Detection method, detection system, storage medium and computer program product

Abstract

The invention discloses a detection method, a detection system, a storage medium and a computer program product. The detection method is used for detecting the goods storage depth of a target goods channel (11) in a goods shelf (1) and comprises the steps that the target goods channel (11) is scanned through a laser radar (2) located on the side, away from a goods outlet end (111), of the target goods channel (11) to obtain point cloud data, and in the process of scanning the target goods channel (11), the target goods channel (11) is scanned through the laser radar (2) to obtain point cloud data; a scanning surface (21) of the laser radar (2) is configured to intersect with a bottom surface (112) of the target goods channel (11); determining the distance between the goods in the target goods channel (11) and the laser radar (2) according to the point cloud data; and determining the cargo storage depth of the target cargo channel (11) according to the distance. The cargo storage depth of the target cargo channel can be detected more effectively.

Description

Technical Field

[0001] The present disclosure relates to a detection method, a detection system, a storage medium and a computer program product. Background Art

[0002] In the field of warehousing and logistics, it is often necessary to take inventory of each aisle in the shelf regularly or irregularly to understand the inventory status. In some related technologies, when taking inventory of the aisles in the shelf, a laser ranging sensor is used to detect the storage depth of the goods. The single laser beam emitted by the sensor is measured along the direction of the aisle to obtain the distance from the laser ranging sensor to the goods in the aisle, so as to further infer the actual storage depth of the goods. Summary of the invention

[0003] Research has found that the measurement method used in related technologies requires that the emission angle of the laser emitted by the sensor be as parallel to the cargo aisle as possible, and at the same time requires that the flatness of the cargo aisle be very high, so that the laser can accurately reach the surface of the goods to be measured. However, in actual scenarios, the cargo aisle may be deformed due to its long length, and it is not easy to ensure flatness. The laser may be blocked by the deformed cargo aisle. For thinner goods, if the emission angle of the laser is not parallel enough to the cargo aisle or there is obvious deformation of the cargo aisle, it is possible that the laser path will be offset from the surface of the goods, and thus the goods cannot be accurately reached. These situations make the detection of storage depth more difficult.

[0004] In view of this, the embodiments of the present disclosure provide a detection method, a detection system, a storage medium, and a computer program product, which can more effectively detect the cargo storage depth of a target cargo channel.

[0005] In one aspect of the present disclosure, a detection method is provided for detecting the cargo storage depth of a target aisle in a shelf, comprising: scanning the target aisle by means of a laser radar located on a side of the target aisle away from a shipping end to obtain point cloud data, wherein during scanning the target aisle, a scanning surface of the laser radar is configured to intersect with a bottom surface of the target aisle; determining a distance between the cargo in the target aisle and the laser radar based on the point cloud data; and determining the cargo storage depth of the target aisle based on the distance.

[0006] In some embodiments, the step of determining the distance between the goods in the target cargo aisle and the laser radar based on the point cloud data includes: filtering out the point cloud data corresponding to the target cargo aisle from the point cloud data; and determining the distance between the goods in the target cargo aisle and the laser radar based on each sampling angle and length value in the point cloud data corresponding to the target cargo aisle.

[0007] In some embodiments, the step of filtering out the point cloud data corresponding to the target cargo lane from the point cloud data includes: in the point cloud data, determining the point cloud data where the absolute value of the difference between the length values corresponding to the sampling angles continuously exceeding a preset number is not greater than a preset length threshold relative to the length value corresponding to the initial count, so as to obtain a continuous segment record of the point cloud data, where the continuous segment record includes the sampling angle corresponding to the initial count, the length value corresponding to the initial count, and the continuous sampling point count; filtering out the continuous segment records where the sampling angle and the length value do not conform to the preset corresponding relationship from the obtained continuous segment records, so as to determine the point cloud data corresponding to the target cargo lane.

[0008] In some embodiments, the step of excluding the continuous segment records where the sampling angle and the length value do not conform to the preset corresponding relationship from the obtained continuous segment records includes: querying each continuous segment record according to the pre-stored table of the corresponding relationship between the sampling angle and the length value, so as to determine the continuous segment records that do not conform to the preset corresponding relationship in the corresponding relationship pre-stored table; filtering out the continuous segment records that do not conform to the preset corresponding relationship in the corresponding relationship pre-stored table.

[0009] In some embodiments, the step of filtering out the continuous segment records where the sampling angle and the length value do not conform to the preset corresponding relationship from the obtained continuous segment records includes: filtering out the continuous segment records of the sampling angles and the length values corresponding to the support beams of the target cargo lane and the support beams of the adjacent cargo lanes respectively from the obtained continuous segment records.

[0010] In some embodiments, the step of filtering out the point cloud data corresponding to the target cargo lane from the point cloud data includes: further filtering out the point cloud data corresponding to the target cargo lane in the point cloud data according to the sampling angles and the length values corresponding to the support beams of the target cargo lane and the support beams of the adjacent cargo lanes respectively.

[0011] In some embodiments, the step of determining the distance between the goods in the target cargo lane and the lidar according to the point cloud data includes: filtering out the point cloud data where the sampling angle conforms to a preset angle range in the point cloud data, where the target cargo lane is located in the preset angle range; determining the distance between the goods in the target cargo lane and the lidar according to the sampling angle and the corresponding length value in the point cloud data that conforms to the preset angle range.

[0012] In some embodiments, the angle value corresponding to the preset angle range is less than 45°.

[0013] In some embodiments, the shelf includes multiple layers of lanes, and the point cloud data meeting the preset angular range includes: the point cloud data corresponding to the target lane, and the point cloud data corresponding to the lanes in the adjacent lanes of the target lane where the bottom surface intersects the scanning surface; wherein, the step of determining the distance between the goods in the target lane and the lidar according to the point cloud data includes: further screening out the point cloud data corresponding to the target lane from the point cloud data meeting the preset angular range; and determining the distance between the goods in the target lane and the lidar according to each sampling angle and length value in the point cloud data corresponding to the target lane.

[0014] In some embodiments, the detection method further includes: in response to an instruction to detect the target lane, driving the lidar to a position above the extension line on the side away from the shipping end along the length direction of the target lane, so as to perform a scanning operation at this position.

[0015] In some embodiments, the distance of the position where the lidar performs the scanning operation relative to the extension line in the vertical direction is not greater than the height of the target lane.

[0016] In one aspect of the present disclosure, there is provided a detection system, including: a lidar; a memory; and a processor coupled to the memory and configured to execute the foregoing detection method based on instructions stored in the memory.

[0017] In one aspect of the present disclosure, there is provided a computer-readable storage medium that non-temporarily stores computer instructions, and when the instructions are executed by a processor, the foregoing detection method is implemented.

[0018] In one aspect of the present disclosure, there is provided a computer program product including a computer program, and when the computer program is executed by a processor, the foregoing detection method is implemented.

[0019] According to the embodiments of the present disclosure, the lidar scans the target lane through a scanning surface that intersects the bottom surface of the target lane. Since the lidar can cover a large spatial range, the goods in the lane are more likely to be captured by the lidar, reducing the influence of factors such as lane deformation and goods thickness on goods detection; compared with the relatively single ranging data of the laser ranging sensor in the related art, the point cloud data obtained by lidar scanning has more detailed information, which is beneficial to screening out the interference of structures such as other lanes and support beams on the detection of the storage depth of the goods in the target lane, thereby more effectively detecting the storage depth of the goods in the target lane. Description of the Drawings

[0020] The accompanying drawings, which form a part of the specification, illustrate embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0021] With reference to the accompanying drawings, the present disclosure can be more clearly understood from the following detailed description, wherein:

[0022] Figure 1 is a schematic diagram of the scene structure to which the detection method embodiment of the present disclosure is applied;

[0023] Figure 2 is a schematic diagram of the lidar scanning the shelf in the detection method embodiment of the present disclosure;

[0024] Figure 3 is a schematic flowchart of some embodiments of the detection method of the present disclosure;

[0025] Figure 4 is a schematic diagram of the relationship between the scanning plane and the bottom surfaces of the target aisle and the adjacent aisles in the detection method embodiment of the present disclosure;

[0026] Figure 5 is a schematic diagram of the principle of screening goods based on the obtained continuous segment records in the detection method embodiment of the present disclosure;

[0027] Figure 6 is a schematic diagram of the principle of eliminating other interferences except the goods in the target aisle in the detection method embodiment of the present disclosure;

[0028] Figure 7 is a schematic diagram of the processing of the point cloud data corresponding to the support beam in the detection method embodiment of the present disclosure;

[0029] Figure 8 is a schematic diagram of the structure of some embodiments of the detection system of the present disclosure.

[0030] It should be understood that the dimensions of the various parts shown in the drawings are not drawn in actual proportional relationship. In addition, the same or similar reference numerals denote the same or similar components. Detailed Description of the Invention

[0031] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. The description of the exemplary embodiments is merely illustrative and in no way limits the present disclosure and its application or use. The present disclosure can be implemented in many different forms and is not limited to the embodiments described herein. These embodiments are provided to make the present disclosure thorough and complete and to fully convey the scope of the present disclosure to those skilled in the art. It should be noted that: unless otherwise specifically stated, the relative arrangements of the components and steps, the compositions of the materials, the numerical expressions and the numerical values set forth in these embodiments should be construed as merely exemplary and not as limitations.

[0032] The words "first", "second" and similar words used in this disclosure do not indicate any order, quantity or importance, but are only used to distinguish different parts. The words "include" or "comprise" and similar words mean that the elements before the word include the elements listed after the word, and do not exclude the possibility of including other elements. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0033] In the present disclosure, when a specific device is described as being located between a first device and a second device, there may or may not be an intermediate device between the specific device and the first device or the second device. When a specific device is described as being connected to other devices, the specific device may be directly connected to the other device without an intermediate device, or may not be directly connected to the other device but have an intermediate device.

[0034] All terms (including technical terms or scientific terms) used in the present disclosure have the same meanings as those understood by ordinary technicians in the field to which the present disclosure belongs, unless otherwise specifically defined. It should also be understood that terms defined in general dictionaries, such as general dictionaries, should be interpreted as having meanings consistent with their meanings in the context of the relevant technology, and should not be interpreted in an idealized or extremely formal sense, unless explicitly defined herein.

[0035] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.

[0036] In some related technologies, when taking inventory of the aisles in the shelves, a laser ranging sensor is used to detect the storage depth of the goods. The single laser beam emitted by the sensor is measured along the direction of the aisle to obtain the distance from the laser ranging sensor to the goods in the aisle, thereby further inferring the actual storage depth of the goods.

[0037] Research has found that the measurement method used in related technologies requires that the emission angle of the laser emitted by the sensor be as parallel to the cargo aisle as possible, and that the flatness of the cargo aisle is very high, so that the laser can accurately reach the surface of the goods to be measured. However, in actual scenarios, the cargo aisle may be deformed due to its long length, and it is not easy to ensure flatness. The laser may be blocked by the deformed cargo aisle. For thinner goods, if the emission angle of the laser is not parallel enough to the cargo aisle or there is obvious deformation of the cargo aisle, it is possible that the laser path will be offset from the surface of the goods, and thus the goods cannot be accurately reached. These situations make the detection of storage depth more difficult.

[0038] In view of this, embodiments of the present disclosure provide a detection method, a detection system, a storage medium, and a computer program product, which can more effectively detect the storage depth of goods in a target lane.

[0039] Figure 1 It is a schematic structural diagram of the scenario to which the detection method embodiment of the present disclosure is applied. Figure 2 It is a schematic diagram of a lidar scanning a shelf according to an embodiment of the detection method of the present disclosure. Figure 3 It is a schematic flowchart of some embodiments of the detection method of the present disclosure.

[0040] Reference Figures 1-3 , embodiments of the present disclosure provide a detection method for detecting the storage depth of goods in a target lane 11 of a shelf 1. The shelf 1 has at least one lane for storing goods. The target lane 11 is the lane to be detected in the shelf 1, and it can be determined according to relevant detection instructions. The storage depth of goods can be defined as the distance from the reference plane of the lane entrance to the goods closest to the lane entrance in the lane, and it can be used to judge the quantity and size of goods that can be further stored in this lane.

[0041] Figure 1 An example of the shelf 1 is shown. The shelf 1 may include a plurality of columns 12. The plurality of columns 12 can be divided into at least two groups, and one or more crossbeams 13 can be arranged between at least two columns 12 in each group. The shelf 1 may include a plurality of lanes, and the plurality of lanes can be arranged as multi-layer lanes and can be further arranged as multi-column lanes. The crossbeams 13 arranged between different groups of columns 12 can be used as support beams to support the plurality of lanes.

[0042] Each lane can but is not limited to adopt a gravity lane in an inclined arrangement form, and the lower end of the lane has a baffle to stop the goods. And this end can be used as the shipping end 111 to output the goods. The upper end of the lane can be used as the lane entrance to receive the goods.

[0043] The detection method of the embodiments of the present disclosure includes step S1, step S2, and step S3.

[0044] In step S1, a lidar 2 located on the side of the target lane 11 away from the shipping end 111 scans the target lane 11 to obtain point cloud data. During the process of scanning the target lane 11, the scanning plane 21 of the lidar 2 is configured to intersect the bottom surface 112 of the target lane 11.

[0045] The laser emitted by the lidar 2 can form a scanning plane 21, and corresponding point cloud data can be generated according to the signals reflected by the objects scanned by the scanning plane 21. The scanning plane 21 can be a 360° circular scanning plane or a fan-shaped scanning plane within a preset angular range. The lidar 2 can adopt various existing lidars that can form the scanning plane 21, such as a mechanically rotating single-line lidar, a microelectromechanical system lidar, a rotating mirror lidar, etc.

[0046] The lidar 2 can be pre-set at a position on the side of the target cargo lane far from the shipping end 111, or it can be moved to a position on the side of the target cargo lane far from the shipping end 111 by other driving mechanisms.

[0047] The lidar 2 scans the target cargo lane 11 to obtain point cloud data. During the scanning process, the point cloud data of the target cargo lane 11 and the objects inside it can be obtained, and the point cloud data of other objects scanned by the scanning plane 21 outside the target cargo lane 11 can also be obtained.

[0048] In step S2, the distance between the goods in the target cargo lane 11 and the lidar 2 is determined according to the point cloud data.

[0049] The point cloud data obtained by the lidar 2 contains length values corresponding to each sampling angle. The straight-line distance from the lidar 2 to the goods in the target cargo lane 11 can be determined according to the length values, or the distance from the lidar 2 along the extension direction of the target cargo lane 11 to the goods in the target cargo lane 11 can be determined.

[0050] For example, when the lidar 2 scans the front end face of the goods closest to the cargo lane entrance in the target cargo lane 11 (i.e., the end face on the side close to the cargo lane entrance), the point cloud data obtained contains the straight-line distance from the lidar 2 to this end face (i.e., the length value). In some cases, for example, when the length of the target cargo lane 11 is much greater than the height, or the vertical distance from the lidar 2 to the extension line of the cargo lane 11 is close to the height of the goods, the distance from the lidar 2 along the length direction of the target cargo lane 11 to this end face may not differ much from the straight-line distance from the lidar 2 to this end face. At this time, this straight-line distance can be used as the distance between the goods in the target cargo lane 11 and the lidar 2.

[0051] If the distance from the lidar 2 along the length direction of the target cargo lane 11 to this end face is used as the distance between the goods in the target cargo lane 11 and the lidar 2, then the straight-line distance from the lidar 2 to this end face can be calculated through trigonometric functions.

[0052] In step S3, the storage depth of the goods in the target cargo lane 11 is determined according to the distance.

[0053] The lidar 2 is outside the target cargo lane 11 and can have a preset distance from the entrance of the cargo lane. Correspondingly, after determining the distance between the goods in the target cargo lane 11 and the lidar 2, the storage depth of the goods in the target cargo lane 11 can be determined by subtracting this preset distance.

[0054] In this embodiment, the scanning plane 21 of the lidar 2 is set to intersect with the bottom surface 112 of the target cargo lane 11, which enables the lidar 2 to cover a larger spatial range, and the goods in the cargo lane are more easily captured by the lidar 2, reducing the influence of factors such as cargo lane deformation and cargo thickness on cargo detection, and reducing the possibility of goods being missed or misdetected.

[0055] Compared with the relatively single ranging data of the laser ranging sensor in the related art, the point cloud data scanned by the lidar 2 has more detailed information, which is beneficial to screening out the interference of structures such as other cargo lanes and support beams on the detection of the storage depth of the goods in the target cargo lane, so as to more effectively detect the storage depth of the goods in the target cargo lane.

[0056] Figure 4 It is a schematic diagram of the relationship between the scanning plane and the bottom surfaces of the target cargo lane and adjacent cargo lanes in the detection method embodiment of the present disclosure. In Figure 4 (a) and (b) of, three-layer cargo lanes are briefly schematized, where the second-layer cargo lane is the target cargo lane 11, and the first-layer and third-layer cargo lanes are the adjacent cargo lanes 11a of the target cargo lane 11. Here, the adjacent cargo lanes 11a of the target cargo lane 11 include the directly adjacent (i.e., directly adjacent) cargo lanes, as well as the cargo lanes adjacent to more than two layers. Goods 114 can be stored in the target cargo lane 11 and adjacent cargo lanes 11a.

[0057] In some implementation forms of the cargo lane, the cargo lane can be surrounded by beams on both sides, so it has a partially hollow bottom surface (schematically shown by a double-dashed line). From the perspective of the lidar 2 facing the target cargo lane 11, Figure 4 the bottom surfaces of each layer of cargo lanes and the scanning plane 21 of the lidar 2 in (a) and (b) of are both shown as straight line segments. The scanning plane 21 can intersect with the bottom surface 112 of the target cargo lane 11 obliquely as shown in Figure 4 (a) of, or perpendicularly as shown in Figure 4 (b) of, and the intersection position is on the bottom surface 112 schematically shown by the double-dashed line. The scanning plane 21 can be set to be centered with respect to the cargo lane or biased to one side, as long as it can scan the goods in the cargo lane.

[0058] The scanning plane 21 can also intersect obliquely or perpendicularly with a reference plane perpendicular to the length direction ld of the cargo lane. For Figure 4For the cuboid-shaped goods 114 shown in (a) and (b), its length and width surfaces are substantially parallel to the bottom surface of the goods lane, and the front end surface adjacent to the lidar 2 is substantially parallel to the reference surface perpendicular to the length direction of the goods lane. Therefore, the scanning surface 21 also passes through the length and width surfaces and the front end surface of the goods 114, so that the goods 114 can be accurately scanned.

[0059] From Figure 4 As can be seen from (a) and (b), the scanning surface 21 not only intersects the bottom surface 112 of the target goods lane 11, but also intersects the bottom surfaces 112a of multiple adjacent goods lanes 11a in the same column. In this way, not only can the point cloud data of the goods in the target goods lane 11 be obtained, but also the point cloud data of the goods in the adjacent goods lanes 11a can be obtained.

[0060] Reference Figure 2 , in some embodiments, step S2 includes: screening out the point cloud data with sampling angles within a preset angle range AR from the point cloud data, where the target goods lane 11 is located within the preset angle range AR; determining the distance between the goods 114 in the target goods lane 11 and the lidar 2 according to the sampling angles and the corresponding length values in the point cloud data that meet the preset angle range AR.

[0061] Among the point cloud data that can be obtained by the lidar 2, only the length values corresponding to some sampling angles may be related to the target goods lane 11. By screening the point cloud data according to the preset angle range AR, the point cloud data outside the preset angle range AR is excluded before subsequent processing, thereby reducing the amount of data processing and improving the detection efficiency.

[0062] Figure 2 In [reference], the preset angle range AR is enclosed by two opposite arc arrows. It can be seen that the laser beam based on the preset angle range AR covers the target goods lane 11 and several adjacent goods lanes 11a of the target goods lane 11.

[0063] The position of the preset angle range AR and the covered angle value can be set according to the position of the lidar 2 relative to the target goods lane 11 during scanning, and it is necessary to make the target goods lane 11 located within the preset angle range AR. The angle value corresponding to the preset angle range AR is optionally set to be less than 45°, so as to reduce the amount of data processing to a greater extent and further improve the detection efficiency.

[0064] In some embodiments, the preset angle range AR can be set to be relatively narrow so that the point cloud data obtained by the lidar 2 only includes the point cloud data corresponding to the target goods lane 11, in order to reduce the amount of data processing and reduce the interference of the point cloud data corresponding to other goods lanes on the point cloud data corresponding to the target goods lane.

[0065] Reference Figure 2, in some embodiments, the shelf 1 includes multiple layers of lanes, and the point cloud data that meets the preset angle range AR may include: the point cloud data corresponding to the target lane 11, and the point cloud data corresponding to the lanes in the adjacent lanes 11a of the target lane 11 where the bottom surface 112a intersects the scanning surface 21.

[0066] In Figure 4 , the bottom surfaces 112a of the adjacent lanes 11a above and below the target lane 11 also intersect the scanning surface 21. Therefore, the lidar 2 can obtain the point cloud data corresponding to these two adjacent lanes 11a. This can reduce the requirement for the setting position accuracy of the lidar 2 and reduce the possibility of missed detection caused by the preset angle range AR not covering or completely covering the target lane.

[0067] Since the point cloud data that meets the preset angle range AR includes both the point cloud data corresponding to the target lane 11 and the point cloud data corresponding to the adjacent lanes 11a. Therefore, in some embodiments, the steps of determining the distance between the goods 114 in the target lane 11 and the lidar 2 according to the point cloud data include: further screening out the point cloud data corresponding to the target lane 11 from the point cloud data that meets the preset angle range AR; determining the distance between the goods 114 in the target lane 11 and the lidar 2 according to the respective sampling angles and length values in the point cloud data corresponding to the target lane 11.

[0068] After obtaining the point cloud data that meets the preset angle range AR, further determine which of these sampling angles and length values correspond to the goods 114 in the target lane 11, so as to exclude the interference of the point cloud data corresponding to the adjacent lanes 11a and obtain a more accurate distance between the goods 114 in the target lane 11 and the lidar 2.

[0069] To reduce the amount of data to be processed, the step of screening the point cloud data corresponding to the target lane 11 can be directed to the point cloud data that meets the preset angle range AR. And in some cases, such as when the point cloud data in the entire angle range obtained by the lidar 2 is relatively limited or there is sufficient data processing capacity, the step of screening the point cloud data corresponding to the target lane 11 can also be directed to the point cloud data in the entire angle range obtained by the lidar 2. Therefore, in some embodiments, the steps of determining the distance between the goods 114 in the target lane 11 and the lidar 2 according to the point cloud data in step S2 can also include: screening out the point cloud data corresponding to the target lane 11 from the point cloud data; determining the distance between the goods 114 in the target lane 11 and the lidar 2 according to the respective sampling angles and length values in the point cloud data corresponding to the target lane 11. Figure 5It is a schematic diagram of the principle of screening goods according to the continuous segment records obtained in the embodiment of the detection method of the present disclosure. As Figure 5 shown, the laser beam of the lidar 2 can form multiple sampling points on the front end face of the goods 114 to obtain length values corresponding to multiple sampling angles. For some goods with regular shapes, their front end faces are continuously regular, and the laser beam is also relatively close to being perpendicular to the front end face of the goods 114 or has a small skew angle, which makes the length values in the multiple point cloud data obtained on the front end face of the goods 114 also relatively close. Based on this principle, the goods to be detected can be identified by the similarity of the length values corresponding to consecutive sampling angles in the point cloud data.

[0070] In some embodiments, the step of further screening out the point cloud data corresponding to the target cargo lane 11 from the point cloud data includes: in the point cloud data, determining the point cloud data in which the absolute value of the difference between the length values corresponding to consecutive sampling angles exceeding a preset number is not greater than a preset length threshold relative to the length value corresponding to the initial count, so as to obtain a continuous segment record of the point cloud data, where the continuous segment record includes the sampling angle corresponding to the initial count, the length value corresponding to the initial count, and the number of consecutive sampling points; screening out the continuous segment records in which the sampling angle and the length value do not conform to the preset corresponding relationship from the obtained continuous segment records to determine the point cloud data corresponding to the target cargo lane 11.

[0071] Among them, the interval between adjacent sampling angles can be determined by the resolution of the lidar, and each sampling angle can correspond to the length value obtained by the lidar 2. Calculate the absolute value of the difference between the length values corresponding to adjacent sampling angles exceeding a preset number. If the absolute value of the difference is not greater than the preset length threshold, a continuous segment record cs of the point cloud data can be determined according to this set of point cloud data. The continuous segment record here can include the sampling angle corresponding to the initial count, the length value corresponding to the initial count, and the number of consecutive sampling points in this set of point cloud data.

[0072] For example, for a mechanical rotary single-line lidar, take the current sampling angle A n along the rotation direction of the laser beam, and its corresponding length value L n If the absolute value of the difference from the length value L n+1 corresponding to the next sampling angle A n (i.e., A n+1 + a0, where a0 is the preset interval of the sampling angle) is less than or equal to the preset length threshold, then this sampling angle and length value can be used as the sampling angle A0 and length value L0 corresponding to the initial count, and the number of consecutive sampling points S is set to 1. At this time, continue to select the next sampling angle, and the current sampling angle A n is the A n+1 of the previous operation, and the length value L nThat is the L of the previous operation n+1 , and correspondingly, its next sampling angle A n+1 The corresponding length value L n+1 Also calculates the absolute value of the difference between the length value L corresponding to the initial count. If the absolute value of this difference is still less than or equal to the preset length threshold, the continuous sampling point number S is set to 2, and the operation corresponding to the next sampling angle is continued. Until the absolute value of the difference exceeds the preset length threshold, stop increasing the count of the continuous sampling point number S.

[0073] If the continuous sampling point number S has exceeded the preset number N at this time, determine the continuous segment record cs according to this set of point cloud data and the continuous sampling point number S. The continuous segment record cs may include the sampling angle A0 corresponding to the initial count, the length value L0 corresponding to the initial count, and the continuous sampling point number S. If the continuous sampling point number S does not exceed the preset number N, it means that this set of point cloud data does not correspond to the continuous surface of a cargo, and it is not determined as the continuous segment record cs. The setting of the preset number N may be related to factors such as the height of the cargo to be detected, the angular resolution of the lidar, and the farthest detection distance.

[0074] Reference Figure 5 , in some embodiments, the vertical distance h between the position where the lidar 2 performs the scanning operation and the extension line 113 of the target cargo lane 11 along the cargo lane length direction ld is not greater than the height H of the target cargo lane 11.

[0075] In Figure 5 , the lidar 2 is located outside the target cargo lane 11, and its vertical distance h from the extension line 113 of the bottom surface 112 is less than the height H of the target cargo lane 11. This vertical distance h can be 1 / 4, 1 / 3, 1 / 2, 2 / 3, etc. of the height H. For the target cargo lane mainly storing relatively thin goods (such as medicine boxes, etc.), the vertical distance h can be set to a size close to the height of the goods, so that the absolute value of the difference in the length values in the point cloud data of the front end surface of the goods in the target cargo lane 11 is relatively close, making it easier to identify the goods in the target cargo lane 11.

[0076] Figure 6 Is a schematic diagram of the principle of eliminating other interferences except the goods in the target cargo lane according to the embodiment of the detection method of the present disclosure. Reference Figure 6 , for the structure with a hollow part in each layer of the cargo lane, the point cloud data corresponding to the goods 114 in the target cargo lane 11 and the adjacent cargo lane 11a can both form continuous segment records.

[0077] Figure 6The objects labeled A, B, C, D, and E (which may be, but are not limited to, goods) respectively correspond to the continuous segment records cs1, cs2, cs3, cs4, and cs5. It can be seen that the length value of the continuous segment record cs1 corresponding to the object labeled A in the target lane 11 is not much different from the length value of the continuous segment record cs2 corresponding to the object labeled B in the adjacent lane 11a. However, the sampling angles corresponding to each continuous segment record are significantly different. Therefore, the length value and sampling angle of the continuous segment record cs2 do not conform to the preset correspondence relationship between the length value and sampling angle in the continuous segment records of the target lane 11. In this way, the continuous segment record cs2 with a sampling angle not conforming to the target lane 11 can be screened out.

[0078] For the object labeled E in the target lane 11, the corresponding continuous segment record cs5 is relatively close to the continuous segment record cs3 corresponding to the object labeled C in the adjacent lane 11a in terms of the sampling angle. However, the length value of the continuous segment record cs5 is significantly different from the length value of the continuous segment record cs3. Therefore, the length value and sampling angle of the continuous segment cs3 also do not conform to the preset correspondence relationship between the length value and sampling angle in the continuous segment records of the target lane 11. In this way, the continuous segment record cs3 with a sampling angle not conforming to the target lane 11 can be screened out.

[0079] For the object labeled D in the adjacent lane 11a, its corresponding sampling angle is basically not within the range of the target lane 11. Then, the length value and sampling angle of the corresponding continuous segment record cs4 obviously do not conform to the preset correspondence relationship between the length value and sampling angle in the continuous segment records of the target lane 11. In this way, the continuous segment record cs4 with a sampling angle not conforming to the target lane 11 can be screened out.

[0080] In this way, after obtaining the continuous segment records of the point cloud data, the continuous segment records with sampling angles and length values not conforming to the preset correspondence relationship can be screened out from the obtained continuous segment records. Thus, when determining the point cloud data corresponding to the target lane 11, the interference of the point cloud data of other lanes to the detection of goods in the target lane can be effectively removed.

[0081] For the convenience of screening, a pre-stored table of the correspondence relationship between the sampling angle and length value matching the target lane 11 can be set in advance. On this basis, the steps of excluding the continuous segment records with sampling angles and length values not conforming to the preset correspondence relationship from the obtained continuous segment records may include: querying each continuous segment record according to the pre-stored table of the correspondence relationship between the sampling angle and length value to determine the continuous segment records not conforming to the preset correspondence relationship in the pre-stored table of the correspondence relationship; screening out the continuous segment records not conforming to the preset correspondence relationship in the pre-stored table of the correspondence relationship.

[0082] The records in the pre-stored correspondence table can be obtained by summarizing the results of multiple actual measurements. For example, by loading a small amount of goods and full-load goods in the cargo lane to determine the relationship between the sampling angles and length values corresponding to the goods in the target cargo lane at different storage depths. The pre-stored correspondence table can also obtain the records of the correspondence relationship between each sampling angle and length value through calculation.

[0083] Figure 7 is a schematic diagram of the processing of the point cloud data corresponding to the support beam in the embodiment of the detection method according to the present disclosure. In Figure 7 For the structure with a hollow part in each layer of the cargo lane, the support beam 115 of the target cargo lane 11 and the support beam 115a of the adjacent cargo lane 11a can both be scanned by the scanning plane 21 of the lidar 2, and the point cloud data of the support beams 115 and 115a with a certain height may also form continuous segment records.

[0084] It can be seen that Figure 7 There are two support beams 115 supporting the target cargo lane 11, which can form continuous segment records cs13 and cs15. The two support beams 115a of the adjacent cargo lane 11a above the target cargo lane 11 can form continuous segment records cs14 and cs16. The objects marked F and G in the target cargo lane 11 and the adjacent cargo lane 11a respectively correspond to the continuous segment records cs11 and cs12.

[0085] The installation position of the support beam relative to the cargo lane is relatively fixed. Therefore, the sampling angles and length values corresponding to the support beam can be obtained in advance accordingly as the basis for data filtering. Therefore, in some embodiments, the step of screening out the continuous segment records whose sampling angles and length values do not conform to the preset correspondence relationship from the obtained continuous segment records includes: screening out the continuous segment records of the sampling angles and length values corresponding to the support beam 115 of the target cargo lane 11 and the support beam 115a of the adjacent cargo lane respectively from the obtained continuous segment records.

[0086] Even in the specific case where the front end face of the goods in the target cargo lane 11 is in the same plane as the front end face of the support beam 115, it can also be screened out by the sampling angle and length value corresponding to the support beam 115, so as to clearly determine the continuous segment record corresponding to the front end face of the goods. In this way, the interference of the support beams 115 and 115a on the detection of the goods in the target cargo lane 11 can be conveniently removed, thereby improving the accuracy of the detection of the storage depth of the cargo lane.

[0087] Refer to Figure 7, considering that there are support beams on both the lower side and the upper side of each lane, for the target lane 11, the sampling angles corresponding to the internal goods are basically between the sampling angles corresponding to the support beam 115 on the side of the target lane 11 close to the lidar 2 and the support beam 115a of the adjacent lane 11a above it. This can be used as a basis for determining the point cloud data corresponding to the target lane.

[0088] Therefore, in some embodiments, the step of screening out the point cloud data corresponding to the target lane 11 from the point cloud data may include: further screening out the point cloud data corresponding to the target lane 11 from the point cloud data according to the sampling angles and length values corresponding to the support beam 115 of the target lane 11 and the support beam 115a of the adjacent lane. This can conveniently screen out the point cloud data at angles other than the support beams 115 and 115a, so as to more quickly and conveniently screen out the point cloud data corresponding to the target lane 11.

[0089] In the above embodiments, the basis for screening the point cloud data corresponding to the target lane 11 may be the point cloud data that conforms to the preset angle range AR, or the point cloud data in the entire angle range obtained by the lidar 2.

[0090] In the above embodiments, refer to Figure 2 , in some embodiments, the detection method further includes: in response to an instruction to detect the target lane 11, driving the lidar 2 to a position above the extension line 113 on the side of the target lane 11 away from the shipping end 111 along the lane length direction ld, so as to perform a scanning operation at this position.

[0091] Refer to Figure 2 , the lidar 2 can be arranged on the driving mechanism 5. The driving mechanism 5 can drive the lidar 2 to a suitable detection position of the target lane 11 to be detected. The driving mechanism 5 can be an XYZ three-axis linear module, a multi-joint robot, etc.

[0092] Figure 8 is a schematic structural diagram of some embodiments of the detection system according to the present disclosure. Refer to Figure 8 , based on the detection methods of the foregoing embodiments, the embodiments of the present disclosure provide a detection system, including: a lidar 2, a memory 3, and a processor 4 coupled to the memory. The processor 4 is configured to execute the detection method of any of the foregoing embodiments based on the instructions stored in the memory.

[0093] The memory 3 can be a high-speed RAM memory, a non-volatile memory, etc. The memory 3 can also be a memory array, and may be partitioned, and the partitions can be combined into virtual volumes according to certain rules. The processor 4 can be a central processing unit CPU, or an application specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the detection method of the present disclosure.

[0094] An embodiment of the present disclosure also provides a computer-readable storage medium, which non-temporarily stores computer instructions, and when the instructions are executed by a processor, the detection method of any of the foregoing embodiments is implemented.

[0095] Here, the computer-readable medium can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. The computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. Examples of the computer-readable storage medium can include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a RAM, a ROM, an erasable programmable read-only memory (EPROM), or a flash memory, an optical fiber, a portable compact disc read-only memory (Compact Disc Read-Only Memory, CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0096] In some embodiments of the present disclosure, the computer-readable storage medium can be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, the computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, and the computer-readable signal medium can send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted by any suitable medium, including: wires, optical cables, radio frequency (RF), etc., or any suitable combination of the above.

[0097] Embodiments of the present disclosure also provide a computer program product, including a computer program which, when executed by a processor, implements the detection method in any of the foregoing embodiments.

[0098] The code of the computer program can be written in one or more programming languages or combinations thereof. The programming languages may include object-oriented programming languages such as Java, Smalltalk, C++, and may also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a LAN or WAN, or can be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0099] So far, the embodiments of the present disclosure have been described in detail. To avoid obscuring the concept of the present disclosure, some details well known in the art have not been described. Those skilled in the art can fully understand how to implement the technical solutions disclosed herein based on the above description.

[0100] Although some specific embodiments of the present disclosure have been described in detail by way of examples, those skilled in the art should understand that the above examples are for illustrative purposes only and not for limiting the scope of the present disclosure. Those skilled in the art should understand that the above embodiments can be modified or partial technical features can be equivalently replaced without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. A detection method for detecting the storage depth of goods in a target aisle (11) in a shelf (1), comprising: The target aisle (11) is scanned by a laser radar (2) located on a side of the target aisle (11) away from the delivery end (111) to obtain point cloud data, wherein during the scanning of the target aisle (11), a scanning surface (21) of the laser radar (2) is configured to intersect with a bottom surface (112) of the target aisle (11); Determining the distance between the goods (114) in the target cargo lane (11) and the laser radar (2) according to the point cloud data; The cargo storage depth of the target cargo lane (11) is determined according to the distance.

2. The detection method according to claim 1, wherein: The step of determining the distance between the goods (114) in the target cargo lane (11) and the laser radar (2) according to the point cloud data comprises: Filtering out point cloud data corresponding to the target cargo channel (11) from the point cloud data; The distance between the goods (114) in the target cargo lane (11) and the laser radar (2) is determined based on the sampling angles and length values ​​in the point cloud data corresponding to the target cargo lane (11).

3. The detection method according to claim 2, wherein: The step of selecting point cloud data corresponding to the target cargo channel (11) from the point cloud data comprises: In the point cloud data, determine the point cloud data in which the absolute value of the difference between the length value corresponding to the sampling angles exceeding the preset number continuously and the length value corresponding to the initial count is not greater than the preset length threshold, so as to obtain a continuous segment record (cs) of the point cloud data, wherein the continuous segment record (cs) includes the sampling angle corresponding to the initial count, the length value corresponding to the initial count and the number of continuous sampling points; Continuous segment records (cs) whose sampling angles and length values ​​do not conform to a preset corresponding relationship are screened out from the obtained continuous segment records (cs) to determine the point cloud data corresponding to the target cargo channel (11).

4. The detection method according to claim 3, wherein: The step of excluding the continuous segment records (cs) whose sampling angle and length values ​​do not conform to the preset corresponding relationship from the obtained continuous segment records (cs) comprises: Query each continuous segment record (cs) according to a pre-stored table of correspondence between sampling angles and length values ​​to determine a continuous segment record (cs) that does not conform to a preset correspondence in the pre-stored table of correspondence; Continuous segment records (cs) that do not conform to the preset corresponding relationship in the corresponding relationship pre-stored table are screened out.

5. The detection method according to claim 3, wherein: The step of screening out the continuous segment records (cs) whose sampling angle and length values ​​do not conform to the preset corresponding relationship from the obtained continuous segment records (cs) includes: The continuous segment records (cs) of the sampling angles and length values ​​corresponding to the support beam (115) of the target cargo lane (11) and the support beam (115a) of the adjacent cargo lane (11a) are respectively filtered out from the obtained continuous segment records (cs).

6. The detection method according to claim 2, wherein: The step of selecting point cloud data corresponding to the target cargo channel (11) from the point cloud data comprises: According to the sampling angles and length values ​​respectively corresponding to the support beam (115) of the target cargo aisle (11) and the support beam (115a) of the adjacent cargo aisle (11a), the point cloud data corresponding to the target cargo aisle (11) is further screened out from the point cloud data.

7. The detection method according to claim 1, wherein: The step of determining the distance between the goods (114) in the target cargo lane (11) and the laser radar (2) according to the point cloud data comprises: Filtering out point cloud data whose sampling angles conform to a preset angle range (AR) from the point cloud data, wherein the target cargo lane (11) is located within the preset angle range (AR); The distance between the goods (114) in the target cargo lane (11) and the laser radar (2) is determined based on the sampling angle and the corresponding length value in the point cloud data that meets the preset angle range (AR).

8. The detection method according to claim 7, wherein: The angle value corresponding to the preset angle range (AR) is less than 45°.

9. The detection method according to claim 7, wherein: The shelf (1) includes multiple layers of aisles, and the point cloud data that conforms to the preset angle range (AR) includes: point cloud data corresponding to the target aisle (11), and point cloud data corresponding to an aisle whose bottom surface intersects with the scanning surface (21) in an adjacent aisle (11a) of the target aisle (11); The step of determining the distance between the goods (114) in the target cargo lane (11) and the laser radar (2) according to the point cloud data comprises: Further selecting the point cloud data corresponding to the target cargo lane (11) from the point cloud data that meets the preset angle range (AR); The distance between the goods (114) in the target cargo lane (11) and the laser radar (2) is determined based on the sampling angles and length values ​​in the point cloud data corresponding to the target cargo lane (11).

10. The detection method according to claim 1, further comprising: In response to an instruction to detect the target cargo lane (11), the laser radar (2) is driven to move to a position above an extension line (113) of the target cargo lane (11) away from a delivery end (111) along the cargo lane length direction (ld), so as to perform a scanning operation at this position.

11. The detection method according to claim 10, wherein: The distance in the vertical direction between the position of the laser radar (2) when performing a scanning operation and the extension line (113) is no greater than the height of the target cargo lane (11).

12. A detection system comprising: LiDAR (2); Memory (3); and A processor (4) coupled to the memory, configured to execute the detection method according to any one of claims 1 to 11 based on instructions stored in the memory.

13. A computer-readable storage medium, wherein the computer-readable storage medium non-temporarily stores computer instructions, wherein the instructions, when executed by a processor, implement the detection method according to any one of claims 1 to 11.

14. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the detection method according to any one of claims 1 to 11.

Images