Cliff detection method and device, bulldozer and readable storage medium

Abstract

The invention discloses a cliff detection method and device, a bulldozer and a readable storage medium, and is applied to the bulldozer, and a scanning unit is arranged on a front hood of the bulldozer. The method comprises the steps that point cloud data collected by a scanning unit are acquired, a grid map is constructed according to a preset detection range and the point cloud data, and the grid map comprises at least one grid area; respectively determining candidate cliff points of each grid region; obtaining the current position of the bulldozer, and determining a target cliff point according to the current position and the candidate cliff point; and determining a cliff-breaking detection distance according to the target cliff-breaking point, and displaying the cliff-breaking detection distance on a center console of the bulldozer. According to the method provided by the invention, the problems of poor precision and high time delay when the millimeter wave radar is used for carrying out cliff detection are solved, the scanning unit is used for rapidly and accurately scanning the front ground, and when the bulldozer works in real time, the cliff detection distance of the front area is accurately and timely provided for a driver.

Description

Technical Field

[0001] The present invention relates to the field of image detection technology, and in particular to a cliff detection method, device, bulldozer and readable storage medium. Background Art

[0002] In traditional construction projects, bulldozer operations often face complex terrain and environmental conditions, such as cliffs, steep slopes and other terrain features. These features may cause accidents or damage to the bulldozer during operation, and even pose a safety threat to the operator. Therefore, the bulldozer needs to ensure accurate perception of the terrain during rapid operation to avoid accidents caused by failure to detect danger in time.

[0003] At present, millimeter-wave radar is used for cliff detection during bulldozer operation. However, millimeter-wave radar has a long wavelength and cannot effectively distinguish more complex and small terrain features. In addition, millimeter-wave radar has certain limitations in real-time rapid response. When the bulldozer is operating at high speed, the terrain data provided by the millimeter-wave radar may have the risk of delayed safety warning. Summary of the invention

[0004] The present invention provides a cliff detection method, device, bulldozer and readable storage medium to solve the problems of poor accuracy and high latency when using millimeter wave radar for cliff detection. A scanning unit such as a laser radar or a depth camera sensor is used to scan the ground in front, providing a scanning unit with higher accuracy, faster response and stronger environmental adaptability to achieve fast and accurate scanning of the ground in front.

[0005] According to one aspect of the present invention, a cliff detection method is provided, which is applied to a bulldozer, wherein a scanning unit is provided on a front hood of the bulldozer; the method comprises:

[0006] Acquire point cloud data collected by the scanning unit, and construct a grid map according to a preset detection range and the point cloud data, wherein the grid map includes at least one grid area;

[0007] Determine the candidate cliff points for each grid area respectively;

[0008] Get the current position of the bulldozer, and determine the target cliff point based on the current position and the candidate cliff points;

[0009] The cliff detection distance is determined according to the target cliff point and is displayed on the center console of the bulldozer.

[0010] According to another aspect of the present invention, a cliff detection device is provided, which is applied to a bulldozer, and a scanning unit is provided on the front hood of the bulldozer; the device comprises:

[0011] A construction module, used to obtain the point cloud data collected by the scanning unit, and to construct a grid map according to a preset detection range and the point cloud data, wherein the grid map includes at least one grid area;

[0012] A determination module, used to determine candidate cliff points in each grid area respectively;

[0013] An acquisition module is used to acquire the current position of the bulldozer and determine the target cliff point based on the current position and the candidate cliff points;

[0014] The display module is used to determine the cliff detection distance according to the target cliff point and display the cliff detection distance on the center console of the bulldozer.

[0015] According to another aspect of the present invention, there is provided a bulldozer, the bulldozer comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by at least one processor. The computer program is executed by the at least one processor so that the at least one processor can execute the cliff detection method of any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the cliff detection method described in any embodiment of the present invention when executed.

[0020] The cliff detection method provided by the embodiment of the present invention obtains the point cloud data collected by the scanning unit, and constructs a grid map according to the pre-set detection range and point cloud data; determines the candidate cliff points of each grid area respectively; obtains the current position of the bulldozer, and determines the target cliff point according to the current position and the candidate cliff point; determines the cliff detection distance according to the target cliff point, and displays the cliff detection distance on the central console of the bulldozer. On the one hand, the collected point cloud data is used to construct a grid map according to the detection range and the distribution of the point cloud data. Each grid map includes at least one grid area, which realizes the reasonable division of the point cloud data and provides accurate data for determining the cliff point according to the point cloud data. At the same time, the problems of poor precision, high latency and slow response when using millimeter wave radar for cliff detection are solved. The scanning unit such as laser radar or depth camera sensor is used to scan the ground in front, and a scanning unit with higher precision, faster response and stronger environmental adaptability is provided to realize fast and accurate scanning of the ground in front. On the other hand, the target cliff point is determined based on the current position of the bulldozer and the candidate cliff points, so that the cliff point closest to the current position of the bulldozer can be accurately determined when the bulldozer is working in real time. Finally, the cliff detection distance is determined based on the target cliff point, and the cliff detection distance is displayed on the central console of the bulldozer, so that the data of the ground in front can be displayed to the bulldozer driver in real time, so that the driver can know the danger in the front area in time and make a judgment in time. In turn, the driving experience of the bulldozer driver is improved, and the safety and efficiency of the bulldozer driver's operation when using the bulldozer is also effectively improved.

[0021] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 A flowchart of a cliff detection method provided by an embodiment of the present invention;

[0024] Figure 2 A flowchart of another cliff detection method provided by an embodiment of the present invention;

[0025] Figure 3 A schematic structural diagram of a bulldozer provided by an embodiment of the present invention;

[0026] Figure 4 An example diagram of a grid map provided by an embodiment of the present invention;

[0027] Figure 5 A schematic diagram of the structure of a cliff detection device provided by an embodiment of the present invention;

[0028] Figure 6 Another structural schematic diagram of a bulldozer provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0029] 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.

[0030] It should be noted that the terms "candidate", "target", 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.

[0031] Figure 1 A flowchart of a cliff detection method provided in an embodiment of the present invention. This embodiment is applicable to the case where a bulldozer is working under complex terrain conditions. The method can be executed by a cliff detection device. The cliff detection device can be implemented in the form of hardware and / or software. The cliff detection device can be configured in a bulldozer. In this embodiment, an electronic device such as a data processing unit is provided in the bulldozer. A scanning unit is provided on the front hood of the bulldozer. Figure 1 As shown, the method includes:

[0032] S101, acquiring point cloud data collected by a scanning unit, and constructing a grid map according to a preset detection range and point cloud data.

[0033] The grid map includes at least one grid area. The scanning unit is used to scan the data of the ground in front of the bulldozer. In this embodiment, the scanning unit can be an instrument such as a laser radar or a depth camera sensor that can scan the ground through laser pulses.

[0034] Specifically, the scanning unit is installed above the front hood of the bulldozer. When the bulldozer starts construction, the scanning unit scans the ground in front of it, and the scanning unit can obtain the three-dimensional coordinates of each point on the ground to form point cloud data. At this time, the bulldozer can obtain the point cloud data collected by the scanning unit.

[0035] Since the point cloud data is a coordinate system established based on the scanning unit, that is, if the scanning unit is a laser radar, the point cloud data is data in the laser radar coordinate system. Therefore, in order to ensure the unity of the coordinate system, the point cloud data needs to be converted to the self-vehicle coordinate system centered on the bulldozer. The rotation matrix and translation matrix can be determined, and the coordinate system of the point cloud data can be converted according to the conversion formula of the coordinate system. Among them, the self-vehicle coordinate system takes the vertical projection point of the geometric center of the bulldozer body on the ground as the origin, the forward direction of the bulldozer as the positive direction of the Y axis, the right side of the bulldozer as the positive direction of the X axis (the left side of the bulldozer is the negative direction of the X axis), and the upward direction perpendicular to the bulldozer track plane as the positive direction of the Z axis.

[0036] After converting the coordinate system of the point cloud data into the vehicle coordinate system, all collected point cloud data can be segmented according to the preset detection range. For example, if the range of the point cloud data collected at one time is 100*100m, the preset detection range can be 80*80m. In addition, after segmenting the point cloud data according to the detection range, the segmented detection range can be grid-constructed according to the distribution of the point cloud data. Among them, when constructing the grid map, since the Y-axis points to the forward direction of the vehicle, the grid is only divided along the X-axis direction. For example, when the density of the point cloud data is large, the grid of the X-axis can be divided with a smaller division scale. When the density of the point cloud data is small, the grid of the X-axis can be divided with a larger division scale.

[0037] After the point cloud data is meshed, a grid map can be obtained with the detection range as a whole, including x1*y, ..., xn*y as different grid areas. Among them, y is the total length of the Y axis. x is the total length of the X axis. By dividing the X axis, x1, ..., xn can be obtained after equal division.

[0038] In this embodiment, the collected point cloud data is used to construct a grid map according to the detection range and the distribution of the point cloud data. Each grid map includes at least one grid area, which realizes the reasonable division of the point cloud data and provides accurate data for determining the cliff point based on the point cloud data. At the same time, the problem that the millimeter wave radar cannot effectively distinguish the more complex and fine terrain features when performing cliff detection, and the real-time rapid response has limitations, is solved. The scanning unit such as a laser radar or a depth camera sensor is used to scan the ground in front, providing a scanning unit with higher precision, faster response, and stronger environmental adaptability to achieve fast and accurate scanning of the ground in front.

[0039] S102: Determine candidate cliff points in each grid area respectively.

[0040] Among them, the candidate cliff point is the cliff point to be selected.

[0041] Specifically, for each grid area, it is necessary to determine the candidate cliff points in this grid area.

[0042] In one implementation, the bulldozer location can be used as the origin, and multiple direction lines can be determined in a preset direction order. If a ground point or a hole point is found on the current direction line, the ground point or the hole point can be used as a candidate cliff point. The ground point is determined based on its slope.

[0043] In another implementation, each point cloud data in the grid area is sorted from small to large according to the Y coordinate, and the Y coordinate difference between two adjacent points is calculated in sequence. The candidate cliff point is determined according to the Y coordinate difference and the preset difference threshold. Among them, the candidate cliff point is a point cloud data with a coordinate difference greater than or equal to the preset threshold and a smaller Y coordinate value.

[0044] S103, obtaining the current position of the bulldozer, and determining the target cliff point according to the current position and the candidate cliff points.

[0045] The target cliff point is a cliff point determined as a target from the candidate cliff points.

[0046] Specifically, since the bulldozer is in operation, it is necessary to determine the current position of the bulldozer, and determine the target cliff point from the candidate cliff points according to the current position. For example, according to the current position of the bulldozer, first determine which grid area the current position is in or which grid area it is closest to. Then, determine the target cliff point according to the candidate cliff points in this grid area and the current position of the bulldozer.

[0047] In this embodiment, the target cliff point is determined based on the current position of the bulldozer and the candidate cliff points, so that the cliff point closest to the current position of the bulldozer can be accurately determined when the bulldozer is working in real time, providing a basis for subsequently determining the distance between the cliff point and the current position.

[0048] S104. Determine a cliff detection distance according to the target cliff point, and display the cliff detection distance on a central console of the bulldozer.

[0049] Among them, the central console is installed in the driving operation room of the bulldozer, and can display relevant content of controlling the bulldozer to the bulldozer driver.

[0050] Specifically, after the target cliff point is determined, the distance between the target cliff point and the bulldozer, i.e., the cliff detection distance, can be determined according to the target cliff point and the current position of the bulldozer. Moreover, after the cliff detection distance is determined, the cliff detection distance can be displayed on the central console of the bulldozer to remind the bulldozer driver to avoid the cliff point ahead in time.

[0051] In this embodiment, the cliff detection distance is determined according to the target cliff point, and the cliff detection distance is displayed on the central console of the bulldozer, so that the data of the ground ahead can be displayed to the bulldozer driver in real time, so that the driver can know the danger in the area ahead and make a judgment in time. This improves the driving experience of the bulldozer driver and effectively improves the safety and efficiency of the bulldozer driver when using the bulldozer.

[0052] The cliff detection method provided by the embodiment of the present invention obtains the point cloud data collected by the scanning unit, and constructs a grid map according to the pre-set detection range and point cloud data; determines the candidate cliff points of each grid area respectively; obtains the current position of the bulldozer, and determines the target cliff point according to the current position and the candidate cliff point; determines the cliff detection distance according to the target cliff point, and displays the cliff detection distance on the central console of the bulldozer. On the one hand, the collected point cloud data is used to construct a grid map according to the detection range and the distribution of the point cloud data. Each grid map includes at least one grid area, which realizes the reasonable division of the point cloud data and provides accurate data for determining the cliff point according to the point cloud data. At the same time, the problems of poor precision, high latency and slow response when using millimeter wave radar for cliff detection are solved. The scanning unit such as laser radar or depth camera sensor is used to scan the ground in front, and a scanning unit with higher precision, faster response and stronger environmental adaptability is provided to realize fast and accurate scanning of the ground in front. On the other hand, the target cliff point is determined based on the current position of the bulldozer and the candidate cliff points, so that the cliff point closest to the current position of the bulldozer can be accurately determined when the bulldozer is working in real time. Finally, the cliff detection distance is determined based on the target cliff point, and the cliff detection distance is displayed on the central console of the bulldozer, so that the data of the ground in front can be displayed to the bulldozer driver in real time, so that the driver can know the danger in the front area in time and make a judgment in time. In turn, the driving experience of the bulldozer driver is improved, and the safety and efficiency of the bulldozer driver's operation when using the bulldozer is also effectively improved.

[0053] Figure 2 A flowchart of another cliff detection method provided in an embodiment of the present invention. Based on the above embodiments, this embodiment describes in detail the steps before "building a grid map according to a preset detection range and the point cloud data", the step of "building a grid map according to the preset detection range and the point cloud data", the step of "determining candidate cliff points in the grid area", the step of "determining a target cliff point according to the current position and the candidate cliff points" and the step of "determining a cliff detection distance according to the target cliff point".

[0054] Prior to this, a structure of a bulldozer provided in an embodiment of the present invention is described. Figure 3 A schematic diagram of the structure of a bulldozer provided by an embodiment of the present invention. Figure 3As shown, a bulldozer 10 may include a center console 101 and a data processing unit 102, as well as a scanning unit 20 installed above the front hood of the bulldozer 10. The center console 101 may be installed in the cab of the bulldozer 10, and is used to provide the driver with an operating lever or operating button to control the bulldozer, and to display various operating states of the bulldozer to the driver. The data processing unit 102 is a unit for processing data in the bulldozer 10, and may be presented in the form of an electronic device. The data processing unit 102 is electrically connected or communicatively connected to the center console 101, and is communicatively connected to the scanning unit 20. In this embodiment, the bulldozer serves as the executor of the entire solution, and its specific processing process may be processed by the data processing unit in the bulldozer.

[0055] Continue to refer to Figure 2 ,like Figure 2 As shown, the method includes:

[0056] S201, acquiring point cloud data collected by a scanning unit.

[0057] Specifically, the scanning unit is installed above the front hood of the bulldozer. When the bulldozer starts construction, the scanning unit scans the ground in front of it, and the scanning unit can obtain the three-dimensional coordinates of each point on the ground to form point cloud data. At this time, the bulldozer can obtain the point cloud data collected by the scanning unit.

[0058] S202: Determine the current operating direction of the bulldozer.

[0059] Specifically, since the coordinate system of the point cloud data is established based on the scanning unit, and the final cliff detection distance needs to be determined based on the bulldozer as a reference, the vehicle coordinate system needs to be determined based on the current working condition of the bulldozer. First, the current working direction of the bulldozer can be determined.

[0060] S203: Convert the coordinate system of the point cloud data according to the current working direction.

[0061] The converted coordinate system is the bulldozer's own vehicle coordinate system, which is a coordinate system established with the bulldozer as the origin and the current working direction as the positive direction of the Y axis. In the actual process, the origin of the coordinate system can be the vertical projection point of the geometric center of the bulldozer body on the ground as the origin.

[0062] Specifically, after the current operating direction of the bulldozer is determined, a coordinate system can be established with the vertical projection point of the geometric center of the bulldozer body on the ground as the origin of the coordinate system and the current operating direction of the bulldozer as the positive direction of the Y axis of the vehicle coordinate system.

[0063] Exemplarily, the position and posture of the scanning unit relative to the vehicle coordinate system are determined, that is, the translation vector and the rotation matrix are determined, and the point cloud data are transformed using the rotation matrix and the translation vector.

[0064] In this embodiment, data integration is achieved by converting the point cloud data into the vehicle coordinate system. At the same time, based on the point cloud data in the vehicle coordinate system, real-time detection data can be provided for detecting whether there is a cliff point in front of the bulldozer, thereby improving the real-time performance of data acquisition and data processing.

[0065] S204: Determine the grid map range according to the detection range.

[0066] Specifically, since the range of the acquired point cloud data is determined according to the scanning range of the scanning unit, and the scanning range of the scanning unit is not fixed, the detection range can be preset, that is, the required detection range is preset, and the scanning range scanned by the scanning unit is segmented based on the detection range to obtain the point cloud data within the required detection range, that is, to determine the range of the grid map.

[0067] S205 , according to the distribution quantity of the point cloud data and the range of the grid map, the range of the grid map is divided along the X-axis direction of the vehicle coordinate system to obtain a grid map.

[0068] Specifically, since the distribution of point cloud data needs to be determined according to the specific terrain, before each division, the division size needs to be determined according to the distribution quantity of point cloud data. Also, the range of the grid map is divided along the X-axis direction of the vehicle coordinate system to obtain multiple grid areas. All grid areas are a whole grid map.

[0069] For example, Figure 4 This is an example diagram of a grid map provided by an embodiment of the present invention. Figure 4 As shown in the figure, if the range of the grid map is x6*y, then the entire grid map can be divided according to the distribution quantity of the point cloud data and the range of the grid map. Figure 4 By dividing in the way in , different grid areas with different ranges of x1*y, x2*y, x3*y, x4*y, x5*y and x6*y can be obtained. Among them, the point cloud data contained in each grid area is the same or similar. x1 to x3 are x coordinates in the negative direction of the X axis, and x4 to x6 are x coordinates in the positive direction of the X axis. It is only a reference example to reflect the division of the grid map. 0 is the position of the vertical projection point of the geometric center of the bulldozer body on the ground.

[0070] S206: For any grid area, determine the arrangement order of each point cloud data in the grid area.

[0071] The arrangement order is from small to large according to the coordinate value of the point cloud data on the Y-axis of the vehicle coordinate system.

[0072] Specifically, for any grid area, the point cloud data can be sorted from small to large according to the Y coordinate value.

[0073] S207 , calculating the coordinate difference between two adjacent point cloud data on the Y axis of the vehicle coordinate system in sequence according to the arrangement order.

[0074] Specifically, according to the arrangement order of the point cloud data, the coordinate difference between two adjacent point cloud data on the Y axis of the vehicle coordinate system is calculated in sequence.

[0075] For example, assume that there are three point cloud data A, B, and C in a certain grid area. The Y coordinate value of A is Ay, the Y coordinate value of B is By, and the Y coordinate value of C is Cy. Among them, Ay<By<Cy. At this time, the coordinate difference value By-Ay between A and B can be determined, and the coordinate difference value Cy-By between B and C can be determined.

[0076] S208. Determine candidate cliff points according to the coordinate difference.

[0077] Specifically, the candidate cliff points can be determined as follows:

[0078] (1) If at least one coordinate difference in the grid area is greater than or equal to a preset threshold, a point cloud data having a smaller Y-axis coordinate value corresponding to the coordinate difference greater than or equal to the preset threshold is determined as a candidate cliff point.

[0079] (2) If all coordinate differences in the grid area are less than the preset threshold, the point cloud data with the largest coordinate value on the Y axis of the vehicle coordinate system is determined as the candidate cliff point.

[0080] Exemplarily, following the above example, assume that at least one of the coordinate difference value By-Ay between A and B and the coordinate difference value Cy-By between B and C is greater than or equal to the preset threshold, for example, By-Ay is greater than or equal to the preset threshold. At this time, A can be determined as a candidate cliff point. Assuming that By-Ay and Cy-By are both greater than or equal to the preset threshold, at this time, A and B can be determined as candidate cliff points. Assuming that the coordinate difference value By-Ay between A and B and the coordinate difference value Cy-By between B and C are both less than the preset threshold, C is determined as a candidate cliff point.

[0081] S209: Obtain the current position of the bulldozer.

[0082] Specifically, a positioning instrument may be used to obtain the current position of the bulldozer.

[0083] S210, discretizing the candidate cliff points and eliminating the data to obtain the intermediate cliff points.

[0084] Specifically, all candidate cliff points in the grid area are discretized and processed, and after the discrete candidate cliff points are eliminated, the remaining candidate cliff points are used as intermediate cliff points.

[0085] S211 , determining an intermediate cliff point whose Y-axis coordinate value is the smallest with respect to the current position among the intermediate cliff points as a target cliff point.

[0086] Specifically, the Y coordinates of all the intermediate cliff points are compared with the Y-axis coordinate value of the current position, and the intermediate cliff point corresponding to the Y coordinate closest to the Y coordinate of the current position is determined as the target cliff point. That is, the intermediate cliff point with the smallest Y-axis coordinate value is determined as the target cliff point.

[0087] S212: Determine the Y-axis coordinate value of the target cliff point as the cliff detection distance.

[0088] Specifically, after the target cliff point is determined, in one implementation, the Y-axis coordinate value of the target cliff point can be directly determined as the cliff detection distance.

[0089] In this embodiment, the cliff detection distance is quickly determined by directly using the intermediate cliff point closest to the current position of the bulldozer as the target cliff point.

[0090] S213: Calculate the distance from the target cliff point to the bulldozer using a point-to-plane calculation method, and determine the distance from the target cliff point to the bulldozer as the cliff detection distance.

[0091] Specifically, after the target cliff point is determined, in another implementation method, a more accurate distance from the target cliff point to the bulldozer can be calculated based on the coordinate value of the target cliff point and the surface coordinates of the current position of the bulldozer using a point-to-surface calculation method, and the distance from the target cliff point to the bulldozer can be determined as the cliff detection distance.

[0092] In this embodiment, after the target cliff point is determined, the cliff detection distance can be calculated more accurately by using a point-to-plane calculation method.

[0093] It is worth noting that S212 and S213 are two different methods for determining the cliff detection distance. In the actual process, any one of them can be selected as the method for determining the cliff detection distance this time.

[0094] S214. The cliff detection distance is displayed on the central console of the bulldozer.

[0095] Specifically, after the cliff detection distance is calculated, the cliff detection distance can be sent to the central console of the bulldozer, so that the bulldozer driver can know the current distance from the bulldozer to the edge of the cliff, so as to avoid dangerous areas such as cliffs in time.

[0096] In this embodiment, the cliff detection distance is displayed on the central console of the bulldozer, which can not only provide accurate danger warnings for the bulldozer operators and help them avoid dangerous areas such as cliffs in time, but also apply this solution to unmanned and remote-controlled bulldozers, effectively improving the safety and automation level of operations. It is particularly suitable for mining, spoil dumps and complex terrain construction environments, significantly reducing accident risks and improving work efficiency.

[0097] The cliff detection method provided by the embodiment of the present invention obtains point cloud data collected by a scanning unit; determines the current working direction of the bulldozer; converts the coordinate system of the point cloud data according to the current working direction; determines the range of the grid map according to the detection range; divides the range of the grid map along the X-axis direction of the vehicle coordinate system according to the distribution quantity of the point cloud data and the grid map range to obtain a grid map; for any grid area, determines the arrangement order of each point cloud data in the grid area; and calculates the distance between two adjacent point cloud data in the Y-axis direction of the vehicle coordinate system in turn according to the arrangement order. ; determine the candidate cliff point according to the coordinate difference; obtain the current position of the bulldozer; discretize the candidate cliff points to eliminate the data and obtain the intermediate cliff point; determine the intermediate cliff point with the smallest Y-axis coordinate value with the current position as the target cliff point; determine the Y-axis coordinate value of the target cliff point as the cliff detection distance, or, use the point-to-surface calculation method to calculate the distance from the target cliff point to the bulldozer, and determine the distance from the target cliff point to the bulldozer as the cliff detection distance; display the cliff detection distance on the center console of the bulldozer. The above technical solution, on the one hand, realizes the integration of data by converting the point cloud data into the self-vehicle coordinate system. At the same time, based on the point cloud data in the self-vehicle coordinate system, it can provide real-time detection data for detecting whether there is a cliff point in front of the bulldozer, thereby improving the real-time performance of data acquisition and data processing. On the other hand, the cliff detection distance can be quickly determined by directly using the intermediate cliff point that is the smallest relative to the current position of the bulldozer as the target cliff point; or, after the target cliff point is determined, the cliff detection distance can be more accurately calculated using the point-to-surface calculation method. Finally, displaying the cliff detection distance on the bulldozer's central console can not only provide accurate danger warnings for bulldozer operators and help them avoid dangerous areas such as cliffs in a timely manner, but also apply this solution to unmanned and remote-controlled bulldozers, effectively improving the safety and automation level of operations. It is particularly suitable for mining, spoil dumps, and complex terrain construction environments, significantly reducing accident risks and improving work efficiency.

[0098] Figure 5 A schematic diagram of the structure of a cliff detection device provided by an embodiment of the present invention. Applied to a bulldozer, a scanning unit is provided on the front hood of the bulldozer; Figure 5 As shown, the device comprises:

[0099] A construction module 501 is used to obtain the point cloud data collected by the scanning unit, and to construct a grid map according to a preset detection range and the point cloud data, wherein the grid map includes at least one grid area;

[0100] A determination module 502, used to determine candidate cliff points in each grid area respectively;

[0101] The acquisition module 503 is used to acquire the current position of the bulldozer and determine the target cliff point according to the current position and the candidate cliff points;

[0102] The display module 504 is used to determine the cliff detection distance according to the target cliff point and display the cliff detection distance on the central console of the bulldozer.

[0103] Optionally, before constructing the grid map according to the preset detection range and point cloud data, the construction module 501 is further used to:

[0104] Determine the current working direction of the bulldozer; convert the coordinate system of the point cloud data according to the current working direction, wherein the converted coordinate system is the bulldozer's own vehicle coordinate system, and the own vehicle coordinate system is a coordinate system established with the bulldozer as the origin and the current working direction as the positive direction of the Y axis.

[0105] Optionally, a grid map is constructed according to a preset detection range and point cloud data, and the construction module 501 is specifically used for:

[0106] According to the detection range, the grid map range is determined; according to the distribution quantity of the point cloud data and the grid map range, the grid map range is divided along the X-axis direction of the vehicle coordinate system to obtain the grid map.

[0107] Optionally, for any grid area, the determination module 502 is specifically configured to:

[0108] Determine the arrangement order of each point cloud data in the grid area, where the arrangement order is arranged from small to large according to the coordinate value of the point cloud data on the Y axis of the vehicle coordinate system; calculate the coordinate difference of two adjacent point cloud data on the Y axis of the vehicle coordinate system in turn according to the arrangement order; determine the candidate cliff point according to the coordinate difference.

[0109] Optionally, the candidate cliff point is determined according to the coordinate difference, and the determination module 502 is specifically used to:

[0110] If at least one coordinate difference in the grid area is greater than or equal to a preset threshold, a point cloud data with a smaller Y-axis coordinate value corresponding to a coordinate difference greater than or equal to the preset threshold is determined as a candidate cliff point; if all coordinate differences in the grid area are less than the preset threshold, a point cloud data with the largest coordinate value on the Y-axis of the vehicle coordinate system is determined as a candidate cliff point.

[0111] Optionally, the acquisition module 503 is specifically used for:

[0112] Discretized data of candidate cliff points are eliminated to obtain intermediate cliff points; the intermediate cliff point with the smallest Y-axis coordinate value with the current position is determined as the target cliff point.

[0113] Optionally, the display module 504 is specifically used for:

[0114] The Y-axis coordinate value of the target cliff point is determined as the cliff detection distance; or, the distance from the target cliff point to the bulldozer is calculated using a point-to-plane calculation method, and the distance from the target cliff point to the bulldozer is determined as the cliff detection distance.

[0115] The cliff detection device provided in the embodiment of the present invention can execute the cliff detection method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0116] Figure 6 Another structural schematic diagram of a bulldozer provided for an embodiment of the present invention. In this embodiment, the bulldozer can be presented in the form of an electronic device, or a data processing unit in the bulldozer can be presented in the form of an electronic device. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0117] like Figure 6As shown, the bulldozer 6 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the bulldozer 6 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0118] A number of components in the bulldozer 6 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the bulldozer 6 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0119] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the cliff detection method.

[0120] In some embodiments, the cliff detection method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the bulldozer 6 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the cliff detection method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the cliff detection method in any other appropriate manner (e.g., by means of firmware).

[0121] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0122] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0123] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0124] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0125] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0126] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0127] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0128] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A cliff detection method, characterized in that: Applied to a bulldozer, a scanning unit is provided on the front hood of the bulldozer; the method comprises: Acquire the point cloud data collected by the scanning unit, and construct a grid map according to a preset detection range and the point cloud data, wherein the grid map includes at least one grid area; Determine candidate cliff points for each of the grid areas respectively; Acquire the current position of the bulldozer, and determine a target cliff point according to the current position and the candidate cliff points; A cliff detection distance is determined according to the target cliff point, and the cliff detection distance is displayed on a central console of the bulldozer.

2. The cliff detection method according to claim 1, characterized in that: Before constructing a grid map according to the preset detection range and the point cloud data, it also includes: determining a current operating direction of the bulldozer; The coordinate system of the point cloud data is converted according to the current working direction, wherein the converted coordinate system is the bulldozer's own vehicle coordinate system, and the own vehicle coordinate system is a coordinate system established with the bulldozer as the origin and the current working direction as the positive direction of the Y axis.

3. The cliff detection method according to claim 2, characterized in that: The step of constructing a grid map according to the preset detection range and the point cloud data includes: Determining a grid map range according to the detection range; According to the distribution quantity of the point cloud data and the range of the grid map, the range of the grid map is divided along the X-axis direction of the vehicle coordinate system to obtain the grid map.

4. The cliff detection method according to claim 2, characterized in that: For any of the grid areas, determining a candidate cliff point of the grid area includes: Determine an arrangement order of each point cloud data in the grid area, wherein the arrangement order is arranged from small to large according to the coordinate value of the point cloud data on the Y axis of the vehicle coordinate system; According to the arrangement order, the coordinate difference between two adjacent point cloud data on the Y axis of the vehicle coordinate system is calculated in sequence; The candidate cliff point is determined according to the coordinate difference.

5. The cliff detection method according to claim 4, characterized in that: The determining the candidate cliff point according to the coordinate difference includes: If at least one coordinate difference in the grid area is greater than or equal to a preset threshold, a point cloud data having a smaller Y-axis coordinate value corresponding to the coordinate difference greater than or equal to the preset threshold is determined as the candidate cliff point; If all coordinate differences in the grid area are less than a preset threshold, a point cloud data having the largest coordinate value on the Y-axis of the vehicle coordinate system is determined as the candidate cliff point.

6. The cliff detection method according to claim 2, characterized in that: The step of determining a target cliff point according to the current position and the candidate cliff point includes: Discretizing the candidate cliff points and eliminating the data to obtain intermediate cliff points; Among the intermediate cliff points, an intermediate cliff point having the smallest Y-axis coordinate value with respect to the current position is determined as the target cliff point.

7. The cliff detection method according to claim 2, characterized in that: The determining of the cliff detection distance according to the target cliff point includes: The Y-axis coordinate value of the target cliff point is determined as the cliff detection distance; or, The distance from the target cliff point to the bulldozer is calculated by using a point-to-plane calculation method, and the distance from the target cliff point to the bulldozer is determined as the cliff detection distance.

8. A cliff detection device, characterized in that: Applied to a bulldozer, a scanning unit is provided on the front hood of the bulldozer; the device comprises: A construction module, used to obtain the point cloud data collected by the scanning unit, and construct a grid map according to a preset detection range and the point cloud data, wherein the grid map includes at least one grid area; A determination module, used to determine candidate cliff points in each grid area respectively; An acquisition module, used for acquiring the current position of the bulldozer, and determining a target cliff point according to the current position and the candidate cliff points; A display module is used to determine a cliff detection distance according to the target cliff point, and display the cliff detection distance on a central console of the bulldozer.

9. A bulldozer, characterized in that: include: one or more processors; a memory for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the cliff detection method according to any one of claims 1 to 7.

10. A readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the cliff detection method according to any one of claims 1 to 7 is implemented.

Images