Lock station passing method based on laser edge detection

Abstract

The invention discloses a lock station passing method based on laser edge detection, and relates to the technical field of wharf automatic operation. In order to solve the problems that in the prior art, when complex environment information of a lock station area is processed, route planning and correction are not accurate enough when a vehicle passes through a lock station, driving shaking is possibly caused, traffic jam is easily caused under the condition that a lock station passing opening is compressed, and then the overall operation efficiency of a wharf is affected. According to the method, lock station edge laser points are collected in stages, lock station edge positions are accurately determined, interference items such as middle guardrails are removed according to vehicle chassis data, data accuracy and reliability are ensured, automatic optimization is carried out when positioning is unstable by utilizing a positioning weight and multi-path fusion scheme, shaking when a vehicle passes through the lock station is greatly reduced, transportation safety is ensured, and the safety of the vehicle is improved. The hidden danger of container sliding is reduced, accurate detection and correction enable the vehicle to quickly pass through the lock station, the container circulation speed is increased, and the overall operation efficiency of an automatic wharf is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of dock automation operations, and in particular to a lock station passage method based on laser edge detection. Background Art

[0002] In automated container terminals, terminal lock stations, critical facilities for container unpacking and unlocking operations, are typically located near quay crane lanes or at essential intersections. When large workloads require multi-line operations, the access points to the lock stations are compressed. Currently, vehicles face numerous challenges navigating lock stations. Existing autonomous vehicle lock station navigation solutions typically employ pure satellite positioning, visual recognition, and laser recognition. However, these traditional lock station navigation solutions are inefficient and struggle to adapt to the growing operational demands of terminals. When access points are compressed, they can easily cause traffic congestion, slow container turnover, and impact overall terminal operational efficiency. Existing technologies also struggle to process the complex environmental information within the lock station area, such as accurately identifying the lock station's edges and eliminating interference from unnecessary intermediate fences. This results in inaccurate route planning and corrections for vehicles navigating the lock station, potentially causing jitter or safety issues. Summary of the Invention

[0003] The purpose of the present invention is to provide a lock station passage method based on laser edge detection. Through strategies such as staged fitting, relative position filtering and route weight stitching, the lock station edge can be accurately identified and interference items can be eliminated. It can effectively improve the lock station passage efficiency, reduce vehicle dwell time, reduce passage jitter, ensure driving safety, and significantly improve the operation efficiency of automated terminals, so as to solve the problems raised in the above-mentioned background technology.

[0004] To achieve the above object, the present invention provides the following technical solutions: A lock station traversal method based on laser edge detection, comprising: Determine whether the vehicle has entered the lock station area and activate the lock station edge detection module for detection. Based on the segmented detection strategy, perform a LiDAR scan of the lock station and directionally eliminate unnecessary interference items in the middle section. Route correction is performed using a splicing solution that combines positioning weights with multi-route fusion, outputting standard lock station edge lines to guide vehicles in route correction operations.

[0005] Furthermore, it is determined whether the vehicle has entered the lock station area, specifically including: Use the positioning device to obtain the vehicle's location information in real time, and compare the obtained vehicle location information with the pre-set locking station area range; When the vehicle's location information is completely within the pre-set locking area, it is determined that the vehicle has entered the locking area; When it is detected that the vehicle position information partially or completely exceeds the pre-set locking station area, it is determined that the vehicle has not entered the locking station area; If, in the process of determining that the vehicle has not entered the lock station area, the distance between the vehicle position and the boundary of the lock station area continues to decrease during the continuous monitoring period, and the reduction rate exceeds the preset threshold, then it is determined that the vehicle position has a trend of approaching the lock station area, and the vehicle position information is continuously monitored until the vehicle position information is compared with the lock station area range again to re-determine whether the vehicle has entered the lock station area.

[0006] Furthermore, the segmented detection strategy includes three stages: entering the lock station, passing through the lock station, and exiting the lock station: During the station lock phase: When the positioning device determines that the vehicle is gradually approaching the station lock area and its position information shows that it is about to enter the pre-set station lock area, the laser point at the inner edge of the right station lock area scanned by the left laser radar of the vehicle is saved in the left point set for left station lock edge detection, and the laser point at the left station lock area scanned by the right laser radar of the vehicle is saved in the right point set for right station lock edge detection; During the lock station phase: when it is determined that the vehicle is within the lock station area, the laser points at the inner edge of the left lock station scanned by the left laser of the vehicle are saved in the left point set for left lock station edge detection, and the laser points at the right lock station scanned by the right laser are saved in the right point set for right lock station edge detection; During the exit lock station phase: When it is detected that the vehicle is about to leave the lock station area, continue to follow the operating methods of the passing lock station phase, and save the lock station laser points scanned by the lidar on the left and right sides into the corresponding left point set and right point set respectively.

[0007] Furthermore, during the stage of passing through the locking station, it also includes: obtaining vehicle chassis data based on the sensors carried by the vehicle, determining the distance range of the middle guardrail based on the vehicle chassis data, filtering the interference points of the obtained locking station laser points according to the distance range of the middle guardrail, judging the relationship between the locking station laser points and the locking station position and the distance range of the middle guardrail, and removing the laser points determined to belong to the middle guardrail based on the relationship.

[0008] Furthermore, a lidar scan is performed on the lock station, specifically including: Receive the raw scanning data output by the LiDAR device, including the three-dimensional coordinates and intensity information of the locked laser point; Pre-process the acquired raw scan data and set filtering criteria based on the specific dimensions of the vehicle and the actual layout of the lock station area; Determine the vehicle's driving status based on the real-time vehicle location information and dynamically adjust the screening conditions; Perform real-time condition judgment on each locking station laser point, filter the collected scanning data according to the preset filtering conditions and dynamically adjusted filtering conditions, and obtain valid locking station laser points based on the filtering results.

[0009] Furthermore, performing a lidar scan on the lock station also includes: classifying the valid lock station laser points based on the vehicle's reference system, and saving the valid lock station laser points located on the vehicle into corresponding left point sets and right point sets based on a segmented detection strategy.

[0010] Furthermore, the effective locking station laser points are classified into the following categories: Read the valid station-locking laser points in the left point set and the right point set, and determine the data type of the valid station-locking laser points based on the data features of the valid station-locking laser points; Match the corresponding laser scanning data samples in the locking station laser scanning database according to the valid locking station laser point data type; Based on the laser scanning data samples, the reasonable fluctuation range and distribution pattern of the effective locking station laser point in the spatial coordinates are determined, and the constraint conditions for data verification are generated; According to the generated constraint conditions, the valid locking station laser points in the left point set and the right point set are checked one by one, and the valid locking station laser points that do not meet the constraint conditions are marked as abnormal points; If the number and degree of deviation of abnormal points in the left point set and the right point set are lower than the preset threshold, the abnormal points are corrected according to the distribution pattern of the surrounding normal points; If the number of abnormal points or the degree of deviation in the left point set and the right point set is higher than the preset threshold, the abnormal points are removed and an abnormal warning is issued.

[0011] Furthermore, the operation of directional elimination of redundant interference items in the middle segment further includes: When filtering interference points for the left and right locking station laser points, the vehicle is initially assumed to be in front of the locking station. The number of locking station laser points on the left and right sides that are more than 7.5 meters away from the front of the vehicle is counted. If more than half of the left and right locking station laser points are more than 7.5 meters away from the front of the vehicle, two special signs will be marked to indicate that the vehicle is not on the corresponding side of the locking station; On the contrary, when the number of locking station laser points less than 7.5 meters from the front of the vehicle on the left and right sides is counted to be more than half, the vehicle is determined to be in the locking station, and two specific flag bits are marked to indicate that the vehicle is in the corresponding side of the locking station.

[0012] Furthermore, after removing the redundant interference items in the middle section, the following is also included: The valid locked station laser clouds stored in the left point set and the right point set are processed to obtain two segmented point cloud sets, namely the left segmented point cloud set and the right segmented point cloud set; Perform straight line fitting operations on the left segmentation point cloud set and the right segmentation point cloud set respectively, so as to obtain the slope and intercept of the left and right locking station edge straight lines respectively; Verify the slope and intercept of the left and right side lock station edge straight lines, determine whether the slope and intercept of the left and right side lock station edge straight lines meet the standards based on the verification results, and output the lock station edge line parameters that meet the standards.

[0013] Furthermore, a splicing solution combining positioning weights and multi-route fusion is used for route correction, specifically including: Determine whether the real-time vehicle location information is within the locking station area. If the vehicle is within the locking station area, read the configuration information of the corresponding area, obtain the relative offset of the locking station laser edge line, and calculate the absolute value of the difference between the actual offset and the relative offset. At the same time, obtain the absolute value of the slope of the locking station edge line. When the absolute value of the difference between the actual offset and the relative offset and the absolute value of the slope of the lock station edge line are both less than the preset thresholds, the lock station edge line is confirmed to meet the correction conditions, the lock station edge line parameters at the current moment are saved, and the lock station edge line recognition status flag is set to valid, otherwise no route correction is performed; Determine whether the current vehicle positioning state is stable. If the vehicle positioning state is unstable, calculate the current bias weight and adjust the bias weight value according to the calculation result; When the lock station edge line recognition status flag is valid, the route weight splicing judgment is performed to determine whether the curvature of the current route meets the straight line threshold. If the curvature exceeds the preset straight line threshold, the sequence number of the route point where the curvature exceeds the straight line threshold is recorded; Traverse all route points from the current route to the curvature limit point sequence number, read the corresponding correction weight parameters, and perform weighted calculation on the original route and the lock station edge line based on the correction weight to generate the final corrected route.

[0014] Compared with the prior art, the present invention has the following beneficial effects: By collecting laser points at the edge of the locking station in stages, the edge position of the locking station is accurately determined, and interference items such as the middle guardrail are eliminated based on the vehicle chassis data to ensure data accuracy and reliability. The positioning weight and multi-route fusion solution are used to adjust the route based on various factors. Automatic optimization is performed when the positioning is unstable, which greatly reduces the jitter of the vehicle when passing through the locking station, ensures transportation safety, and reduces the hidden dangers of container sliding. Accurate detection and correction enable vehicles to pass through the locking station quickly, avoid congestion in the locking station area, and improve the container turnover speed. In the case of multi-line operations and narrow passages at the terminal, it effectively improves the overall operating efficiency of the automated terminal, providing strong support for the efficient operation of the terminal. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 Schematic diagram of the lock station passage process based on laser edge detection of the present invention; Figure 2 Schematic diagram of the laser radar device of the present invention; Figure 3 This is a schematic diagram of eliminating redundant interference items in the middle section of the present invention; Figure 4 A schematic diagram of the splicing route of the splicing solution of the present invention; Figure 5 This is a flow chart of the station lock passage method based on laser edge detection of the present invention. DETAILED DESCRIPTION

[0016] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0017] To address the technical issues that existing technologies face in processing complex environmental information in the lock station area, resulting in inaccurate route planning and correction for vehicles passing through the lock station, which may cause driving jitters. This can easily lead to traffic congestion when the lock station entrance is compressed, reducing container turnover speed and thus affecting the overall operational efficiency of the terminal, please refer to Figure 1-Figure 5 , this embodiment provides the following technical solutions: A lock station traversal method based on laser edge detection, comprising: Determine whether the vehicle has entered the lock station area and activate the lock station edge detection module for detection. Perform a LiDAR scan of the lock station based on a segmented detection strategy to reduce the amount of calculation and eliminate unnecessary interference items in the middle section. Route correction is performed using a splicing solution that combines positioning weights with multi-route fusion, outputting standard lock station edge lines to guide vehicles in route correction operations.

[0018] In this embodiment, determining whether the vehicle has entered the lock station area specifically includes: Use the positioning device to obtain the vehicle's location information in real time, and compare the obtained vehicle location information with the pre-set locking station area range; When the vehicle's location information is completely within the pre-set locking area, it is determined that the vehicle has entered the locking area; When it is detected that the vehicle position information partially or completely exceeds the pre-set locking station area, it is determined that the vehicle has not entered the locking station area; If, in the process of determining that the vehicle has not entered the lock station area, the distance between the vehicle position and the boundary of the lock station area continues to decrease during the continuous monitoring period, and the reduction rate exceeds the preset threshold, then it is determined that the vehicle position has a trend of approaching the lock station area, and the vehicle position information is continuously monitored until the vehicle position information is compared with the lock station area range again to re-determine whether the vehicle has entered the lock station area.

[0019] In this embodiment, the segmented detection strategy includes three stages: entering the lock station, passing through the lock station, and exiting the lock station: During the station lock phase: When the positioning device determines that the vehicle is gradually approaching the station lock area and its position information shows that it is about to enter the pre-set station lock area, the laser point at the inner edge of the right station lock scanned by the left laser radar of the vehicle is saved (with its height compressed) to the left point set for left station lock edge detection. The laser point at the left station lock scanned by the right laser radar of the vehicle is saved (with its height compressed) to the right point set for right station lock edge detection. The vehicle chassis data, including vehicle speed, angular velocity, and steering information, is acquired based on the vehicle chassis data. The distance range to the center guardrail is determined based on the vehicle chassis data. The distance range is equal to the vehicle speed multiplied by one-fifth of a second. Interference points are filtered out of the acquired locking station laser points based on the distance range to the center guardrail. The relationship between the locking station laser points, the locking station position, and the distance range to the center guardrail is determined. Laser points determined to belong to the center guardrail are removed based on this relationship. During the lock station phase: when it is determined that the vehicle is within the lock station area, the laser points at the inner edge of the left lock station scanned by the left laser of the vehicle are saved in the left point set for left lock station edge detection, and the laser points at the right lock station scanned by the right laser are saved in the right point set for right lock station edge detection; During the exit lock station phase: When it is detected that the vehicle is about to leave the lock station area, continue to follow the operating methods of the passing lock station phase, and save the lock station laser points scanned by the lidar on the left and right sides into the corresponding left point set and right point set respectively.

[0020] In this embodiment, the height of the laser point of the locking station scanned by the laser is compressed; In this embodiment, by accurately judging the vehicle entering the lock station area and applying a segmented detection strategy, the laser radar is used to collect laser points at the edge of the lock station at different stages of the vehicle entering, passing through and exiting the lock station, ensuring the integrity and accuracy of the lock station edge line and accurately identifying the lock station edge, which helps to reduce the risk of collision when the vehicle passes through the lock station. When the vehicle position information partially or completely exceeds the lock station area, by monitoring the changing trend of the distance between the vehicle position and the lock station area boundary, it can be predicted whether the vehicle is approaching the lock station area, thereby realizing a more flexible and intelligent detection process.

[0021] In this embodiment, performing a laser radar scan on the lock station specifically includes: Receive the raw scanning data output by the LiDAR device, including the three-dimensional coordinates and intensity information of the locked laser point; In this embodiment, three laser radar devices are provided. One laser radar is installed at the front of the vehicle and is responsible for scanning and detecting the area directly in front of the vehicle to obtain environmental information in front of the vehicle. When the vehicle approaches, enters, and exits the locking station, it provides data support for determining the position and shape of the locking station in front. Two laser radars are installed on both sides of the vehicle to scan the area on the side of the vehicle and can detect the edge information of the locking stations on the left and right sides of the vehicle, including the internal edge of the locking station and possible obstacles on the side. Through the coordinated operation of these three laser radars, the vehicle can obtain more comprehensive point cloud data of the locking station and the surrounding environment. Preprocess the acquired raw scan data, including denoising to remove outliers caused by equipment errors or environmental factors, time-synchronizing the locking station laser points to ensure that all locking station laser point data corresponds to the vehicle's position and status at the same time, and setting filtering conditions based on the specific size of the vehicle and the actual layout of the locking station area; In this embodiment, the screening conditions specifically include: Eliminate points that are more than 25 meters in front of the vehicle, as these points are of little significance for guiding the passage through the lock station; More than 2.5 meters away from the side of the vehicle, these points may belong to the environment outside the lock station area; LiDAR lock laser points within the area below 0.2 meters and above 1.0 meters in height. These points may belong to the ground or low obstacles, as well as elevated structures or other non-relevant obstacles; Based on real-time vehicle location information, the system determines the vehicle's driving status, such as acceleration, deceleration, and turning, and dynamically adjusts the screening conditions. For example, when the vehicle is accelerating, the screening distance of the front locking station laser point is adjusted according to the driving speed to ensure that the screening conditions match the vehicle's actual driving conditions. When the vehicle is turning, the screening range of the side locking station laser point is appropriately expanded to prevent interference points outside the locking station area due to vehicle posture changes from entering the subsequent processing flow; Perform real-time condition judgment on each locking station laser point, filter the collected scan data according to the preset filtering conditions and dynamically adjusted filtering conditions, and obtain valid locking station laser points based on the filtering results; The valid locking station laser points are classified based on the vehicle's reference frame, and the valid locking station laser points located on the vehicle are saved into the corresponding left point set and right point set based on the segmented detection strategy.

[0022] In this embodiment, the laser radar on the vehicle collects all-round point cloud data of the locking station and the surrounding environment, providing the vehicle with detailed front and side environmental information, which helps to more accurately judge the position and shape of the locking station. The screening conditions are dynamically adjusted according to the real-time position information and driving status of the vehicle, so that the screening of the locking station laser points is more in line with the actual driving conditions of the vehicle, enhancing the adaptability and flexibility of the system. It not only improves the comprehensiveness and accuracy of environmental perception, but also improves the quality of data processing through efficient data preprocessing and dynamic adaptability, and ultimately achieves accurate identification of the edge of the locking station and precise guidance of the vehicle, significantly improving the safety and efficiency of the vehicle in the process of passing through the locking station.

[0023] In this embodiment, the effective locking laser points are classified as follows: Read the valid station-locking laser points in the left point set and the right point set, and determine the data type of the valid station-locking laser points based on the data features of the valid station-locking laser points; Match the corresponding laser scanning data samples in the locking station laser scanning database according to the valid locking station laser point data type, such as normal locking station edge points, possible interference points (such as residual guardrail reflection points), etc. Based on laser scanning data samples, the reasonable fluctuation range and distribution pattern of the effective locking station laser points in the spatial coordinates (x, y, and z directions) are determined, and constraints for data verification are generated. The range of variation of the horizontal (similar to the x direction) and vertical (similar to the y direction) coordinates of the locking station edge points within a specific area should meet certain standards. For suspected interference points, corresponding exclusion rules are set. For example, points with certain combinations of position and intensity characteristics are highly likely to be interference points. According to the generated constraint conditions, the valid locking station laser points in the left point set and the right point set are checked one by one, and the valid locking station laser points that do not meet the constraint conditions are marked as abnormal points; If the number and degree of deviation of abnormal points in the left point set and the right point set are lower than the preset threshold, the abnormal points are corrected according to the distribution pattern of the surrounding normal points; If the number of abnormal points or the degree of deviation in the left point set and the right point set is higher than the preset threshold, the abnormal points are removed and an abnormal warning is issued.

[0024] In this embodiment, the operation of directional elimination of redundant interference items in the middle section, i.e., filtering interference points of the acquired station-locking laser points according to the distance range of the middle guardrail, further includes: When filtering interference points for the left and right locking station laser points, the vehicle is initially assumed to be in front of the locking station. The number of locking station laser points on the left and right sides that are more than 7.5 meters away from the front of the vehicle is counted. If more than half of the laser points at the left and right locking stations are more than 7.5 meters from the vehicle's front, two specific symbols are marked, indicating that the vehicle is not on the corresponding side of the locking station. This means that the vehicle may still be on its way to the locking station and has not yet entered the actual locking station area. These points farther from the front of the vehicle may be generated by the distant environment (rather than the locking station itself). They are not very useful for determining the edge of the locking station or the vehicle's position within the locking station and are more likely to be interference points. Conversely, if more than half of the laser points on the left and right sides of the locking station are less than 7.5 meters away from the front of the vehicle, the vehicle is determined to be in the locking station and two specific flags are marked to indicate that the vehicle is on the corresponding side of the locking station. This helps to identify interference points. When the vehicle is in the locking station, the closer laser points are more likely to be reflection points of the locking station itself. At this time, those points that do not meet the locking station characteristics (such as those located at the middle guardrail position) are the interference points that need to be filtered out. In this embodiment, if Figure 3 As shown, the relative position of the lock station is P, and the distance from the vehicle to the lock station is P x , according to the locking station parameters, the middle position is calculated as P x +L,P x The calculation of G x -v*t,G x represents the current position coordinates of the vehicle, v represents the speed of the vehicle at this time, and t represents the time interval. That is, the frame rate of program execution is 0.2s, then P x =G x -0.2v.

[0025] In this embodiment, after the redundant interference items in the middle section are eliminated, the following steps are also included: The valid locked station laser clouds stored in the left point set and the right point set are processed to obtain two segmented point cloud sets, namely the left segmented point cloud set and the right segmented point cloud set. A specific direction is set and used to segment the laser point clouds in the lists recording the relevant information of the left and right locked stations to obtain two new segmented point cloud sets. Fitting straight lines is performed on the left and right segmented point cloud sets respectively, thereby obtaining the slopes and intercepts of the left and right lock station edge lines respectively. The slopes and intercepts of the left lock station edge line and the slopes and intercepts of the right lock station edge line are calculated using the corresponding fitting algorithm. Verify the slopes and intercepts of the left and right station edge lines. Based on the verification results, determine whether the slopes and intercepts of the left and right station edge lines meet the standards. Output the station edge line parameters that meet the standards, namely the average intercept (i.e., (left line intercept + right line intercept) / 2) and the average slope (i.e., (left line slope + right line slope) / 2), for subsequent route correction. In this embodiment, when the verification result shows that the difference in the slopes of the left and right straight lines is between plus or minus 0.08, and the difference in the intercepts of the left and right straight lines minus 3.5 meters (which can be adjusted according to actual conditions) is within the range of plus or minus 0.4 meters, it is determined that the parameters of the lock station edge straight line at this time meet the standards. If the conditions are not met, no correction operation is performed and the self-driving car drives normally according to satellite positioning.

[0026] In this embodiment, through data processing and outlier marking, as well as early warning when the number of outliers or the degree of deviation exceeds the threshold, the impact of erroneous data on the system is effectively reduced, and the robustness of the system is enhanced. By directional elimination of redundant interference items in the middle section, unnecessary data processing is reduced, the data processing process is optimized, and the operating efficiency of the system is improved. A straight line fitting operation is performed on the laser point clouds of the left and right locking stations to obtain precise locking station edge straight line parameters, providing accurate data support for vehicle route correction, enhancing the safety of the vehicle during the locking station passage and the overall performance of the autonomous driving system.

[0027] In this embodiment, a positioning weight combined with a multi-route fusion splicing solution is used to perform route correction, specifically including: Determine whether the real-time vehicle location information is within the locking station area. When the vehicle is in the locking station area, read the configuration information of the corresponding area, obtain the relative offset of the locking station laser edge line, that is, the distance between the center line of the vehicle's preset original route and the locking station edge line, and calculate the absolute value of the difference between the actual offset and the relative offset. At the same time, obtain the absolute value of the slope of the locking station edge line; When the absolute value of the difference between the actual offset and the relative offset and the absolute value of the slope of the lock station edge line are both less than the preset thresholds, the lock station edge line is confirmed to meet the correction conditions, the lock station edge line parameters at the current moment are saved, and the lock station edge line recognition status flag is set to valid, otherwise no route correction is performed; In this embodiment, when the absolute value of the relative offset of the locking station laser edge line is less than 0.3 meters and the absolute value of the slope value is less than 0.03, the corresponding values ​​at the current moment are saved, and the flag indicating the locking station edge line recognition status is set to true. When this flag is true, it means that the vehicle is positioned within the locking station area and the deviation between the detected locking station edge line and the preset reference line is within an acceptable range. If it is not within this range, it means that the deviation from the actual value is too large. If forced to accept the correction, it will cause huge jitter in the vehicle production field, so no correction is made. Determine whether the current vehicle positioning state is stable. The positioning stability threshold is 0.05, which is set based on the empirical value of the positioning system under stable conditions. It is used to evaluate the stability of the positioning state. If the vehicle positioning state is unstable, the current bias weight is calculated and the bias weight value is adjusted according to the calculation result. The value range is (0, 1). Determine whether it exceeds the set maximum value. If so, take the maximum value and save the bias weight parameter at the current moment. When the lock station edge line identification status flag is valid, the route weight splicing judgment is performed to determine whether the curvature of the current route meets the straight line threshold. If the curvature exceeds the preset straight line threshold, the sequence number of the route point where the curvature exceeds the straight line threshold is recorded. The route curvature threshold is 0.004, which is set based on port route experience and is used to determine whether the route meets the straight line condition. Traverse all route points from the current route to the curvature limit violation point number, and read the corresponding correction weight parameters. Based on the correction weight, perform weighted calculation on the original route and the lock station edge line to generate the final corrected route. The splicing formula is: the y coordinate of the new route point = the y coordinate of the original route point * bias weight + (1-bias weight) * the y coordinate of the original route point.

[0028] In this embodiment, a multi-route fusion splicing solution is used to perform route correction. Retaining a certain portion of the route can greatly reduce the jitter caused by the correction during the passage process. By accurately calculating the difference between the actual offset and the relative offset and combining it with the slope of the locking station edge line, the accuracy of the route correction is ensured. The setting of the identification status flag and stability threshold avoids overcorrection and improves stability. The weighted splicing formula achieves smooth route splicing, which overall improves the driving performance and safety of autonomous vehicles in the locking station area, provides drivers with a continuous and smooth driving experience, ensures smooth driving, and reduces the safety risks of container sliding cabinets.

[0029] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solution and inventive concept of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. A lock station passing method based on laser edge detection, characterized in that: include: Determine whether the vehicle has entered the lock station area and activate the lock station edge detection module for detection. Based on the segmented detection strategy, perform a LiDAR scan of the lock station and directionally eliminate unnecessary interference items in the middle section. Route correction is performed using a splicing solution that combines positioning weights with multi-route fusion, outputting standard lock station edge lines to guide vehicles in route correction operations.

2. The method for passing through a station lock based on laser edge detection according to claim 1, characterized in that: Determine whether the vehicle has entered the lock station area, specifically including: Use the positioning device to obtain the vehicle's location information in real time, and compare the obtained vehicle location information with the pre-set locking station area range; When the vehicle's location information is completely within the pre-set locking area, it is determined that the vehicle has entered the locking area; When it is detected that the vehicle position information partially or completely exceeds the pre-set locking station area, it is determined that the vehicle has not entered the locking station area; If, in the process of determining that the vehicle has not entered the lock station area, the distance between the vehicle position and the boundary of the lock station area continues to decrease during the continuous monitoring period, and the reduction rate exceeds the preset threshold, then it is determined that the vehicle position has a trend of approaching the lock station area, and the vehicle position information is continuously monitored until the vehicle position information is compared with the lock station area range again to re-determine whether the vehicle has entered the lock station area.

3. The method for passing through a station lock based on laser edge detection according to claim 2, characterized in that: The segmented detection method comprises: During the station lock phase: When the positioning device determines that the vehicle is gradually approaching the station lock area and its position information shows that it is about to enter the pre-set station lock area, the laser point at the inner edge of the right station lock area scanned by the left laser radar of the vehicle is saved in the left point set for left station lock edge detection, and the laser point at the left station lock area scanned by the right laser radar of the vehicle is saved in the right point set for right station lock edge detection; During the lock station phase: when it is determined that the vehicle is within the lock station area, the laser points at the inner edge of the left lock station scanned by the left laser of the vehicle are saved in the left point set for left lock station edge detection, and the laser points at the right lock station scanned by the right laser are saved in the right point set for right lock station edge detection; During the exit lock station phase: When it is detected that the vehicle is about to leave the lock station area, continue to follow the operating methods of the passing lock station phase, and save the lock station laser points scanned by the lidar on the left and right sides into the corresponding left point set and right point set respectively.

4. The method for passing through a station lock based on laser edge detection according to claim 3, characterized in that: During the stage of passing through the locking station, it also includes: obtaining vehicle chassis data based on the sensors installed on the vehicle, determining the distance range of the middle guardrail based on the vehicle chassis data, filtering the interference points of the obtained locking station laser points according to the distance range of the middle guardrail, judging the relationship between the locking station laser points and the locking station position and the distance range of the middle guardrail, and removing the laser points determined to belong to the middle guardrail based on the relationship.

5. The method for passing through a station lock based on laser edge detection according to claim 1, characterized in that: Perform a LiDAR scan of the lock station, including: Receive the raw scanning data output by the LiDAR device, including the three-dimensional coordinates and intensity information of the locked laser point; Pre-process the acquired raw scan data and set filtering criteria based on the specific dimensions of the vehicle and the actual layout of the lock station area; Based on the real-time location information of the vehicle, the driving status of the vehicle is judged and the screening conditions are dynamically adjusted; Perform real-time condition judgment on each locking station laser point, filter the collected scanning data according to the preset filtering conditions and dynamically adjusted filtering conditions, and obtain valid locking station laser points based on the filtering results.

6. The method for passing through a lock station based on laser edge detection according to claim 5, characterized in that: The laser radar scanning of the locking station also includes: classifying the valid locking station laser points based on the vehicle's reference system, and saving the valid locking station laser points located on the vehicle into corresponding left point sets and right point sets based on a segmented detection strategy.

7. The method for passing through a lock station based on laser edge detection according to claim 6, characterized in that: Classify the effective locking laser points, including: Read the valid station-locking laser points in the left point set and the right point set, and determine the data type of the valid station-locking laser points based on the data features of the valid station-locking laser points; Match the corresponding laser scanning data samples in the locking station laser scanning database according to the valid locking station laser point data type; Based on the laser scanning data samples, the reasonable fluctuation range and distribution pattern of the effective locking station laser point in the spatial coordinates are determined, and the constraint conditions for data verification are generated; According to the generated constraint conditions, the valid locking station laser points in the left point set and the right point set are checked one by one, and the valid locking station laser points that do not meet the constraint conditions are marked as abnormal points; If the number and degree of deviation of abnormal points in the left point set and the right point set are lower than the preset threshold, the abnormal points are corrected according to the distribution pattern of the surrounding normal points; If the number of abnormal points or the degree of deviation in the left point set and the right point set is higher than the preset threshold, the abnormal points are removed and an abnormal warning is issued.

8. The method for passing through a lock station based on laser edge detection according to claim 4, characterized in that: The operation of directional elimination of redundant interference items in the middle segment also includes: When filtering interference points for the left and right locking station laser points, the vehicle is initially assumed to be in front of the locking station. The number of locking station laser points on the left and right sides that are more than 7.5 meters away from the front of the vehicle is counted. If more than half of the left and right locking station laser points are more than 7.5 meters away from the front of the vehicle, two special signs will be marked to indicate that the vehicle is not on the corresponding side of the locking station; On the contrary, when the number of locking station laser points less than 7.5 meters from the front of the vehicle on the left and right sides is counted to be more than half, the vehicle is determined to be in the locking station, and two specific flag bits are marked to indicate that the vehicle is in the corresponding side of the locking station.

9. The method for passing through a lock station based on laser edge detection according to claim 8, characterized in that: After removing the redundant interference items in the middle section, it also includes: The valid locked station laser clouds stored in the left point set and the right point set are processed to obtain two segmented point cloud sets, namely the left segmented point cloud set and the right segmented point cloud set; Perform straight line fitting operations on the left segmentation point cloud set and the right segmentation point cloud set respectively, so as to obtain the slope and intercept of the left and right locking station edge straight lines respectively; Verify the slope and intercept of the left and right side lock station edge straight lines, determine whether the slope and intercept of the left and right side lock station edge straight lines meet the standards based on the verification results, and output the lock station edge line parameters that meet the standards.

10. The method for passing through a lock station based on laser edge detection according to claim 1, characterized in that: Route correction is performed using a splicing solution that combines positioning weights with multi-route fusion, specifically including: Determine whether the real-time vehicle location information is within the locking station area. If the vehicle is within the locking station area, read the configuration information of the corresponding area, obtain the relative offset of the locking station laser edge line, and calculate the absolute value of the difference between the actual offset and the relative offset. At the same time, obtain the absolute value of the slope of the locking station edge line. When the absolute value of the difference between the actual offset and the relative offset and the absolute value of the slope of the lock station edge line are both less than the preset thresholds, the lock station edge line is confirmed to meet the correction conditions, the lock station edge line parameters at the current moment are saved, and the lock station edge line recognition status flag is set to valid, otherwise no route correction is performed; Determine whether the current vehicle positioning state is stable. If the vehicle positioning state is unstable, calculate the current bias weight and adjust the bias weight value according to the calculation result; When the lock station edge line recognition status flag is valid, the route weight splicing judgment is performed to determine whether the curvature of the current route meets the straight line threshold. If the curvature exceeds the preset straight line threshold, the sequence number of the route point where the curvature exceeds the straight line threshold is recorded; Traverse all route points from the current route to the curvature limit point sequence number, read the corresponding correction weight parameters, and perform weighted calculation on the original route and the lock station edge line based on the correction weight to generate the final corrected route.

Images