A path planning method, device, equipment and storage medium for a quadruped robot

Abstract

The present invention discloses a path planning method, device, equipment, and storage medium for a quadruped robot. The method includes: during the movement of the quadruped robot, identifying obstacles on the route in real time, and obtaining the size information of the target obstacle when the target obstacle is identified; when it is determined based on the size information that the quadruped robot can cross the target obstacle, determining the position range of the starting point of the quadruped robot when crossing the obstacle; based on the starting point position range, planning at least one travel stride of the quadruped robot on the route, and controlling the quadruped robot to cross the target obstacle according to the travel stride. By adopting the above technical solution, it is possible to ensure that the quadruped robot can safely cross the obstacle even if there is an obstacle on the route.

Description

Technical Field

[0001] The present invention relates to the field of robotics technology, and in particular to a path planning method, device, equipment and storage medium for a quadruped robot. Background Art

[0002] Because their mechanical structure is similar to that of the human body, quadruped robots are often used to replace humans in complex or dangerous environments. When operating independently, quadruped robots must monitor road conditions in real time and, upon detecting obstacles, plan appropriate paths to avoid them, ensuring safe and efficient operation.

[0003] At present, the commonly used technical means is to equip the quadruped robot with sensors, obtain obstacle information through the sensors, and then plan the quadruped robot's route.

[0004] However, when using sensors to detect obstacles, only partial information about the obstacles can be obtained. If the quadruped robot chooses to cross the obstacle, it may fail to cross. Summary of the Invention

[0005] The present invention provides a path planning method, device, equipment and storage medium for a quadruped robot, which can ensure that the quadruped robot can safely cross obstacles when there are obstacles on the quadruped robot's travel route.

[0006] According to one aspect of the present invention, a path planning method for a quadruped robot is provided, the method comprising:

[0007] During the movement of the quadruped robot, obstacles are identified in real time along the route, and when a target obstacle is identified, the size information of the target obstacle is obtained;

[0008] When it is determined based on the size information that the quadruped robot is capable of crossing the target obstacle, a position range of a starting point of the quadruped robot when crossing the obstacle is determined;

[0009] According to the starting point position range, at least one travel stride of the quadruped robot on the travel route is planned, and the quadruped robot is controlled to cross the target obstacle according to the travel stride.

[0010] According to another aspect of the present invention, there is provided a path planning device for a quadruped robot, comprising:

[0011] The size information acquisition module is used to identify obstacles on the moving route of the quadruped robot in real time during its movement, and obtain the size information of the target obstacle when it is identified;

[0012] A foothold position range determination module is used to determine the foothold position range of the quadruped robot when crossing the obstacle when it is determined based on the size information that the quadruped robot can cross the target obstacle;

[0013] The stride planning module is used to plan at least one travel stride of the quadruped robot on the travel route according to the position range of the starting point, and control the quadruped robot to cross the target obstacle according to the travel stride.

[0014] According to another aspect of the present invention, an electronic device is provided, comprising:

[0015] at least one processor; and

[0016] a memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the path planning method for a quadruped robot described in any embodiment of the present invention.

[0018] 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 path planning method for a quadruped robot described in any embodiment of the present invention when executed.

[0019] The technical solution of the embodiment of the present invention can obtain more accurate size information of the target obstacle by detecting obstacles in real time on the travel route of the quadruped robot and obtaining the size information of the obstacles, determining the target stride and the starting point position range based on the obstacle size information, and planning the stride on the travel route based on the starting point position range, so as to reasonably plan the target stride of the quadruped robot for crossing the target obstacle and the travel stride before crossing the target obstacle, so that the quadruped robot can stably and safely cross the target obstacle that can be crossed.

[0020] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] 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.

[0022] Figure 1 is a flow chart of a path planning method for a quadruped robot provided according to the first embodiment of the present invention;

[0023] Figure 2 is a flow chart of a path planning method for a quadruped robot provided according to the second embodiment of the present invention;

[0024] Figure 3 2 is a schematic structural diagram of a path planning device for a quadruped robot according to a third embodiment of the present invention;

[0025] Figure 4 It is a structural diagram of an electronic device for implementing the path planning method for a quadruped robot according to an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions 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 embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first", "second", etc. in the description 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 numbers 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 clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] Example 1

[0029] Figure 1This is a flow chart of a path planning method for a quadruped robot provided in the first embodiment of the present invention. This embodiment can be applied to obtain the size information of obstacles on the quadruped robot's route and perform stride planning on the quadruped robot to achieve safe crossing of obstacles. This method can be executed by a path planning device of the quadruped robot. The path planning device of the quadruped robot can be implemented in the form of hardware and / or software. The path planning device of the quadruped robot can be configured in a control system of the quadruped robot with image processing capabilities. Figure 1 As shown, the method includes:

[0030] S110 . During the movement of the quadruped robot, obstacles are identified on the movement route in real time, and when a target obstacle is identified, size information of the target obstacle is obtained.

[0031] Optionally, the camera installed on the quadruped robot can be a high-definition camera, a binocular camera, a fisheye camera, or other type of camera capable of capturing real-time images of the road environment along the quadruped robot's route. Optionally, the highest camera on the quadruped robot can be used to capture real-time images of the environment along the quadruped robot's route, or multiple cameras can be used to capture images of the environment from multiple perspectives. This can be determined based on the complexity of the specific environment and is not limited here.

[0032] Before the quadruped robot moves along its current route, it needs to obtain pixel values for the unobstructed ground along that route. To facilitate comparison between the previously obtained pixel values for the unobstructed ground and the pixel values of the real-time road environment image captured by the quadruped robot, multiple images of the unobstructed ground environment can be captured using cameras of the same type, number, and height as the cameras installed on the quadruped robot. This allows the pixel value range for the unobstructed ground to be determined. Furthermore, the pixel difference between the maximum and minimum pixels within the pixel value range is obtained, and this pixel difference is set as the abnormality threshold.

[0033] After extracting the real-time road environment image captured by the quadruped robot, the pixel value of each pixel in the real-time road environment image is extracted. The difference between the pixel value of each pixel in the real-time road environment image and the pixel value of each corresponding pixel in the previously acquired obstacle-free ground environment image at the same location is obtained, and each difference is compared with a preset anomaly threshold. If the difference is greater than the anomaly threshold, each pixel exceeding the anomaly threshold is classified as an anomaly pixel, indicating that the environment corresponding to the pixel may not be an obstacle-free ground environment. If the difference is less than the anomaly threshold, it indicates that the pixel may belong to the ground environment and is temporarily ignored.

[0034] Furthermore, all abnormal pixels in each real-time road environment image are obtained, and the number of consecutive abnormal pixels in each group is calculated. The number of consecutive abnormal pixels in each group is compared with a pre-set abnormal continuity threshold. If the number of consecutive abnormal pixels exceeds the abnormal continuity threshold, it is determined that there is an obstacle in the quadruped robot's path. If the number of consecutive abnormal pixels does not exceed the abnormal continuity threshold, the group of consecutive abnormal pixels can be temporarily ignored and not processed.

[0035] The anomaly continuity threshold can be determined based on researchers' historical experience. In a specific example, researchers can use the same road environment image acquisition method as described above to obtain an image of a road environment containing small objects. These small objects can be objects such as stones and leaves that do not affect the movement of the quadruped robot. After obtaining the road environment image containing small objects, the pixel values of each pixel in the image are extracted, and the difference between the pixel values of each pixel in the environment image of the unobstructed ground is obtained. The number of consecutive anomaly pixels that can represent small objects is then determined, and an appropriate anomaly continuity threshold is selected.

[0036] The advantage of this setting is that by adopting the same image acquisition method as the quadruped robot to obtain the road environment image, the obstacle-free ground and the road environment with small objects are obtained, and then the abnormal threshold and abnormal continuous threshold are obtained, which can make a more accurate judgment on obstacles.

[0037] In order to ensure that the real-time road environment information obtained is relatively accurate, multiple cameras can generally be set on the quadruped robot. The camera setting position is not limited here, but it is necessary to ensure that the cameras set on the quadruped robot can obtain image contour information of the target obstacle under multiple perspectives.

[0038] After obtaining the image contour information of the target obstacle, the three-dimensional shape of the target obstacle can be reconstructed based on the image contour information and the coordinate mapping relationship under different viewing angles. The length information of the target obstacle in the direction of travel of the quadruped robot and the height information of the target obstacle can be directly obtained through the three-dimensional shape as the size information of the target obstacle.

[0039] The advantage of this setting is that compared with using sensors to obtain obstacle size information, using a camera can obtain more accurate length information of the target obstacle. This prevents the quadruped robot from judging that it can cross the target obstacle only by the obstacle height, and then causing movement safety problems because the length of the target obstacle exceeds the stride length of the quadruped robot.

[0040] S120. When it is determined based on the size information that the quadruped robot is capable of crossing the target obstacle, determine a position range of a starting point of the quadruped robot when crossing the obstacle.

[0041] Different strides of the quadruped robot correspond to different span heights. The larger the stride, the smaller the span height. After obtaining the size information of the target obstacle, multiple strides greater than the length of the target obstacle can be selected based on the length of the target obstacle. Furthermore, based on the span heights obtained under the multiple strides, it can be determined whether the length and height of the target obstacle are simultaneously less than at least one stride and the span height under the stride. If the above conditions are met, it is determined that the quadruped robot has a stride that can span the target obstacle, that is, the quadruped robot can span the target obstacle.

[0042] Furthermore, if the quadruped robot can cross the target obstacle, a more appropriate stride length can be selected from all strides that can cross the target obstacle according to the actual movement of the quadruped robot as the target stride length for the quadruped robot to cross the target obstacle.

[0043] It's understandable that if the quadruped robot's stride length is the same as the target obstacle's length, it means that after detecting the target obstacle, the robot must travel to the edge of the target obstacle on its current path, take steps at the target obstacle's edge, and then cross the target obstacle. However, considering the complexity of the quadruped robot's motion planning and the stability of crossing the target obstacle, a stride length that is slightly different from the current stride length is generally selected as the target stride length.

[0044] The reason for not directly selecting the maximum stride that can cross the target obstacle as the target stride is that: under normal circumstances, the quadruped robot will use a stride with a relatively moderate stride length to move during movement. If the maximum stride that can cross the target obstacle is directly selected as the target stride, when the maximum stride differs too much from the current movement stride of the quadruped robot, the movement stability of the quadruped robot may be reduced. However, there is no restriction on the selection method of the target stride here.

[0045] After determining the target stride length for the quadruped robot to cross the target obstacle, the position range of the starting point of the quadruped robot when crossing the target obstacle can be determined according to the difference between the length of the target obstacle and the target stride length.

[0046] It can be understood that the starting point position range is the maximum range within which a quadruped robot can cross the target obstacle. The quadruped robot can use the target stride to cross the target obstacle at any point within the starting point position range. If the quadruped robot does not take the target stride within the starting point range, the quadruped robot cannot cross the target obstacle.

[0047] The advantage of this setting is that by analyzing the stride of the quadruped robot and the corresponding crossing height, the target stride is selected, and then the starting point position range for crossing the target obstacle is determined, so that the quadruped robot can still maintain its original motion stability when crossing the target obstacle.

[0048] S130 , planning at least one travel stride of the quadruped robot on the travel route according to the foothold position range, and controlling the quadruped robot to cross the target obstacle according to the travel stride.

[0049] After obtaining the foot point position range corresponding to the target stride, the stride before entering the foot point position range can be planned to ensure that the quadruped robot can cross the target obstacle from within the foot point position range.

[0050] In order to minimize the complexity of quadruped robot control, the first stride of the quadruped robot can be calculated to determine whether the quadruped robot can pass through the starting point position range using the first stride. If the quadruped robot can pass through the starting point position range using the first stride, the quadruped robot can maintain the first stride and continue to move until it passes through the starting point position range and then change to the target stride to cross the target obstacle. If the quadruped robot cannot pass through the starting point position range using the first stride, a second stride with a smaller stride size than the first stride and that can pass through the starting point position range can be selected through reasonable calculation as the quadruped robot's current stride until it passes through the starting point position range and then change to the target stride to cross the target obstacle.

[0051] The technical solution of the embodiment of the present invention can obtain more accurate size information of the target obstacle by detecting obstacles in real time on the travel route of the quadruped robot and obtaining the size information of the obstacles, determining the target stride and the starting point position range based on the obstacle size information, and planning the stride on the travel route based on the starting point position range, so as to reasonably plan the target stride of the quadruped robot for crossing the target obstacle and the travel stride before crossing the target obstacle, so that the quadruped robot can stably and safely cross the target obstacle that can be crossed.

[0052] Example 2

[0053] Figure 2 This is a flow chart of a path planning method for a quadruped robot provided in the second embodiment of the present invention. This embodiment further specifies the path planning method for a quadruped robot based on the above embodiment. Figure 2 As shown, the method includes:

[0054] S210. Acquire real-time road environment images along the route of the quadruped robot through multiple cameras provided on the quadruped robot.

[0055] S220: Extract the pixel value of each pixel point in the real-time road environment image, and compare the pixel value of each pixel point in the road environment image with the pre-input pixel value of the obstacle-free ground on the same travel route.

[0056] S230: Obtain pixel points whose difference between the pixel value of the pixel point in the real-time road environment image and the pixel value of the obstacle-free ground exceeds a preset abnormality threshold, and classify them as abnormal pixel points.

[0057] S240: Determine whether the number of continuously appearing abnormal pixels exceeds a preset abnormal continuity threshold. If so, execute S250; if not, execute S260.

[0058] S250, determining that there is an obstacle on the moving route of the quadruped robot, obtaining image contour information of the target obstacle under multiple viewing angles through multiple cameras provided on the quadruped robot, and executing S270.

[0059] S260: The quadruped robot continues to move forward along the current route.

[0060] S270 : Reconstruct the three-dimensional shape of the target obstacle according to the contour information of each image and the coordinate mapping relationship under different viewing angles.

[0061] S280 . Acquire, according to the three-dimensional shape, a height value of the target obstacle and a length value of the target obstacle in the moving direction of the quadruped robot as size information.

[0062] S290. Obtain the crossing height of the quadruped robot at different strides, and determine whether the quadruped robot can cross the target obstacle at the target stride based on the length information and height information of the target obstacle.

[0063] Optionally, obtaining a plurality of strides of the quadruped robot that are greater than the length of the target obstacle, and obtaining a crossing height corresponding to each stride;

[0064] Determine whether the length and height of the target obstacle are both less than at least one stride length and its corresponding span height;

[0065] If yes, it means that the quadruped robot has a stride that can cross the target obstacle. Among all the strides that can cross the target obstacle, the quadruped robot selects a stride that is smaller than the current stride as the target stride for crossing the target obstacle, and executes S2100.

[0066] If not, it means that the target robot cannot cross the target obstacle.

[0067] S2100: If the quadruped robot can cross the target obstacle within the target stride, determine the starting point position range of the quadruped robot when crossing the obstacle based on the difference between the length value and the target stride.

[0068] S2110. Calculate the positions of each waypoint when the quadruped robot moves with the first step of the current movement, and determine whether there is a waypoint within the range of the starting point position. If so, execute S2120; if not, execute S2130.

[0069] S2120: The quadruped robot continues to move with the first step until the quadruped robot is within the starting point position range, and switches to a target stride that can cross the target obstacle to cross the target obstacle.

[0070] S2130: Generate a second stride, and the quadruped robot switches to the second stride and continues to move until the quadruped robot is within the range of the starting point position, and then switches to a target stride capable of crossing the target obstacle to cross the target obstacle.

[0071] When the robot moves with the second stride, there are waypoints that can be within the range of the starting point position.

[0072] The technical solution of the embodiment of the present invention selects a target stride by analyzing the stride of the quadruped robot and the corresponding crossing height, and then determines the position range of the starting point for crossing the target obstacle. This enables the quadruped robot to maintain its original motion stability when crossing the target obstacle. At the same time, the stride of the quadruped robot before crossing the target obstacle is planned, which can ensure that the quadruped robot crosses the target obstacle stably and safely.

[0073] Furthermore, when a target obstacle is identified and the size information of the target obstacle is obtained, the following steps may be performed:

[0074] When it is determined based on the size information that the quadruped robot cannot cross the target obstacle, a detour route for bypassing the target obstacle is generated, and the quadruped robot is controlled to continue moving along the detour route.

[0075] Optionally, if any stride that the quadruped robot can provide is unable to cross the target obstacle, the quadruped robot can be made to go around the target obstacle from the left or right side of the target obstacle, so as to achieve the purpose of the quadruped robot continuing to move forward.

[0076] Furthermore, generating a detour route for bypassing the target obstacle may specifically include:

[0077] Acquiring spatial position information of the three-dimensional shape and the quadruped robot in a three-dimensional coordinate system, and constructing a minimum circumscribed sphere of the three-dimensional shape;

[0078] Obtaining the tangent distances between the quadruped robot and the minimum circumscribed sphere on the left and right sides of the quadruped robot's moving direction;

[0079] comparing the tangent distances, and selecting a detour side around the target obstacle based on the tangent distance comparison result;

[0080] A detour route for detouring the target obstacle is generated based on the selected detour side information.

[0081] Optionally, the forward direction of the quadruped robot is used as the X-axis of the three-dimensional coordinate system, the direction perpendicular to the X-axis is used as the Y-axis of the three-dimensional coordinate system, and the direction perpendicular to the ground is used as the Z-axis of the three-dimensional coordinate system; the center of the largest section of the obstacle on the XY plane is used as the origin of the three-dimensional coordinate system.

[0082] Alternatively, a three-dimensional coordinate system for the quadruped robot and the target obstacle can be constructed using the aforementioned method, and a minimum circumscribed sphere representing the target obstacle's three-dimensional shape can be constructed within the three-dimensional coordinate system. By comparing the tangent distances between the quadruped robot's current position and the left and right sides of the minimum circumscribed sphere of the three-dimensional shape, a shorter detour can be selected between the left and right detour options, thereby generating a detour route for the quadruped robot.

[0083] The advantage of this setting is that when the quadruped robot cannot cross the target obstacle, it can avoid the obstacle by detouring it. By constructing the minimum circumscribed sphere of a three-dimensional shape, it can accurately select the side with a shorter detour distance, thereby improving the operating efficiency of the quadruped robot.

[0084] Example 3

[0085] Figure 3 This is a schematic diagram of the structure of a path planning device for a quadruped robot provided in the third embodiment of the present invention. Figure 3 As shown, the device includes: a size information acquisition module 310, a foot starting point position range determination module 320 and a stride planning module 330.

[0086] The size information acquisition module 310 is used to identify obstacles on the moving route in real time during the moving process of the quadruped robot, and to obtain the size information of the target obstacle when the target obstacle is identified.

[0087] The foothold position range determination module 320 is configured to determine the foothold position range of the quadruped robot when crossing the obstacle when determining that the quadruped robot is capable of crossing the target obstacle based on the size information.

[0088] The stride planning module 330 is used to plan at least one stride of the quadruped robot on the travel route according to the position range of the starting point, and control the quadruped robot to cross the target obstacle according to the stride.

[0089] The technical solution of the embodiment of the present invention can obtain more accurate size information of the target obstacle by detecting obstacles in real time on the travel route of the quadruped robot and obtaining the size information of the obstacles, determining the target stride and the starting point position range based on the obstacle size information, and planning the stride on the travel route based on the starting point position range, so as to reasonably plan the target stride of the quadruped robot for crossing the target obstacle and the travel stride before crossing the target obstacle, so that the quadruped robot can stably and safely cross the target obstacle that can be crossed.

[0090] Based on the above embodiments, the size information acquisition module 310 may include: an obstacle recognition unit and an obstacle size information acquisition unit.

[0091] Based on the above embodiments, the obstacle recognition unit can be specifically used to:

[0092] Using multiple cameras installed on the quadruped robot, real-time images of the road environment along the quadruped robot's route are obtained;

[0093] Extracting a pixel value of each pixel point in the real-time road environment image, and comparing the pixel value of each pixel point in the road environment image with a pre-input pixel value of an obstacle-free ground on the same travel route;

[0094] If the difference between the pixel value of a pixel point in the real-time road environment image and the pixel value of the obstacle-free ground exceeds a preset abnormality threshold, the pixel point in the real-time road environment is classified as an abnormal pixel point;

[0095] If the number of consecutive abnormal pixel points exceeds a preset abnormal continuity threshold, it is determined that there is an obstacle on the quadruped robot's route.

[0096] Based on the above embodiments, the obstacle size information acquisition unit may be specifically configured to:

[0097] Acquiring image contour information of the target obstacle at multiple viewing angles through multiple cameras provided on the quadruped robot;

[0098] Reconstruct the three-dimensional shape of the target obstacle based on the contour information of each image and the coordinate mapping relationship under different viewing angles;

[0099] According to the three-dimensional shape, a height value of the target obstacle and a length value of the target obstacle in the moving direction of the quadruped robot are acquired as size information.

[0100] Based on the above embodiments, the foot point position range determination module 320 can be specifically used to:

[0101] Get the stride height of the quadruped robot at different strides;

[0102] If it is determined that the length value is less than or equal to the target stride, and the height value is less than or equal to the crossing height under the target stride, it is determined that the quadruped robot can cross the target obstacle under the target stride;

[0103] The position range of the starting point of the quadruped robot when crossing the obstacle is determined according to the difference between the length value and the target stride.

[0104] Based on the above embodiments, the stride planning module 330 can be specifically used to:

[0105] Calculating the positions of each waypoint when the quadruped robot moves with the first step of the current movement, and determining whether there is a waypoint within the range of the starting point position;

[0106] If the waypoint of the first stride is within the range of the starting point, the quadruped robot continues to move with the first stride until the quadruped robot is within the range of the starting point, and then switches to the target stride that can cross the target obstacle;

[0107] If the waypoint of the first stride cannot be located within the starting footpoint position, a second stride is generated;

[0108] When the robot moves with the second stride, there is a waypoint that can be within the range of the starting point position;

[0109] The quadruped robot switches to the second stride and continues to move until the quadruped robot is within the range of the starting point position and switches to the target stride that can cross the target obstacle.

[0110] Based on the above embodiments, the system may further include: a quadruped robot circumvention module, which is configured to obtain the size information of the target obstacle upon identifying the target obstacle:

[0111] When it is determined based on the size information that the quadruped robot cannot cross the target obstacle, a detour route for bypassing the target obstacle is generated, and the quadruped robot is controlled to continue moving along the detour route.

[0112] Based on the above embodiments, the quadruped robot detour module may further include a detour route generating unit, which may be specifically used to:

[0113] Acquiring spatial position information of the three-dimensional shape and the quadruped robot in a three-dimensional coordinate system, and constructing a minimum circumscribed sphere of the three-dimensional shape;

[0114] Obtaining the tangent distances between the quadruped robot and the minimum circumscribed sphere on the left and right sides of the quadruped robot's moving direction;

[0115] comparing the tangent distances, and selecting a detour side around the target obstacle based on the tangent distance comparison result;

[0116] A detour route for detouring the target obstacle is generated based on the selected detour side information.

[0117] The path planning device for a quadruped robot provided in an embodiment of the present invention can execute the path planning method for a quadruped robot provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0118] Example 4

[0119] Figure 4 A schematic diagram of the structure of an electronic device 40 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, 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 claimed herein.

[0120] like Figure 4 As shown, the electronic device 40 includes at least one processor 41 and a memory, such as a read-only memory (ROM) 42, a random access memory (RAM) 43, etc., which is communicatively connected to the at least one processor 41. The memory stores a computer program that can be executed by the at least one processor, and the processor 41 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 42 or the computer program loaded from the storage unit 48 into the random access memory (RAM) 43. Various programs and data required for the operation of the electronic device 40 can also be stored in the RAM 43. The processor 41, ROM 42, and RAM 43 are connected to each other via a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.

[0121] Multiple components in the electronic device 40 are connected to the I / O interface 45, including an input unit 46, such as a keyboard, a mouse, etc.; an output unit 47, such as various types of displays, speakers, etc.; a storage unit 48, such as a magnetic disk, an optical disk, etc.; and a communication unit 49, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 49 allows the electronic device 40 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0122] The processor 41 may be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors for running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 41 executes the various methods and processes described above, such as the path planning method for a quadruped robot as described in an embodiment of the present invention. That is:

[0123] During the movement of the quadruped robot, obstacles are identified in real time along the route, and when a target obstacle is identified, the size information of the target obstacle is obtained;

[0124] When it is determined based on the size information that the quadruped robot is capable of crossing the target obstacle, a position range of a starting point of the quadruped robot when crossing the obstacle is determined;

[0125] According to the starting point position range, at least one travel stride of the quadruped robot on the travel route is planned, and the quadruped robot is controlled to cross the target obstacle according to the travel stride.

[0126] In some embodiments, the path planning method for a quadruped robot can be implemented as a computer program that is tangibly contained in a computer-readable storage medium, such as a storage unit 48. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 40 via the ROM 42 and / or the communication unit 49. When the computer program is loaded into the RAM 43 and executed by the processor 41, one or more steps of the path planning method for a quadruped robot described above can be performed. Alternatively, in other embodiments, the processor 41 can be configured to execute the path planning method for a quadruped robot by any other suitable means (e.g., by means of firmware).

[0127] Various embodiments of the systems and techniques described 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), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes 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.

[0128] 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, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0129] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0130] To provide interaction with a user, the systems and techniques described herein can 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 pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0131] The systems and techniques described herein can be implemented in a computing system that includes back-end 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 front-end components (e.g., a user computer with a graphical user interface or 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 back-end components, middleware components, or front-end components. The components of the system can 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.

[0132] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0133] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0134] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A path planning method for a quadruped robot, characterized in that: include: During the movement of the quadruped robot, obstacles are identified in real time along the route, and when a target obstacle is identified, the size information of the target obstacle is obtained; Wherein, the acquiring the size information of the target obstacle includes: acquiring the size information of the target obstacle according to the three-dimensional shape of the target obstacle; When determining that the quadruped robot is capable of crossing the target obstacle based on the size information, determining a starting point position range of the quadruped robot when crossing the obstacle; wherein the starting point position range is a maximum range within which the quadruped robot can achieve crossing the target obstacle; Planning at least one travel stride of the quadruped robot on a travel route according to the range of the starting point positions, and controlling the quadruped robot to cross the target obstacle according to the travel stride; When it is determined based on the size information that the quadruped robot cannot cross the target obstacle, a detour route for bypassing the target obstacle is generated, and the quadruped robot is controlled to continue moving along the detour route; The method for generating a detour route for bypassing a target obstacle includes: obtaining the three-dimensional shape of the target obstacle and the spatial position information of the quadruped robot in a three-dimensional coordinate system, and constructing a minimum circumscribed sphere of the three-dimensional shape; obtaining tangent distances between the quadruped robot and the minimum circumscribed sphere on the left and right sides of the quadruped robot's travel direction; comparing the tangent distances, and selecting a detour side for bypassing the target obstacle based on the tangent distance comparison result; and generating a detour route for bypassing the target obstacle based on the selected detour side information.

2. The method according to claim 1, characterized in that Obstacle identification on the planned route in real time, including: Using multiple cameras installed on the quadruped robot, real-time images of the road environment along the quadruped robot's route are obtained; Extracting a pixel value of each pixel point in the real-time road environment image, and comparing the pixel value of each pixel point in the road environment image with a pre-input pixel value of an obstacle-free ground on the same travel route; If the difference between the pixel value of a pixel point in the real-time road environment image and the pixel value of the obstacle-free ground exceeds a preset abnormality threshold, the pixel point in the real-time road environment is classified as an abnormal pixel point; If the number of consecutive abnormal pixel points exceeds a preset abnormal continuity threshold, it is determined that there is an obstacle on the quadruped robot's route.

3. The method according to claim 1, characterized in that When a target obstacle is identified, obtain the size information of the target obstacle, including: Acquiring image contour information of the target obstacle at multiple viewing angles through multiple cameras provided on the quadruped robot; Reconstruct the three-dimensional shape of the target obstacle based on the contour information of each image and the coordinate mapping relationship under different viewing angles; According to the three-dimensional shape, a height value of the target obstacle and a length value of the target obstacle in the moving direction of the quadruped robot are acquired as size information.

4. The method according to claim 3, characterized in that When determining that the quadruped robot is capable of crossing a target obstacle based on size information, the starting point position range of the quadruped robot when crossing the obstacle is determined, including: Get the stride height of the quadruped robot at different strides; If it is determined that the length value is less than or equal to the target stride, and the height value is less than or equal to the crossing height under the target stride, it is determined that the quadruped robot can cross the target obstacle under the target stride; The position range of the starting point of the quadruped robot when crossing the obstacle is determined according to the difference between the length value and the target stride.

5. The method according to claim 4, characterized in that Planning at least one travel stride of the quadruped robot on a travel route according to the foothold position range includes: Calculating the positions of each waypoint when the quadruped robot moves with the first step of the current movement, and determining whether there is a waypoint within the range of the starting point position; If the waypoint of the first stride is within the range of the starting point, the quadruped robot continues to move with the first stride until the quadruped robot is within the range of the starting point, and then switches to the target stride that can cross the target obstacle; If the waypoint of the first stride cannot be located within the starting footpoint position, a second stride is generated; When the robot moves with the second stride, there is a waypoint that can be within the range of the starting point position; The quadruped robot switches to the second stride and continues to move until the quadruped robot is within the range of the starting point position and switches to the target stride that can cross the target obstacle.

6. A path planning device for a quadruped robot, characterized in that: include: The size information acquisition module is used to identify obstacles on the moving route of the quadruped robot in real time during its movement, and obtain the size information of the target obstacle when it is identified; Wherein, the acquiring the size information of the target obstacle includes: acquiring the size information of the target obstacle according to the three-dimensional shape of the target obstacle; A foothold position range determination module is used to determine the foothold position range of the quadruped robot when crossing the obstacle when it is determined based on the size information that the quadruped robot can cross the target obstacle; wherein the foothold position range is the maximum range within which the quadruped robot can cross the target obstacle; a stride planning module, configured to plan at least one stride of the quadruped robot on a travel route according to the range of the foothold positions, and control the quadruped robot to cross a target obstacle according to the stride; A quadruped robot detour module is used to generate a detour route for detour the target obstacle when it is determined based on the size information that the quadruped robot cannot cross the target obstacle, and control the quadruped robot to continue moving along the detour route; The quadruped robot bypass module includes: A detour route generating unit is configured to obtain the three-dimensional shape of the target obstacle and the spatial position information of the quadruped robot in a three-dimensional coordinate system, and construct a minimum circumscribed sphere of the three-dimensional shape; obtain the tangent distances between the quadruped robot and the minimum circumscribed sphere on the left and right sides of the direction of travel of the quadruped robot; compare the tangent distances, and select a detour side for detour around the target obstacle based on the comparison result of the tangent distances; and generate a detour route for detour around the target obstacle based on the selected detour side information.

7. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can implement the path planning method for a quadruped robot according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the path planning method for a quadruped robot according to any one of claims 1 to 5 when executed.

Images