Robot control method, robot, robot control system, and storage medium

Abstract

The application discloses a robot control method, a robot, a robot control system and a storage medium, and relates to the technical field of robots. The robot control method comprises the following steps: performing path planning based on an environment map of an environment in which the robot is located, and obtaining a moving route of the robot; the environment map is constructed based on an environment image captured by a camera device on the environment in which the robot is located, and the camera device is installed on the environment in which the robot is located and is arranged separately from the robot; and in the process of moving along the moving route, the cleaning mode of the robot is controlled based on detection data of a ground detector. The above scheme can accurately plan the moving route of the robot and control the cleaning mode of the robot.

Description

Technical Field

[0001] This application relates to the field of robotics technology, and in particular to a robot control method, a robot, a robot control system, and a storage medium. Background Technology

[0002] With the rapid development of computer technology and artificial intelligence, various cleaning robots, such as robotic vacuum cleaners, have entered thousands of households.

[0003] However, due to the inherent complexity of real-world application scenarios, robots are prone to issues such as unreasonable route planning and inaccurate cleaning mode control during operation. For example, when passing over carpets, the robot may fail to switch to carpet mode, resulting in wetting or even damaging the carpet. Therefore, accurately planning the robot's movement route and controlling its cleaning mode have become urgent problems to be solved. Summary of the Invention

[0004] The main technical problem addressed by this application is to provide a robot control method, a robot, a robot control system, and a storage medium, which can accurately plan the robot's movement route and control its cleaning mode.

[0005] To address the aforementioned technical problems, the first aspect of this application provides a robot control method, comprising: performing path planning based on an environmental map of the robot's environment to obtain the robot's movement route; wherein the environmental map is constructed based on environmental images captured by a camera device of the robot's environment, and the camera device is installed in the robot's environment but separately from the robot; and controlling the robot's cleaning mode based on detection data from a ground detector during movement along the movement route.

[0006] To address the aforementioned technical problems, a second aspect of this application provides a robot, including a ground detector, a processor, and a memory, wherein the ground detector and the memory are respectively coupled to the processor; the processor is used to execute program instructions stored in the memory to implement the robot control method described in the first aspect.

[0007] To address the aforementioned technical problems, a third aspect of this application provides a robot control system, including a camera device and the robot described in the second aspect above.

[0008] To address the aforementioned technical problems, a fourth aspect of this application provides a computer-readable storage medium storing program instructions executable by a processor, the program instructions being used to implement the robot control method described in the first aspect.

[0009] In the above scheme, on the one hand, environmental images are obtained by installing cameras in the robot's environment, and then an environmental map is constructed for path planning to obtain the robot's movement route. The cameras are set up separately from the robot, which improves the accuracy of environmental map construction and thus enables accurate planning of movement routes. On the other hand, during the movement along the movement route, ground condition analysis is performed based on the detection data of ground detectors, and the robot's cleaning mode is accurately controlled according to the ground condition. Attached Figure Description

[0010] Figure 1 This is a schematic diagram of the framework of an embodiment of the robot of this application;

[0011] Figure 2 This is a schematic diagram showing the installation location and structure of the ground detector in the robot;

[0012] Figure 3 This is a schematic diagram of the framework of an embodiment of the robot control system of this application;

[0013] Figure 4 This is a schematic diagram of the camera device.

[0014] Figure 5 This is a flowchart illustrating an embodiment of the robot control method of this application;

[0015] Figure 6 This is a schematic diagram of a practical application scenario of the robot control method of this application;

[0016] Figure 7 This is a schematic diagram of the camera's shooting angle;

[0017] Figure 8 This is a schematic diagram illustrating the principle by which a camera device acquires depth information;

[0018] Figure 9 yes Figure 5 A flowchart illustrating an embodiment of step S11;

[0019] Figure 10 yes Figure 5 A flowchart illustrating another embodiment of step S11;

[0020] Figure 11 This is a flowchart illustrating another embodiment of the robot control method of this application;

[0021] Figure 12 This is a schematic diagram of the framework of an embodiment of a robot control device;

[0022] Figure 13 This is a schematic diagram of a framework of an embodiment of the computer-readable storage medium of this application. Detailed Implementation

[0023] The embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0024] In the following description, specific details such as particular system architectures, interfaces, and technologies are presented for illustrative purposes rather than for limiting purposes, in order to provide a thorough understanding of this application.

[0025] In this paper, the terms "system" and "network" are often used interchangeably. The term "and / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. Additionally, the character " / " generally indicates that the preceding and following related objects have an "or" relationship. Furthermore, "many" in this paper means two or more.

[0026] For clarity in illustrating embodiments of the robot control method of this application, please refer to [link / reference needed]. Figure 1 , Figure 1 This is a schematic diagram of a framework of one embodiment of the robot 10 of this application. The robot 10 can specifically be an intelligent machine capable of semi-autonomous or fully autonomous cleaning work, such as a sweeping robot, a mopping robot, or a disinfection robot. Specifically, the robot 10 includes a ground detector 103, a processor 101, and a memory 102. The ground detector 103 and the memory 102 are respectively coupled to the processor 101. The processor 101 is used to execute program instructions stored in the memory 102 to implement the steps of any embodiment of the robot movement control method.

[0027] Specifically, processor 101 can control itself and memory 102 to execute the steps in any embodiment of the robot movement control method. Processor 101 can also be referred to as a CPU (Central Processing Unit). Processor 101 may be an integrated circuit chip with signal processing capabilities. Processor 101 can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor can be a microprocessor or any conventional processor. Furthermore, processor 101 can be implemented by multiple integrated circuit chips.

[0028] Please see Figure 2 , Figure 2This is a schematic diagram of the installation location and structure of the ground detector 103 in the robot 10. Specifically, the ground detector 103 is located at the bottom of the robot 10. The ground detector 103 includes a first camera element 1031 and an illumination element 1032. The first camera element 1031 is used to capture ground images of the ground where the robot 10 is located, and the illumination element 1032 is used to illuminate the ground below the robot 10, which helps to improve the accuracy of the ground image information collected.

[0029] In specific implementation scenarios, you can refer to Figure 2 The number of first camera elements 1031 is set to 1, and the number of lighting elements 1032 is set to 4. Of course, in real-world scenarios, these can be set as needed, and there is no specific limitation on the number of both the first camera elements 1031 and the lighting elements 1032. Furthermore, the first camera element 1031 can be an infrared camera, and the lighting elements 1032 can be infrared lights or combinations of other camera and lighting devices; no specific limitations are imposed here.

[0030] In the above scheme, on the one hand, environmental images are obtained by installing cameras in the robot's environment, and then an environmental map is constructed for path planning to obtain the robot's movement route. The cameras are set up separately from the robot, which improves the accuracy of environmental map construction and thus enables accurate planning of movement routes. On the other hand, during the movement along the movement route, ground condition analysis is performed based on the detection data of ground detectors, and the robot's cleaning mode is accurately controlled according to the ground condition.

[0031] Please see Figure 3 , Figure 3 This is a schematic diagram of a framework of an embodiment of the robot control system 30 of this application. Specifically, the robot control system 30 includes a camera device 31 and a robot 10, wherein the robot 10 has the same meaning as the robot in the previous embodiment, and will not be described again here; the camera device 31 is installed in the environment where the robot 10 is located, and is set separately from the robot 10. For example, when the robot 10 is working in an indoor space such as a room or exhibition hall, the camera device 31 can be installed on the wall or roof of the indoor space; or, when the robot 10 is working in an outdoor space such as a street or park, the camera device 31 can be installed on a street lamp pole or the exterior wall of a building in the outdoor space. It should be noted that the installation position of the camera device 31 should preferably cover its working area as much as possible. Other cases can be deduced by analogy, and will not be listed one by one here.

[0032] Figure 4This is a schematic diagram of the camera device 31. Specifically, the camera device 31 includes a gimbal 311 and a second camera element 312 supported on the gimbal 311. The gimbal 311 is used to control the rotation of the second camera element 312, which is used to capture environmental images of the environment in which the robot 10 is located. The gimbal 311 can control the rotation of the second camera element 312 in the vertical or horizontal direction, thus maximizing the shooting angle of the second camera element 312 and achieving comprehensive imaging of the environment in which the robot 10 is located.

[0033] In a specific implementation scenario, the second camera element 312 can be a structured light depth camera, a binocular depth camera, a TOF (time of flight) depth camera, etc., without any specific restrictions.

[0034] In the above scheme, on the one hand, environmental images are obtained by installing cameras in the robot's environment, and then an environmental map is constructed for path planning to obtain the robot's movement route. The cameras are set up separately from the robot, which improves the accuracy of environmental map construction and thus enables accurate planning of movement routes. On the other hand, during the movement along the movement route, ground condition analysis is performed based on the detection data of ground detectors, and the robot's cleaning mode is accurately controlled according to the ground condition.

[0035] Please see Figure 5 , Figure 5 This is a flowchart illustrating an embodiment of the robot control method of this application. Specifically, the robot control method in this embodiment may include the following steps:

[0036] Step S11: Perform path planning based on the environmental map of the robot's location to obtain the robot's movement route.

[0037] In one implementation scenario, an environmental map can be constructed from images of the robot's environment captured by cameras. Please refer to [link / reference]. Figure 6 , Figure 6 This is a schematic diagram of a practical application scenario of the robot control method of this application. In a living and dining room environment, a camera is installed on the wall, and the robot works on the floor, constructing an environmental map based on the environmental images captured by the camera.

[0038] In one implementation scenario, the robot can receive an environmental map, which is constructed by a cloud server based on environmental images uploaded to the cloud server by camera devices. Alternatively, the robot can directly receive environmental images and construct an environmental map based on them.

[0039] In a specific implementation scenario, in order to reduce the workload of devices such as cameras, the cameras can upload the captured environmental images to a cloud server for image processing. The cloud server can then build an environmental map based on the environmental images and send the environmental map to the robot.

[0040] In another specific implementation scenario, to further improve the robot's rate of acquiring environmental maps while reducing the motion load on devices such as cameras, thereby increasing the robot's work efficiency, a hardware server can be built. This hardware server can communicate with both the camera and the robot. Based on this, the camera can send the captured environmental images to the hardware server, which is connected to both the camera and the robot, for image processing. The hardware server can then construct an environmental map based on the environmental images and send the map to the robot.

[0041] In another specific implementation scenario, when the robot has surplus computing power, the camera device can forward the captured environmental images to the robot. The robot's internal processor can then perform image processing based on the environmental images, thereby constructing an environmental map locally on the robot.

[0042] It should be noted that the implementation methods for image processing and environmental map construction include, but are not limited to, the three implementation methods described above.

[0043] In a specific implementation scenario, an environmental map can be built based on SLAM (Simultaneous Localization and Mapping) technology.

[0044] In another specific implementation scenario, an environmental map can be constructed based on topological mapping technology.

[0045] In another specific implementation scenario, an environmental map can also be built based on semantic mapping technology.

[0046] It should be noted that the methods for constructing environmental maps include, but are not limited to, the three map construction techniques mentioned above.

[0047] Please see Figure 7 , Figure 7 This is a schematic diagram of the camera's field of view. The camera's vertical field of view is 'a', and its horizontal field of view is 'b'. By combining the gimbal's rotation along both the vertical and horizontal directions, the camera's field of view is maximized. Therefore, the image information of the robot's environment captured by the camera can be as comprehensive and accurate as possible. Furthermore, the camera is a depth gimbal camera, so the environmental images it captures also include depth information. Thus, the environmental map also contains depth information for various locations within the robot's environment. Please refer to [link / reference]. Figure 8 , Figure 8 This is a schematic diagram illustrating the principle of a camera device acquiring depth information. It can use the rising or falling edge of the emitted and received signal pulses as a basis to obtain the transmission and reception time interval td of the pulse signal, and then calculate the depth data of the target plane based on the speed of light and the angle data of the camera device.

[0048] Please refer to the above. Figure 9 , Figure 9 yes Figure 5 A flowchart illustrating an embodiment of step S11 is provided above. Step S11 in the above embodiment may specifically include:

[0049] Step S111: Divide the region based on the depth information of each location in the environment map to obtain the region division result.

[0050] In a specific implementation scenario, the area is divided based on a comparison between the depth information of each location on the environmental map and the robot's mobility, resulting in the following area division results: passable area, prohibited area, and area to be determined.

[0051] For example, a robot's mobility can include its maximum climbing height and maximum clearance height. The maximum climbing height reflects the height of the highest planar protrusion the robot can climb, while the maximum clearance height reflects the depth of the highest planar indentation the robot can traverse. If the depth information of a location falls between the robot's maximum climbing height and maximum clearance height, the location is determined to be a traversable area; if the depth information exceeds these values, the location is determined to be a prohibited area; and if no depth information is available for the location, the location is determined to be an area to be determined. By comparing the location's depth information with the robot's mobility capabilities on the environmental map, traversable areas, prohibited areas, and areas to be determined are identified, facilitating accurate path planning based on these area divisions.

[0052] In another specific implementation scenario, regions are divided based on whether there are sudden changes in depth information at various locations in the environmental map, resulting in region division results. For example, a sudden change threshold can be set to a specific value such as 10 centimeters. If the depth difference between a location and its adjacent locations exceeds the sudden change threshold, the relevant location is divided into a danger zone, and other locations are divided into safe zones.

[0053] In another specific implementation scenario, regions are divided based on the rate of change of depth information at various locations in the environmental map, resulting in region division results. For example, a specific value such as a rate of change threshold of 20% can be set. Unknown areas where the rate of change of depth values ​​with adjacent locations is less than the rate of change threshold are designated as key cleaning areas, unknown areas where the rate of change of depth values ​​with adjacent locations is not less than the rate of change threshold are designated as areas that do not need cleaning, and other locations are designated as selective cleaning areas.

[0054] Step S112: Based on the region division results, the movement route is planned.

[0055] In a specific implementation scenario, as mentioned above, the area division results include passable areas, prohibited areas, and areas to be determined. When planning a movement route, it is advisable to prioritize planning the route along the passable areas. If the movement route cannot be determined solely by the passable areas, it is permissible to pass through some areas to be determined. However, it is strictly forbidden to plan the movement route to the prohibited areas.

[0056] In another specific implementation scenario, as mentioned earlier, the area division results include dangerous areas and safe areas. When planning the movement route, only the safe areas can be considered to avoid the movement route passing through the dangerous areas.

[0057] In another specific implementation scenario, as mentioned earlier, the area division results include key cleaning areas, areas that do not need cleaning, and areas to be cleaned. When planning the path, key cleaning areas are given priority, some areas to be cleaned are added appropriately, and areas that do not need cleaning are avoided.

[0058] In the above scheme, by analyzing the depth information of various locations in the robot's environment, the environment is divided into different areas, and then the movement route is planned according to the different areas. Therefore, the route planning can be more accurate, and at the same time, the possibility of the robot entering dangerous areas is minimized.

[0059] In another implementation scenario, the robot's environment contains several objects on the ground, and the environment map labels each object and its category. For example, the environment map may label passable objects such as tables, chairs, coffee tables, dining tables, and high sofas, as well as impassable obstacles such as blankets, walls, and refrigerators. Please refer to [further details needed]. Figure 10 , Figure 10 yes Figure 5 A flowchart illustrating another embodiment of step S11 is provided above. In the above embodiment, step S11 may specifically include:

[0060] Step S113: In response to the user's selection instruction on the environment map based on the object category, the area where the selected object is located is designated as a passable area.

[0061] In a specific implementation scenario, semantic recognition can be performed on the image information acquired by the camera device, and the recognition results can be classified. The object categories include passable objects and impassable obstacles. Furthermore, the environmental map labeled with each object and its category can be displayed on smart mobile terminals such as mobile phones and tablets. Users can select several objects and designate the area where the object is located as a passable area, or select several other objects and designate the area where they are located as a prohibited area.

[0062] Step S114: Based on the passable areas in the environment map, a movement route is planned.

[0063] For the accessible area selected by the user, the robot can be planned to go there once to perform cleaning work, and avoid prohibited areas on the route to the accessible area.

[0064] In the above solution, the environmental map is marked with each object and its category, which allows users to intuitively see the appearance of the robot's working area, effectively improving the human-computer interaction experience. At the same time, users can choose the accessible areas for cleaning, realizing selective cleaning of specific areas and further improving the user experience.

[0065] In another implementation scenario, in response to a user's selection instruction on an object on the environment map based on object category, the area where the selected object is located is designated as a passable area. Then, the passable area is verified based on the depth information of each location on the environment map. A movement route is planned according to the finally determined passable area. The relevant execution steps can be referred to in the aforementioned embodiments and will not be repeated here. The finally determined passable area satisfies both the user's selection and the division based on depth information. Areas satisfying only one condition can be considered as areas to be determined.

[0066] In another implementation scenario, regions are divided based on depth information at various locations on the environmental map, resulting in region division results. This, in response to user commands to select objects on the environmental map based on object categories, ultimately determines passable areas and plans movement routes. Similarly, the relevant execution steps can be referred to the aforementioned embodiments and will not be repeated here.

[0067] In the above scheme, on the one hand, the area division can be achieved by analyzing based on depth information, and on the other hand, the user can select objects on the environment map based on object categories, thereby determining the passable area. The two methods can corroborate each other in the area division, greatly improving the accuracy of area division and route planning.

[0068] Step S12: During the movement along the route, the cleaning mode of the robot is controlled based on the detection data of the ground detector.

[0069] In one implementation scenario, a ground detector is used to detect the working conditions of the ground where the robot is currently located, including the ground material. Therefore, by analyzing the detection data from the ground detector, the ground material of the ground where the robot is currently located can be determined.

[0070] In a specific implementation scenario, semantic recognition is performed on the ground image captured by the first camera element on the ground where the robot is located. The recognition results include the ground material and ground covering. Specifically, the ground material includes: tiles, flooring, cement, etc., and the ground covering includes blankets, water stains, oil stains, wires, etc.

[0071] In another specific implementation scenario, the different reflectivity of different materials can be used to analyze the ground image of the robot's location captured by the first camera element and compare it with a preset reflectivity library to determine the ground material.

[0072] Furthermore, in this implementation scenario, the robot's cleaning mode can be controlled based on the ground material.

[0073] In a specific implementation scenario, the robot's database contains a preset cleaning mode table, allowing it to select the appropriate cleaning mode for different floor materials or floor coverings. For example, when the floor material is identified as wood, the preset cleaning mode table is searched for to find the corresponding cleaning mode, and the robot switches to floor mode, reducing cleaning intensity and stopping water spraying to minimize damage to the floor. When the floor material is identified as tile and the floor covering is oil, the preset cleaning mode table is searched for to find the corresponding cleaning mode, and the robot switches to stain removal mode, increasing suction power to effectively clean the oil stains. When the floor covering is identified as carpet, the preset cleaning mode table is searched for to find the corresponding cleaning mode, and the robot switches to carpet mode, activating vacuuming to minimize damage and wetting of the carpet. Therefore, by analyzing the detection data from the floor detectors to obtain floor material information and controlling the robot's cleaning mode based on this information, the cleaning mode can be adjusted for different floor materials, making the robot's operation more intelligent.

[0074] In another specific implementation scenario, cleaning scores can be assigned to different floor materials and floor coverings. Based on the final score, the robot's cleaning mode can be controlled, and cleaning parameters adjusted. For example, a floor material can be assigned a score of 5, and an oil stain on the floor can be assigned a score of 50. Therefore, the score for an oil stain on the floor is 55. Unlike the previous embodiment, even though it's a floor material, the robot's cleaning mode still needs to be switched to a stain removal mode to clean the oil stain. Specific assignment methods are not limited here.

[0075] In the above scheme, on the one hand, environmental images are obtained by installing cameras in the robot's environment, and then an environmental map is constructed for path planning to obtain the robot's movement route. The cameras are set up separately from the robot, which improves the accuracy of environmental map construction and thus enables accurate planning of movement routes. On the other hand, during the movement along the movement route, ground condition analysis is performed based on the detection data of ground detectors, and the robot's cleaning mode is accurately controlled according to the ground condition.

[0076] Please see Figure 11 , Figure 11 This is a flowchart illustrating another embodiment of the robot control method of this application. Specifically, the robot control method in this embodiment may include the following steps:

[0077] Step S101: Based on the environmental map of the robot's environment, perform path planning to obtain the robot's movement route.

[0078] The steps are completely consistent with step S11 in the previous embodiments. The specific implementation steps can be referred to the previous embodiments, and will not be repeated here.

[0079] Step S102: Analyze the detection data to obtain the flatness of the ground where the robot is currently located.

[0080] In one implementation scenario, a ground detector is used to detect the working conditions of the ground where the robot is currently located, including the flatness of the ground. Therefore, by analyzing the detection data from the ground detector, the flatness of the ground where the robot is currently located can be determined. The ground detector includes a first imaging element and an illumination element. The first imaging element can be any type of depth camera, without specific limitations.

[0081] In a specific implementation scenario, the flatness of the ground can be obtained based on the change in depth data. For example, if the depth camera acquires depth data at 1-second intervals, and the difference between two adjacent intervals is 10 centimeters, then 10 centimeters can be used as the flatness of the ground.

[0082] In another specific implementation scenario, the flatness of the ground can be obtained based on the rate of change of depth data. For example, if a depth camera acquires depth data at 1-second intervals, and the depth data from two adjacent time intervals are 5 cm and 15 cm respectively, 200% can be used as the flatness of the ground.

[0083] In another specific implementation scenario, the flatness of the ground can be obtained based on the change value and rate of change of depth data. For example, if the depth camera acquires depth data at a time interval of 1 second, and the depth data of two adjacent time intervals are 5 cm and 15 cm respectively, 10 cm and 200% can be used as the flatness of the ground.

[0084] In another implementation scenario, before analyzing the detection data to determine the flatness of the ground where the robot is currently located, the region category of the area to which the robot is currently located can also be obtained. The region category is determined based on the environmental map. The specific implementation steps can refer to the "dividing the region based on the depth information of each location in the environmental map to obtain the region division result" in the aforementioned embodiment. The region category includes passable areas, prohibited areas, and areas to be determined.

[0085] Furthermore, when the area category of the ground region where the robot is currently located is an area to be determined, step S102 and subsequent steps can be executed. Specific implementation details can be found in other embodiments and will not be repeated here. When the area category of the ground region where the robot is currently located is a passable area or a prohibited area, steps S102 and S103 do not need to be executed; step S104 can be executed directly. Therefore, before analyzing the detection data to determine the flatness of the ground where the robot is currently located, area category classification can be performed first. Based on the classification results, it can be determined whether flatness data needs to be obtained, allowing for targeted verification of the areas to be determined. This helps optimize and improve the robot's working logic, making it more intelligent.

[0086] Step S103: Based on the flatness, determine whether to adjust the moving route.

[0087] In one implementation scenario, the decision to adjust the movement route is based on the flatness of the ground and the robot's mobility. The robot's mobility typically includes its maximum climbing height, maximum vertical clearance, and the maximum degree of ground unevenness it can traverse.

[0088] In a specific implementation scenario, as mentioned earlier, if the flatness of the ground is 10 centimeters, and the robot's maximum climbing height is greater than or equal to 10 centimeters, then there is no need to adjust the movement route; otherwise, the movement route needs to be adjusted and the robot should continue to move along the adjusted route.

[0089] In another specific implementation scenario, as mentioned earlier, if the flatness of the ground is 200%, and the robot's ability to navigate the maximum ground unevenness is greater than or equal to 200%, then there is no need to adjust the movement route; otherwise, the movement route needs to be adjusted and the robot should continue to move along the adjusted route.

[0090] In another specific implementation scenario, as mentioned earlier, the flatness of the ground is 10 cm and 200%. If the robot's mobility simultaneously meets the requirements of a maximum climbing height greater than or equal to 10 cm and a maximum traversable ground unevenness greater than or equal to 200%, then there is no need to adjust the movement route; otherwise, the movement route needs to be adjusted and the robot should continue to move along the adjusted movement route.

[0091] In another implementation scenario, the decision to adjust the route can be made directly based on the flatness of the surface. Specifically, if the flatness exceeds a flatness threshold, the movement route needs to be adjusted, and the movement should continue along the adjusted route; otherwise, no adjustment is necessary. For example, if the flatness is 10 centimeters and the flatness threshold is 5 centimeters, the movement route needs to be adjusted, and the movement should continue along the adjusted route.

[0092] Therefore, by analyzing the detection data, the flatness of the ground where the robot is currently located can be obtained. Based on the flatness, it can be determined whether to adjust the movement route. The movement route planned based on the environmental map is verified and adjusted, which further improves the accuracy of the movement route.

[0093] Step S104: During the movement along the route, the cleaning mode of the robot is controlled based on the detection data of the ground detector.

[0094] The steps are completely consistent with step S12 in the previous embodiments. The specific implementation steps can be referred to the previous embodiments, and will not be repeated here.

[0095] In the above scheme, on the one hand, environmental images are obtained by installing cameras in the robot's environment, and then an environmental map is constructed for path planning to obtain the robot's movement route. The cameras are set up separately from the robot, which improves the accuracy of environmental map construction and thus enables accurate planning of movement routes. On the other hand, during the movement along the movement route, ground condition analysis is performed based on the detection data of ground detectors, and the robot's cleaning mode is accurately controlled according to the ground condition.

[0096] Please see Figure 12 , Figure 12This is a schematic diagram of a framework of an embodiment of the robot control device 12. Specifically, the robot control device 12 includes a path planning module 1201 and a mode control module 1202. The path planning module 1201 is used to plan a path based on an environmental map of the robot's environment to obtain the robot's movement route. The environmental map is constructed based on environmental images captured by a camera device of the robot's environment, and the camera device is installed in the robot's environment but separately from the robot. The mode control module 1202 is used to control the robot's cleaning mode based on detection data from a ground detector during movement along the movement route. Additionally, the robot includes a ground detector, which is used to detect the working conditions of the ground where the robot is currently located.

[0097] In the above scheme, on the one hand, environmental images are obtained by installing cameras in the robot's environment, and then an environmental map is constructed for path planning to obtain the robot's movement route. The cameras are set up separately from the robot, which improves the accuracy of environmental map construction and thus enables accurate planning of movement routes. On the other hand, during the movement along the movement route, ground condition analysis is performed based on the detection data of ground detectors, and the robot's cleaning mode is accurately controlled according to the ground condition.

[0098] In some disclosed embodiments, the working conditions include the ground material of the ground where the robot is currently located, and the mode control module 1202 also includes a material determination unit. The material determination unit is used to analyze the detection data to obtain the ground material of the ground where the robot is currently located; the mode control module 1202 is used to control the robot's cleaning mode based on the ground material.

[0099] Therefore, by analyzing the detection data of the ground detector to obtain ground material information, and based on the ground material information, the cleaning mode of the robot can be controlled. Thus, the cleaning mode can be adjusted for different ground materials, making the robot's work more intelligent.

[0100] In some disclosed embodiments, the environmental map contains depth information of various locations in the robot's environment, and the path planning module 1201 further includes a region division unit. The region division unit is used to divide regions based on the depth information of each location in the environmental map to obtain region division results; wherein, the region division results include several sub-regions and the region category of each sub-region, and the region category includes: passable region, prohibited region, and region to be determined; the path planning module 1201 is used to plan a movement route based on the region division results.

[0101] Therefore, by analyzing the depth information of various locations in the robot's environment, the environment can be divided into different areas, and then the movement route can be planned according to the different areas. Thus, the route planning can be more accurate, and at the same time, the possibility of the robot entering dangerous areas can be minimized.

[0102] In some disclosed embodiments, the region segmentation unit is further configured to determine that the location belongs to a passable area in response to the location's depth information not exceeding the robot's passability; and / or, determine that the location belongs to a prohibited area in response to the location's depth information exceeding the robot's passability; and / or, determine that the location belongs to an area to be determined in response to the location having no depth information.

[0103] Therefore, by comparing the location depth information in the environmental map with the robot's mobility, passable areas, prohibited areas, and areas to be determined can be identified, which facilitates accurate path planning based on the area division.

[0104] In some disclosed embodiments, the robot control device 12 can receive an environmental map; wherein the environmental map is constructed by a cloud server based on an environmental image, and the environmental image is uploaded to the cloud server by a camera device; or the robot control device 12 receives an environmental image and constructs an environmental map based on the environmental image.

[0105] Therefore, environmental maps can be constructed from environmental images, and these maps can be built using multiple computing devices. Users can choose the appropriate method based on their computing power limitations, facilitating flexible control of the robot.

[0106] In some disclosed embodiments, the working conditions also include the flatness of the ground where the robot is currently located, and the robot control device 12 further includes a flatness analysis module and a route adjustment module. The flatness analysis module is used to analyze the detection data to obtain the flatness of the ground where the robot is currently located; the route adjustment module is used to determine whether to adjust the movement route based on the flatness.

[0107] Therefore, by analyzing the detection data, the flatness of the ground where the robot is currently located can be obtained. Based on the flatness, it can be determined whether to adjust the movement route. The movement route planned based on the environmental map is verified and adjusted, which further improves the accuracy of the movement route.

[0108] In some disclosed embodiments, the robot control device 12 further includes a region category acquisition module. The region category acquisition module is used to acquire the region category of the area to which the robot is currently located; wherein, the region category is determined based on an environmental map, and the region category includes: passable area, prohibited area, and area to be determined; the flatness analysis module, in response to the region category being an area to be determined, analyzes the detection data to obtain the flatness of the ground where the robot is currently located; and / or, the route adjustment module, in response to the region category being a passable area or a prohibited area, continues to move along the movement route.

[0109] Therefore, before analyzing the detection data to determine the flatness of the ground where the robot is currently located, we can first classify the areas and determine whether it is necessary to obtain the flatness information based on the classification results. This allows for targeted verification of the specific areas, which helps to optimize and improve the robot's working logic and make it more intelligent.

[0110] Please see Figure 13 , Figure 13 This is a schematic diagram of a framework of an embodiment of the computer-readable storage medium 13 of this application. In this embodiment, the computer-readable storage medium 13 stores processor-executable program instructions 1301, which are used to execute the steps in the above-described robot movement control method embodiment.

[0111] The computer-readable storage medium 13 can be a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, or a medium that can store program instructions. Alternatively, it can be a server that stores the program instructions, which can send the stored program instructions to other devices for execution or execute the stored program instructions itself.

[0112] In the above scheme, on the one hand, environmental images are obtained by installing cameras in the robot's environment, and then an environmental map is constructed for path planning to obtain the robot's movement route. The cameras are set up separately from the robot, which improves the accuracy of environmental map construction and thus enables accurate planning of movement routes. On the other hand, during the movement along the movement route, ground condition analysis is performed based on the detection data of ground detectors, and the robot's cleaning mode is accurately controlled according to the ground condition.

[0113] In the several embodiments provided in this application, it should be understood that the disclosed methods and apparatus can be implemented in other ways. For example, the apparatus implementations described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0114] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0115] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0116] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods of various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0117] If the technical solution of this application involves personal information, the product using this technical solution has clearly informed the user of the personal information processing rules and obtained the user's voluntary consent before processing the personal information. If the technical solution of this application involves sensitive personal information, the product using this technical solution has obtained the user's separate consent before processing the sensitive personal information, and also meets the requirement of "express consent". For example, at personal information collection devices such as cameras, clear and prominent signs are set up to inform users that they have entered the scope of personal information collection and that personal information will be collected. If an individual voluntarily enters the collection scope, it is deemed that they have agreed to the collection of their personal information; or on the personal information processing device, with clear signs / information informing users of the personal information processing rules, authorization is obtained from the individual through pop-up information or by asking the individual to upload their personal information; wherein, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the types of personal information processed.

Claims

1. A robot control method, characterized in that, The robot includes a ground detector, which is used to detect the working conditions of the ground where the robot is currently located. The method includes: Path planning is performed based on the environmental map of the robot's environment to obtain the robot's movement route; wherein, the environmental map is constructed based on environmental images captured by a camera device of the robot's environment, and the camera device is installed in the robot's environment but set separately from the robot; During the movement along the moving route, the cleaning mode of the robot is controlled based on the detection data of the ground detector; The camera device covers the robot's working area, and the path planning based on the environmental map of the robot's environment to obtain the robot's movement route includes: The semantic recognition results based on the environmental image are classified to obtain each object in the environment and its category; wherein, the environmental map is marked with each object and its category, the object category includes passable objects and impassable obstacles, and the environmental map contains depth information of each location of the robot in the environment. In response to a user's selection instruction on the environment map based on the object category, the area where the selected object is located is designated as a passable area. The passable area is then verified based on the depth information of each location on the environment map to obtain a finalized passable area. The movement route is then planned according to the finalized passable area. The finalized passable area is defined as one that simultaneously satisfies both the user's selection and the verification based on depth information. Areas that satisfy only one condition are considered to be undetermined.

2. The method according to claim 1, characterized in that, The operating conditions include the ground material where the robot is currently located, and the control of the robot's cleaning mode based on the detection data from the ground detector includes: Based on the detection data, the ground material of the ground where the robot is currently located is obtained through analysis. The cleaning mode of the robot is controlled based on the ground material.

3. The method according to claim 1, characterized in that, Before performing path planning based on the environmental map of the robot's location to obtain the robot's movement route, the method includes: Receive the environmental map; wherein the environmental map is constructed by a cloud server based on the environmental image, and the environmental image is uploaded to the cloud server by the camera device; or Receive the environmental image and construct the environmental map based on the environmental image.

4. The method according to claim 1, characterized in that, The working conditions also include the flatness of the ground where the robot is currently located. After path planning is performed based on the environmental map of the robot's environment to obtain the robot's movement route, the method further includes: Based on the analysis of the detection data, the flatness of the ground where the robot is currently located is obtained; Based on the flatness, determine whether to adjust the movement route.

5. The method according to claim 4, characterized in that, Before analyzing the detection data to determine the flatness of the ground where the robot is currently located, the method includes: Obtain the region category of the ground area where the robot is currently located; wherein, the region category is determined based on the environment map, and the region category includes: passable area, prohibited area, and area to be determined; The analysis based on the detected data to determine the flatness of the ground where the robot is currently located includes: In response to the region being classified as the region to be determined, the flatness of the ground where the robot is currently located is obtained by analyzing the detection data. And / or, in response to the area category being the passable area or the prohibited area, continue moving along the movement route.

6. A robot, characterized in that, The device includes a ground detector, a processor, and a memory, wherein the ground detector and the memory are respectively coupled to the processor; the processor is used to execute program instructions stored in the memory to implement the robot control method according to any one of claims 1-5.

7. A robot control system, characterized in that, It includes a camera device and the robot as described in claim 6, wherein the camera device is installed in the environment in which the robot is located and is separately set from the robot.

8. A computer-readable storage medium, characterized in that, The system stores program instructions that can be executed by a processor, the program instructions being used to implement the robot control method according to any one of claims 1-6.

Images