Map generation method and cleaning robot

Abstract

The invention relates to a map generation method and a cleaning robot. The method comprises the steps that in the process that the robot moves from a first position to a second position, the actual movement distance of the robot in the movement process is determined according to movement sensing data of the robot; according to respective positioning positions of the first position and the second position in a map coordinate system of the robot, determining a map reference distance of the robot in a movement process; a map matched with the scanning area of the robot is generated according to a correction proportion parameter between the actual movement distance and the map reference distance, and the correction proportion parameter is used for representing the conversion relation between the actual movement distance and the map reference distance. By adopting the method, the sensing distance of the robot can be accurately converted into the distance of the real world, so that the accuracy of the constructed operation map is higher.

Description

Technical Field

[0001] The present application relates to the field of robotics technology, and in particular to a map generating method and a cleaning robot. Background Art

[0002] With the continuous advancement of science and technology and society, the smart home industry is ushering in a new period of development. Smart home devices are becoming an indispensable part of the family, providing people with a more convenient, comfortable and safe life experience. Among smart home devices, smart home cleaning robots are an important component. They can complete home cleaning tasks independently, thus saving people time and energy. As people's requirements for quality of life become higher and higher, people's demand and requirements for cleaning robots are also increasing. The cleaning robot industry will be more widely used and developed in the future. With the widespread application, cleaning robots need to adapt to a variety of home environments and scenarios.

[0003] When constructing a work map for a cleaning robot, the traditional technical solution usually uses various sensors in the cleaning robot to collect various environmental information in the current area, such as information about the walls and furniture placed in the current area. However, the accuracy of the constructed map is relatively low if the information collected by the sensors is used as the basis for the work map. Summary of the invention

[0004] Based on this, it is necessary to provide a more accurate map generation method and a cleaning robot that can implement the map generation method in response to the above technical problems.

[0005] In a first aspect, the present application provides a map generation method, the method comprising:

[0006] During the movement of the robot from the first position to the second position, determining the actual movement distance of the robot during the movement according to the motion sensor data of the robot;

[0007] Determining a map reference distance of the robot during the movement according to respective positioning positions of the first position and the second position in the map coordinate system of the robot;

[0008] A map matching the scanning area of ​​the robot is generated according to a correction ratio parameter between the actual movement distance and the map reference distance, wherein the correction ratio parameter is used to characterize the conversion relationship between the actual movement distance and the map reference distance.

[0009] In one embodiment, the motion sensing data includes wheel speed data. Further, determining the actual motion distance of the robot during the motion according to the motion sensing data of the robot includes:

[0010] Determining the actual motion distance of the robot during the motion according to the motion duration corresponding to the robot during the motion and the wheel speed data.

[0011] In one embodiment, the acquisition method of the wheel speed data includes:

[0012] Acquiring the current change data of the motor of the robot during the motion;

[0013] If the current change data is less than or equal to the abnormal load threshold preset for the motor, acquiring the wheel speed data of the robot during the motion.

[0014] In one embodiment, determining the map reference distance of the robot during the motion according to the positioning positions of the first position and the second position in the map coordinate system of the robot includes:

[0015] Determining a first coordinate and a second coordinate in the map coordinate system of the robot according to the pose information of the robot at the first position and the second position;

[0016] Determining the map reference distance of the robot during the motion according to the first coordinate and the second coordinate.

[0017] In one embodiment, the map reference distance is the Euclidean distance between the first coordinate and the second coordinate;

[0018] Generating a map matching the scanning area of the robot according to the correction ratio parameter between the actual motion distance and the map reference distance includes:

[0019] Determining the ratio between the actual motion distance and the Euclidean distance as the correction ratio parameter;

[0020] Generating a map matching the scanning area of the robot according to the correction ratio parameter.

[0021] In one embodiment, the positioning method of the first coordinate and the second coordinate includes:

[0022] According to the first pose corresponding to the first position, identifying the reference object of the robot at the first position and determining the reference coordinate of the reference object in the map coordinate system;

[0023] Determine the first coordinate of the robot in the map coordinate system according to the relative position relationship between the first position and the reference object and the reference coordinate;

[0024] Determine the second coordinate of the robot in the map coordinate system according to the relative position relationship between the second position and the reference object and the reference coordinate.

[0025] In one embodiment, the determining the reference coordinate of the reference object in the map coordinate system includes:

[0026] Determine the viewing angle range of the robot at the first position according to the current orientation of the first position and the preset viewing angle of the robot;

[0027] If there is a reference object within the viewing angle range, determine the reference position coordinate of the reference object in the map coordinate system.

[0028] In one embodiment, the map generation method further includes:

[0029] If there is no reference object within the viewing angle range, update the current orientation of the first position, and update the viewing angle range according to the updated current orientation;

[0030] Based on the updated viewing angle range, determine the reference position coordinate of the reference object in the map coordinate system.

[0031] In one embodiment, the map generation method further includes:

[0032] Respond to the map correction instruction;

[0033] According to the map correction instruction and the current orientation corresponding to the first position of the robot, control the robot to move from the first position to the second position.

[0034] In one embodiment, before determining the actual movement distance of the robot during the movement process according to the movement sensing data of the robot during the movement of the robot from the first position to the second position, the method further includes:

[0035] Respond to the map correction instruction;

[0036] According to the map correction instruction and the current orientation corresponding to the first position of the robot, control the robot to move from the first position to the second position.

[0037] In one embodiment, the controlling the robot to move from the first position to the second position according to the map correction instruction and the current orientation corresponding to the first position of the robot includes:

[0038] Control the robot to move from the first position to the second position according to the preset movement distance in the map correction instruction and the current orientation corresponding to the robot at the first position.

[0039] In one embodiment, generating a map that matches the scanning area of the robot according to the correction ratio parameter between the actual movement distance and the map reference distance includes:

[0040] Visualize and push the correction ratio parameter between the actual movement distance and the map reference distance;

[0041] According to the confirmation instruction corresponding to the visual push, generate a map that matches the scanning area of the robot according to the correction ratio parameter.

[0042] In a second aspect, the present application provides a cleaning robot, which includes a body, a driving component, a cleaning component, a detection sensor, a memory, and a processor. The driving component, the cleaning component, and the detection sensor are all installed on the body. The driving component is used to drive the body to walk on the working surface, the cleaning component is used to clean the working surface, and the memory stores a computer program; when the processor executes the foregoing computer program, it can implement the map generation method as described in the first aspect.

[0043] The present application provides a map generation method and a cleaning robot. During the movement of the robot from the first position to the second position, the actual movement distance formed after the robot moves in the real scene is determined based on the motion sensing data of the robot. In addition, according to the first position and the second position of the robot in the real scene, position positioning is performed in the map coordinate system constructed by the robot based on the real scene, the coordinate change of the robot in the constructed map coordinate system is determined, and the map reference distance is formed accordingly; further, based on the obtained actual movement distance and the map reference distance, the difference between the distances corresponding to the real scene and the map in the map coordinate system is determined, which is the correction ratio parameter; the correction ratio parameter can be used to convert the distance scanned, detected, and measured by the robot into the distance in the real scene; by introducing the correction ratio parameter, the perceived distance of the robot can be accurately converted into the distance in the real world, thereby making the constructed operation map more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is an application environment diagram of the map generation method in an embodiment;

[0045] Figure 2 It is a flowchart of the map generation method in an embodiment;

[0046] Figure 3 Schematic diagram of sub - step process for collecting wheel speed data in an embodiment;

[0047] Figure 4 Schematic diagram of sub - step process for determining map reference distance in an embodiment;

[0048] Figure 5 Schematic diagram of the process of a map generation method in another embodiment;

[0049] Figure 6 Internal structure diagram of a cleaning robot in an embodiment. Detailed implementation manners

[0050] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application 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 application and are not used to limit the present application.

[0051] As pointed out in the background art, with the popularization of the use of cleaning robots, cleaning robots need to adapt to various household environments and scenarios. In various complex operation scenarios, positioning and map construction of cleaning robots are two important basic functions for cleaning robots to better complete all tasks. Good map accuracy and accurate distance information are the basis for the robot to perceive the world and also the basis for robot positioning and map construction. However, whether it is robot positioning or map construction, the positioning result or map data needs to basically match the actual scenario and have sufficient accuracy. In traditional technical solutions, the way for cleaning robots to eliminate the difference from the actual scenario is usually to use sensors with higher accuracy, such as high - precision radars or to use high - precision depth image algorithms to achieve robot positioning. However, the foregoing methods have the following drawbacks: First, it is necessary to add sensors, which increases the volume, weight and cost of the machine. Second, adding mechanical components or sensors will also lead to an increase in the overall failure rate and instability. Third, it adds additional computational overhead to the cleaning robot. Fourth, it is overly dependent on sensors. Once any link (such as hardware circuits, line connections, sensor boards or host communication, etc.) fails, it may cause relatively serious consequences.

[0052] To solve the above problems and defects existing in the traditional technical solutions, the map generation method provided by the technical solution of the present application can be applied to an application environment as shown in Figure 1 the following figure. Taking the cleaning robot scanning the actual scenario to construct a corresponding operation map as an example, Figure 1In the application environment shown, the cleaning robot 102 communicates with the server 104 via a network. Among them, the server 104 is built-in with a data storage system, which can store various types of data generated by the cleaning robot when scanning the actual scenario, such as motion data, pose data, and environmental information, etc. This data storage system can be integrated on the server 104, or implemented in the form of the cloud and a distributed storage architecture; and the server 104 can be implemented with an independent server or a server cluster composed of multiple servers.

[0053] In Figure 1 In the application environment shown, the server 104 can receive a map construction instruction or a map correction instruction initiated from the user side; the server 104 responds to the map construction instruction or the map correction instruction, triggers a motion control instruction, and sends it to the cleaning robot 102. The cleaning robot 102 responds to the motion control instruction and moves from the first position in the current scenario to the second position. Before performing the corresponding action based on the motion control instruction, the server 104 can locate the first position in the map coordinate system formed by simulating and emulating the current scenario by calling various sensors or information collection devices of the cleaning robot 102. And when the cleaning robot 102 arrives at the second position after completing the movement, the second position is located in the map coordinate system in the same way. During the process of the cleaning robot 102 moving from the first position in the current scenario to the second position, the server 104 can also call the corresponding motion parameter sensors to obtain the corresponding operating parameters of the cleaning robot 102, and determine the actual movement distance of the cleaning robot 102 in the current scenario. After determining the starting point and the ending point of the movement process in the map coordinate system, that is, after completing the positioning of the first position and the second position, the map reference distance in the map coordinate system is calculated. The server 104 generates a correction ratio coefficient between the map coordinate system and the actual current scenario based on the difference between the actual movement distance and the map reference distance. After collecting other environmental information in the current scenario, a map matching the scanned area of the cleaning robot 102 is generated based on the aforementioned correction ratio coefficient, or the already constructed map is corrected.

[0054] In another implementation environment, a cleaning robot is built-in with a processor and a memory. Among them, the processor can control the cleaning robot to perform corresponding actions to get out of the state of restricted operation when the cleaning robot is in the state of restricted operation. Map data and other content during the task operation of the cleaning robot can be stored in the memory. Specifically, the processor in the cleaning robot can directly call the sensors related to motion parameters to obtain the actual motion distance generated when the cleaning robot moves from the first position to the second position in the current scene. At the same time, the processor can also directly schedule the sensors and information collection devices of the cleaning robot to measure the position change of the machine, and determine the map reference distance corresponding to the motion process in the map coordinate system corresponding to the area. Finally, the processor can form a correction proportionality coefficient between the map and the actual scene based on the actual motion distance and the map reference distance, so as to generate a map of the current area or correct the existing map.

[0055] To elaborate more specifically on the implementation process of the method provided in this application, as Figure 2 shown, as Figure 2 shown, a map generation method is provided. This method can be executed by the server 104 in Figure 1 or independently executed by a cleaning robot device with certain data processing capabilities. The map generation method includes the following steps:

[0056] Step 202, during the movement of the robot from the first position to the second position, determine the actual movement distance of the robot during the movement according to the motion sensing data of the robot.

[0057] In the embodiment, the robot can be a device integrating multiple functions such as environmental perception, dynamic decision-making and planning, behavior control and execution; for example, a cleaning robot or a floor sweeping robot. In the following description of the specification, the cleaning robot is taken as an example to expand the description of the embodiment. The first position and the second position in the embodiment are both used to represent the actual position of the cleaning robot in the current actual scene (such as a certain place on the room floor). Among them, the first position is the position before the cleaning robot generates a motion behavior, and the second position is the position after the cleaning robot generates a motion behavior. Further, the distance between the two actual positions is the actual motion distance of the cleaning robot during the movement. The motion sensing data in the embodiment refers to the data collected by the sensor device related to motion parameters during the process of the cleaning robot moving from the first position to the second position, including but not limited to motion parameters such as linear acceleration and angular velocity.

[0058] Exemplarily, after the cleaning robot in the embodiment receives the motion control instruction from the server, it moves from location A on the room floor to location B according to this instruction, that is, the first position and the second position in the embodiment. During its movement, it can call the inertial measurement sensors inside the robot, for example, an accelerometer and a gyroscope, etc., to measure the linear acceleration and angular velocity of the cleaning robot during the movement. Based on the movement time of the cleaning robot from location A to location B, it calculates and determines the straight-line movement distance of the cleaning robot from location A to location B, and takes the distance of this straight-line movement as the actual movement distance of the cleaning robot.

[0059] Step 204, determine the map reference distance of the robot during the movement according to the respective positioning positions of the first position and the second position in the map coordinate system of the robot.

[0060] In the embodiment, the map coordinate system is a coordinate system established when constructing the map based on the current actual scene. Furthermore, in the embodiment, the positioning process in the map coordinate system is a process of determining the position and pose of the cleaning robot itself based on the cleaning robot sensing the surrounding environment information in the current actual scene through various types of sensors or acquisition devices.

[0061] Exemplarily, before the cleaning robot in the embodiment executes the motion action, it needs to pre-construct the map coordinate system corresponding to the current actual scene as a reference for the operation map of the cleaning robot. Specifically, in the embodiment, when the cleaning robot is at the first position in the current scene, it measures the surrounding environment by using a lidar or a vision sensor. These sensors can emit laser beams or light rays and measure the time of reflection back, so as to determine the distance between the robot and the surrounding objects. In this way, the robot can obtain the geometric shape and distance information about the surrounding environment, and thus establish the map coordinate system. After the establishment of the map coordinate system, further through a reference object or a selected coordinate origin, the first position of the cleaning robot in the current actual scene is mapped into the map coordinate system to determine the corresponding position of the first position in the map coordinate system. Similarly to the first position, after the cleaning robot executes the motion action and moves to the second position, the second position of the cleaning robot in the current actual scene is also mapped to determine the response position of the second position in the map coordinate system. After the positioning mapping of the first position and the second position in the map coordinate system has been completed, calculate the distance between the two mapped positions in the map coordinate system, determine the change in the position of the cleaning robot in the map coordinate system, and record it as the map reference distance.

[0062] Step 206: Generate a map that matches the scanning area of the robot according to the correction ratio parameter between the actual movement distance and the map reference distance; wherein, the correction ratio parameter is used to represent the conversion relationship between the actual movement distance and the map reference distance.

[0063] In the embodiment, the correction ratio parameter can reflect the difference between the actual movement distance and the map reference distance, that is, the difference between any distance in the current actual scene and the distance mapped in the map coordinate system. At the same time, the correction ratio parameter in the embodiment can be used as the conversion parameter between the current actual scene and the map coordinate system. Based on this correction ratio parameter, the conversion between the distance in the actual scene and the distance in the map coordinate system can be realized. The scanning area of the cleaning robot in the embodiment is the current actual scene where a map needs to be constructed or the map needs to be corrected.

[0064] Specifically in the embodiment, when the actual movement distance of the cleaning robot in the current actual scene is determined through motion sensing data; combined with the map reference distance mapped in the map coordinate system, the difference between the two distances is measured and determined. For example, the conversion relationship between the actual movement distance and the map reference distance is determined by means of function fitting, and the function coefficient formed after function fitting is the correction ratio parameter. After determining the correction ratio parameter and the corresponding fitting function, the true distance in the current actual scene can be determined according to the distance between any two determined points in the map coordinate system. Through the correction ratio parameter and the corresponding fitting function, reliable data basis can be provided when generating a specific operation map or correcting the operation map.

[0065] It should be noted that the operation map constructed in the embodiments is a map for path planning, including but not limited to two-dimensional / three-dimensional grid maps, two-dimensional / three-dimensional cost maps, or two-dimensional / three-dimensional point cloud maps. The operation map can also include various layers, such as: Obstacle layer: representing basic obstacles, including fixed and moving objects, as well as living and inanimate objects. Historical trajectory layer: used to represent the position information that the machine has reached. Carpet layer: a carpet layer marked by the robot according to the actual perception. Cliff layer: a cliff layer marked by the robot according to the actual perception. If the machine does not avoid it, it may cause a fall or get stuck. Prohibited area layer: a layer set by the user to prohibit the machine from entering. Virtual wall layer: a layer set by the user to prohibit the machine from crossing (penetrating). Prohibited mopping area layer: a layer of the area where the machine is prohibited from mopping set by the user. Semantic information layer: semantic information marked by the machine according to the recognition results of artificial intelligence (AI) or other methods. After generating the above rich layers, all the layers are superimposed based on the map coordinate system constructed in the foregoing embodiments, and the target positions in each layer are corrected based on the correction ratio parameter, and finally the map simulation of the current actual area is realized to form the operation map of the cleaning robot.

[0066] In the above map generation method, during the movement of the robot from the first position to the second position, the actual movement distance formed after the robot moves in the real scene is determined based on the motion sensing data of the robot. In addition, according to the first position and the second position of the robot in the real scene, the position is located in the map coordinate system constructed by the robot based on the real scene, the coordinate change of the robot in the constructed map coordinate system is determined, and the map reference distance is formed accordingly; further based on the obtained actual movement distance and the map reference distance, the difference between the distances of the real scene and the map corresponding to the map coordinate system is determined, which is the correction ratio parameter; this correction ratio parameter can be used to convert the distance measured by the robot through scanning, detection, and calculation into the distance in the real scene; by introducing the correction ratio parameter, the sensing distance of the robot can be accurately converted into the distance in the real world, so that the accuracy of the constructed operation map is higher.

[0067] In one embodiment, in order to more accurately describe the actual movement distance of the cleaning robot during the movement, the wheel speed data collected by the wheel speedometer is selected as the motion sensing data in the embodiment. Furthermore, in the above method, the process of determining the actual movement distance of the robot during the movement based on the motion sensing data of the robot is specifically as follows:

[0068] The actual movement distance of the robot during the movement is determined according to the movement duration and the wheel speed data corresponding to the robot during the movement.

[0069] In an embodiment, the wheel speed data is collected by a wheel speed meter built into the cleaning robot. More specifically, the wheel speed meter in the cleaning robot is a sensor mainly used to measure the speed of the center of the rear axle of the cleaning robot in the forward direction of the carrier. The wheel speed meter consists of a rotational speed sensor and a signal processing circuit. The rotational speed sensor is responsible for measuring the rotational speed of the wheel, and the signal processing circuit converts the rotational speed signal into an electrical signal for subsequent processing. The movement duration in the embodiment can be determined by a timer.

[0070] Exemplarily, in the embodiment, a timer is initialized on the server, or a timer is initialized locally by the processor of the cleaning robot. When the cleaning robot starts to move from the first position, timing begins. The cleaning robot moves slowly and uniformly towards the second position in the current actual scenario. During the process of the cleaning robot moving from the first position to the second position, the wheel speed meter at the rear wheel of the cleaning robot collects the wheel speed data during the movement of the cleaning robot. When the cleaning robot ends its movement state and reaches the second position, the timing ends, thereby obtaining the movement duration of the cleaning robot. Then, the actual movement distance of the cleaning robot is measured. During the movement time, the number of rotations of the rear wheel of the cleaning robot and the length of each rotation are measured, and then they are multiplied to obtain the driving distance of the cleaning robot, that is, the actual movement distance. It should be noted that the movement mode of the cleaning robot in the embodiment also includes turning or rotating actions in place. Therefore, the timer in the embodiment will only start timing after the cleaning robot has a real displacement. In the embodiment, the measurement through the wheel speed data makes the finally measured actual movement distance more accurate.

[0071] More specifically, in the embodiment, the cleaning robot can detect changes in the surrounding environment through various sensors assembled on itself, such as infrared rays and ultrasonic waves, so as to determine whether the cleaning robot has had a real displacement. When the cleaning robot starts to have a real displacement, sensors such as infrared rays and ultrasonic waves will continuously collect environmental data and compare these data with the environmental information collected when the cleaning robot is stationary. If it is found that the data is inconsistent, for example, a new obstacle or environmental change is detected, it can be determined that the robot has moved.

[0072] In one embodiment, in order to more accurately describe the actual movement distance, during the measurement process, it is necessary to exclude the wheel speed data generated by the cleaning robot due to slipping during the movement. Specifically, as Figure 3 shown, the acquisition method of the wheel speed data in the above method includes the following two steps:

[0073] Step 302, collect the current change data of the motor during the movement of the robot.

[0074] In an embodiment, the motor refers to the motor that controls the rotation of the rear wheels of the cleaning robot. The current change data in the embodiment is used to characterize the change or change trend of the current of the rear-wheel motor during the movement process.

[0075] Specifically in the embodiment, a current sensor may also be provided in the rear-wheel motor of the cleaning robot to collect the current data of the cleaning robot during the movement process, and summarize all the current data during the movement process, so as to be able to reflect the change of the current in the rear-wheel motor during the movement process, that is, obtain the current change data.

[0076] Step 304, if the current change data is less than or equal to the abnormal load threshold preset for the motor, collect the wheel speed data of the robot during the movement process.

[0077] In the embodiment, specifically, when the chassis wheels slip, the load on the motor will suddenly increase, resulting in a sudden increase in the current of the motor. Therefore, it is possible to judge whether the wheels are slipping by monitoring the current of the motor. The abnormal load threshold is the current value when the motor operates abnormally pre-written into the judgment logic; more specifically, the abnormal operation of the motor may refer to the situation where the rear wheels of the cleaning robot slip or rotate idly during the movement process. After determining the abnormal load threshold of the motor and forming the corresponding judgment logic, the embodiment can judge the movement state of the cleaning robot based on this judgment logic and the current change data collected in real time.

[0078] Exemplarily, during the movement of the cleaning robot, when slipping occurs, the contact area between the rear wheels and the ground decreases, the pressure per unit area increases, resulting in an increase in friction. Also, since the friction between the rear wheels and the ground will suddenly increase and generate an additional load on the motor, the current in the rear-wheel motor will increase abnormally. Therefore, in the embodiment, by setting the abnormal load threshold of the rear-wheel motor, for example, taking the maximum load current value of 2A of the motor when the rear wheels rotate normally as the abnormal load threshold. Then, when the load current of the motor changes by more than 2A during the movement of the cleaning robot, it can be determined that the cleaning robot has slipped during the movement process. Since slipping and idling conditions will affect the actual movement distance. If the cleaning robot frequently slips during a certain movement process, the first position and the second position will be re-determined to make the accuracy of the finally measured actual movement distance higher.

[0079] In one embodiment, as Figure 4 shown, the process of determining the map reference distance of the robot during the movement process according to the respective positioning positions of the first position and the second position in the map coordinate system of the robot may specifically include the following steps:

[0080] Step 402: Determine a first coordinate and a second coordinate in the map coordinate system of the robot according to the pose information of the robot at the first position and the second position.

[0081] In an embodiment, the pose information is used to characterize the position and pose of the cleaning robot in the map coordinate system; wherein, the pose may refer to the orientation direction of the cleaning robot.

[0082] Exemplarily, in the embodiment, various types of sensor data of the cleaning robot itself can be called, for example, lidar, vision sensor, inertial measurement unit, etc. to obtain various types of sensor data, and the pose information of the cleaning robot is obtained based on the integration of various types of sensor data. For example, the lidar can measure the environmental information around the cleaning robot in the current actual scene, and according to the relative position information between the cleaning robot and the surrounding environment (objects), map it to the map coordinate system to determine the position and direction of the cleaning robot; the vision sensor can capture the images around the cleaning robot, and through image processing and computer vision technology, the position and direction of the robot can be further determined.

[0083] Step 404: Determine the map reference distance of the robot during the movement process according to the first coordinate and the second coordinate.

[0084] Specifically, in the embodiment, since when forming the pose information of the cleaning robot, through various types of sensor data of the lidar or the vision sensor, the pose information of the cleaning robot in the map coordinate system has been calculated, including the coordinates of the cleaning robot in the map coordinate system. Therefore, the pose information of the cleaning robot at the first position is mapped to the map coordinate system to determine the first coordinate corresponding to the pose information; and the pose information at the second position after the movement process is also mapped to the map coordinate system to determine the second coordinate corresponding to the pose information. Through the distance calculation between the two coordinates, the map reference distance generated by the movement of the cleaning robot in the map coordinate system can be obtained. By collecting and mapping the pose information of the cleaning robot, the coordinate values corresponding to each position can be more accurately determined in the map coordinate system, so that the calculated map reference distance is more accurate.

[0085] In one embodiment, the Euclidean distance calculation method can be used to determine the distance between two coordinates in the map coordinate system. Therefore, the process of generating a map matching the scanning area of the robot according to the correction ratio parameter between the actual movement distance and the map reference distance in the above method may include the following steps:

[0086] Step 1: Determine the ratio between the actual movement distance and the Euclidean distance as the correction ratio parameter.

[0087] Step 2: Generate a map matching the scanning area of the robot according to the correction ratio parameter.

[0088] Specifically, in the embodiments, since the pose information of the cleaning robot in the map coordinate system is composed of position and orientation. For example, in a three-dimensional map coordinate system, the position is represented by three-dimensional coordinates (x, y, z), and the orientation is represented by a quaternion. Therefore, the pose information of the first position in the map coordinate system is recorded as Pose1, and the pose information of the second position in the map coordinate system is recorded as Pose2. And P1 and P2 are used to represent the corresponding coordinate positions respectively. Thus, in the embodiments, the correction ratio parameter = S / ||P2 - P1||; where ||P2 - P1|| represents the Euclidean distance between P1 and P2, that is, the map reference distance corresponding to the cleaning robot in the map coordinate system after pose estimation; S is the actual movement distance of the cleaning robot, which can be determined by measuring with a wheel speedometer. It should be noted that if there is an accuracy error in a single measurement, the error can be reduced by multiple measurements.

[0089] The finally calculated correction ratio parameter, which can also be called the scale factor, is a parameter used to represent the ratio between the real-world distance and the robot's perceived distance in the process of Simultaneous Localization and Mapping (SLAM); that is, the scale factor is a conversion factor used to convert the robot's perceived distance into the real-world distance.

[0090] In one embodiment, when determining the corresponding coordinate position of the cleaning robot in the map coordinate system based on its pose information, the corresponding coordinate position can be determined by based on the positional relationship between the cleaning robot and the obstacles in the environment characterized in the pose information. Furthermore, the positioning method of the first coordinate in the above method can include the following steps:

[0091] Step 1, according to the first pose corresponding to the first position, identify the reference object of the robot at the first position, and determine the reference coordinates of the reference object in the map coordinate system.

[0092] Step 2, according to the relative position relationship and the reference coordinates between the first position and the reference object, determine the first coordinate of the robot in the map coordinate system.

[0093] In an embodiment, the first pose refers to the positioning information mapped to the map coordinate system based on various sensor data when the cleaning robot is at the first position in the current actual scenario, including coordinate position, attitude, etc. The reference coordinate in the embodiment is the position coordinate corresponding to the reference object in the map coordinate system. It should be noted that the reference object in the embodiment may include, but is not limited to, walls, steps, large furniture, etc. Due to the immovable or unchangeable attributes of the foregoing objects or terrains, they can be selected as reference objects; at the same time, due to the immovable or unchangeable attributes, their positions are usually fixed, so their coordinate positions in the map coordinate system are also clear and fixed, so they can be selected as reference objects during positioning.

[0094] Specifically in the embodiment, during the process of positioning the cleaning robot in the map coordinate system based on the first position of the cleaning robot in the current actual scenario, first, various sensor data collected when the cleaning robot is at the first position are sorted out to determine each reference object in the surrounding environment of the cleaning robot. For example, in the case of obtaining image data of the surrounding environment of the cleaning robot, a wall is found by combining 2D or 3D semantic recognition effects, and the wall is used as a reference object. In addition, the pose information also includes the relative position relationship with each reference object in the surrounding environment. Based on this relative position relationship, more accurate positioning in the map coordinate system can be achieved. For example, after the cleaning robot recognizes the surrounding wall, it can move towards the wall until it is close to the wall, so that the position coordinate of the edge of the wall in contact with the cleaning robot in the map coordinate system can be used as the first coordinate of the cleaning robot, thereby realizing accurate positioning of the cleaning robot in the map coordinate system.

[0095] In one embodiment, the process of determining the reference coordinate of the reference object in the map coordinate system in the above method may specifically include the following steps:

[0096] Step 1, determine the viewing angle range of the robot at the first position according to the current orientation at the first position and the preset viewing angle of the robot.

[0097] Step 2, if there is a reference object within the viewing angle range, determine the reference position coordinate of the reference object in the map coordinate system.

[0098] In the embodiment, the viewing angle refers to the included angle between the outer contour from which the sensor for image acquisition can obtain data and the center of the sensor module, and it is specifically an angle range; the viewing angle in the embodiment may include a horizontal viewing angle and a vertical viewing angle. Furthermore, the viewing angle range in the embodiment refers to the range of the surrounding environment that the cleaning robot can perceive when the viewing angle is determined.

[0099] Exemplarily, when the cleaning robot is at the first position, the surrounding environment information of the cleaning robot is explored through the field of view angle of its own image acquisition sensor and the visual field range formed by the current orientation of the robot. During the exploration process, based on the environmental image acquired within the visual field range, target recognition is performed on the environmental image by combining 2D or 3D semantic recognition methods to determine whether there is a reference object similar to a wall within the current visual field range. When it is determined through target recognition that there is a reference object, more types of sensors such as ultrasonic sensors can be called to determine the positional relationship between the cleaning robot and the reference object at the first position. Finally, various sensor data are integrated as the pose data for positioning the first position in the map coordinate system.

[0100] In one embodiment, the above method further includes the following steps: If there is no reference object within the viewing angle range, update the current orientation of the first position and re-determine the viewing angle range of the robot at the first position.

[0101] Specifically in the embodiment, if the cleaning robot does not obtain any reference object through target recognition within the current viewing angle range, the current orientation of the cleaning robot needs to be adjusted. For example, the current orientation of the cleaning robot is adjusted 45° clockwise to form a new viewing angle range, and target recognition is performed on the new viewing angle range until it is determined that there is a reference object, and then the subsequent positioning process is carried out.

[0102] In one embodiment, the cleaning robot needs to respond to corresponding control instructions before it can perform movement actions. Therefore, the map generation method in the embodiment can further include the following steps:

[0103] Step 1, respond to the map correction instruction.

[0104] Step 2, according to the map correction instruction and the current orientation corresponding to the robot at the first position, control the robot to move from the first position to the second position.

[0105] In an embodiment, the map correction instruction may carry specific orientation change parameters and movement displacement distances, which are used to indicate the correction of the cleaning operation map of the cleaning robot, so that the map can more clearly and accurately describe the real distances in the actual scenario. Exemplarily, in the embodiment, the user initiates a map generation instruction or a map correction instruction through a user terminal in a manner such as pressing a key / voice, etc.; in response to the foregoing instruction value, the cleaning robot first moves to closely adhere to the wall surface frontally and performs pose measurement to obtain the current pose as Pose1. Then, it moves backward a certain distance, and the current pose is measured to be Pose2, and the distance of backward movement is the distance S measured by the wheel speedometer. Among them, Pose1 and Pose2 are poses estimated by existing positioning algorithms, and the sensor can be a monocular, binocular or other perception devices that can be used for positioning and mapping. According to the positions of Pose1 and Pose2, the deviation of the displacement with S is calculated, and a more accurate scale factor can be estimated.

[0106] In one embodiment, in the process of controlling the robot to move from the first position to the second position according to the map correction instruction and the current orientation corresponding to the robot at the first position in the foregoing method, the specific process is as follows: According to the preset movement distance in the map correction instruction and the current orientation corresponding to the robot at the first position, control the robot to move from the first position to the second position.

[0107] In an embodiment, the preset movement distance refers to the distance of the robot's movement set by the user through the interactive operation interface, and the foregoing map correction instruction is generated according to the distance of the robot's movement. Exemplarily, in the embodiment, the user can correct the initial cleaning operation map of the cleaning robot by means of voice control. When the user issues a map correction instruction to the cleaning robot through voice interaction, it is specified that the movement distance control of the cleaning machine during the correction process is one meter, that is, the preset movement distance in the embodiment is one meter. After the cleaning robot receives and responds to the map correction instruction and starts to execute the action according to the preset movement distance carried in the instruction, it moves forward one meter while maintaining the current orientation of the cleaning robot. It should be noted that in the embodiment, the movement distance of the cleaning robot can be determined by the foregoing sensors such as the wheel speedometer; that is, when it is calculated and determined according to the data collected by the wheel speedometer that the cleaning robot has moved forward one meter, the robot is controlled to stop, so that the cleaning robot moves from the first position to the second position. It should be noted that in this embodiment, the preset movement distance is the same as the actual movement distance generated by the robot during the movement process. The subsequent steps of generating the correction ratio parameter and the map are the same as the implementation manners provided in the foregoing embodiments, and will not be elaborated herein.

[0108] Further, the map correction instruction in the embodiment may further carry adjustment information of other motion states, including but not limited to the orientation adjustment information of the robot and the motion direction information of the robot, etc. Taking the motion direction information of the robot as an example, in the control instruction issued by the user in the embodiment through semantic interaction, the preset motion distance is specified as one meter, and at the same time, the motion direction of the robot is specified as backward. Therefore, after receiving this map correction instruction, the cleaning robot in the embodiment will move backward one meter while maintaining the current orientation and reach the second position from the first position. The method of generating the correction ratio parameter between the actual motion distance and the map reference distance through the semi-automatic mode of interactive control in the embodiment can handle complex actual scenarios and assist the cleaning robot to accurately complete the relevant actions of map correction.

[0109] In one embodiment, the process of generating a map matching the scanning area of the robot according to the correction ratio parameter between the actual motion distance and the map reference distance in the foregoing method may include the following steps:

[0110] Step 1, visually push the correction ratio parameter between the actual motion distance and the map reference distance.

[0111] Step 2, according to the confirmation instruction corresponding to the visual push, generate a map matching the scanning area of the robot according to the correction ratio parameter.

[0112] In the embodiment, the visual push means that the generated correction ratio parameter is displayed on the display interface of the user terminal through message reminders or pop-up windows, etc., and the map and other information after reprocessing with the optimized correction ratio parameter (such as the scale factor) are shown to the user for the user to refer to and decide whether to adopt the obtained scale factor. Exemplarily, after generating the correction ratio parameter according to the actual motion distance and the map reference distance of the cleaning robot in the embodiment, this specific correction ratio parameter is displayed in the form of a message pop-up window on the interactive operation page of the application software (Application, APP) in the user's mobile terminal, and the user's instruction is obtained in the message pop-up window in the form of a touch control. For example, the instruction triggered by the touch control with the word "confirm" is the confirmation instruction, and the touch control with the word "cancel" triggers the cancel instruction. When the confirmation instruction feedback by the APP is received, the foregoing generated scale factor is used as the conversion parameter between the actual motion distance and the map reference distance in the current cleaning operation map of the cleaning robot.

[0113] It should be noted that, in order to achieve the automatic interaction control method, in the process of visualizing and pushing the correction ratio parameter, a corresponding response time can be set. During this response time, the confirmation instruction and cancellation instruction triggered by the user through the touch control in the message pop-up window can directly facilitate the subsequent actions of generating or correcting the cleaning operation map; if the user does not feedback any instruction within this response time, it will be default to generate the cleaning operation map of the cleaning robot with the scale factor generated in the previous step, or correct the existing cleaning operation map. Through the visual interaction control method in the embodiment, the user's needs can be more accurately determined, so that the accuracy of the finally generated map or the corrected map is higher.

[0114] Combined with the specification Figure 5 , the complete process description of the map generation method provided by this application is as follows:

[0115] Step 1, according to the pose sensor of the cleaning robot itself, such as a monocular, binocular or other perception devices that can be used for positioning and mapping, identify the reference objects within the perspective range of the cleaning robot. Combine 2D or 3D semantic recognition algorithms to identify reference objects such as walls. Then move to the front and stick tightly to the wall, and perform pose measurement to obtain the current pose as Pose1.

[0116] Step 2, the cleaning robot moves backward for a certain distance, and measures the current pose as Pose2, and the distance of backward movement is obtained by the wheel speedometer as S. Specifically, the cleaning robot moves slowly during the movement, and judges that the chassis wheels do not slip through the current trend, which is used to give the distance reference for the machine movement. When the chassis wheel speedometer moves slowly without slipping and the travel distance is relatively short, the measured distance is used as a high-precision distance reference.

[0117] Step 3, according to the positions of Pose1 and Pose2, calculate the deviation from the displacement of S, and calculate a more accurate scale factor. Among them, the pose is composed of position and direction, the position is represented by three-dimensional coordinates (x, y, z), and the direction is usually represented by quaternions. Represent the position parts of Pose1 and Pose2 as P1 and P2, and then calculate the moving distance of the robot based on these two positions. Scale factor = S / ||P2 - P1||; where ||P2 - P1|| represents the Euclidean distance between P1 and P2, that is, the moving distance of the cleaning robot estimated by pose. S is the actual moving distance of the robot, obtained through the wheel speedometer. If there is an accuracy error in a single measurement, the error can be reduced by multiple measurements in the embodiment.

[0118] It should be understood that although the steps in the flowcharts involved in the above embodiments are sequentially shown according to the indications of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same moment, but can be executed at different moments. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0119] Based on the same inventive concept, an embodiment of the present application also provides a map generation device for implementing the above-mentioned map generation method. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the map generation device provided below can refer to the limitations on the map generation method in the above text, and will not be repeated here.

[0120] In one embodiment, a map generation device is provided, including: an actual distance measurement module, a reference distance measurement module, and a proportional parameter calculation module, where:

[0121] The actual distance measurement module is used to determine the actual movement distance of the robot during the movement process according to the movement sensing data of the robot when the robot moves from the first position to the second position;

[0122] The reference distance measurement module is used to determine the map reference distance of the robot during the movement process according to the respective positioning positions of the first position and the second position in the map coordinate system of the robot;

[0123] The proportional parameter calculation module is used to generate a map that matches the scanning area of the robot according to the correction proportional parameter between the actual movement distance and the map reference distance.

[0124] In one embodiment, the movement sensing data includes wheel speed data. The actual distance measurement module is further used to determine the actual movement distance of the robot during the movement process according to the movement duration corresponding to the robot during the movement process and the wheel speed data.

[0125] In one embodiment, the actual distance measurement module is further used to collect the current change data of the motor of the robot during the movement process; if the current change data is less than or equal to the preset abnormal load threshold of the motor, the wheel speed data of the robot during the movement process is collected.

[0126] In one embodiment, the reference distance measurement module is further configured to determine a first coordinate and a second coordinate in the map coordinate system of the robot according to the pose information of the robot at the first position and the second position; and determine the map reference distance of the robot during the movement according to the first coordinate and the second coordinate.

[0127] In one embodiment, the map reference distance is the Euclidean distance between the first coordinate and the second coordinate. The proportional parameter calculation module is further configured to determine the ratio between the actual movement distance and the Euclidean distance as the correction proportional parameter; and generate a map matching the scanning area of the robot according to the correction proportional parameter.

[0128] In one embodiment, the reference distance measurement module is further configured to identify a reference object of the robot at the first position according to the first pose corresponding to the first position, and determine the reference coordinate of the reference object in the map coordinate system; and determine the first coordinate of the robot in the map coordinate system according to the relative position relationship between the first position and the reference object and the reference coordinate.

[0129] In one embodiment, the reference distance measurement module is further configured to determine the viewing angle range of the robot at the first position according to the current orientation of the first position and the preset viewing angle of the robot; if there is a reference object within the viewing angle range, determine the reference position coordinate of the reference object in the map coordinate system.

[0130] In one embodiment, the reference distance measurement module is further configured to update the current orientation of the first position if there is no reference object within the viewing angle range, and re-determine the viewing angle range of the robot at the first position.

[0131] In one embodiment, the device further includes an instruction receiving module, configured to respond to a map correction instruction; and control the robot to move from the first position to the second position according to the map correction instruction and the current orientation of the robot corresponding to the first position.

[0132] Each module in the above map generation device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor of the computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above respective modules.

[0133] In one embodiment, a cleaning robot is provided, including a body, a driving component, a cleaning component, a detection sensor, a memory, and a processor. The driving component, the cleaning component, and the detection sensor are all installed on the body. The driving component is used to drive the body to walk on the working surface, and the cleaning component is used to clean the working surface. The internal structure diagram of its core control module can be as Figure 6As shown in the figure. The cleaning robot includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface, the display unit, and the input device are connected to the system bus through the input / output interface. Among them, the processor of the cleaning robot is used to provide computing and control capabilities. The memory of the cleaning robot includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the cleaning robot is used to exchange information between the processor and external devices. The communication interface of the cleaning robot is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a map generation method.

[0134] Those skilled in the art can understand that Figure 6 the structure shown in the figure is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have a different component layout.

[0135] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0136] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0137] The above embodiments only represent several implementation manners of the present application. Their descriptions are relatively specific and detailed, but they should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method for generating a map, characterized in that, The method includes: During the movement of the robot from the first position to the second position, determining the actual movement distance of the robot during the movement according to the movement sensing data of the robot; Determining the map reference distance of the robot during the movement according to the respective positioning positions of the first position and the second position in the map coordinate system of the robot; Generating a map matching the scanning area of the robot according to the correction ratio parameter between the actual movement distance and the map reference distance, where the correction ratio parameter is used to characterize the conversion relationship between the actual movement distance and the map reference distance.

2. The method according to claim 1, wherein The movement sensing data includes wheel speed data; The determining the actual movement distance of the robot during the movement according to the movement sensing data of the robot includes: Determining the actual movement distance of the robot during the movement according to the movement duration corresponding to the robot during the movement and the wheel speed data.

3. The method according to claim 2, wherein The acquisition method of the wheel speed data includes: Acquiring the current change data of the motor of the robot during the movement; If the current change data is less than or equal to the abnormal load threshold preset for the motor, acquiring the wheel speed data of the robot during the movement.

4. The method according to claim 1, characterized in that, The determining the map reference distance of the robot during the movement according to the respective positioning positions of the first position and the second position in the map coordinate system of the robot includes: Determining a first coordinate and a second coordinate in the map coordinate system of the robot according to the pose information of the robot at the first position and the second position; Determining the map reference distance of the robot during the movement according to the first coordinate and the second coordinate.

5. The method according to claim 4, wherein The map reference distance is the Euclidean distance between the first coordinate and the second coordinate; The generating a map matching the scanning area of the robot according to the correction ratio parameter between the actual movement distance and the map reference distance includes: Determining the ratio between the actual movement distance and the Euclidean distance as the correction ratio parameter; Generating a map matching the scanning area of the robot according to the correction ratio parameter.

6. The method according to claim 4, characterized in that, The positioning method of the first coordinate and the second coordinate includes: According to the first pose corresponding to the first position, identifying the reference object of the robot at the first position and determining the reference coordinate of the reference object in the map coordinate system; Determining the first coordinate of the robot in the map coordinate system according to the relative position relationship between the first position and the reference object and the reference coordinate; Determining the second coordinate of the robot in the map coordinate system according to the relative position relationship between the second position and the reference object and the reference coordinate.

7. The method according to claim 6, wherein The determining the reference coordinate of the reference object in the map coordinate system includes: Determining the viewing angle range of the robot at the first position according to the current orientation of the first position and the preset viewing angle of the robot; If there is a reference object within the viewing range, determine the reference position coordinates of the reference object in the map coordinate system.

8. The method according to claim 7, wherein The method further includes: If there is no reference object within the viewing range, update the current orientation of the first position, and update the viewing range according to the updated current orientation; Based on the updated viewing range, determine the reference position coordinates of the reference object in the map coordinate system.

9. The method according to claim 1, wherein Before determining the actual movement distance of the robot during the movement process from the first position to the second position according to the movement sensing data of the robot, the method further includes: Respond to the map correction instruction; According to the map correction instruction and the current orientation corresponding to the first position of the robot, control the robot to move from the first position to the second position.

10. The method according to claim 9, wherein The controlling the robot to move from the first position to the second position according to the map correction instruction and the current orientation corresponding to the first position of the robot includes: According to the preset movement distance in the map correction instruction and the current orientation corresponding to the first position of the robot, control the robot to move from the first position to the second position.

11. The method according to any one of claims 1 to 10, characterized in that, The generating a map matching the scanning area of the robot according to the correction ratio parameter between the actual movement distance and the map reference distance includes: Visualize and push the correction ratio parameter between the actual movement distance and the map reference distance; According to the confirmation instruction corresponding to the visualization push, generate a map matching the scanning area of the robot according to the correction ratio parameter.

12. A cleaning robot, characterized in that, It includes a fuselage, a driving component, a cleaning component, a detection sensor, a memory, and a processor. The driving component, the cleaning component, and the detection sensor are all installed on the fuselage. The driving component is used to drive the fuselage to walk on the working surface. The cleaning component is used to clean the working surface. The memory stores a computer program. When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 11.

Images