Robot navigation method and system, storage medium and electronic equipment

Abstract

The invention relates to the technical field of artificial intelligence, and discloses a robot navigation method and system, a storage medium and electronic equipment. The robot navigation method provided by the invention comprises the following steps: acquiring task assignment information acquired by terminal equipment; the task assignment information is input into a cloud server, so that the cloud server determines position information of a destination where the robot executes the task and semantic description information of the destination based on the task assignment information; and inputting the position information of the destination and the semantic description information of the destination into the robot, so that the robot navigates to the destination to execute the task according to the position information of the destination and the semantic description information of the destination. According to the invention, the robot can accurately navigate to the destination to execute the operation task, and the user can assign the robot to operate at the far end, so that the user experience can be improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a robot navigation method, system, storage medium and electronic equipment. Background Art

[0002] With the rapid development of industrial automation and intelligent technologies, robotics has been widely used in many fields, becoming a key technology for promoting industrial upgrading, improving production efficiency, and improving working conditions. Currently, robotics are used in a variety of industries, including manufacturing, logistics, healthcare, and agriculture.

[0003] Robot navigation, a core technology for autonomous robot operation, provides the foundation for robots to perceive their environment, plan paths, and move safely. However, some robotic navigation technologies suffer from inaccurate navigation, which prevents robots from accurately completing tasks at their destinations. This impacts operational efficiency and user experience, and makes it difficult for users to remotely assign robot tasks, creating inconvenience. Summary of the Invention

[0004] In view of this, the present invention provides a robot navigation method, system, storage medium, and electronic device. The present invention enables a robot to accurately navigate to a destination to perform a task, and allows users to remotely assign robot tasks, thereby improving user experience.

[0005] In a first aspect, the present invention provides a robot navigation method for a robot navigation system, wherein the robot navigation system includes a terminal device, a cloud server, and a robot. The robot navigation method includes: Obtain task assignment information through terminal devices; Inputting the task assignment information into the cloud server, so that the cloud server determines the location information of the destination to be reached by the robot when performing the task and the semantic description information of the destination based on the task assignment information; The location information of the destination and the semantic description information of the destination are input into the robot, so that the robot navigates to the destination to perform the task according to the location information of the destination and the semantic description information of the destination.

[0006] In one possible implementation of the first aspect, the task assignment information includes task assignment image information, and the cloud server determines the location information of the destination to be reached by the robot when performing the task and the semantic description information of the destination based on the task assignment information in the following manner: The cloud server extracts semantic features from the task assignment image information to obtain the image semantic feature information of the target object in the task assignment image; The cloud server matches the image semantic feature information of the target object with the set 3D semantic map information to obtain the category information of the target object, the position information of the target object in 3D space, and the size information; The cloud server determines the location information and semantic description information of the destination based on the category information of the target object, the location information and size information of the target object in three-dimensional space.

[0007] In one possible implementation of the first aspect, the task assignment information includes task assignment voice information, and the cloud server determines the location information of the destination to be reached by the robot when performing the task and the semantic description information of the destination based on the task assignment information in the following manner: The cloud server converts the task assignment voice information into text information; The cloud server extracts a first text feature from the text information; The cloud server encodes the first text feature to obtain a first text feature vector; The cloud server matches the first text feature vector with the set three-dimensional semantic map information to obtain category information of the target object, position information and size information of the target object in the three-dimensional space; The cloud server determines the location information and semantic description information of the destination based on the category information of the target object, the location information and size information of the target object in three-dimensional space.

[0008] In one possible implementation of the first aspect, the task assignment information includes task assignment text information, and the cloud server determines the location information of the destination to be reached by the robot when performing the task and the semantic description information of the destination based on the task assignment information in the following manner: The cloud server extracts a second text feature from the task assignment text information; The cloud server encodes the second text feature to obtain a second text feature vector; The cloud server matches the second text feature vector with the set three-dimensional semantic map information to obtain the category information of the target object, the position information of the target object in the three-dimensional space, and the size information; The cloud server determines the location information and semantic description information of the destination based on the category information of the target object, the location information and size information of the target object in three-dimensional space.

[0009] In a possible implementation of the first aspect, the position information of the target object in the three-dimensional space includes: coordinate information of the target object in the three-dimensional space and a position association relationship between the target object and surrounding objects in the three-dimensional space. The cloud server determines the location information and semantic description of the destination based on the category information, location information, and size information of the target object in three-dimensional space in the following ways: The cloud server determines the location information of the destination based on the coordinate information and size information of the target object in three-dimensional space; The cloud server determines the destination semantic description information based on the category information of the target object and the positional relationship between the target object and surrounding objects in three-dimensional space.

[0010] In a possible implementation of the first aspect, the robot navigates to the destination and performs the task according to the location information and semantic description information of the destination in the following manner: The robot determines the navigation target location based on the location information of the destination; The robot determines the navigation path based on the initial position and the navigation target position; The robot navigates to the navigation target location according to the navigation path; The robot obtains environmental information around the navigation target location at the navigation target location; The robot compares the acquired environmental information around the navigation target location with the semantic description information of the destination. If the robot determines that the environmental information around the navigation target location is consistent with the semantic description information of the destination, the robot determines the navigation target location as the destination and performs the task at the destination; or The robot uploads the acquired environmental information around the navigation target location to the cloud server, which compares the environmental information around the navigation target location with the semantic description information of the destination and sends the comparison result to the robot. When the robot determines that the environmental information around the navigation target location is consistent with the semantic description information of the destination, it determines the navigation target location as the destination and performs the task at the destination.

[0011] In a possible implementation of the first aspect above, the set three-dimensional semantic map information is obtained by the cloud server based on an acquired set three-dimensional map, wherein the set three-dimensional map is created based on environmental information of the destination.

[0012] In a possible implementation of the first aspect, the cloud server obtains the set three-dimensional semantic map information according to the acquired set three-dimensional map in the following manner: The cloud server is pre-installed with a set multimodal large model; The cloud server performs semantic segmentation processing on the set three-dimensional map through the set multimodal large model to obtain the set three-dimensional semantic map information.

[0013] In a possible implementation of the first aspect above, a predetermined application is installed on the terminal device. After the terminal device obtains the task assignment information, the terminal device uploads the task assignment information to the cloud server through the predetermined application.

[0014] In a second aspect, the present invention provides another robot navigation method, applied to a cloud server, the method comprising: receiving task assignment information, wherein the task assignment information is obtained through a terminal device; Determine the location information of the destination to be reached by the robot when performing the task and the semantic description information of the destination based on the task assignment information; The location information of the destination and the semantic description information of the destination are sent to the robot, so that the robot navigates to the destination and performs the task according to the location information of the destination and the semantic description information of the destination.

[0015] In a third aspect, the present invention provides another robot navigation method, applied to a robot, comprising: Receiving location information of a destination to be reached for executing the task and semantic description information of the destination, wherein the location information of the destination and the semantic description information of the destination are determined by the cloud server based on the task assignment information received from the terminal device; Navigate to the destination and perform the task based on the location information of the destination and the semantic description information of the destination.

[0016] In a fourth aspect, the present invention provides a robot navigation system, comprising: a terminal device, a cloud server, and a robot. The terminal device is used to obtain task assignment information; The cloud server is used to determine the location information of the destination to be reached by the robot when performing the task and the semantic description information of the destination based on the task assignment information; The robot is used to navigate to the destination and perform tasks based on the location information of the destination and the semantic description information of the destination.

[0017] In a fifth aspect, the present invention provides a computer-readable storage medium having instructions stored thereon, which, when executed on an electronic device, enables the electronic device to execute the robot navigation method in the above-mentioned first aspect, second aspect, third aspect and any possible implementation of the first aspect.

[0018] In a sixth aspect, the present invention provides a computer program product, which includes instructions that, when executed by one or more processors, are used to implement a robot navigation method as described in the first aspect, the second aspect, the third aspect, and any possible implementation of the first aspect.

[0019] In a seventh aspect, the present invention provides an electronic device, comprising: memory for storing instructions, and One or more processors, when the instructions are executed by the one or more processors, the processors execute the robot navigation method in any possible implementation of the first aspect, the second aspect, the third aspect and the first aspect.

[0020] Compared with the prior art, the beneficial effect of the present invention is that: in the robot navigation method provided by the present invention, task assignment information is obtained through a terminal device, and then the task assignment information is input into a cloud server. The cloud server determines the location information of the destination to be reached by the robot to perform the task and the semantic description information of the destination based on the task assignment information. After the location information of the destination and the semantic description information of the destination are input into the robot, the robot navigates to the destination to perform the task according to the location information of the destination and the semantic description information of the destination.

[0021] In the technical solution of the present invention, the task assignment information is obtained by the terminal device and then input into the cloud server for processing. The robot navigates according to the location information of the destination and the semantic description information of the destination obtained by the cloud server.

[0022] During this process, the user does not have to face the robot directly. If the user and the robot are not in the same place, the user can use his or her mobile phone to obtain an image of the destination, or the user can input a voice or text into the mobile phone, and then upload it to the cloud server through the mobile phone's mini-program. The robot obtains the information processed by the cloud server to realize navigation and perform work tasks. The user can remotely assign the robot to perform work tasks, providing convenience to the user.

[0023] Since in the technical solution of the present invention, the processing of task assignment information is performed by the cloud server instead of the robot, it avoids occupying the robot's computing power, so that the robot can have more computing power for navigation and execution of work tasks, thereby improving the robot's navigation and work efficiency.

[0024] Since in the technical solution of the present invention, the robot navigates based on the location information of the destination and the semantic description information of the destination, the semantic description information of the destination can reflect the environmental information around the destination. The destination determined by the robot based on the location information of the destination and the semantic description information of the destination is more accurate, making the location where the robot performs the operation more accurate, thereby accurately performing the operation at the destination, thereby improving the robot's operating efficiency and further improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1According to some embodiments of the present invention, a robot navigation application scenario is shown; Figure 2 According to some embodiments of the present invention, a schematic flow chart of a robot navigation method is shown; Figure 3 According to some embodiments of the present invention, a Figure 1 Schematic diagram of the interaction process between multiple devices in the; Figure 4 According to some embodiments of the present invention, a schematic flow chart of another robot navigation method is shown; Figure 5 According to some embodiments of the present invention, a schematic flow chart of another robot navigation method is shown; Figure 6 According to some embodiments of the present invention, a structural block diagram of an electronic device is shown. DETAILED DESCRIPTION

[0026] Illustrative embodiments of the present invention include, but are not limited to, a robot navigation method, system, storage medium, and electronic device.

[0027] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0028] In order to better understand the technical solution of the present invention, the following will first be combined with Figure 1 The schematic diagram of the robot's operating scene is shown, which provides a detailed introduction to the application scenarios to which the technical solution of the present invention is applicable.

[0029] refer to Figure 1 ,exist Figure 1 In the illustrated embodiment, a robot navigation system 10 is provided. The robot navigation system 10 includes a terminal device 100 , a cloud server 200 , and a robot 300 .

[0030] The terminal device 100 is used to obtain task assignment information, which includes but is not limited to images, voice, text and other forms. For example, the terminal device 100 is installed with a set application, and the terminal device 100 obtains the environmental image around the destination, obtains a voice input by the user, or obtains a text input by the user, and then uploads the environmental image around the destination, a voice or a text to the cloud server 200 through the above application, so that the user can flexibly choose different ways to assign the robot 300 to perform tasks.

[0031] It should be understood that the aforementioned image of the environment surrounding the destination, a voice message, or a text message may represent information about the destination at which the user desires the robot 300 to perform an operation. The image of the environment surrounding the destination may be an image captured by the user via the terminal device 100, an image downloaded by the user via the terminal device 100, or an image pre-stored locally on the terminal device 100. The terminal device 100 may be an electronic device with a camera function, a voice pickup function, and a text input function, for example, including but not limited to a mobile phone and a tablet computer.

[0032] Since the task assignment information is obtained by the terminal device 100 rather than directly by the robot 300, the user does not need to face the robot 300 directly. If the user and the robot 300 are not in the same place, the user can use his or her mobile phone to obtain an image of the destination, or the user can input a voice or text into the mobile phone, and then upload it to the cloud server 200 through the mobile phone's mini-program. The robot 300 obtains the information processed by the cloud server 200 to realize navigation and perform work tasks, which allows the user to remotely assign the robot 300 to perform work tasks, providing convenience to the user.

[0033] Based on the task assignment information, cloud server 200 determines the location information and semantic description of the destination to be reached by robot 300 during the task. Because the task assignment information is processed by cloud server 200, rather than robot 300, cloud server 200 has higher computing power, which avoids occupying the computing power of robot 300. This allows robot 300 to use more computing power for navigation and task execution, thereby improving navigation and operational efficiency.

[0034] The robot 300 is configured to navigate to a destination and perform a task based on the location information and semantic description of the destination. Because the robot 300 navigates based on the location information and semantic description of the destination, which reflect the surrounding environment, the robot 300 can more accurately determine the destination based on the location information and semantic description of the destination. This allows the robot 300 to more accurately locate the task it is performing, thereby precisely performing the task at the destination. This improves the robot's operational efficiency and further enhances the user experience.

[0035] It should be understood that the above-mentioned terminal device 100, cloud server 200 and robot 300 can communicate with each other, and the communication methods between the terminal device 100, cloud server 200 and robot 300 include but are not limited to Bluetooth Low Energy (BLE) and Wireless Fidelity (Wi-Fi).

[0036] The following will be combined Figure 2 , a robot navigation method provided by the present invention is introduced in detail. Figure 2 Some embodiments of the present invention provide a robot navigation method for Figure 1 The robot navigation system 10 shown, with reference to Figure 2 The present invention provides a robot navigation method comprising the following steps: S11: Acquire task assignment information through the terminal device 100.

[0037] In some embodiments, the terminal device 100 is installed with a set application. After the terminal device 100 obtains the task assignment information, it uploads the task assignment information to the cloud server 200 through the set application.

[0038] Task assignment information can be in various forms, such as images, voice, and text. In some embodiments, when task assignment information is in image form, the image-based task assignment information is referred to as task assignment image information. For example, the terminal device 100 stores an image of an office printer, and the user uploads the image of the office printer through a pre-defined application installed on the terminal device 100.

[0039] In some embodiments, when the task assignment information is in voice format, the voice-based task assignment information is referred to as task assignment voice information. For example, a user inputs a voice message through a pre-set application installed on the terminal device 100, and the content of the voice message is: "Please ask the robot to go to the office printer and pick up the printed document."

[0040] In some embodiments, when the task assignment information is in text form, the text-based task assignment information is referred to as task assignment text information. For example, a user enters a text message through a preset application installed on the terminal device 100, and the content of the text message is: "Please ask the robot to go to the office printer and pick up the printed document."

[0041] Since the task assignment information is obtained by the terminal device 100, the user can use the terminal device 100 next to him to obtain the image of the destination, or the user can input a voice or text into the mobile phone, and then upload it to the cloud server 200 through the mobile phone's mini-program. The robot obtains the information processed by the cloud server 200 to realize navigation and perform work tasks, which allows the user to remotely assign the robot 300 to perform work tasks, and the user can remotely control the robot 300 to perform operations using a mobile phone.

[0042] S12: Inputting the task assignment information into the cloud server 200, so that the cloud server 200 determines the location information of the destination to be reached by the robot 300 when performing the task and the semantic description information of the destination based on the task assignment information.

[0043] In some embodiments, the task assignment information includes task assignment image information. The cloud server 200 determines the location information of the destination to be reached by the robot 300 when performing the task and the semantic description information of the destination based on the task assignment information in the following manner: The cloud server 200 performs semantic feature extraction on the task assignment image information, for example, through a trained large model to perform semantic feature extraction on the task assignment image information, and obtains the image semantic feature information of the target object in the task assignment image, and the image semantic feature information of the target object includes the segmentation mask, category, confidence and other information of the target object; the cloud server 200 matches the image semantic feature information of the target object with the set three-dimensional semantic map information to obtain the category information of the target object, the position information and size information of the target object in the three-dimensional space; the cloud server 200 determines the location information of the destination and the semantic description information of the destination based on the category information of the target object, the position information and size information of the target object in the three-dimensional space.

[0044] The target object in the task assignment image is the object at the destination location to which the user wants the robot 300 to navigate. For example, if the user wants the robot 300 to navigate to the printer in the office, the user uploads an image of the printer in the office through a preset application installed on the terminal device 100. In this case, the printer in the image is the target object in the image.

[0045] In some embodiments, the position information of the target object in the three-dimensional space includes: coordinate information of the target object in the three-dimensional space and a position association relationship between the target object and surrounding objects in the three-dimensional space.

[0046] In some embodiments, the cloud server 200 determines the location information of the destination and the destination semantic description information based on the category information of the target object, the position information and size information of the target object in the three-dimensional space in the following manner: the cloud server 200 determines the location information of the destination based on the coordinate information and size information of the target object in the three-dimensional space; the cloud server 200 determines the destination semantic description information based on the category information of the target object and the positional association relationship between the target object and surrounding objects in the three-dimensional space.

[0047] In the technical solution of the present invention, the cloud server 200 determines the location information of the destination based on the coordinate information and size information of the target object in three-dimensional space. By complementing spatial positioning with geometric features, the obtained location information of the destination can be made more accurate.

[0048] Among them, the location information of the destination is the location information of the destination in the real world. The cloud server 200 can convert the coordinate information of the target object in the three-dimensional space according to a pre-calibrated position conversion relationship, thereby obtaining the location information of the destination in the real world, wherein the pre-calibrated position conversion relationship is used to represent the coordinate conversion relationship between the coordinate system belonging to the above-mentioned three-dimensional space and the real-world coordinate system.

[0049] Since the above-mentioned destination semantic description information is determined based on the category information of the target object and the positional association relationship between the target object and surrounding objects in three-dimensional space, the environmental information around the destination can be accurately known through the semantic description information of the destination. The subsequent destination determined by the robot 300 in combination with the location information of the destination and the semantic description information of the destination is more accurate, making the position where the robot 300 performs the operation more accurate, thereby accurately realizing the operation at the destination, thereby improving the operation efficiency of the robot 300 and further improving the user experience.

[0050] In some embodiments, the above-mentioned set three-dimensional semantic map information is obtained by the cloud server 200 based on the acquired set three-dimensional map, wherein the set three-dimensional map is created based on the environmental information of the destination.

[0051] In some embodiments, the cloud server 200 obtains the set three-dimensional semantic map information based on the acquired set three-dimensional map in the following manner: the cloud server 200 is pre-installed with a set multimodal large model; the cloud server 200 performs semantic segmentation processing on the set three-dimensional map through the set multimodal large model to obtain the set three-dimensional semantic map information.

[0052] The set 3D map may be reconstructed by a third-party 3D map reconstruction device, for example, by using a structured light scanner or a handheld LiDAR device to collect environmental information at the destination area and then construct the set 3D map. Alternatively, the set 3D map may be constructed by using a robot to collect environmental information at the destination area.

[0053] In some embodiments, the task assignment information includes task assignment voice information.

[0054] In some embodiments, the cloud server 200 determines the location information of the destination to be reached by the robot 300 when performing the task and the semantic description information of the destination based on the task assignment information in the following manner: the cloud server 200 converts the task assignment voice information into text information; the cloud server 200 extracts a first text feature from the text information; the cloud server 200 encodes the first text feature to obtain a first text feature vector; the cloud server 200 matches the first text feature vector with the set three-dimensional semantic map information to obtain the category information of the target object, the position information and size information of the target object in the three-dimensional space; the cloud server 200 determines the location information and the semantic description information of the destination based on the category information of the target object, the position information and size information of the target object in the three-dimensional space.

[0055] In some embodiments, the task assignment information includes task assignment text information.

[0056] In some embodiments, the cloud server 200 determines the location information of the destination to be reached by the robot 300 when performing the task and the semantic description information of the destination based on the task assignment information in the following manner: the cloud server 200 extracts a second text feature from the task assignment text information; the cloud server 200 encodes the second text feature to obtain a second text feature vector; the cloud server 200 matches the three-dimensional semantic map information set by the second text feature vector to obtain the category information of the target object, the location information and the size information of the target object in the three-dimensional space; the cloud server 200 determines the location information and the semantic description information of the destination based on the category information of the target object, the location information and the size information of the target object in the three-dimensional space.

[0057] From the above description, it can be seen that in the robot navigation method provided by the present invention, the processing of task assignment information is performed by the cloud server 200 instead of the robot 300, and there is no need to occupy the computing power of the robot 300, so that the robot 300 can have more computing power for navigation and execution of work tasks, thereby improving the navigation and operation efficiency of the robot 300.

[0058] S13: Inputting the location information of the destination and the semantic description information of the destination into the robot 300, so that the robot 300 navigates to the destination to perform the task according to the location information of the destination and the semantic description information of the destination.

[0059] In some embodiments, the robot 300 navigates to a destination to perform a task based on the location information of the destination and the semantic description information of the destination in the following manner: The robot 300 determines a navigation target location based on the location information of the destination; the robot 300 determines a navigation path based on the initial location and the navigation target location; the robot 300 navigates to the navigation target location according to the navigation path; the robot 300 obtains environmental information surrounding the navigation target location at the navigation target location; the robot 300 compares the obtained environmental information surrounding the navigation target location with the semantic description information of the destination. If the robot 300 determines that the environmental information surrounding the navigation target location and the semantic description information of the destination are consistent, the robot 300 determines that the navigation target location is the destination and performs the task at the destination. Alternatively, the robot 300 uploads the obtained environmental information surrounding the navigation target location to the cloud server 200, which compares the environmental information surrounding the navigation target location with the semantic description information of the destination and sends the comparison result to the robot 300. If the robot 300 determines that the environmental information surrounding the navigation target location and the semantic description information of the destination are consistent, the robot 300 determines that the navigation target location is the destination and performs the task at the destination.

[0060] The initial position mentioned above may be the position of the robot 300 before this navigation.

[0061] After navigating to the target location, the robot 300 can compare the environmental information surrounding the navigation target location with the semantic description information of the destination locally, or the robot 300 can upload the acquired environmental information surrounding the navigation target location to the cloud server 200, which then compares the environmental information surrounding the navigation target location with the semantic description information of the destination. The robot 300 will only determine the navigation target location as the destination if the environmental information surrounding the navigation target location and the semantic description information of the destination are consistent.

[0062] The present invention combines the location information of the destination and the semantic description information of the destination to determine a destination more accurately, so that the location where the robot 300 performs the operation is more accurate, thereby accurately realizing the operation at the destination, thereby improving the operating efficiency of the robot 300 and further improving the user experience.

[0063] It can be understood that the execution order of the above steps S11 to S13 is only an illustration. In other embodiments, other execution orders may be adopted, and some steps may be split or combined, which is not limited here.

[0064] In order to better understand the technical solution of the present invention, Figure 3 The interactive flow chart shown is Figure 1 The interaction process of the terminal device 100, the cloud server 200 and the robot 300 in the robot navigation system 10 is described in detail. Figure 3 , an embodiment of the present invention provides an interaction flow chart of a terminal device 100, a cloud server 200, and a robot 300, including the following steps: S20: The terminal device 100 and the robot 300 establish communication connections with the cloud server 200 respectively.

[0065] It should be understood that since the terminal device 100 and the robot 300 have established communication connections with the cloud server 200 respectively, the terminal device 100 and the robot 300 can interact with the cloud server 200.

[0066] S21: The terminal device 100 obtains task assignment information.

[0067] Regarding how the terminal device 100 specifically obtains the task assignment information and the meaning and several forms of the task assignment information, Figure 1 and as well as Figure 2 The text portion of step S11 has been described in detail and will not be repeated here.

[0068] S22: The terminal device 100 uploads the task assignment information to the cloud server 200.

[0069] For example, the terminal device 100 uploads the task assignment information to the cloud server 200 for processing through an installed and set application.

[0070] S23: The cloud server 200 determines the location information of the destination to be reached by the robot 300 when performing the task and the semantic description information of the destination based on the task assignment information.

[0071] Since the processing of task assignment information is performed by the cloud server 200 rather than the robot 300, the robot 300 can have more computing power for navigation and execution of work tasks, thereby improving the navigation and work efficiency of the robot 300.

[0072] Step S23 and the above Figure 2Similar to step S12 in, regarding how the cloud server 200 determines the location information of the destination to be reached by the robot 300 to perform the task and the semantic description information of the destination based on the task assignment information, please refer to the above description of the text part in S12, which will not be repeated here.

[0073] S24: The cloud server 200 sends the location information of the destination and the semantic description information of the destination to the robot 300.

[0074] S25: The robot 300 navigates to the destination to perform the task according to the location information of the destination and the semantic description information of the destination.

[0075] Since the semantic description information of the destination can reflect the environmental information around the destination, the destination determined by robot 300 in combination with the location information of the destination and the semantic description information of the destination is more accurate, making the location where robot 300 performs operations more accurate, thereby helping robot 300 to accurately perform operations at the destination, improving the operating efficiency of robot 300, and further improving user experience.

[0076] Step S25 and the above Figure 2 Similar to step S13 in , the robot 300 navigates to the destination to perform the task according to the location information of the destination and the semantic description information of the destination. For details, please refer to the text description of the above S13, which will not be repeated here.

[0077] It can be understood that the execution order of the above steps S21 to S25 is only an illustration. In other embodiments, other execution orders may be adopted, and some steps may be split or combined, which is not limited here.

[0078] Figure 4 According to some embodiments of the present invention, a flowchart of another robot navigation method is provided. Figure 4 The robot navigation method shown is applied to the cloud server 200, referring to Figure 4 Another robot navigation method provided by the present invention includes the following steps: S31 : Receive task assignment information, wherein the task assignment information is acquired through the terminal device 100 .

[0079] Specifically, the cloud server 200 receives the task assignment information sent by the terminal device 100. For details about the terminal device 100 obtaining the task assignment information, please refer to the above-mentioned Figure 2 The text description of step S11 in the illustrated embodiment will not be repeated here.

[0080] S32: Determine the location information of the destination to be reached by the robot 300 when performing the task and the semantic description information of the destination based on the task assignment information.

[0081] S33: Sending the location information of the destination and the semantic description information of the destination to the robot 300, so that the robot 300 navigates to the destination to perform the task according to the location information of the destination and the semantic description information of the destination.

[0082] Regarding the robot 300 navigating to the destination to perform the task based on the location information of the destination and the semantic description information of the destination, please refer to the above description of the text part in S13, which will not be repeated here.

[0083] Figure 5 According to some embodiments of the present invention, a flowchart of another robot navigation method is provided. Figure 5 The robot navigation method shown is applied to the robot 300, referring to Figure 5 Another robot navigation method provided by the present invention includes the following steps: S41: Receive the location information of the destination to be reached for executing the task and the semantic description information of the destination, wherein the location information of the destination and the semantic description information of the destination are determined by the cloud server 200 based on the task assignment information received from the terminal device 100.

[0084] S42: Navigate to the destination and perform the task according to the location information of the destination and the semantic description information of the destination.

[0085] Regarding how the cloud server 200 determines the location information of the destination to be reached by the robot 300 and the semantic description information of the destination based on the task assignment information, and how the robot 300 navigates to the destination to perform the task based on the location information of the destination and the semantic description information of the destination, please refer to the Figure 2 The description of the text part in the embodiment will not be repeated here.

[0086] An embodiment of the present invention further provides an electronic device 400, such as Figure 6 As shown, the electronic device 400 includes a memory 401 and one or more processors 402. The memory 401 is used to store instructions. When the instructions are executed by one or more processors, the processor 402 executes the robot navigation method in any of the above embodiments.

[0087] Figure 6 The electronic device 400 shown further includes a communication interface 403. The processor 402, the memory 401 and the communication interface 403 are connected via a communication bus and communicate with each other.

[0088] The processor 402 may be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the above-mentioned programs.

[0089] The communication interface 403 is used to communicate with other devices or communication networks, such as Ethernet, Radio Access Network (RAN), Wireless Local Area Networks (WLAN), etc.

[0090] The memory 401 can be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program codes in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory can be independent and connected to the processor via a bus. The memory can also be integrated with the processor.

[0091] An embodiment of the present invention further provides a computer-readable storage medium having instructions stored thereon. When the instructions are executed on an electronic device, the electronic device executes the robot navigation method in any one of the above embodiments.

[0092] An embodiment of the present invention further provides a computer program product, which includes instructions. When the instructions are executed by one or more processors, they are used to implement the robot navigation method in any one of the above embodiments.

[0093] The various embodiments of the mechanisms disclosed in the present invention can be implemented in hardware, software, firmware, or a combination of these implementation methods. The embodiments of the present invention can be implemented as a computer program or program code executed on a programmable system, the programmable system including at least one processor, a storage system (including volatile and non-volatile memory and / or storage elements), at least one input device, and at least one output device.

[0094] It should be noted that in the examples and description of this patent, relational terms such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "including a" does not exclude the presence of other identical elements in the process, method, article or device that includes the element.

[0095] While the present invention has been shown and described with reference to certain preferred embodiments thereof, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention.

Claims

1. A robot navigation method, characterized in that: For a robot navigation system, the robot navigation system includes a terminal device, a cloud server and a robot, and the method includes: Obtain task assignment information through terminal devices; Inputting the task assignment information into the cloud server, so that the cloud server determines the location information of the destination to be reached by the robot when performing the task and the semantic description information of the destination based on the task assignment information; Inputting the location information of the destination and the semantic description information of the destination into the robot, so that the robot navigates to the destination to perform a task according to the location information of the destination and the semantic description information of the destination, The robot navigates to the destination and performs the task according to the location information of the destination and the semantic description information of the destination in the following manner: The robot determines a navigation target position according to the position information of the destination; The robot determines a navigation path according to an initial position and the navigation target position; The robot navigates to the navigation target location according to the navigation path; The robot acquires environmental information around the navigation target location at the navigation target location; The robot compares the acquired environmental information around the navigation target position with the semantic description information of the destination, and if the robot determines that the environmental information around the navigation target position is consistent with the semantic description information of the destination, determines the navigation target position as the destination and performs the task at the destination; or The robot uploads the acquired environmental information around the navigation target position to the cloud server, which compares the environmental information around the navigation target position with the semantic description information of the destination and sends the comparison result to the robot. When the robot determines that the environmental information around the navigation target position is consistent with the semantic description information of the destination, the robot determines the navigation target position as the destination and performs the task at the destination.

2. The robot navigation method according to claim 1, characterized in that: The task assignment information includes task assignment image information. The cloud server determines the location information of the destination to be reached by the robot when performing the task and the semantic description information of the destination based on the task assignment information in the following manner: The cloud server extracts semantic features from the task assignment image information to obtain image semantic feature information of the target object in the task assignment image; The cloud server matches the image semantic feature information of the target object with the set three-dimensional semantic map information to obtain the category information of the target object, the position information and the size information of the target object in the three-dimensional space; The cloud server determines the location information of the destination and the destination semantic description information according to the category information of the target object, the location information and the size information of the target object in the three-dimensional space.

3. The robot navigation method according to claim 1, characterized in that: The task assignment information includes task assignment voice information, and the cloud server determines the location information of the destination to be reached by the robot when performing the task and the semantic description information of the destination based on the task assignment information in the following manner: The cloud server converts the task assignment voice information into text information; The cloud server extracts a first text feature from the text information; The cloud server encodes the first text feature to obtain a first text feature vector; The cloud server matches the first text feature vector with the set three-dimensional semantic map information to obtain category information of the target object, and position information and size information of the target object in the three-dimensional space; The cloud server determines the location information of the destination and the destination semantic description information according to the category information of the target object, the location information and the size information of the target object in the three-dimensional space.

4. The robot navigation method according to claim 1, characterized in that: The task assignment information includes task assignment text information, and the cloud server determines the location information of the destination to be reached by the robot when performing the task and the semantic description information of the destination based on the task assignment information in the following manner: The cloud server extracts a second text feature from the task assignment text information; The cloud server encodes the second text feature to obtain a second text feature vector; The cloud server matches the second text feature vector with the set three-dimensional semantic map information to obtain category information of the target object, and position information and size information of the target object in the three-dimensional space; The cloud server determines the location information of the destination and the destination semantic description information according to the category information of the target object, the location information and the size information of the target object in the three-dimensional space.

5. The robot navigation method according to any one of claims 2 to 4, characterized in that: The position information of the target object in the three-dimensional space includes: the coordinate information of the target object in the three-dimensional space and the position association relationship between the target object and surrounding objects in the three-dimensional space, The cloud server determines the location information of the destination and the destination semantic description information according to the category information of the target object, the location information and the size information of the target object in three-dimensional space in the following manner: The cloud server determines the location information of the destination based on the coordinate information of the target object in three-dimensional space and the size information; The cloud server determines the destination semantic description information according to the category information of the target object and the position association relationship between the target object and surrounding objects in three-dimensional space.

6. The robot navigation method according to claim 5, characterized in that: The set three-dimensional semantic map information is obtained by the cloud server according to the acquired set three-dimensional map, wherein the set three-dimensional map is created based on the environmental information of the destination.

7. The robot navigation method according to claim 6, characterized in that: The cloud server obtains the set three-dimensional semantic map information according to the obtained set three-dimensional map in the following manner: The cloud server is pre-installed with a set multimodal large model; The cloud server performs semantic segmentation processing on the set three-dimensional map through the set multimodal large model to obtain the set three-dimensional semantic map information.

8. The robot navigation method according to claim 1, characterized in that: The terminal device is installed with a set application program. After the terminal device obtains the task assignment information, the terminal device uploads the task assignment information to the cloud server through the set application program.

9. A robot navigation method, characterized in that: Applied to a cloud server, the method includes: receiving task assignment information, wherein the task assignment information is obtained through a terminal device; Determining, based on the task assignment information, location information of a destination to be reached by the robot when performing the task and semantic description information of the destination; The location information of the destination and the semantic description information of the destination are sent to the robot, so that the robot navigates to the destination to perform a task according to the location information of the destination and the semantic description information of the destination.

10. A robot navigation method, characterized in that: Applied to a robot, the method comprises: Receiving location information of a destination to be reached for executing the task and semantic description information of the destination, wherein the location information of the destination and the semantic description information of the destination are determined by the cloud server based on task assignment information received from the terminal device; Navigate to the destination and perform a task based on the location information of the destination and the semantic description information of the destination.

11. A robot navigation system, characterized in that: include: Terminal devices, cloud servers and robots, The terminal device is used to obtain task assignment information; The cloud server is used to determine the location information of the destination to be reached by the robot when performing the task and the semantic description information of the destination based on the task assignment information; The robot is used to navigate to the destination and perform a task according to the location information of the destination and the semantic description information of the destination.

12. A computer-readable storage medium, characterized in that The computer-readable storage medium stores instructions, which, when executed on an electronic device, enable the electronic device to execute the robot navigation method according to any one of claims 1 to 10.

13. A computer program product, characterized in that The computer program product comprises instructions for implementing the robot navigation method according to any one of claims 1 to 10 when the instructions are executed by one or more processors.

14. An electronic device, characterized in that: include: memory for storing instructions, and One or more processors, when the instructions are executed by the one or more processors, the processors perform the robot navigation method according to any one of claims 1 to 10.

Images