scene. The method of navigating through left and right double visual processing images completely acquires environmental information by itself and greatly improves navigation accuracy through pixel-level deviation processing, thereby reducing the occurrence of yaw.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of trolley straight running control, and particularly relates to a trolley straight running control method and system. BACKGROUND

[0002] In order to complete the autonomous operation requirement, the autonomous mobile unmanned trolley has strict travel requirements in the travel process. In the indoor environment with grid lines and the slope scene, the unmanned trolley is prone to yawing due to environmental factors.

[0003] In the working process, in order to strictly control the trolley to move straight, the traditional technical means is to use the linear control of the encoder, use the linear control of the high-precision RTK or the linear control of the SLAM technology; use the encoder to measure the wheel speed of the trolley, and compare the speed feedback signal with the expected speed through the controller, control the wheel speed of the trolley to tend to the expected speed, so as to make the trolley move straight along the line; use the high-precision RTK receiver to receive satellite signals from multiple base stations, and then the receiver eliminates the error of the satellite signals through the differential positioning technology to obtain high-precision position information, so that the trolley travels along the predetermined route; use the SLAM technology to obtain the information of the surrounding environment; then the algorithm processes the sensor data to extract the environmental features; secondly, the algorithm estimates the current position and attitude of the trolley according to the environmental features; finally, the algorithm combines the position and attitude information of the trolley with the environmental features to construct the surrounding environment map to control the trolley to move straight. However, the linear control method using the encoder has a deviation between the measured speed and the actual speed, which will cause the control system to issue incorrect instructions, so that the trolley deviates from the straight line, on the other hand, it is difficult to deal with complex road conditions: on uneven or sloping road surfaces, the encoder is difficult to accurately measure the wheel speed, resulting in a decrease in control accuracy; the cost of the RTK receiver and the base station is high, which increases the overall cost of the unmanned trolley, and it is easy to be affected by the environment: in the strong interference environment, the RTK signal is easy to be disturbed, resulting in a decrease in positioning accuracy; the SLAM algorithm involves a large amount of calculation, and the algorithmic requirement is high, which is difficult to apply to low-cost unmanned trolleys, and is dependent on the environment: in the environment with insufficient light or many obstructions, the positioning accuracy and robustness of the SLAM technology will be affected; therefore, the traditional technical means is difficult to overcome the problem of easy yawing in complex operation scenes. SUMMARY

[0004] In order to solve the above problems, the present application provides a trolley straight running control method and system, which can correct the displacement deviation of the trolley in real time in a complex environment, so as to make the trolley keep straight running and reduce the yawing phenomenon.

[0005] To achieve the above object, the embodiment of the present application provides a trolley straight running control method, which comprises the following steps:

[0006] acquire the sensing images at the left and right ends of the advancing direction of the trolley;

[0007] acquire the left straight line endpoint coordinates and the right straight line endpoint coordinates based on the sensing images at the left and right ends of the advancing direction of the trolley;

[0008] calculate the deviation pixel value based on the left straight line endpoint coordinates and the right straight line endpoint coordinates;

[0009] when the displacement deviation value does not meet the preset deviation requirement, correct the deviation pixel value by a preset pixel control algorithm to obtain deviation correction data;

[0010] based on the deviation correction data, control the trolley driving posture in real time.

[0011] The embodiment of the application proposes a trolley straight driving control method. The environment information at the left and right ends of the trolley can be acquired by acquiring the sensing images at the left and right ends of the advancing direction of the trolley, which does not depend on external devices, reduces the error rate of data processing, and further improves the accuracy of subsequent deviation correction. The deviation calculation is further performed by acquiring the straight line coordinates at the left and right ends of the advancing direction of the trolley, which reduces the intervention of additional sensing or positioning devices, prevents the hidden danger of data calculation error caused by the collection of multiple data by multiple external devices, and thus improves the accuracy of the data for controlling the trolley straight driving and reduces the yawing phenomenon. The displacement deviation is calculated by the left and right straight line coordinates, which can completely rely on itself to acquire environment information for calculation, without relying on external positioning information, further reducing data redundancy and data congestion to cause inaccurate data processing and affect the navigation accuracy. The pixel-level positioning accuracy is achieved by acquiring the pixel deviation for deviation correction and trolley posture control, further improving the navigation correction accuracy and reducing the yawing occurrence. Therefore, the navigation method by processing the images on both sides of the vision completely acquires the environment information by itself and greatly improves the navigation accuracy by pixel-level deviation processing, reducing the occurrence of yawing.

[0012] Further, the left straight line endpoint coordinates and the right straight line endpoint coordinates are acquired based on the sensing images at the left and right ends of the advancing direction of the trolley, specifically as follows:

[0013] acquire the left straight line and the right straight line meeting the preset requirement based on the sensing images at the left and right ends of the advancing direction of the trolley;

[0014] acquire the initial left straight line endpoint coordinates and the initial right straight line endpoint coordinates based on the left straight line and the right straight line meeting the preset requirement;

[0015] based on the initial left straight line endpoint coordinates and the initial right straight line endpoint coordinates, acquire the left straight line endpoint coordinates and the right straight line endpoint coordinates in real time by updating the sensing images at the left and right ends of the advancing direction of the trolley in real time.

[0016] The trolley straight driving control method provided by the embodiment of the application obtains the environment information at the left and right ends of the trolley advancing direction, obtains the left straight line and the right straight line meeting the preset requirements, and then obtains the left and right end points of the trolley advancing direction, so that the end points can be obtained by the trolley itself without relying on external equipment, the error rate of data processing is reduced, and the accuracy of subsequent deviation correction is improved.

[0017] Further, the left straight line and the right straight line meeting the preset requirements are obtained based on the sensing images at the left and right ends of the trolley advancing direction, and specifically:

[0018] The first image is obtained by performing region of interest extraction on the sensing images at the left and right ends of the trolley advancing direction.

[0019] The second image is obtained by sequentially performing graying and histogram equalization on the first image.

[0020] The third image is obtained by performing color extraction on the second image based on a preset color range threshold value, wherein the extracted colors are white, silver and gray.

[0021] The fourth image is obtained by performing edge detection and binarization processing on the third image.

[0022] The fifth image is obtained by performing morphological dilation operation, morphological erosion operation and morphological closing operation on the fourth image.

[0023] The left straight line and the right straight line meeting the preset requirements are obtained by performing gradual probability Hough transform on the fifth image based on a preset distance resolution, a preset angle resolution, a preset accumulator threshold value, a preset straight line minimum length and a preset straight line slope.

[0024] The trolley straight driving control method provided by the embodiment of the application further guarantees that the obtained environment information is closer to the true value and has higher accuracy by multiple processing of the image, so that the effect of deviation correction is more ideal, and meanwhile, a simpler algorithm than the prior art is adopted to reduce the complexity of overall operation and the error rate, so that the accuracy of coordinate acquisition, deviation calculation and deviation correction is improved.

[0025] Further, the deviation pixel value is calculated based on the left straight line end point coordinates and the right straight line end point coordinates, and specifically:

[0026] The left displacement deviation is obtained by subtracting the fourth end point coordinate of the right straight line end point coordinate from the first end point coordinate of the left straight line end point coordinate.

[0027] The right displacement deviation is obtained by subtracting the third end point coordinate of the right straight line end point coordinate from the second end point coordinate of the left straight line end point coordinate.

[0028] Based on the left displacement deviation and the right displacement deviation, a deviation pixel value is obtained.

[0029] The trolley straight driving control method provided by the embodiment of the application has low requirements on calculation power and low calculation complexity, so that the application range of the method can be expanded to more complex environments for operation control, and good operation effect and good adaptability can be ensured.

[0030] Further, based on the left displacement deviation and the right displacement deviation, a deviation pixel value is obtained, specifically as follows:

[0031] The sum of the absolute value of the left displacement deviation and the absolute value of the right displacement deviation is obtained as a deviation sum.

[0032] The half value of the deviation sum is obtained as the deviation pixel value.

[0033] Further, when the displacement deviation value does not meet the preset deviation requirement, the deviation pixel value is corrected by a preset pixel control algorithm to obtain deviation correction data, specifically as follows:

[0034] When the displacement deviation value does not meet the preset deviation requirement, the offset state of the current trolley is obtained.

[0035] Based on the offset state of the current trolley, the pixel position ring PID control algorithm is used to calculate the trolley expected thrust and rudder amount to obtain the deviation correction data.

[0036] The trolley straight driving control method provided by the embodiment of the application takes the deviation pixel value as input and uses the pixel position ring PID control algorithm for calculation, realizes pixel-based position closed-loop PID control, and the precision can reach the pixel level, so that the interference of complex environments is effectively avoided and the occurrence probability of yaw events is reduced.

[0037] Further, based on the deviation correction data, the deviation pixel value is corrected until the deviation pixel value meets the preset deviation requirement to obtain a corrected deviation pixel value.

[0038] Based on the corrected deviation pixel value, the trolley is controlled to drive straight.

[0039] The embodiment of the application also provides a trolley straight driving control system, which comprises a coordinate acquisition module, a displacement deviation calculation module, a deviation pixel acquisition module, a displacement deviation correction module and a trolley control module.

[0040] The coordinate acquisition module is used to acquire left straight end point coordinates and right straight end point coordinates based on left and right sensing images of the trolley.

[0041] The displacement deviation calculation module is used to calculate and update the displacement deviation in real time based on the coordinates of the left and right line endpoints to obtain the displacement deviation value.

[0042] The deviation pixel acquisition module is used to update the deviation pixel value to the displacement deviation value when the displacement deviation value does not meet the preset deviation requirement;

[0043] The displacement deviation correction module is used to correct the deviation pixel value based on the deviation pixel value using a preset pixel control algorithm to obtain deviation correction data.

[0044] The vehicle control module is used to control the vehicle's driving posture in real time based on the deviation correction data.

[0045] This invention proposes a vehicle straight-line driving control system. A coordinate acquisition module obtains the straight-line coordinates of the left and right ends of the vehicle from the perceived images at both ends for subsequent deviation calculation. This reduces the need for additional sensors or positioning devices, preventing errors in data calculation caused by multiple external devices collecting various data, thus improving the accuracy of the final control data for the vehicle's straight-line driving and reducing yaw. Simultaneously, a displacement deviation calculation module calculates displacement deviation using the left and right straight-line coordinates. This module relies entirely on its own acquired environmental information for calculation, eliminating the need for external positioning information and further reducing data redundancy and data congestion that could lead to inaccurate data processing and affect navigation accuracy. Finally, a deviation pixel acquisition module, a displacement deviation correction module, and a vehicle control module use pixel deviation acquisition for deviation correction and vehicle attitude control, achieving pixel-level positioning accuracy. This further improves navigation correction accuracy and reduces yaw. Therefore, this navigation method using bilateral visual image processing obtains environmental information entirely on its own and significantly improves navigation accuracy and reduces yaw by processing pixel-level deviations.

[0046] Furthermore, the coordinate acquisition module is used to acquire the coordinates of the left and right straight line endpoints based on the perceived images at both ends of the vehicle's forward direction, and also includes:

[0047] Line acquisition unit, endpoint coordinate acquisition unit, and real-time coordinate update unit;

[0048] The straight line acquisition unit is used to acquire a left straight line and a right straight line that meet preset requirements based on the images perceived at both ends of the vehicle's forward direction.

[0049] The endpoint coordinate acquisition unit is used to acquire the initial left line endpoint coordinates and the initial right line endpoint coordinates based on the left and right lines that meet the preset requirements.

[0050] The coordinate real-time update unit is used to obtain the coordinates of the left and right straight line endpoints in real time by updating the perception images at both ends of the vehicle's forward direction in real time, based on the initial left and right straight line endpoint coordinates and the initial right straight line endpoint coordinates.

[0051] Furthermore, the deviation pixel calculation module, used to calculate the deviation pixel value based on the coordinates of the left and right line endpoints, also includes:

[0052] Left displacement deviation calculation unit, right displacement deviation calculation unit, and deviation pixel acquisition unit;

[0053] The left displacement deviation calculation unit is used to obtain the left displacement deviation by subtracting the coordinates of the first endpoint of the left straight line endpoint from the coordinates of the fourth endpoint of the right straight line endpoint.

[0054] The right displacement deviation calculation unit is used to obtain the right displacement deviation by subtracting the coordinates of the second endpoint of the left straight line endpoint from the coordinates of the third endpoint of the right straight line endpoint.

[0055] The deviation pixel acquisition unit is used to obtain the deviation pixel value based on the left displacement deviation and the right displacement deviation. Attached Figure Description

[0056] Figure 1 This is a flowchart illustrating the steps of a method for controlling the straight-line driving of a vehicle according to a certain embodiment of the present invention;

[0057] Figure 2 This is a schematic diagram of the initial position of a vehicle according to a certain embodiment of the present invention for a vehicle straight-line driving control method;

[0058] Figure 3 A schematic diagram of a vehicle deflecting to the left, provided in a certain embodiment of the present invention, illustrates a method for controlling the straight-line driving of a vehicle.

[0059] Figure 4 This is a schematic diagram of a vehicle deflecting to the right, provided in a certain embodiment of the present invention, for a vehicle straight-line driving control method;

[0060] Figure 5 This is a schematic diagram of the image processing flow of a car straight-line driving control method according to a certain embodiment of the present invention;

[0061] Figure 6 This is a schematic diagram of the module structure of a vehicle straight-line driving control system according to a certain embodiment of the present invention;

[0062] Figure 7 A schematic diagram of the coordinate acquisition module of a car straight-line driving control system provided in a certain embodiment of the present invention;

[0063] Figure 8This is a schematic diagram of the deviation pixel calculation module of a car straight driving control system according to a certain embodiment of the present invention. Detailed Implementation

[0064] 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, and 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.

[0065] In order to strictly control the straight-line movement of existing autonomous mobile unmanned vehicles and complete autonomous tasks, there are usually three methods.

[0066] One method is encoder-based linear control: This method uses an encoder to measure the wheel speed of the vehicle and compares the speed feedback signal with the desired speed through a controller. If there is a deviation between the actual speed and the desired speed, the controller will issue a command to adjust the motor power so that the wheel speed of the vehicle tends to the desired speed, thus allowing the vehicle to move in a straight line. However, encoder-based control is sensitive to wheel slippage: when the vehicle's wheels slip, the speed measured by the encoder deviates from the actual speed, causing the control system to issue incorrect commands and causing the vehicle to deviate from the straight line. Furthermore, it struggles to handle complex road conditions: on uneven or sloping surfaces, the encoder has difficulty accurately measuring the wheel speed, leading to a decrease in control accuracy.

[0067] Secondly, linear control is based on high-precision RTK (Real-Time Kinematics) positioning, a high-precision positioning technology capable of providing centimeter-level accuracy. In the linear motion control of unmanned vehicles, the RTK scheme can improve the vehicle's positioning accuracy, thereby achieving more precise straight-line travel. The principle is as follows: an RTK receiver is installed on the vehicle to receive satellite signals from multiple base stations; then, the receiver uses differential positioning technology to eliminate satellite signal errors, obtaining high-precision position information; finally, the control system calculates the vehicle's direction and deviation based on the position information and issues commands to adjust the motor power, enabling the vehicle to travel along the predetermined route. However, the RTK-based scheme has two main drawbacks: firstly, it is costly: the RTK receiver and base stations are expensive, increasing the overall cost of the unmanned vehicle; secondly, it is susceptible to environmental interference: in environments with strong interference, RTK signals are easily affected, leading to a decrease in positioning accuracy.

[0068] Thirdly, there's the linear control using SLAM technology: SLAM (Simultaneous Localization and Mapping) is a technology that simultaneously estimates the position of an autonomous vehicle and builds a map of its surrounding environment. In the linear control of autonomous vehicles, SLAM technology can improve the vehicle's positioning accuracy and robustness, thus achieving more reliable straight-line travel. The principle is as follows: First, sensors such as cameras and LiDAR are installed on the vehicle to acquire information about the surrounding environment; then, the algorithm processes the sensor data to extract environmental features; second, the algorithm estimates the vehicle's current position and attitude based on these environmental features; finally, the algorithm combines the vehicle's position and attitude information with the environmental features to build a map of the surrounding environment, thereby controlling the vehicle's linear movement. However, SLAM technology has two main drawbacks: First, it has high algorithm complexity: SLAM algorithms involve a large amount of computation, requiring significant computing power, making it difficult to apply to low-cost autonomous vehicles; second, it is environmentally dependent: in environments with insufficient lighting or numerous obstructions, the positioning accuracy and robustness of SLAM technology will be affected.

[0069] Therefore, to address the drawbacks of traditional methods, this invention proposes a method for controlling the straight-line driving of a vehicle. This embodiment explains a method based on bilateral vision, where bilateral vision is positioned on the left and right sides of the autonomous mobile unmanned vehicle's forward direction to perceive the left and right first near lines in the environmental information on both sides of the vehicle's forward direction. In this embodiment, the left and right ends refer to the left and right ends of the vehicle's forward direction. Furthermore, the left and right first near lines represent left and right lines that meet preset requirements, including: preset distance resolution, preset angle resolution, preset accumulator threshold, preset minimum line length, and preset line slope, which will not be elaborated further below.

[0070] Example 1

[0071] See Figure 1 , Figure 1 This is a flowchart illustrating the steps of a method for controlling the straight-line driving of a vehicle according to a certain embodiment of the present invention. Figure 1 As shown, this embodiment of the invention proposes a method for controlling the straight-line driving of a vehicle, including steps 101 to 105, the specific details of which are as follows:

[0072] Step 101: Obtain the perception images of the left and right ends of the car's forward direction;

[0073] As one possible implementation method of this embodiment, such as Figure 2As shown, images can be acquired by setting sensing cameras or vision sensors on the left and right sides of the autonomous mobile unmanned vehicle's forward direction. Many existing conventional devices capable of image acquisition can be used as examples of embodiments of the present invention.

[0074] Step 102: Based on the sensor images at both ends of the car's forward direction, obtain the coordinates of the left and right straight line endpoints;

[0075] As an example of this embodiment, based on the perceived images of the left and right ends of the vehicle's forward direction, a left straight line and a right straight line that meet preset requirements are obtained; based on the left and right straight lines that meet the preset requirements, the initial coordinates of the left straight line endpoint and the initial coordinates of the right straight line endpoint are obtained; based on the initial coordinates of the left straight line endpoint and the initial coordinates of the right straight line endpoint, the coordinates of the left straight line endpoint and the coordinates of the right straight line endpoint are obtained in real time by updating the perceived images of the left and right ends of the vehicle's forward direction in real time. For a specific possible implementation, see [link to implementation details]. Figure 2 , Figure 2 This is a schematic diagram of the initial position of a vehicle according to a certain embodiment of the present invention for a vehicle straight-line driving control method. When the autonomous mobile unmanned vehicle starts, the left and right visual systems begin to perceive the left first near line and the right first near line in the environmental information on both sides, thereby determining and recording the initial position of the autonomous mobile unmanned vehicle. The coordinates of the endpoint of the left first near line in the image are: First endpoint (X... 1 L(0) Y 1 L(0) ) and the second endpoint (X) 2 L(0) Y 2 L(0) ); where the coordinates of the endpoint of the first right near line in the image are: the coordinates of the third endpoint (X 1 R(0) Y 1 R(0) ) and the fourth endpoint (X) 2 R(0) Y 2 R(0) Based on practical operational experience, if the autonomous mobile vehicle maintains a straight-line movement, then at any given moment, the X-direction (row) coordinates of the endpoint pixels of the left and right first near-line lines in the image will remain within a certain pixel range, while the Y-direction (column) coordinates will never change. Therefore, in this embodiment of the invention, only the deviation in the X-direction is considered.

[0076] As another example of this embodiment, a first image is obtained by extracting regions of interest from the perceived images at both ends of the vehicle's forward direction; a second image is obtained by sequentially performing grayscale conversion and histogram equalization on the first image; a third image is obtained by extracting colors from the second image based on a preset color range threshold, wherein the extracted colors are white, silver, and gray; a fourth image is obtained by performing edge detection and binarization on the third image; a fifth image is obtained by performing morphological dilation, morphological erosion, and morphological closing operations on the fourth image; and a left and right straight lines that meet preset requirements are calculated by performing an asymptotic probabilistic Hough transform on the fifth image based on preset distance resolution, preset angle resolution, preset accumulator threshold, preset minimum line length, and preset line slope. For a specific possible implementation, see [link to implementation details]. Figure 5 , Figure 5 This is a schematic diagram of the image processing flow of a car straight-line driving control method according to a certain embodiment of the present invention; as shown below. Figure 5As shown, firstly, the regions of interest (ROIs) are extracted from the original RGB images perceived by the left and right cameras to obtain roi_img (equivalent to the first image): the 1080p image is cropped to a pixel size of 640×480 to reduce the computational load of subsequent algorithms and improve the processing speed and accuracy of the algorithms; secondly, the roi_img image is converted to grayscale from the RGB color space, and then histogram equalization is performed to obtain the equalizeHist_img image (equivalent to the second image). By stretching the grayscale distribution of the image to the entire possible range, the contrast of the image is significantly enhanced, making the details in the dark and bright areas clearer and adaptable to different lighting environments; thirdly, the equalizeHist_img image is converted to the HSV color space and color extraction is performed, selecting white, silver, and gray, and setting appropriate thresholds to select the color range of the left and right first near lines. Then, the image is converted to grayscale color space to obtain gray_img (equivalent to the third image); in the fourth step, Sobel edge detection is performed on gray_img, and then adaptive thresholding is used to binarize the image to obtain binary_img (equivalent to the fourth image); in the fifth step, morphological dilation, morphological erosion, and morphological closing operations are sequentially performed on the binary_img image to enhance the features of the left and right first near lines in the image and suppress the interference of small spots. Then, the processed image is converted into an unsigned integer image to obtain edge_img (equivalent to the fifth image); in the sixth step, the edge_img image is subjected to asymptotic probabilistic Hough transform to calculate the endpoint pixel coordinates of the left and right first near lines. The system employs five parameters to ensure the autonomous vehicle can reliably detect the left and right first near lines at any given time during straight-line movement. These parameters include: a suitable distance resolution (in pixels); a suitable angle resolution (in degrees); a suitable accumulator threshold (where the number of times each discretized square in the parameter space is traversed exceeds the threshold to be identified as a straight line, otherwise it is not); a minimum line length; a maximum distance parameter between two adjacent points on the same straight line; and a line slope. The seventh step compares the endpoint pixel coordinates of the detected left and right first near lines at each moment with their initial position coordinates. If the difference in endpoint pixel coordinates falls within the θ neighborhood, the autonomous vehicle has not veered off course and continues moving forward. If the difference in endpoint pixel coordinates does not fall within the θ neighborhood, the autonomous vehicle has veered off course. Based on the pixel coordinate deviation, a pixel position loop PID calculation is used to adjust the driver, controlling the autonomous vehicle to quickly correct the deviation as close to zero as possible, and then maintaining straight-line movement.

[0077] Step 103: Calculate the deviation pixel value based on the coordinates of the left and right line endpoints;

[0078] As an example of this embodiment, the left displacement deviation is obtained by subtracting the coordinates of the first endpoint of the left line endpoint from the coordinates of the fourth endpoint of the right line endpoint; the right displacement deviation is obtained by subtracting the coordinates of the second endpoint of the left line endpoint from the coordinates of the third endpoint of the right line endpoint; and the deviation pixel value is obtained based on the left displacement deviation and the right displacement deviation. For a specific possible implementation, see [link to implementation details]. Figure 3 and Figure 4 , Figure 3 A schematic diagram of a vehicle deflecting to the left, provided in a certain embodiment of the present invention, illustrates a method for controlling the straight-line driving of a vehicle. Figure 4 This invention provides a schematic diagram of a vehicle's rightward deviation in a linear driving control method for a vehicle according to a certain embodiment of the present invention; at time t during the autonomous mobile unmanned vehicle's linear movement, the pixel endpoint coordinates of the leftmost near-line in the image are (X... 1 L(t) Y 1 L(t) ) and (X 2 L(t) Y 2 L(t) The pixel coordinates of the first right near line in the image are (X...). 1 R(t) Y 1 R(t) ) and (X 2 R(t) Y 2 R(t) The deviation value is calculated as follows:

[0079] Left displacement deviation: Lerror = X 1 L(0) -X 1 R(t)

[0080] Right displacement deviation: Rerror = X 2 L(0) -X 2 R(t)

[0081] As another example of this embodiment, the deviation sum is obtained by summing the absolute values ​​of the left and right displacement deviations; the deviation pixel value is obtained by obtaining half of the deviation sum. In a specific implementation, when the deviation pixel value (|Lerror|+|Rerror|) / 2∈θ, the autonomous moving unmanned vehicle always maintains straight-line movement: the left and right endpoint pixel coordinates of the left and right first near straight lines perceived by the left and right visions remain within a certain θ pixel range in the two images, where θ∈(-10, 10).

[0082] Step 104: When the displacement deviation value does not meet the preset deviation requirement, the deviation pixel value is corrected by a preset pixel control algorithm to obtain deviation correction data.

[0083] As an example of this embodiment, when the displacement deviation value does not meet the preset deviation requirement, the current offset state of the vehicle is obtained; based on the current offset state of the vehicle, the expected thrust and steering input of the vehicle are calculated using a pixel position loop PID control algorithm to obtain deviation correction data. Specifically, in one possible implementation, when... When Lerror < 0 and Rerror > 0, the autonomous moving unmanned vehicle veers to the left, with the deviation value being: error = (|Lerror| + |Rerror|) / 2, in pixels. Figure 3 As shown;

[0084] when When Lerror > 0 and Rerror < 0, the autonomous moving unmanned vehicle veers to the right, with the deviation value being: error = (|Lerror| + |Rerror|) / 2, in pixels. Figure 4 As shown;

[0085] When the autonomous mobile vehicle deviates from its intended path while moving in a straight line (i.e., the error value is not zero), the PID control algorithm of the pixel position loop is used to quickly correct the deviation and achieve straight-line control. Specifically, based on the obtained deviation value, the pixel position loop PID control algorithm calculates the vehicle's desired thrust and steering input to obtain the deviation correction data. The pixel position loop PID control algorithm is a mature existing technology and will not be explained in detail here.

[0086] Step 105: Based on the deviation correction data, perform real-time control on the vehicle's driving posture.

[0087] As an example of this embodiment, based on the deviation correction data, the deviation pixel value is corrected until the deviation pixel value meets the preset deviation requirement, thus obtaining the corrected deviation pixel value; based on the corrected deviation pixel value, the vehicle is controlled to travel in a straight line. Specifically, the environmental information perceived by bilateral vision during the straight-line movement of the autonomous mobile unmanned vehicle is processed and calculated to obtain the pixel-level lateral deviation during the straight-line movement of the autonomous mobile unmanned vehicle, and then the lateral deviation is corrected to control the vehicle to move in a straight line.

[0088] This invention proposes a method for controlling the straight-line driving of a vehicle. By acquiring perceived images from both the left and right ends of the vehicle's forward direction, environmental information at both ends can be obtained without relying on external devices, reducing the error rate of data processing and thus improving the accuracy of subsequent deviation correction. Further deviation calculation is performed by acquiring the linear coordinates of the left and right ends of the vehicle's forward direction, reducing the need for additional sensors or positioning devices and preventing errors in data calculation caused by multiple external devices collecting various data. This improves the accuracy of the final data controlling the vehicle's straight-line driving and reduces yaw. Simultaneously, the calculation of displacement deviation using the left and right linear coordinates relies entirely on the acquired environmental information, eliminating the need for external positioning information and further reducing data redundancy and data congestion that could lead to inaccurate data processing and affect navigation accuracy. By acquiring pixel deviations for deviation correction and vehicle attitude control, pixel-level positioning accuracy is achieved, further improving navigation correction accuracy and reducing yaw. Therefore, this method of navigation using bilateral visual image processing acquires environmental information entirely on its own and significantly improves navigation accuracy through pixel-level deviation processing. This method improves accuracy and reduces yaw occurrences. By acquiring environmental information at both ends of the vehicle's forward direction, it obtains left and right straight lines that meet preset requirements, thus determining the endpoints of the vehicle's forward direction. This endpoint acquisition is achieved automatically, without relying on external devices, reducing data processing errors and improving the accuracy of subsequent deviation correction. Multiple image processing steps further ensure that the acquired environmental information is closer to the true value, resulting in higher accuracy and a more ideal yaw correction effect. Simultaneously, a simpler algorithm than existing technologies is used, reducing overall computational complexity and error rates, thereby improving the accuracy of coordinate acquisition, deviation calculation, and deviation correction. Calculating deviation values ​​by acquiring straight line segments requires low computational power and has low computational complexity, allowing the method to be applied to more complex environments for operation control, ensuring good computational performance and adaptability. Using the deviation pixel value as input, a pixel position loop PID control algorithm is used for calculation, achieving pixel-level accuracy in closed-loop PID control, effectively reducing interference from complex environments and lowering the probability of yaw events.

[0089] Example 2

[0090] See Figure 6 , Figure 6 This is a schematic diagram of the module structure of a car straight-line driving control system according to a certain embodiment of the present invention. Figure 6 As shown, an embodiment of the present invention proposes a vehicle straight-line driving control system, comprising:

[0091] Image acquisition module 601, coordinate acquisition module 602, deviation pixel calculation module 603, displacement deviation correction module 604, and trolley control module 605;

[0092] The image acquisition module 601 is used to acquire the perceived images at both ends of the car's forward direction;

[0093] The coordinate acquisition module 602 is used to acquire the coordinates of the left and right straight line endpoints based on the perceived images at both ends of the vehicle's forward direction.

[0094] As an example of this embodiment, see Figure 7 , Figure 7 This is a schematic diagram of the coordinate acquisition module structure of a car straight-line driving control system according to a certain embodiment of the present invention; as shown. Figure 7 As shown, the coordinate acquisition module 602 is used to acquire the coordinates of the left and right straight line endpoints based on the perceived images at both ends of the vehicle's forward direction, and also includes:

[0095] Line acquisition unit 701, endpoint coordinate acquisition unit 702 and coordinate real-time update unit 703;

[0096] The straight line acquisition unit 701 is used to acquire a left straight line and a right straight line that meet preset requirements based on the images perceived at both ends of the vehicle's forward direction.

[0097] The endpoint coordinate acquisition unit 702 is used to acquire the initial left line endpoint coordinates and the initial right line endpoint coordinates based on the left line and right line that meet the preset requirements.

[0098] The coordinate real-time update unit 703 is used to acquire the coordinates of the left and right straight ends in real time by updating the perception images of the left and right ends of the vehicle's forward direction in real time, based on the initial left and right straight end coordinates.

[0099] The deviation pixel calculation module 603 is used to calculate the deviation pixel value based on the coordinates of the left and right line endpoints.

[0100] As an example of this embodiment, see Figure 8 , Figure 8This is a schematic diagram of the deviation pixel calculation module structure of a car straight-line driving control system according to a certain embodiment of the present invention. Figure 8 As shown, the deviation pixel calculation module 603 is used to calculate the deviation pixel value based on the coordinates of the left and right line endpoints, and further includes:

[0101] Left displacement deviation calculation unit 801, right displacement deviation calculation unit 802 and deviation pixel acquisition unit 803;

[0102] The left displacement deviation calculation unit 801 is used to obtain the left displacement deviation by subtracting the coordinates of the first endpoint of the left straight line endpoint from the coordinates of the fourth endpoint of the right straight line endpoint.

[0103] The right displacement deviation calculation unit 802 is used to obtain the right displacement deviation by subtracting the second endpoint coordinate of the left straight line endpoint coordinate from the third endpoint coordinate of the right straight line endpoint coordinate.

[0104] The deviation pixel acquisition unit 803 is used to obtain the deviation pixel value based on the left displacement deviation and the right displacement deviation.

[0105] The displacement deviation correction module 604 is used to correct the deviation pixel value through a preset pixel control algorithm when the displacement deviation value does not meet the preset deviation requirement, so as to obtain deviation correction data.

[0106] The vehicle control module 605 is used to control the vehicle's driving posture in real time based on the deviation correction data.

[0107] This invention proposes a vehicle straight-line driving control system. A coordinate acquisition module obtains the straight-line coordinates of the left and right ends of the vehicle from the perceived images at both ends for subsequent deviation calculation. This reduces the need for additional sensors or positioning devices, preventing errors in data calculation caused by multiple external devices collecting various data, thus improving the accuracy of the final control data for the vehicle's straight-line driving and reducing yaw. Simultaneously, a displacement deviation calculation module calculates displacement deviation using the left and right straight-line coordinates. This module relies entirely on its own acquired environmental information for calculation, eliminating the need for external positioning information and further reducing data redundancy and data congestion that could lead to inaccurate data processing and affect navigation accuracy. Finally, a deviation pixel acquisition module, a displacement deviation correction module, and a vehicle control module use pixel deviation acquisition for deviation correction and vehicle attitude control, achieving pixel-level positioning accuracy. This further improves navigation correction accuracy and reduces yaw. Therefore, this navigation method using bilateral visual image processing obtains environmental information entirely on its own and significantly improves navigation accuracy and reduces yaw by processing pixel-level deviations.

[0108] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the technical principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

[0109] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of those different embodiments or examples.

[0110] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "a plurality of" means two or more, unless otherwise explicitly specified.

Claims

1. A method for controlling the straight-line driving of a car, characterized in that, include: Acquire sensor images of the left and right ends of the car's forward direction; Based on the sensor images at both ends of the vehicle's forward direction, the coordinates of the left and right straight line endpoints are obtained. Specifically, this involves: obtaining a left and right straight line that meets preset requirements based on the sensor images at both ends of the vehicle's forward direction; obtaining initial left and right straight line endpoint coordinates based on the left and right straight lines that meet the preset requirements; and obtaining the left and right straight line endpoint coordinates in real time by updating the sensor images at both ends of the vehicle's forward direction in real time based on the initial left and right straight line endpoint coordinates. Specifically, obtaining the left and right straight lines that meet preset requirements based on the sensor images at both ends of the vehicle's forward direction involves: performing an interest-based analysis on the sensor images at both ends of the vehicle's forward direction. Region extraction yields a first image; grayscale conversion and histogram equalization are performed sequentially on the first image to obtain a second image; color extraction is performed on the second image based on a preset color range threshold to obtain a third image, wherein the extracted colors are white, silver, and gray; edge detection and binarization are performed on the third image to obtain a fourth image; morphological dilation, morphological erosion, and morphological closing operations are performed on the fourth image to obtain a fifth image; based on preset distance resolution, preset angle resolution, preset accumulator threshold, preset minimum line length, and preset line slope, the fifth image is calculated using an asymptotic probabilistic Hough transform to obtain a left and right straight line that meet preset requirements; Based on the coordinates of the left and right line endpoints, the deviation pixel value is calculated as follows: The left displacement deviation is obtained by subtracting the first endpoint coordinate of the left line endpoint from the fourth endpoint coordinate of the right line endpoint; the right displacement deviation is obtained by subtracting the second endpoint coordinate of the left line endpoint from the third endpoint coordinate of the right line endpoint; the deviation pixel value is obtained based on the left and right displacement deviations; specifically, obtaining the deviation pixel value based on the left and right displacement deviations involves: summing the absolute values ​​of the left and right displacement deviations to obtain the deviation sum; and obtaining the deviation pixel value by taking half of the deviation sum. When the displacement deviation value does not meet the preset deviation requirement, the deviation pixel value is corrected by a preset pixel control algorithm to obtain deviation correction data; Based on the deviation correction data, the vehicle's driving posture is controlled in real time.

2. The method for controlling the straight-line driving of a vehicle as described in claim 1, characterized in that, When the displacement deviation value does not meet the preset deviation requirement, the deviation pixel value is corrected by a preset pixel control algorithm to obtain deviation correction data, specifically: When the displacement deviation value does not meet the preset deviation requirement, the current offset state of the trolley is obtained; Based on the current offset state of the vehicle, the desired thrust and steering input of the vehicle are calculated using a pixel position loop PID control algorithm to obtain deviation correction data.

3. A method for controlling the straight-line driving of a vehicle as described in claim 1 or 2, characterized in that, Based on the aforementioned deviation correction data, the vehicle's driving posture is controlled in real time, specifically as follows: Based on the deviation correction data, the deviation pixel value is corrected until the deviation pixel value meets the preset deviation requirement, and the corrected deviation pixel value is obtained. Based on the corrected deviation pixel value, the car is controlled to travel in a straight line.

4. A vehicle linear motion control system, characterized in that, include: Image acquisition module, coordinate acquisition module, deviation pixel calculation module, displacement deviation correction module, and trolley control module; The image acquisition module is used to acquire the perceived images at both ends of the car's forward direction; The coordinate acquisition module is used to acquire the coordinates of the left and right straight line endpoints based on the perceived images at both ends of the vehicle's forward direction. It includes: a straight line acquisition unit, an endpoint coordinate acquisition unit, and a real-time coordinate update unit. The straight line acquisition unit is used to acquire left and right straight lines that meet preset requirements based on the perceived images at both ends of the vehicle's forward direction. The endpoint coordinate acquisition unit is used to acquire initial left and right straight line endpoint coordinates and initial right straight line endpoint coordinates based on the left and right straight lines that meet the preset requirements. The real-time coordinate update unit is used to acquire the left and right straight line endpoint coordinates and initial right straight line endpoint coordinates in real time by updating the perceived images at both ends of the vehicle's forward direction in real time, based on the initial left and right straight line endpoint coordinates and the initial right straight line endpoint coordinates. The coordinate acquisition unit acquires the coordinates of the left and right straight line endpoints that meet preset requirements based on the perceived images at both ends of the vehicle's forward direction. The left and right straight lines are obtained as follows: A first image is obtained by extracting regions of interest from the perceived images at both ends of the vehicle's forward direction; a second image is obtained by sequentially performing grayscale conversion and histogram equalization on the first image; a third image is obtained by extracting colors from the second image based on a preset color range threshold, wherein the extracted colors are white, silver, and gray; a fourth image is obtained by performing edge detection and binarization on the third image; a fifth image is obtained by performing morphological dilation, morphological erosion, and morphological closing operations on the fourth image; and the left and right straight lines that meet preset requirements are calculated using an asymptotic probabilistic Hough transform based on preset distance resolution, preset angle resolution, preset accumulator threshold, preset minimum line length, and preset line slope. The deviation pixel calculation module is used to calculate the deviation pixel value based on the coordinates of the left and right line endpoints, including: a left displacement deviation calculation unit, a right displacement deviation calculation unit, and a deviation pixel acquisition unit; the left displacement deviation calculation unit is used to obtain the left displacement deviation by subtracting the first endpoint coordinate of the left line endpoint from the fourth endpoint coordinate of the right line endpoint; the right displacement deviation calculation unit is used to obtain the right displacement deviation by subtracting the second endpoint coordinate of the left line endpoint from the third endpoint coordinate of the right line endpoint; the deviation pixel acquisition unit is used to obtain the deviation pixel value based on the left displacement deviation and the right displacement deviation; wherein, obtaining the deviation pixel value based on the left displacement deviation and the right displacement deviation specifically involves: summing the absolute values ​​of the left and right displacement deviations to obtain the deviation sum; and obtaining the deviation pixel value by acquiring half of the deviation sum. The displacement deviation correction module is used to correct the deviation pixel value through a preset pixel control algorithm when the displacement deviation value does not meet the preset deviation requirement, so as to obtain deviation correction data. The vehicle control module is used to control the vehicle's driving posture in real time based on the deviation correction data.

Images