Region boundary detection method and device

Abstract

The invention discloses a method and a device for detecting a region boundary, which are applied to the fields of automatic driving and smart mines, and comprise the following steps: in response to a received input instruction, constructing a to-be-detected line segment set corresponding to the region boundary based on a starting point position and an ending point position carried in the input instruction, a plurality of to-be-detected line segments included in the to-be-detected line segment set form a region boundary; the collection vehicle is controlled to start driving along the area boundary, and when the collection vehicle meets a preset detection condition, the current detection progress of the area boundary is determined based on the driving track of the collection vehicle, and the current detection progress is used for representing the proportion of a target line segment in the to-be-detected line segments in the to-be-detected line segments; the target line segment is used for representing the line segment of the sensing data successfully acquired by the acquired vehicle; and outputting the current detection progress of the region boundary. The technical problem that the updating efficiency of the area boundary is low due to the fact that sensing data of the area boundary needs to be collected repeatedly in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the fields of autonomous driving and smart mining, and in particular to a method and device for detecting a regional boundary. Background Art

[0002] In the soil dumping operation scenario, the soil dumping line is outside the operation area, and a soil dumping position is set near the soil dumping line for vehicles to perform soil dumping operations. During the soil dumping operation, the operation area will continue to expand, causing the position of the soil dumping line to change. Therefore, the soil dumping line needs to be updated with high precision to ensure the safety of the vehicle during the soil dumping operation.

[0003] Currently, the boundaries of the working area can be collected by collecting vehicles to collect perception data, thereby generating high-precision regional boundaries. However, in the process of collecting perception information by the collection vehicle, data missing problems often occur, resulting in poor integrity of the collected perception data, requiring collection personnel to repeatedly collect data, resulting in low efficiency in updating the regional boundaries.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present invention provide a method and device for detecting region boundaries, so as to at least solve the technical problem in the related art that the perception data of region boundaries need to be repeatedly collected multiple times, resulting in low updating efficiency of region boundaries.

[0006] According to one aspect of an embodiment of the present invention, a method for detecting an area boundary is provided, comprising: in response to a received input instruction, constructing a set of to-be-detected line segments corresponding to the area boundary based on a starting position and an end position carried in the input instruction, wherein the starting position is used to characterize the starting point of the area boundary, the end position is used to characterize the end point of the area boundary, and a plurality of to-be-detected line segments included in the set of to-be-detected line segments constitute the area boundary; controlling a collection vehicle to start driving along the area boundary, and determining a current detection progress of the area boundary based on the driving trajectory of the collection vehicle whenever the collection vehicle meets a preset detection condition, wherein the collection vehicle is used to collect perception data of the area boundary during driving along the area boundary, the current detection progress is used to characterize the proportion of a target line segment among a plurality of to-be-detected line segments in the plurality of to-be-detected line segments, and the target line segment is used to characterize a line segment whose perception data is successfully collected by the collection vehicle; and outputting the current detection progress of the area boundary.

[0007] Furthermore, based on the collected vehicle's driving trajectory, the current detection progress of the area boundary is determined, including: based on the collected vehicle's driving trajectory, determining a first parameter corresponding to at least one trajectory segment in the driving trajectory, wherein the type of the first parameter includes one of the following: a vertical direction vector, a heading angle; based on the first parameter corresponding to at least one trajectory segment, determining a target line segment from a plurality of line segments to be detected; based on the number of the target line segment and the number of the plurality of line segments to be detected, obtaining the current detection progress.

[0008] Further, in the case where the type of the first parameter includes: a vertical direction vector, based on the first parameter corresponding to at least one trajectory segment, determining the target line segment from multiple line segments to be detected, including: making an intersection judgment between the first parameter corresponding to each trajectory segment and each line segment to be detected; determining a first distance between the driving trajectory and the line segment to be detected based on the first parameter corresponding to the trajectory segment; and determining that the line segment to be detected is a target line segment when the first parameter corresponding to the trajectory segment intersects with the line segment to be detected and the first distance is less than a first preset distance.

[0009] Furthermore, based on the driving trajectory of the collected vehicle, the current detection progress of the regional boundary is determined, including: obtaining the historical detection progress of the regional boundary, wherein the historical detection progress is used to characterize the detection progress determined when the collected vehicle met the preset detection conditions last time, and when the collected vehicle meets the preset detection conditions for the first time, the historical detection progress is the preset progress; based on the current trajectory point in the driving trajectory of the collected vehicle and a historical trajectory point before the current trajectory point, a second parameter of the driving trajectory is determined, wherein the second parameter includes one of the following: a vertical direction vector, a heading angle; based on the second parameter, a target line segment is determined from multiple line segments to be detected; based on the second parameter, the historical detection progress is adjusted based on the number of target line segments to obtain the current detection progress.

[0010] Furthermore, based on the second parameter, a target line segment is determined from multiple line segments to be detected, including: determining at least one candidate line segment marked with a preset state among the multiple line segments to be detected, wherein the preset state is used to characterize that at least one candidate line segment has not been successfully collected by the collection vehicle for perception data, and when the collection vehicle meets the preset detection conditions for the first time, multiple line segments to be detected are marked with the preset state; based on the second parameter, determining the target line segment from at least one candidate line segment; and clearing the preset state marked for the target line segment.

[0011] Furthermore, after controlling the collection vehicle to start driving along the area boundary, the method also includes: obtaining a current trajectory point of the collection vehicle; determining a second distance between the current trajectory point and a historical trajectory point of the collection vehicle; and determining that the collection vehicle meets a preset detection condition when the second distance is greater than a second preset distance.

[0012] Furthermore, based on the starting point position and the end point position carried in the input instruction, a set of line segments to be detected corresponding to the area boundary is constructed, including: determining whether there is historical perception data of the area boundary, wherein the historical perception data includes perception data of multiple historical detection points; in the case of the existence of historical perception data, the multiple historical detection points are cropped based on the starting point position and the end point position to obtain a cropped detection point set, and a set of line segments to be detected is constructed based on the cropped detection point set; in the case of the absence of historical perception data, interpolation processing is performed between the starting point position and the end point position to generate a set of line segments to be detected.

[0013] Furthermore, the plurality of historical detection points are clipped based on the starting position and the end position to obtain a clipped detection point set, including: searching among the plurality of historical detection points based on the starting position to determine a first target detection point, wherein a distance between the first target detection point and the starting position is less than a distance between a first other detection point and the starting position, and the first other detection point is used to characterize detection points other than the first target detection point in the plurality of historical detection points; searching among the plurality of historical detection points based on the end position to determine a second target detection point, wherein a distance between the second target detection point and the end position is less than a distance between the second other detection point and the end position, and the second other detection point is used to characterize detection points other than the second target detection point in the plurality of historical detection points; determining a candidate detection point between the first target detection point and the second target detection point from the plurality of historical detection points; and clipping detection points other than the candidate detection points from the plurality of historical detection points to obtain a clipped detection point set.

[0014] Furthermore, a set of line segments to be detected is constructed based on the cropped set of detection points, including: determining a target spacing between detection points based on the work task scenario corresponding to the area boundary; interpolating the cropped set of detection points according to the target spacing to generate a set of points to be detected; and segmenting the lines between two adjacent detection points in the set of detection points to obtain a set of line segments to be detected.

[0015] Furthermore, interpolation processing is performed between the starting point position and the end point position to generate a set of line segments to be detected, including: determining the target spacing between detection points based on the work task scenario corresponding to the area boundary; interpolation processing is performed between the starting point position and the end point position according to the target spacing to generate a set of points to be detected; and segmentation processing is performed on the line between two adjacent detection points in the set of points to be detected to obtain the set of line segments to be detected.

[0016] Furthermore, outputting the current detection progress of the region boundary includes one of the following: displaying the current detection progress of the region boundary in an interactive interface; and playing the current detection progress of the region boundary by voice broadcast.

[0017] Furthermore, the method also includes: when the collected vehicle does not meet the preset detection conditions, outputting the historical detection progress of the area boundary.

[0018] Furthermore, the method also includes: outputting line segments marked with a preset state among a plurality of line segments to be detected; and controlling the collection vehicle to re-collect the perception data of the line segments marked with the preset state.

[0019] According to another aspect of an embodiment of the present invention, a device for detecting an area boundary is also provided, including: a construction module, for responding to a received input instruction, and constructing a set of to-be-detected line segments corresponding to the area boundary based on a starting point position and an end point position carried in the input instruction, wherein the starting point position is used to characterize the starting point of the area boundary, and the end point position is used to characterize the end point of the area boundary, and a plurality of to-be-detected line segments contained in the to-be-detected line segment set constitute the area boundary; a determination module, for controlling a collection vehicle to start driving along the area boundary, and whenever the collection vehicle meets a preset detection condition, determining a current detection progress of the area boundary based on the driving trajectory of the collection vehicle, wherein the collection vehicle is used to collect perception data of the area boundary during driving along the area boundary, and the current detection progress is used to characterize the proportion of a target line segment among a plurality of to-be-detected line segments in the plurality of to-be-detected line segments, and the target line segment is used to characterize a line segment whose perception data is successfully collected by the collection vehicle; and an output module, for outputting the current detection progress of the area boundary.

[0020] According to another aspect of an embodiment of the present invention, there is further provided an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the method in each embodiment of the present invention is executed when the program is running.

[0021] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0022] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0023] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0024] According to another aspect of the embodiments of the present invention, a computer program is further provided. When the computer program is executed by a processor, the methods in the embodiments of the present invention are implemented.

[0025] In an embodiment of the present invention, in response to a received input instruction, a set of line segments to be detected corresponding to the regional boundary is constructed based on the starting position and the end position carried in the input instruction, and then the collection vehicle is controlled to start driving along the regional boundary, and whenever the collection vehicle meets the preset detection conditions, the current detection progress of the regional boundary is determined based on the driving trajectory of the collection vehicle, thereby outputting the current detection progress of the regional boundary, and achieving the purpose of progress detection in the real-time data collection process. It is easy to notice that, because the current detection progress is executed when the collection vehicle meets the preset detection conditions, and when it is determined that the current detection progress is lagging, it can be output in real time, so that in the process of perceptual data collection of the regional boundary, the regional boundary can be detected in real time, which is convenient for the collection personnel to report the progress, and the integrity of the collected data is guaranteed, and the collection efficiency is improved. The technical effect is achieved, thereby solving the technical problem that the perceptual data of the regional boundary needs to be repeatedly collected many times in the related technology, resulting in low update efficiency of the regional boundary. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0027] Figure 1 is a flow chart of a method for detecting a region boundary according to an embodiment of the present invention;

[0028] Figure 2 is a schematic diagram of a method for detecting a region boundary according to an embodiment of the present invention;

[0029] Figure 3 is a schematic diagram of a device for detecting a region boundary according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0032] According to an embodiment of the present invention, a method for detecting area boundaries is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0033] Figure 1 is a flow chart of a method for detecting a region boundary according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0034] Step S102, in response to the received input instruction, construct a set of line segments to be detected corresponding to the area boundary based on the starting position and the end position carried in the input instruction, wherein the starting position is used to represent the starting point of the area boundary, and the end position is used to represent the end point of the area boundary, and the multiple line segments to be detected contained in the set of line segments to be detected constitute the area boundary.

[0035] The above-mentioned input instructions can be instructions input by personnel on the vehicle on the central control screen of the vehicle, or instructions input by personnel on the vehicle through an APP on an electronic device, or instructions input by operators in the cloud, but are not limited to these.

[0036] In an optional embodiment, when it is necessary to update the regional boundary through a collection vehicle, the personnel on the collection vehicle can operate on the APP to select the starting point and the end point of the boundary area, thereby generating an input instruction carrying the starting point position and the end point position. The APP can send the input instruction to the collection vehicle through the network, thereby controlling the collection vehicle to collect the perception data of the regional boundary, or the APP can send the input instruction to the cloud through the network, and the cloud controls the collection vehicle to collect the perception data of the regional boundary.

[0037] In another optional embodiment, when it is necessary to update the area boundary through a collection vehicle, the operator on the cloud side can input the starting point and end point of the boundary area, thereby generating an input instruction carrying the starting point location and the end point location. The cloud side then controls the collection vehicle to collect perception data on the area boundary, or sends the input instruction to the collection vehicle through the network, thereby controlling the collection vehicle to collect perception data on the area boundary.

[0038] Considering that the length of the region boundary is usually long, in order to avoid data loss during the acquisition process, we can first determine the line segment between the two positions based on the starting position and the end position as the region boundary, and then divide the complete line segment into multiple line segments to be detected, and further detect each line segment to be detected in turn. Figure 2 As shown, after inputting the starting position start and the end position end, the area boundary between the two positions can be divided to obtain 30 line segments (such as Figure 2 The set of line segments to be detected is composed of the line segments between the solid triangles (shown in FIG. 1 ).

[0039] Step S104, controlling the collection vehicle to start driving along the area boundary, and whenever the collection vehicle meets the preset detection conditions, determining the current detection progress of the area boundary based on the driving trajectory of the collection vehicle, wherein the collection vehicle is used to collect perception data of the area boundary while driving along the area boundary, and the current detection progress is used to characterize the proportion of the target line segment among the multiple line segments to be detected, and the target line segment is used to characterize the line segment whose perception data is successfully collected by the collection vehicle.

[0040] The above-mentioned collection vehicle can be an autonomous vehicle or a manually driven vehicle, and the vehicle is provided with a variety of different types of sensors, through which the regional boundary can be sensed, thereby collecting the perception data of the regional boundary. The perception data here can be point cloud data collected by a laser radar sensor, a millimeter wave radar sensor, etc., or image data collected by a camera, a fisheye camera, etc., but is not limited thereto. In the embodiments of the present application, a variety of different types of data are used as examples for illustration.

[0041] Considering that the collection vehicle can collect the perception data of the regional boundary in real time during the driving process from the starting position to the end position, in order to avoid the problem of data loss during the real-time collection process, the collected perception data can be verified in real time during the process of the collection vehicle collecting the perception data in real time to determine the coverage of the data collection, that is, to determine the detection progress of the regional boundary. Considering that the length of the regional boundary is long, if the verification is performed in real time, the detection progress of the regional boundary will not change much when the collection vehicle travels a short distance, but the computing resources are wasted. Therefore, in the embodiment of the present application, the detection progress of the regional boundary can be determined after determining that the collection vehicle meets certain conditions. The above-mentioned preset detection condition can be the driving distance or driving time of the collection vehicle when the detection progress changes significantly, that is, the preset detection condition can be the driving distance of the collection vehicle exceeds the distance threshold, or the driving time of the collection vehicle exceeds the time threshold, but it is not limited to this. The specific values ​​of the two thresholds here can be limited according to actual conditions, and the present application does not limit this.

[0042] The above-mentioned current detection progress can be the progress of the data collected by the collection vehicle accurately, that is, the probability of no data loss. Since the area boundary has been divided into multiple segments to be detected, the current detection progress can be taken as the proportion of segments that successfully collect perception data in the multiple segments to be detected. For example, the current detection progress can be the ratio of the number of target segments to the total number of multiple segments to be detected. For another example, the current detection progress can be the ratio of the length of the target segment to the total length of multiple segments to be detected, but is not limited to this.

[0043] In an optional embodiment, after determining the starting point and the end point, the collection vehicle can be controlled to travel along the boundary of the area, and during the driving process, each time the collection vehicle is detected to meet the preset detection conditions, the detection progress can be determined. At this time, the current detection progress of the area boundary can be determined based on the driving trajectory of the collection vehicle, that is, based on the driving trajectory of the collection vehicle, the target line segment for which the collection vehicle successfully collects the perception data is determined, and then the proportion of the target line segment in the multiple line segments to be detected is determined to obtain the current detection progress.

[0044] For example, the preset detection condition is that the driving distance of the collected vehicle exceeds the distance threshold (such as 2m). Figure 2 As shown, when the collection vehicle travels from right to left along the boundary of the area (such as Figure 2 After that, determine the driving distance of the collected vehicle (as shown by the arrow in the middle). Figure 2If so, a detection progress is determined based on the driving trajectory of the collection vehicle. Then the collection vehicle continues to drive to determine whether the driving distance of the collection vehicle relative to the last detection position reaches 10m. If so, a new detection progress is determined again based on the driving trajectory of the collection vehicle. This process is repeated in this way until the collection vehicle completely collects the perception data of the area boundary, or the collection vehicle drives to the end position.

[0045] Optionally, since the collection vehicle is always in a driving state during the process of collecting perception data, the driving trajectory of the collection vehicle is always in a cumulative state. If the detection progress is determined based on the driving trajectory, the calculation of the detection progress is repeated, resulting in a waste of computing resources. In order to further avoid the waste of computing resources, the detection progress determined each time can be stored as the historical detection progress for the next time, so that based on the historical detection progress, it is only necessary to determine the new line segments that successfully collect perception data during this detection process as target line segments, and update the historical detection progress based on the number of target line segments, so as to obtain the current detection progress during this detection process.

[0046] For example, Figure 2 As shown, if it is determined that 20 of the 30 line segments have successfully collected perception data, that is, 20 line segments are target line segments, then it can be determined that the current detection progress is: 20 / 30=66.67%.

[0047] In step S104, the current detection progress of the area boundary is output.

[0048] In an optional embodiment, the current detection progress can be output in the form of text, image, voice, etc., so that the personnel on the collection vehicle or the operator in the cloud can determine whether there is data loss, so that the line segment to be detected where data loss occurs can be repeatedly collected as soon as possible. The text here can be the text corresponding to the current detection progress, for example, 66.67%; the image here can be an image that can reflect the current detection progress, such as a progress bar; the voice here can be the current detection progress announced by voice, for example, "The current detection progress is 66.67%", but is not limited to this.

[0049] For personnel on the collection vehicle, if the personnel generates input instructions by operating the central control screen of the collection vehicle, the current detection progress can be displayed on the central control screen or played by voice through the speaker of the collection vehicle; if the personnel generates input instructions by operating the APP, the current detection progress can be displayed on the APP or played by voice through the electronic device where the APP is installed. For operators in the cloud, the current detection progress can be displayed on the electronic device used by the operator or played by voice through the electronic device.

[0050] Through the above steps, in response to the received input instruction, based on the starting position and the end position carried in the input instruction, a set of line segments to be detected corresponding to the regional boundary is constructed, and then the collection vehicle is controlled to start driving along the regional boundary, and whenever the collection vehicle meets the preset detection conditions, the current detection progress of the regional boundary is determined based on the driving trajectory of the collection vehicle, thereby outputting the current detection progress of the regional boundary, and achieving the purpose of progress detection in the real-time data collection process. It is easy to notice that, because the current detection progress is executed when the collection vehicle meets the preset detection conditions, and when it is determined that the current detection progress is lagging, it can be output in real time, so that in the process of perceptual data collection of the regional boundary, the regional boundary can be detected in real time, which is convenient for the progress broadcast to the collection personnel, and the integrity of the collected data is guaranteed and the collection efficiency is improved. The technical effect is achieved, thereby solving the technical problem that the perceptual data of the regional boundary needs to be repeatedly collected many times in the related technology, resulting in low update efficiency of the regional boundary.

[0051] In the above-mentioned embodiment of the present application, based on the collected driving trajectory of the vehicle, the current detection progress of the area boundary is determined, including: based on the collected driving trajectory of the vehicle, determining a first parameter corresponding to at least one trajectory segment in the driving trajectory, wherein the type of the first parameter includes one of the following: a vertical direction vector, a heading angle; based on the first parameter corresponding to at least one trajectory segment, determining a target line segment from multiple line segments to be detected; based on the number of target line segments and the number of multiple line segments to be detected, obtaining the current detection progress.

[0052] The above driving trajectory can be the trajectory that the vehicle has traveled from the beginning of the driving to the time when the vehicle meets the preset detection conditions, which includes multiple trajectory points. Each trajectory point indicates that the vehicle meets the preset detection conditions once. The line segment between two adjacent trajectory points is a trajectory segment, which indicates the trajectory that the vehicle has traveled between two detection progress determinations. Therefore, the driving trajectory of the vehicle includes one or more trajectory segments.

[0053] When the collection vehicle is driving, the direction of the collection vehicle is usually parallel to the boundary of the area. Therefore, if a certain track segment of the collection vehicle is parallel to a line segment to be detected, it can be determined that the collection vehicle can successfully collect the perception data corresponding to the line segment to be detected. Furthermore, considering that the data collection range of the sensor installed on the collection vehicle is limited, in order to ensure that the collection vehicle can successfully collect the perception data, it is necessary not only to determine whether the track segment is parallel to the line segment to be detected, but also to determine whether the distance between the track segment and the line segment to be detected is less than the maximum detection distance of the sensor, that is, the distance threshold.

[0054] In an optional embodiment, the vertical direction vector corresponding to a certain trajectory segment can be determined based on the coordinates of the two endpoints of the trajectory segment, and it can be further determined whether the vertical direction vector intersects with a certain line segment to be detected, and whether the distance between the trajectory segment and the line segment to be detected is less than. If they intersect, it can be determined that the trajectory segment is parallel to the line segment to be detected. At this time, it can be determined that the line segment to be detected is the target line segment; if they do not intersect, it can be determined that the trajectory segment is not parallel to the line segment to be detected, the collection vehicle fails to successfully collect the perception data corresponding to the line segment to be detected, and the line segment to be detected is not the target line segment.

[0055] In another optional embodiment, during the process of generating a certain trajectory segment, the orientation angle corresponding to the trajectory segment can be determined, and whether the trajectory segment is parallel to the line segment to be detected can be further determined based on the orientation angle. If they are parallel, it can be determined that the line segment to be detected is the target line segment; if they are not parallel, it can be determined that the collection vehicle has not successfully collected the perception data corresponding to the line segment to be detected, and the line segment to be detected is not the target line segment.

[0056] After the target line segment is determined, the ratio of the number of the target line segment to the total number of the multiple line segments to be detected can be obtained to obtain the current detection progress. For example, Figure 2 As shown, if it is determined that 20 of the 30 line segments are target line segments, it can be determined that the current detection progress is: 20 / 30=66.67%.

[0057] In the above-mentioned embodiment of the present application, when the type of the first parameter includes: a vertical direction vector, based on the first parameter corresponding to at least one trajectory segment, a target segment is determined from multiple segments to be detected, including: performing an intersection judgment between the first parameter corresponding to each trajectory segment and each segment to be detected; determining a first distance between the driving trajectory and the segment to be detected based on the first parameter corresponding to the trajectory segment; and determining that the segment to be detected is a target segment when the first parameter corresponding to the trajectory segment intersects with the segment to be detected and the first distance is less than a first preset distance.

[0058] The above-mentioned first preset distance can be the maximum detection distance of the sensor installed on the collection vehicle, or it can be the detection distance of the sensor when the accuracy of the perception data collected by the sensor meets certain accuracy requirements, but it is not limited to this and can be determined according to actual needs.

[0059] In an optional embodiment, after obtaining the vertical direction vector of a certain trajectory segment, the vertical direction vector can be judged to intersect with each line segment to be detected. The specific judgment process can be implemented using an algorithm in the relevant technology, and this application does not make specific limitations on this. In addition, the distance between the trajectory segment and the line segment to be detected, that is, the first distance mentioned above, can be further determined. If the vertical direction vector intersects with a certain line segment to be detected, and the first distance is less than the first preset distance, it is determined that the line segment to be detected is a target line segment; if the vertical direction vector does not intersect with a certain line segment to be detected, or the first distance is greater than the first preset distance, it is determined that the line segment to be detected is not a target line segment.

[0060] In the above embodiment of the present application, based on the driving trajectory of the collected vehicle, the current detection progress of the regional boundary is determined, including: obtaining the historical detection progress of the regional boundary, wherein the historical detection progress is used to characterize the detection progress determined when the collected vehicle meets the preset detection conditions for the last time, and when the collected vehicle meets the preset detection conditions for the first time, the historical detection progress is the preset progress; based on the current trajectory point in the driving trajectory of the collected vehicle and a historical trajectory point before the current trajectory point, a second parameter of the driving trajectory is determined, wherein the second parameter includes one of the following: a vertical direction vector, a heading angle; based on the second parameter, a target line segment is determined from multiple line segments to be detected; based on the second parameter, the historical detection progress is adjusted based on the number of target line segments to obtain the current detection progress.

[0061] The above-mentioned historical detection progress can be the detection progress determined by the above-mentioned method when the last collection vehicle meets the preset detection conditions. For the case where the collection vehicle meets the preset detection conditions for the first time, since the detection progress has not been determined before, it can be considered that the collection vehicle has not successfully collected the perception data of the line segment to be detected. Therefore, it can be considered that the historical detection progress at this time is 0, which is the above-mentioned preset progress, but is not limited to this.

[0062] In an optional embodiment, considering that each time the acquisition vehicle meets the preset detection conditions, the line segments to be detected used to determine the current detection progress are repeated, in order to reduce computing resource consumption and save detection time, the historical detection progress can be obtained without repeating the judgment of the line segments to be detected that have been judged. On this basis, when the acquisition vehicle meets the preset detection conditions, the historical detection progress is first obtained, and based on the current position of the acquisition vehicle (i.e., the current trajectory point mentioned above) and the position of the acquisition vehicle when the acquisition vehicle last met the predicted detection conditions (i.e., the historical trajectory point mentioned above), a current trajectory segment is constructed, and the second parameter of the current trajectory segment is determined, and then the method of determining the target line segment based on the first parameter in the above embodiment is used to determine the target line segment based on the second parameter.

[0063] After determining the target line segment, the historical detection progress can be updated based on the number of target line segments or the length of the target line segment. For example, the detection progress calculated this time can be determined based on the proportion of the target line segment in multiple line segments to be detected, and then the sum of the detection progress calculated this time and the historical detection progress is obtained to obtain the current detection progress. For another example, the target line segment determined this time can be summarized with the target line segment in the historical detection progress to determine the total target line segment, and the proportion of the total target line segment in multiple line segments to be detected can be determined to obtain the current detection progress.

[0064] In the above embodiment of the present application, based on the second parameter, a target line segment is determined from multiple line segments to be detected, including: determining at least one candidate line segment marked with a preset state among the multiple line segments to be detected, wherein the preset state is used to characterize that at least one candidate line segment has not been successfully collected by the collection vehicle for perception data, and when the collection vehicle meets the preset detection conditions for the first time, multiple line segments to be detected are marked with the preset state; based on the second parameter, determining the target line segment from at least one candidate line segment; and clearing the preset state marked for the target line segment.

[0065] The above-mentioned candidate line segment may be a line segment to be detected that is marked with a special state. For example, the state of the line segment to be detected may be set to a special value, thereby indicating that the collection vehicle has not successfully collected the perception data of the candidate line segment. The above-mentioned clearing of the preset state may be clearing the above-mentioned special state. For example, the state of the line segment to be detected may be set to a preset value, or the state of the line segment to be detected may not be limited, but is not limited thereto. In an embodiment of the present application, the line segment to be detected for which the perception data has not been successfully collected may be marked as uncovered, and the line segment to be detected for which the perception data has been successfully collected may be marked as covered.

[0066] In an optional embodiment, the direction of the collection vehicle may change during driving, resulting in the random appearance of the line segments to be detected that have not successfully collected the sensing data, and the positions of the line segments to be detected are not fixed. In addition, the collection vehicle can repeatedly collect the line segments to be detected that have not successfully collected the sensing data in the previous collection process at any time during driving. Therefore, whether the line segment to be detected is the target line segment may change in any judgment process.

[0067] On this basis, in order to avoid repeated judgment of the target line segment, the target line segment and the non-target line segment can be marked as different states by marking the line segment to be detected, so that in the process of determining the target line segment this time, only the non-target line segment, that is, at least one candidate line segment marked with a preset state can be judged, and the other line segments to be detected can be considered as target line segments, and after the target line segment is determined again from at least one candidate line segment, the preset state of the target line segment can be cleared. For example, in the process of determining the target line segment this time, only the line segment to be detected whose state is uncovered can be judged, and after determining that the line segment to be detected is the target line segment, the state of the line segment to be detected is set to covered.

[0068] In the above embodiment of the present application, after controlling the collection vehicle to start driving along the boundary of the area, the method also includes: obtaining the current trajectory point of the collection vehicle; determining a second distance between the current trajectory point and the historical trajectory point of the collection vehicle; and determining that the collection vehicle meets the preset detection condition when the second distance is greater than the second preset distance.

[0069] In an optional embodiment, in order to avoid wasting computing resources by determining the detection progress in real time, the current position of the collection vehicle can be determined in real time or periodically during the driving process of the collection vehicle as the current trajectory point, and compared with the historical trajectory point that last met the preset detection condition, and the distance between the two trajectory points (i.e., the second distance mentioned above) is calculated. If the second distance is greater than the second preset distance, it is determined that the collection vehicle meets the preset detection condition and the detection progress can be determined; if the second distance is less than or equal to the second preset distance, it is determined that the collection vehicle does not meet the preset detection condition and there is no need to determine the detection progress.

[0070] In the above embodiment of the present application, based on the starting position and the end position carried in the input instruction, a set of line segments to be detected corresponding to the area boundary is constructed, including: determining whether there is historical perception data of the area boundary, wherein the historical perception data includes perception data of multiple historical detection points; in the case of the existence of historical perception data, the multiple historical detection points are cropped based on the starting position and the end position to obtain a cropped detection point set, and the set of line segments to be detected is constructed based on the cropped detection point set; in the case of the absence of historical perception data, interpolation processing is performed between the starting position and the end position to generate a set of line segments to be detected.

[0071] In an optional embodiment, considering that the collection vehicle will continuously collect perception data on the regional boundary, therefore, after receiving the input command, it can be first determined whether there is historical perception data, that is, whether there is a perception result of the regional boundary, which can be a historical vector line of the regional boundary (often a curve with relatively sparse points), and the historical perception data can be stored on the collection vehicle or in the cloud. If it is determined that there is historical perception data, in order to improve the accuracy of determining the progress of this detection, the points on the historical vector line can be cropped based on the starting position and the end position, and then the cropped detection point set can be segmented to obtain trajectory segments of uniform length, thereby constructing a set of segments to be detected. If there is no historical perception data, the line between the starting position and the end position can be generated by interpolating between the starting position and the end position, and then the line can be segmented to obtain trajectory segments of uniform length, thereby constructing a set of segments to be detected.

[0072] In the above embodiment of the present application, a plurality of historical detection points are clipped based on a starting point position and an end point position to obtain a clipped detection point set, including: searching among the plurality of historical detection points based on the starting point position to determine a first target detection point, wherein a distance between the first target detection point and the starting point position is less than a distance between a first other detection point and the starting point position, and the first other detection point is used to characterize detection points other than the first target detection point in the plurality of historical detection points; searching among the plurality of historical detection points based on the end point position to determine a second target detection point, wherein a distance between the second target detection point and the end point position is less than a distance between the second other detection point and the end point position, and the second other detection point is used to characterize detection points other than the second target detection point in the plurality of historical detection points; determining a candidate detection point located between the first target detection point and the second target detection point from the plurality of historical detection points; and clipping detection points other than the candidate detection points from the plurality of historical detection points to obtain a clipped detection point set.

[0073] In an optional embodiment, considering that the area boundary is often constantly changing, there is a difference between the historical perception data and the actual position of the area boundary. Therefore, by searching near the starting point and the end point, the nearest point in the horizontal position can be searched as the starting point and the end point, and the historical detection points outside the starting point and the end point in the historical perception data are deleted, and only the historical detection points between the starting point and the end point are retained as the cropped detection point set, thereby further reducing the number of detected line segments that need to be judged and ensuring the accuracy of the retained detected line segments.

[0074] In the above-mentioned embodiment of the present application, a set of line segments to be detected is constructed based on the cropped set of detection points, including: determining the target spacing between detection points based on the work task scenario corresponding to the area boundary; interpolating the cropped set of detection points according to the target spacing to generate a set of points to be detected; and segmenting the lines between two adjacent detection points in the set of detection points to obtain the set of line segments to be detected.

[0075] In an optional embodiment, in the case of the existence of historical perception data, the cropped detection point set can be interpolated at a certain spacing to obtain the final set of points to be detected, and then the set of line segments to be detected can be obtained by segmenting the set of points to be detected. Furthermore, considering that the accuracy requirements for progress detection are different in different operation task scenarios, for example, the accuracy requirements for progress detection in the soil removal operation scenario are high, and the accuracy requirements for progress detection in the road construction operation scenario are not high, therefore, the target spacing used in the interpolation process can be determined based on the operation task scenario, so as to ensure that the final constructed set of line segments to be detected matches the operation task scenario, and will not affect the execution efficiency and safety of the operation task.

[0076] In the above embodiment of the present application, interpolation processing is performed between the starting position and the end position to generate a set of line segments to be detected, including: determining the target spacing between detection points based on the work task scenario corresponding to the area boundary; interpolation processing is performed between the starting position and the end position according to the target spacing to generate a set of points to be detected; and segmentation processing is performed on the line between two adjacent detection points in the set of detection points to obtain the set of line segments to be detected.

[0077] In an optional embodiment, in the case where there is no historical perception data, the technical solution in the above embodiment can still be used to determine the target spacing used in the interpolation process based on the job task scenario, thereby ensuring that the final constructed set of line segments to be detected matches the job task scenario and will not affect the execution efficiency, safety, etc. of the job task.

[0078] In the above-mentioned embodiment of the present application, outputting the current detection progress of the area boundary includes one of the following: displaying the current detection progress of the area boundary in the interactive interface; playing the current detection progress of the area boundary by voice broadcast.

[0079] In an optional embodiment, the current detection progress can be displayed in the interactive interface by displaying text or images. The interactive interface here can be an interface on the central control screen of the collection vehicle, and the personnel on the collection vehicle can generate the above-mentioned input instructions by operating in the interface; the interactive interface here can also be an interface displayed on an electronic device used by the personnel on the collection vehicle, that is, an APP interface, and the personnel on the collection vehicle can generate the above-mentioned input instructions by operating in the interface; the interactive interface here can also be an interface displayed on an electronic device used by operators in the cloud, such as a web page, and operators in the cloud can generate the above-mentioned input instructions by operating in the interface.

[0080] In another optional embodiment, the personnel on the collection vehicle may not be able to view the interactive interface in time. In order to facilitate the personnel to know the current detection progress in time, the current detection progress can be played through voice broadcast through the speaker on the collection vehicle, or through the speaker of the electronic device used by the personnel on the collection vehicle, but not limited to this.

[0081] In the above embodiment of the present application, the method further includes: outputting the historical detection progress of the area boundary when the collected vehicle does not meet the preset detection conditions.

[0082] In an optional embodiment, when the collected vehicle does not meet the preset detection conditions, since the current detection progress is no longer determined at this time, the detection progress determined last time, that is, the historical detection progress, can be directly used as the current detection progress and output, thereby ensuring that the output of the detection progress is real-time and there will be no problem of not outputting the detection progress.

[0083] In the above embodiment of the present application, the method also includes: outputting line segments marked with preset states among multiple line segments to be detected; and controlling the collection vehicle to re-collect perception data of the line segments marked with preset states.

[0084] In an optional embodiment, in order to avoid the collection vehicle repeatedly collecting perception data, the line segment for which the perception data has not been successfully collected can be displayed or broadcast while or after the current detection progress is output, so that the collection vehicle can only collect perception data for this line segment and no longer needs to collect other line segments, thereby improving collection efficiency.

[0085] According to an embodiment of the present invention, a device embodiment of a region boundary detection device is provided. It should be noted that the device can be used to execute the above region boundary detection method. Figure 3 is a schematic diagram of a detection device for a region boundary according to an embodiment of the present invention, such as Figure 3 As shown, the device comprises:

[0086] The construction module 32 is used to respond to the received input instruction and construct a set of to-be-detected line segments corresponding to the area boundary based on the starting position and the end position carried in the input instruction, wherein the starting position is used to represent the starting point of the area boundary, and the end position is used to represent the end point of the area boundary. The multiple to-be-detected line segments contained in the to-be-detected line segment set constitute the area boundary.

[0087] The determination module 34 is used to control the collection vehicle to start driving along the area boundary, and whenever the collection vehicle meets the preset detection conditions, determine the current detection progress of the area boundary based on the driving trajectory of the collection vehicle, wherein the collection vehicle is used to collect perception data of the area boundary while driving along the area boundary, and the current detection progress is used to characterize the proportion of the target line segment among the multiple line segments to be detected, and the target line segment is used to characterize the line segment whose perception data is successfully collected by the collection vehicle.

[0088] The output module 36 is used to output the current detection progress of the area boundary.

[0089] In the above embodiment of the present application, the determination module includes: a first determination unit, used to determine a first parameter corresponding to at least one trajectory segment in the driving trajectory based on the collected vehicle's driving trajectory, wherein the type of the first parameter includes one of the following: a vertical direction vector, a heading angle; a second determination unit, used to determine a target line segment from multiple line segments to be detected based on the first parameter corresponding to at least one trajectory segment; and a third determination unit, used to obtain the current detection progress based on the number of target line segments and the number of multiple line segments to be detected.

[0090] In the above embodiment of the present application, when the type of the first parameter includes: a vertical direction vector, the second determination unit is further used to: perform intersection judgment on the first parameter corresponding to each trajectory segment and each line segment to be detected; determine the first distance between the driving trajectory and the line segment to be detected based on the first parameter corresponding to the trajectory segment; and determine that the line segment to be detected is a target line segment when the first parameter corresponding to the trajectory segment intersects with the line segment to be detected and the first distance is less than the first preset distance.

[0091] In the above embodiment of the present application, the determination module includes: an acquisition unit, which is used to acquire the historical detection progress of the area boundary, wherein the historical detection progress is used to characterize the detection progress determined when the last collected vehicle meets the preset detection conditions. When the collected vehicle meets the preset detection conditions for the first time, the historical detection progress is the preset progress; a fourth determination unit, which is used to determine the second parameter of the driving trajectory based on the current trajectory point in the driving trajectory of the collected vehicle and a historical trajectory point before the current trajectory point, wherein the second parameter includes one of the following: a vertical direction vector, a heading angle; a fifth determination unit, which is used to determine the target line segment from multiple line segments to be detected based on the second parameter; an adjustment unit, which is used to adjust the historical detection progress based on the number of target line segments to obtain the current detection progress.

[0092] In the above embodiment of the present application, the fifth determination unit is also used to: determine at least one candidate line segment marked with a preset state among multiple line segments to be detected, wherein the preset state is used to characterize that at least one candidate line segment has not been successfully collected by the collection vehicle for perception data, and when the collection vehicle meets the preset detection conditions for the first time, multiple line segments to be detected are marked with the preset state; based on the second parameter, determine the target line segment from at least one candidate line segment; and clear the preset state marked for the target line segment.

[0093] In the above embodiment of the present application, the device also includes: an acquisition module, which is used to acquire the current trajectory point of the collection vehicle after controlling the collection vehicle to start driving along the boundary of the area; a distance determination module, which is used to determine the second distance between the current trajectory point and the historical trajectory point of the collection vehicle; and a condition determination module, which is used to determine that the collection vehicle meets the preset detection condition when the second distance is greater than the second preset distance.

[0094] In the above embodiment of the present application, the construction module includes: a sixth determination unit, used to determine whether there is historical perception data of the area boundary, wherein the historical perception data includes perception data of multiple historical detection points; a first construction unit, used to crop multiple historical detection points based on the starting point position and the end point position in the case where there is historical perception data, to obtain a cropped detection point set, and to construct a set of line segments to be detected based on the cropped detection point set; a second construction unit, used to perform interpolation processing between the starting point position and the end point position in the case where there is no historical perception data, to generate a set of line segments to be detected.

[0095] In the above embodiment of the present application, the first construction unit is further used to: search among multiple historical detection points based on the starting point position to determine a first target detection point, wherein the distance between the first target detection point and the starting point position is less than the distance between the first other detection point and the starting point position, and the first other detection point is used to characterize the detection points other than the first target detection point in the multiple historical detection points; search among multiple historical detection points based on the end point position to determine a second target detection point, wherein the distance between the second target detection point and the end point position is less than the distance between the second other detection point and the end point position, and the second other detection point is used to characterize the detection points other than the second target detection point in the multiple historical detection points; determine a candidate detection point located between the first target detection point and the second target detection point from the multiple historical detection points; and crop the detection points other than the candidate detection points in the multiple historical detection points to obtain a cropped detection point set.

[0096] In the above embodiments of the present application, the first construction unit is also used to: determine the target spacing between detection points based on the work task scenario corresponding to the area boundary; interpolate the cropped detection point set according to the target spacing to generate a set of points to be detected; and segment the lines between two adjacent detection points in the set of detection points to obtain a set of line segments to be detected.

[0097] In the above embodiment of the present application, the second construction unit is also used to: determine the target spacing between detection points based on the work task scenario corresponding to the area boundary; perform interpolation processing between the starting position and the end position according to the target spacing to generate a set of points to be detected; and segment the lines between two adjacent detection points in the set of detection points to obtain a set of line segments to be detected.

[0098] In the above embodiments of the present application, the output module includes one of the following: a display unit, used to display the current detection progress of the area boundary in the interactive interface; a playback unit, used to play the current detection progress of the area boundary by voice broadcast.

[0099] In the above embodiment of the present application, the output module is also used to output the historical detection progress of the area boundary when the collected vehicle does not meet the preset detection conditions.

[0100] In the above embodiment of the present application, the output module is also used to output the line segments marked with preset states among multiple line segments to be detected; the device also includes: a control module, used to control the collection vehicle to re-collect the perception data of the line segments marked with preset states.

[0101] An embodiment of the present application further provides an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods in various embodiments of the present invention when running.

[0102] An embodiment of the present application further provides a computer-readable storage medium, which includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0103] An embodiment of the present application further provides a computer program product, including a computer program, which implements the methods in various embodiments of the present invention when executed by a processor.

[0104] An embodiment of the present application further provides a computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium is used to store a computer program, and when the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0105] The embodiments of the present application further provide a computer program, which implements the methods in the above-mentioned embodiments of the present invention when executed by a processor.

[0106] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0107] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0108] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0109] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0110] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0111] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for detecting a region boundary, characterized in that: include: In response to the received input instruction, a set of to-be-detected line segments corresponding to the region boundary is constructed based on the starting position and the ending position carried in the input instruction, wherein the starting position is used to represent the starting point of the region boundary, the ending position is used to represent the ending point of the region boundary, and the multiple to-be-detected line segments contained in the to-be-detected line segment set constitute the region boundary; Controlling the collection vehicle to start driving along the area boundary, and whenever the collection vehicle meets a preset detection condition, determining the current detection progress of the area boundary based on the driving trajectory of the collection vehicle, wherein the collection vehicle is used to collect perception data of the area boundary during driving along the area boundary, and the current detection progress is used to characterize the proportion of a target line segment among the multiple line segments to be detected in the multiple line segments to be detected, and the target line segment is used to characterize the line segment whose perception data is successfully collected by the collection vehicle; Output the current detection progress of the region boundary.

2. The method according to claim 1, characterized in that The determining the current detection progress of the area boundary based on the collected vehicle's driving trajectory includes: Based on the collected driving trajectory of the vehicle, determining a first parameter corresponding to at least one trajectory segment in the driving trajectory, wherein the type of the first parameter includes one of the following: a vertical direction vector, a heading angle; Determining the target line segment from the plurality of line segments to be detected based on a first parameter corresponding to the at least one trajectory segment; The current detection progress is obtained based on the number of the target line segments and the number of the plurality of line segments to be detected.

3. The method according to claim 2, characterized in that In the case where the type of the first parameter includes: a vertical direction vector, determining the target line segment from the multiple line segments to be detected based on the first parameter corresponding to the at least one trajectory segment includes: Perform intersection judgment on the first parameter corresponding to each trajectory segment and each line segment to be detected; Determine a first distance between the driving trajectory and the line segment to be detected based on a first parameter corresponding to the trajectory segment; When the first parameter corresponding to the trajectory segment intersects with the line segment to be detected and the first distance is less than a first preset distance, it is determined that the line segment to be detected is the target line segment.

4. The method according to claim 1, characterized in that: The determining the current detection progress of the area boundary based on the collected vehicle's driving trajectory includes: Acquire the historical detection progress of the area boundary, wherein the historical detection progress is used to represent the detection progress determined when the collection vehicle meets the preset detection condition last time, and when the collection vehicle meets the preset detection condition for the first time, the historical detection progress is the preset progress; Determine a second parameter of the driving trajectory based on a current trajectory point in the driving trajectory of the collected vehicle and a historical trajectory point before the current trajectory point, wherein the second parameter includes one of the following: a vertical direction vector, a heading angle; Based on the second parameter, determining the target line segment from the multiple line segments to be detected; The historical detection progress is adjusted based on the number of the target line segments to obtain the current detection progress.

5. The method according to claim 4, characterized in that The step of determining the target line segment from the plurality of line segments to be detected based on the second parameter includes: Determine at least one candidate line segment among the plurality of line segments to be detected that is marked with a preset state, wherein the preset state is used to indicate that the at least one candidate line segment has not been successfully captured by the capture vehicle for sensing data, and when the capture vehicle meets the preset detection condition for the first time, the plurality of line segments to be detected are all marked with the preset state; Based on the second parameter, determining the target line segment from the at least one candidate line segment; The preset state marked for the target line segment is cleared.

6. The method according to any one of claims 1 to 5, characterized in that After controlling the collection vehicle to start driving along the area boundary, the method further includes: Obtaining the current trajectory point of the acquisition vehicle; Determining a second distance between the current track point and the historical track points of the collected vehicle; When the second distance is greater than a second preset distance, it is determined that the collection vehicle meets the preset detection condition.

7. The method according to any one of claims 1 to 6, characterized in that: The step of constructing a set of line segments to be detected corresponding to the region boundary based on the starting point position and the end point position carried in the input instruction includes: Determining whether there is historical perception data of the area boundary, wherein the historical perception data includes perception data of multiple historical detection points; In the case where the historical perception data exists, the plurality of historical detection points are clipped based on the starting point position and the end point position to obtain a clipped detection point set, and the to-be-detected line segment set is constructed based on the clipped detection point set; In the absence of the historical perception data, interpolation processing is performed between the starting point position and the end point position to generate the set of line segments to be detected.

8. The method according to claim 7, characterized in that The clipping of the plurality of historical detection points based on the starting point position and the end point position to obtain a clipped detection point set includes: Searching among the multiple historical detection points based on the starting point position to determine a first target detection point, wherein a distance between the first target detection point and the starting point position is less than a distance between a first other detection point and the starting point position, and the first other detection point is used to represent a detection point other than the first target detection point among the multiple historical detection points; Based on the end point position, searching among the multiple historical detection points, determining a second target detection point, wherein the distance between the second target detection point and the end point position is less than the distance between a second other detection point and the end point position, and the second other detection point is used to represent the detection points other than the second target detection point in the multiple historical detection points; Determine a candidate detection point located between the first target detection point and the second target detection point from the plurality of historical detection points; Detection points other than the candidate detection points in the multiple historical detection points are clipped to obtain the clipped detection point set.

9. The method according to claim 7, characterized in that: The step of constructing the to-be-detected line segment set based on the clipped detection point set includes: Determining a target spacing between detection points based on an operation task scenario corresponding to the area boundary; Performing interpolation processing on the clipped detection point set according to the target spacing to generate a set of points to be detected; The line between two adjacent detection points in the set of points to be detected is segmented to obtain the set of line segments to be detected.

10. The method according to claim 7, characterized in that The interpolation process is performed between the starting point position and the end point position to generate the set of line segments to be detected, including: Determining a target spacing between detection points based on an operation task scenario corresponding to the area boundary; Performing interpolation processing between the starting position and the end position according to the target spacing to generate a set of points to be detected; The line between two adjacent detection points in the set of points to be detected is segmented to obtain the set of line segments to be detected.

11. The method according to any one of claims 1 to 10, characterized in that The outputting the current detection progress of the region boundary includes one of the following: Displaying the current detection progress of the area boundary in the interactive interface; The current detection progress of the area boundary is played by voice broadcast.

12. The method according to any one of claims 1 to 11, characterized in that The method further comprises: When the collection vehicle does not meet the preset detection condition, the historical detection progress of the area boundary is output.

13. The method according to any one of claims 1 to 12, characterized in that The method further comprises: Outputting line segments marked with a preset state among the plurality of line segments to be detected; The collection vehicle is controlled to re-collect the perception data of the line segment marked with a preset state.

14. A device for detecting a region boundary, characterized in that: include: A construction module, configured to construct, in response to a received input instruction, a set of to-be-detected line segments corresponding to the region boundary based on a starting position and an end position carried in the input instruction, wherein the starting position is used to represent the starting point of the region boundary, the end position is used to represent the end point of the region boundary, and a plurality of to-be-detected line segments contained in the to-be-detected line segment set constitute the region boundary; A determination module is used to control the collection vehicle to start driving along the area boundary, and whenever the collection vehicle meets a preset detection condition, determine the current detection progress of the area boundary based on the driving trajectory of the collection vehicle, wherein the collection vehicle is used to collect perception data of the area boundary during the process of driving along the area boundary, and the current detection progress is used to characterize the proportion of the target line segment in the multiple line segments to be detected, and the target line segment is used to characterize the line segment whose perception data is successfully collected by the collection vehicle; The output module is used to output the current detection progress of the area boundary.

Images