Method for Dynamically Adjusting Obstacle Avoidance Sensitivity of Robot and Robot

Abstract

The present invention provides a method for dynamically adjusting the obstacle avoidance sensitivity of a robot. The method includes: obtaining a target movement path of the robot in a grid map; selecting a plurality of positions on the target movement path; determining the distances between the robot and obstacles at the plurality of positions; adjusting the obstacle avoidance sensitivity of the robot based on the distances; and controlling the robot to perform obstacle avoidance operations based on the adjusted obstacle avoidance sensitivity. By adopting the technical solution of the present invention, the adaptive ability of the robot is greatly improved, the stability and flexibility of the robot system are enhanced, which is beneficial for the robot to better balance the relationship between the computational amount and the working efficiency, greatly reduces the maintenance cost and usage cost of the robot system, enables the robot to work more safely and efficiently, and is beneficial for improving the robustness and service life of the robot.

Description

Technical Field

[0001] The present invention generally relates to the field of robotics, and more particularly to a method for dynamically adjusting obstacle avoidance sensitivity of a robot and a robot. Background Art

[0002] With the development of robotics, robots are widely used in various fields, providing convenience for people's work and life. The working environment of robots is complex, and obstacle avoidance performance is crucial for robots.

[0003] Existing robots usually use various sensors to detect obstacles. Regardless of whether the surrounding environment is crowded, they often use the same obstacle avoidance sensitivity and cannot be adjusted according to the actual situation. As a result, when the robot requires a lower obstacle avoidance sensitivity, it wastes storage and computing resources, affecting work efficiency; when a higher obstacle avoidance sensitivity is required, collisions are likely to occur, endangering safety.

[0004] The content of the background art section is only the technology known to the inventor and does not necessarily represent the prior art in this field. Summary of the Invention

[0005] In view of one or more of the problems existing in the prior art, the present invention provides a method for dynamically adjusting obstacle avoidance sensitivity of a robot, the method comprising:

[0006] Obtaining a target movement path of the robot in a grid map;

[0007] Selecting a plurality of positions on the target movement path;

[0008] Determining the distances between the robot and obstacles at the plurality of positions;

[0009] Adjusting the obstacle avoidance sensitivity of the robot based on the distances; and

[0010] Controlling the robot to perform obstacle avoidance operations based on the adjusted obstacle avoidance sensitivity.

[0011] According to one aspect of the present invention, the step of obtaining the target movement path of the robot in the grid map includes: determining the current position and the target position of the robot in the grid map, and obtaining the target movement path based on the current position and the target position.

[0012] According to one aspect of the present invention, the step of determining the distances between the robot and obstacles at the plurality of positions includes: controlling the robot to measure the distances to obstacles at the plurality of positions.

[0013] According to one aspect of the present invention, the step of adjusting the obstacle avoidance sensitivity of the robot based on the distance includes: determining the smoothness level of the target movement path based on the magnitude relationship between the distance and a threshold value, and adjusting the obstacle avoidance sensitivity of the robot according to the smoothness level of the target movement path.

[0014] According to one aspect of the present invention, the step of determining the smoothness level of the target movement path based on the magnitude relationship between the distance and a threshold value includes: determining the average value and the minimum value of the distance, and determining the smoothness level of the target movement path based on the magnitude relationship between the average value and the minimum value and the threshold value.

[0015] According to one aspect of the present invention, the threshold value includes a first threshold value and a second threshold value; the smoothness level includes a high level, a medium level, and a low level.

[0016] According to one aspect of the present invention, the obstacle avoidance sensitivity includes a first sensitivity, a second sensitivity, and a third sensitivity, and the first sensitivity < the second sensitivity < the third sensitivity.

[0017] According to one aspect of the present invention, the step of determining the smoothness level of the target movement path based on the magnitude relationship between the average value and the minimum value and the threshold value includes: when the average value is greater than the first threshold value and the minimum value is greater than the second threshold value, determining that the smoothness level of the target movement path is a high level;

[0018] The step of adjusting the obstacle avoidance sensitivity of the robot according to the smoothness level of the target movement path includes: when it is determined that the smoothness level of the target movement path is a high level, adjusting the current obstacle avoidance sensitivity of the robot to the first sensitivity.

[0019] According to one aspect of the present invention, the step of determining the smoothness level of the target movement path based on the magnitude relationship between the average value and the minimum value and the threshold value further includes: when the average value is greater than the first threshold value and the minimum value is less than the second threshold value, determining that the smoothness level of the target movement path is a medium level;

[0020] The step of adjusting the obstacle avoidance sensitivity of the robot according to the smoothness level of the target movement path includes: when it is determined that the smoothness level of the target movement path is a medium level, adjusting the current obstacle avoidance sensitivity of the robot to the second sensitivity.

[0021] According to one aspect of the present invention, the step of determining the smoothness level of the target movement path based on the magnitude relationship between the average value and the minimum value and the threshold value further includes: when the average value is less than the first threshold value and the minimum value is less than the second threshold value, determining that the smoothness level of the target movement path is a low level;

[0022] The step of adjusting the obstacle avoidance sensitivity of the robot according to the smoothness level of the target movement path includes: when it is determined that the smoothness level of the target movement path is a low level, adjusting the current obstacle avoidance sensitivity of the robot to a third sensitivity.

[0023] According to one aspect of the present invention, wherein the obstacle avoidance sensitivity is the grid map resolution, the step of adjusting the obstacle avoidance sensitivity of the robot according to the smoothness level of the target movement path further includes: updating the grid state of the grid map, and the grid state includes two states of occupied and free.

[0024] According to one aspect of the present invention, the step of controlling the robot to perform obstacle avoidance operations based on the adjusted obstacle avoidance sensitivity includes: controlling the robot to bypass the obstacle with a certain movement step size, and the certain movement step size is the same as the size of the adjusted grid size.

[0025] The present invention also provides a robot, including:

[0026] A housing;

[0027] A mobile chassis having a walking mechanism;

[0028] A sensor installed on the robot and configured to detect the surrounding environment of the robot;

[0029] A controller coupled to the walking mechanism and the sensor and configured to execute the method as described above.

[0030] According to one aspect of the present invention, the sensor includes one or more of a lidar, a binocular vision camera, an odometer, a stereo vision sensor, and an infrared sensor.

[0031] The present invention also provides a computer-readable storage medium, including computer-executable instructions stored thereon and a grid map, and the executable instructions implement the method as described above when executed by a processor.

[0032] Adopting the technical solution of the present invention, compared with the single obstacle avoidance sensitivity in the prior art, the adaptive ability of the robot is greatly improved, the stability and flexibility of the robot system are enhanced, which is beneficial for the robot to better balance the relationship between the calculation amount and the working efficiency, greatly reduces the maintenance cost and use cost of the robot system, enables the robot to work more safely and efficiently, and is beneficial to improving the robustness and service life of the robot. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification, and are used to explain the present invention together with the embodiments of the present invention, and do not constitute a limitation to the present invention. In the drawings:

[0034] Figure 1 Shows a flowchart of a method for dynamically adjusting obstacle avoidance sensitivity of a robot according to an embodiment of the present invention;

[0035] Figure 2A Shows a schematic diagram for determining the level of unobstructedness of a target movement path according to a preferred embodiment of the present invention;

[0036] Figure 2B Shows Figure 2A An enlarged view of the area around the midpoint A;

[0037] Figure 2C Shows a schematic diagram for determining the level of unobstructedness of a target movement path according to a preferred embodiment of the present invention;

[0038] Figure 3 Shows a schematic diagram of a first sensitivity according to a preferred embodiment of the present invention;

[0039] Figure 4 Shows a schematic diagram of a second sensitivity according to a preferred embodiment of the present invention;

[0040] Figure 5 Shows a schematic diagram of a third sensitivity according to a preferred embodiment of the present invention;

[0041] Figure 6 Shows a schematic diagram for adjusting obstacle avoidance sensitivity according to another preferred embodiment of the present invention; and

[0042] Figure 7 Shows a schematic diagram of a robot according to an embodiment of the present invention. Detailed Description of the Invention

[0043] In the following, only some exemplary embodiments are briefly described. As those skilled in the art can recognize, the described embodiments can be modified in various different ways without departing from the spirit or scope of the present invention. Therefore, the drawings and the description are considered to be exemplary in nature and not restrictive.

[0044] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation to the present invention. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the described features. In the description of the present invention, "a plurality" means two or more unless otherwise specifically defined.

[0045] In the description of the present invention, it should be noted that unless otherwise clearly specified and limited, the terms "mounted", "connected" and "coupled" shall be construed in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection: it may be a mechanical connection, an electrical connection or a connection capable of mutual communication; it may be directly connected, or indirectly connected through an intermediate medium, and it may be the internal communication of two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0046] In the present invention, unless otherwise clearly specified and limited, the first feature being "on" or "under" the second feature may include the direct contact between the first and second features, or may include the situation where the first and second features are not in direct contact but in contact through other features therebetween. Moreover, the first feature being "above", "over" and "on top of" the second feature includes that the first feature is directly above and obliquely above the second feature, or merely means that the horizontal height of the first feature is higher than that of the second feature. The first feature being "under", "beneath" and "underneath" the second feature includes that the first feature is directly below and obliquely below the second feature, or merely means that the horizontal height of the first feature is lower than that of the second feature.

[0047] The following disclosure provides many different embodiments or examples for implementing different structures of the present invention. To simplify the disclosure of the present invention, the components and settings of specific examples are described below. Of course, they are only examples and are not intended to limit the present invention. In addition, the present invention may repeat reference numerals and / or reference letters in different examples. Such repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed. In addition, the present invention provides examples of various specific processes and materials, but those of ordinary skill in the art can be aware of the application of other processes and / or the use of other materials.

[0048] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only for the purpose of illustrating and explaining the present invention, and are not used to limit the present invention.

[0049] The present invention provides a method. By using this method, a robot can dynamically adjust the obstacle avoidance sensitivity according to the actual situation of the surrounding environment. The following will specifically describe it with reference to the accompanying drawings.

[0050] Figure 1 The flowchart of a method 100 for a robot to dynamically adjust the obstacle avoidance sensitivity according to an embodiment of the present invention is shown. As Figure 1 shown, the method 100 includes steps S101 - S105. The following will specifically describe each step of the method 100 with reference to the accompanying drawings.

[0051] In step S101, obtain the target movement path of the robot in the grid map.

[0052] Among them, the grid map is a map formed by the robot's mapping of its surrounding environment. Specifically, the robot is configured with a collection sensor and a modeling processor. The modeling processor models the environmental data collected by the collection sensor to construct an environmental map. In this embodiment, the collection sensors include lidar, binocular vision sensors, ultrasonic sensors, and infrared sensors. The working area data where the robot is located is collected by the lidar, binocular vision sensors, ultrasonic sensors, and infrared sensors. The modeling processor uses the data collected by these sensors to create a map. During the process of creating the map, different map layers are generated by different sensors, such as static layers, dynamic obstacle layers, ultrasonic layers, vision layers, etc. By fusing these layers, a map for positioning and navigating the robot is obtained.

[0053] According to a preferred embodiment of the present invention, the step of obtaining the target movement path of the robot in the grid map includes: determining the current position and the target position of the robot in the grid map, and obtaining the target movement path based on the current position and the target position. The target position is the position set by the user or the position that the processing system of the robot determines to move to. Among them, the target position can be the position that needs to be moved to next determined during the movement process, or the position that the robot finally needs to reach. The current position is the real-time position information of the robot determined by the position sensor. The position of the obstacle can be determined through the grid map to better plan the target movement path.

[0054] Figure 2A FIG. shows a schematic diagram of determining the smoothness level of the target movement path according to a preferred embodiment of the present invention. As Figure 2A shown, P1 represents the current position, P2 represents the target position, and L represents the target movement path. The grid map can be created by the robot through SLAM technology and stored in a storage medium. Moreover, according to the grid map, the movement paths of the robot from various starting points to various ending points can be planned and stored in the storage medium. After determining the current position P1 and the target position P2 of the robot, the optimal movement path (such as the shortest distance, etc.) corresponding to the current position P1 and the target position P2 can be obtained from the movement paths as the target movement path L. Of course, if the environment changes, appropriate adjustments need to be made based on the obtained movement path. It should be noted that the present invention does not limit the specific method of planning the movement path. The method can be, for example, the Dijikstra algorithm, the A* algorithm, the RRT algorithm, the ant colony algorithm, and the genetic algorithm, etc., which can be determined according to the actual situation.

[0055] In step S102, select multiple positions on the target movement path.

[0056] Continue to refer to Figure 2A , after obtaining the target movement path L, the robot can be controlled to move from the current position P1 along the target movement path L towards the target position P2. Select multiple positions on the target movement path L, where the multiple positions can refer to Figure 2AExemplarily shown points A, B, C, D, and E. It should be noted that the multiple positions may be multiple path points on the target movement path L. Regarding the specific number of the multiple positions, the present invention does not limit it. In practical applications, the specific number of the multiple positions can be appropriately increased or decreased according to the length of the target movement path L. Specifically, for example, when the length of the target movement path L is greater than the preset length L0, the number of the multiple positions can be more (for example, 10), and conversely, when the length of the target movement path L is not greater than the preset length L0, the number of the multiple positions can be less (for example, 4). In order to obtain more realistic data (such as smoothness) subsequently, the number of the multiple positions should be at least 3. In addition, the present invention does not limit the distance between adjacent positions among the multiple positions. The distance between adjacent positions can be either equal or different, and can be determined according to the actual situation specifically.

[0057] In step S103, determine the distances between the robot and the obstacles at the multiple positions.

[0058] It should be understood that during the process of the robot moving along the target movement path L towards the target position P2, the influence of a farther obstacle on the robot is smaller, and the influence of a nearer obstacle on the robot is greater. Therefore, in order to reduce the calculation amount and improve work efficiency, the farther obstacles can be ignored, and only the nearer obstacles need to be concerned. It should be noted that the farther or nearer refers to the obstacle relative to the multiple positions or the robot. The obstacle can be a static obstacle or a dynamic obstacle. Regarding the type of the obstacle, the present invention does not limit it. In some embodiments, when the obstacle is a dynamic obstacle, the specific number of the multiple positions can be determined according to the current speed of the robot and / or the obstacle. For example, when the speed of the robot and / or the obstacle is relatively large, the multiple positions can be appropriately encrypted, that is, the number of the multiple positions can be appropriately increased, and the distance between adjacent positions can be appropriately decreased; conversely, if the current speed of the robot and / or the obstacle is relatively small, the multiple positions can be appropriately thinned out, that is, the number of the multiple positions can be appropriately decreased, and the distance between adjacent positions can be appropriately increased. In some other embodiments, the number and spacing of the multiple positions can also be determined according to the relative speed between the robot and the dynamic obstacle to determine the smoothness level of the target movement path L (which will be described later). It should be noted that the multiple positions are actually multiple path points on the target movement path L.

[0059] According to a preferred embodiment of the present invention, the step of determining the distance between the robot and the obstacle at multiple positions includes: controlling the robot to measure the distance between the robot and the obstacle at multiple positions. According to an embodiment of the present invention, when detecting obstacles and calculating the obstacle distance, a certain distance threshold can be set; when the distance between the obstacle and the robot is lower than the distance threshold, the obstacle is included in the calculation; when the distance between the obstacle and the robot is greater than the distance threshold, the obstacle does not need to be considered. Figure 2A The circles with midpoints A, B, C, D, and E represent the distance thresholds.

[0060] Continue to refer Figure 2A For example, the robot measures the distance of the obstacle at point A and obtains multiple distances (reference Figure 2A d1, d2, d3, d4 and d5 are shown as examples, Figure 2B Schematically shows Figure 2A Enlarged view around midpoint A). It should be noted that the multiple distances may be the distances of different obstacles around the robot, or may be multiple distances of the same obstacle (for example, due to factors such as the irregular shape of the obstacle). The present invention does not limit the specific number and source of the multiple distances. The multiple distances can be measured by sensors installed on the robot. The sensors include but are not limited to laser radar, binocular vision camera, odometer, stereo vision sensor, infrared sensor, etc., and any one or more of them can be used for distance measurement. It should be understood that the detection range of each sensor is limited and there are certain blind spots. Therefore, in order to reduce the measurement blind spots, obtain more realistic and accurate measurement results, and improve measurement efficiency, when measuring the distance to the obstacle, it is preferred that multiple sensors located at different positions of the robot can be used for parallel measurement, and the data after the parallel measurement data is fused is used as the distance measurement result of the obstacle. The present invention does not limit the specific method of fusion.

[0061] The above embodiment takes point A as an example to describe the situation where the robot measures the distance to an obstacle at the multiple positions. The method of measuring the distance to an obstacle at other positions among the multiple positions (such as points B, C, D, E, etc.) is similar and will not be repeated here.

[0062] In step S104, the obstacle avoidance sensitivity of the robot is adjusted based on the distance.

[0063] According to a preferred embodiment of the present invention, step S104 includes: determining the level of patency of the target moving path L based on the relationship between the distance and the threshold, and adjusting the obstacle avoidance sensitivity of the robot according to the level of patency of the target moving path. The following first introduces the situation of determining the level of patency of the target moving path L based on the relationship between the distance and the threshold.

[0064] According to a preferred embodiment of the present invention, the average value D of the distances is determined ave and the minimum value D min , and based on the relationship between the average value D ave and the minimum value D min and a threshold value, the passability level of the target movement path L is determined. Wherein the threshold value includes a first threshold value D 1 and a second threshold value D 2 , and the passability level includes a high level, a medium level, and a low level. It should be noted that the determination of the average value D ave and the minimum value D min refers to: determining the average value D ave and the minimum value D min of the distances of the obstacles measured at multiple positions or one position of the robot on the target movement path L. Specifically, reference can be continued to Figure 2A or Figure 2B , for example, measuring the distance of the obstacle at point A to obtain multiple distances, such as d1, d2, d3, d4, and d5. The average value of the multiple distances can be calculated using the following formula:

[0065]

[0066] where d1, d2... dn represent the multiple distances, and n represents the number of the multiple distances.

[0067] When the average value D ave and the minimum value D min of the multiple distances are determined, the average value D ave and the minimum value D min can be respectively compared with the first threshold value D 1 and the second threshold value D 2 , and the passability level (the passability level at point A) of the target movement path L is determined according to the comparison result.

[0068] According to a preferred embodiment of the present invention, when the average value D ave is greater than the first threshold value D 1 , and the minimum value D min is greater than the second threshold value D 2 , the passability level of the target movement path L is determined to be a high level. When the average value D ave is greater than the first threshold value D 1 , and the minimum value D min is less than the second threshold value D 2 , the passability level of the target movement path L is determined to be a medium level. When the average value D aveLess than the first threshold D 1 , and the minimum value D min is less than the second threshold D 2 , determine that the passability level of the target movement path L is a low level. It should be understood that the higher the passability level, the farther the obstacle is, and the smoother the target movement path L is. The above embodiments describe the situation of determining the passability level of the local target movement path L, that is, determining the part of the target movement path L that the robot will walk in the current preset range or near the robot and in the future (reference can be made to Figure 2A or Figure 2B the part of the path circled by the dashed rectangle in), hereinafter simply referred to as the target movement path L (part).

[0069] It should be understood that the method of determining the passability level of the target movement path L (part) is not limited to this, and other methods can also be adopted. For example, a preset range (such as a circle, a sector, a rectangle or other shapes) can be delimited with one of the multiple positions as the center. If the obstacle is completely within the preset range, determine that the passability level of the target movement path L (part) is a low level; if the obstacle is completely not within the preset range, determine that the passability level of the target movement path L (part) is a high level; if the obstacle is partially within the preset range and partially outside the preset range, determine that the passability level of the target movement path L (part) is a medium level.

[0070] In addition, the passability level of the entire target movement path L can also be determined, which will be specifically described next.

[0071] Figure 2C shows a schematic diagram of determining the passability level of the target movement path according to a preferred embodiment of the present invention. As Figure 2C shown, there are multiple positions (such as points A, B, C, D, E) on the target movement path L. The distances to the obstacles closest to the multiple positions (such as points A, B, C, D, E) are respectively determined (the distances can be determined by the coordinates between these points on the map and the closest obstacles around them), referring to Figure 2B the exemplary D A , D B , D C , D D and D E , calculate the average value D ave ’ and the minimum value D min ’ of these closest distances, and compare the size relationship between the average value D ave ’ and the first threshold D 1 , compare the size relationship between the minimum value D min ’ and the second threshold D 2Based on the relationship, the smoothness level of the entire target movement path L can be determined through the size relationship. Specifically, when the average value D ave ’ is greater than the first threshold D 1 , and the minimum value D min ’ is greater than the second threshold D 2 , it is determined that the smoothness level of the target movement path L is a high level. When the average value D ave ’ is greater than the first threshold D 1 , and the minimum value D min ’ is less than the second threshold D 2 , it is determined that the smoothness level of the target movement path L is a medium level. When the average value D ave ’ is less than the first threshold D 1 , and the minimum value D min ’ is less than the second threshold D 2 , it is determined that the smoothness level of the target movement path L is a low level. It should be understood that the higher the smoothness level, the farther the obstacle is, and the smoother the entire target movement path L is.

[0072] In the embodiment of FIG. 2c, the robot does not measure the distance to the obstacle when reaching each point, but after path planning and before driving into these points, first determines the distance to the closest obstacle at points A, B, C, D, and E, and then determines the smoothness level of the entire path.

[0073] It should be understood that the method for determining the smoothness level of the target movement path L (in whole or in part) is not limited to this, and other methods can also be adopted. For example, a preset range (such as a circle, rectangle, or other shape) can be delimited with the midpoint of the multiple positions as the center, and the number of obstacles within the preset range (such as by image recognition or other methods) can be determined. If the number of obstacles is greater than the threshold, it is determined that the smoothness level of the target movement path L (in whole or in part) is a low level; if the number of obstacles is greater than 50% of the threshold and less than the threshold, it is determined that the smoothness level of the target movement path L (in whole or in part) is a medium level; if the number of obstacles is less than 50% of the threshold, it is determined that the smoothness level of the target movement path L (in whole or in part) is a high level. It should be understood that the specific magnitudes of the above thresholds and the percentages are only for illustration and depend on the actual situation.

[0074] The above embodiments describe the situation of determining the smoothness level of the target movement path L (in part or in whole) based on the relationship between distance and threshold. After determining the smoothness level of the target movement path L (in part or in whole), the obstacle avoidance sensitivity of the robot can be adjusted according to the smoothness level of the target movement path L (in part or in whole), which will be specifically described next.

[0075] According to a preferred embodiment of the present invention, the obstacle avoidance sensitivity includes a first sensitivity, a second sensitivity, and a third sensitivity, where the first sensitivity < the second sensitivity < the third sensitivity. The obstacle avoidance sensitivity refers to the moving step length of the robot, and the moving step length is equal to the grid size of the grid map. Therefore, the obstacle avoidance sensitivity can be characterized by the grid size, and the obstacle avoidance sensitivity is negatively correlated with the grid size, that is, the larger the grid, the lower the obstacle avoidance sensitivity; the smaller the grid, the higher the obstacle avoidance sensitivity. It should be understood that the obstacle avoidance sensitivity has a significant impact on the safety, computational complexity, and working efficiency of the robot. In order for the robot to work more safely and efficiently, the obstacle avoidance sensitivity can be adaptively adjusted dynamically according to the general level. It should be noted that adjusting the obstacle avoidance sensitivity is actually adjusting the moving step length of the robot. Since the moving step length is equal to the grid size, the obstacle avoidance sensitivity can be adjusted by adjusting the grid size. Next, continue the description.

[0076] Figure 3 FIG. shows a schematic diagram of the first sensitivity according to a preferred embodiment of the present invention. As Figure 3 shown, the grid corresponding to the first sensitivity is larger (for example, the side length of the grid can be 5 cm). When it is determined that the smoothness level of the target moving path L (in whole or in part) is a high level, it indicates that the road conditions in front of the robot are relatively smooth and there is almost no collision risk. The current obstacle avoidance sensitivity of the robot can be adjusted to the first sensitivity to reduce the storage and computational complexity, which is beneficial to improving the working efficiency of the robot.

[0077] Figure 4 FIG. shows a schematic diagram of the second sensitivity according to a preferred embodiment of the present invention. As Figure 4 shown, the grid size corresponding to the second sensitivity is moderate (for example, the side length of the grid can be 3 cm). When it is determined that the smoothness level of the target moving path L (in whole or in part) is a medium level, it indicates that the road conditions in front of the robot are somewhat blocked and there is a certain collision risk. The current obstacle avoidance sensitivity of the robot can be adjusted to the second sensitivity to facilitate the accuracy of the robot's calculation of the grid occupied by the obstacle, so that the robot can reduce the moving step length and reduce the collision risk.

[0078] Figure 5 FIG. shows a schematic diagram of the third sensitivity according to a preferred embodiment of the present invention. As Figure 5 shown, the grid corresponding to the third sensitivity is smaller (for example, the side length of the grid can be 1 cm). When it is determined that the smoothness level of the target moving path L (in whole or in part) is a low level, it indicates that the road conditions in front of the robot are relatively blocked. The current obstacle avoidance sensitivity of the robot can be adjusted to the third sensitivity to facilitate the robot's refined calculation, further improve the accuracy of the grid occupied by the obstacle, and further reduce the moving step length and reduce the collision risk.

[0079] It should be noted that Figure 3 , Figure 4 and Figure 5 the different sensitivities shown are for the same area. The default obstacle avoidance sensitivity of the robot is the second sensitivity. According to a preferred embodiment of the present invention, when the robot walks out of a preset range, the current obstacle avoidance sensitivity can be restored and adjusted to the second sensitivity to obtain a balance between the computational complexity and efficiency. It should be understood that the number of grids occupied by the obstacle and the grid size greatly affect the computational complexity and efficiency when updating the map, and also affect the walking accuracy of the robot. For example, when the side length of the grid is 5 cm, a robot with a diameter of 50 cm has a much greater chance of getting stuck when passing through a narrow passage about 60 cm wide than when the side length of the grid is 1 cm, and it is also easy to damage the robot equipment. Therefore, dynamically feedback-adjusting the obstacle avoidance sensitivity of the robot based on the distance between the robot and the obstacle can better balance the relationship between the computational complexity, work efficiency, and walking accuracy, which is beneficial to improving the robustness of the robot. According to a preferred embodiment of the present invention, when the obstacle avoidance sensitivity needs to be adjusted, the sensitivity can be adjusted only within the current preset range or near the preset range to reduce the computational amount and improve the work efficiency. Of course, it can also be adjusted entirely, depending on the specific situation.

[0080] According to a preferred embodiment of the present invention, the step S104 further includes: updating the grid state of the grid map, and the grid state includes two states: occupied and free.

[0081] Continuing to refer to Figures 3 to 5 , in the grid map, the working area of the robot (such as a restaurant) is divided into several grids, and each grid includes at least two states: free and occupied. The free state is represented by a white grid, and the occupied state is represented by a black grid. And each state has a corresponding state value. For example, the state value of free is 0, and the state value of occupied is 1. It should be understood that the black grid can represent the area occupied by the obstacle, and the white grid can represent the area where the robot can walk freely. When the obstacle avoidance sensitivity is adjusted, the color and state of the grid should be updated adaptively. That is to say, for the same obstacle, the grid that may have been occupied originally may become free after the sensitivity is adjusted. Of course, it is also possible that the grid that was originally free may become occupied after the sensitivity is adjusted, which is dynamically updated according to the detection results of the robot sensor.

[0082] The above embodiments are introduced by taking three obstacle avoidance sensitivities as examples. It should be understood that the present invention is not limited to the above three obstacle avoidance sensitivities. In practical applications, more obstacle avoidance sensitivities can be designed to meet various obstacle avoidance requirements.

[0083] Figure 6FIG. shows a schematic diagram of adjusting obstacle avoidance sensitivity according to another preferred embodiment of the present invention. As Figure 6 shown, L1 and L2 represent obstacles, L3 represents a moving path, and Q1, Q2, and Q3 exemplarily represent multiple positions (path points) on the moving path L3. Similar to the method described in the previous embodiment, the passability level of the moving path L3 can be determined based on the magnitude relationship between the distance between the robot and the obstacle and the threshold, which will not be elaborated here. After determination, the passability level near Q1 is a low level, the passability level near Q2 is a medium level, and the passability level near Q3 is a high level. Therefore, based on the magnitude relationship between the distance between the obstacle and the threshold, when the robot is at Q1, the obstacle avoidance sensitivity can be feedback-adjusted to the third sensitivity; when the robot is at Q2, the obstacle avoidance sensitivity can be feedback-adjusted to the second sensitivity; when the robot is at Q3, the obstacle avoidance sensitivity can be feedback-adjusted to the first sensitivity. And, the grid state is updated according to the detection result of the sensor. Thus, it can be seen that this way of feedback dynamic adjustment of obstacle avoidance sensitivity is very suitable for the scenario when the robot works in narrow and long areas with different widths (such as long corridors, etc.). Of course, it is also applicable when the robot is in other scenarios.

[0084] In step S105, control the robot to perform an obstacle avoidance operation based on the adjusted obstacle avoidance sensitivity.

[0085] Control the robot to bypass the obstacle with a certain moving step length, and the certain moving step length is the same as the size of the adjusted grid size. It should be understood that the obstacle avoidance operation is not limited to bypassing the obstacle, and the type of the obstacle can be a static obstacle or a dynamic obstacle. Preferably, if the obstacle is a static obstacle, the robot can bypass the obstacle with the certain step length, and if the obstacle is a dynamic obstacle, the robot can take measures such as decelerating or first moving to a position opposite to the moving direction of the obstacle based on the detection result of the sensor to prevent collision with the obstacle. Optionally, the position can be determined by an odometer.

[0086] The method 100 is specifically introduced above. The method provides multiple obstacle avoidance sensitivities for the robot to choose from. The robot can determine the passability level of the moving path based on the relationship between the distance between the obstacle and the threshold, and can feedback and dynamically adjust the appropriate obstacle avoidance sensitivity according to the passability level. It should be noted that each step can be performed in the order shown in the flowchart when running, or multiple steps can be performed simultaneously according to the actual situation, which is not limited here. In addition, the present invention does not limit the working environment of the robot, and the robot can work in various scenarios including but not limited to shopping malls, restaurants, libraries, office buildings, warehouses, and homes, etc.

[0087] Adopting the technical solution of the present invention, compared with the single obstacle avoidance sensitivity in the prior art, the adaptive ability of the robot is greatly improved, the stability and flexibility of the robot system are enhanced, which is conducive to the robot better balancing the relationship between the computing amount and the working efficiency, and reducing the maintenance cost and usage cost of the robot system, enabling the robot to work more safely and efficiently, which is conducive to improving the robustness of the robot and extending its service life.

[0088] The present invention also provides a robot 200, Figure 7 which shows a schematic diagram of a robot according to an embodiment of the present invention. As Figure 7 shown, the robot 200 includes:

[0089] A mobile chassis 10, having a walking mechanism;

[0090] A housing 20;

[0091] A sensor, installed on the robot 200, configured to detect the surrounding environment of the robot 200;

[0092] A controller, coupled to the walking mechanism and the sensor, configured to execute the method 100 as described above.

[0093] According to a preferred embodiment of the present invention, the sensor includes one or more of a lidar 30, a binocular vision camera, an odometer, a stereo vision sensor, and an infrared sensor.

[0094] According to a preferred embodiment of the present invention, the lidar 30 can be disposed at the slit of the housing 20, so that the lidar 30 can easily emit laser signals to detect the surrounding environment.

[0095] The lidar 30 can be a multi-line lidar or a single-line lidar. In practical applications, it can be selected according to specific circumstances. When the lidar 30 is a multi-line lidar, the lidar 30 includes a photoelectric receiving array and a laser emitting unit array. Thus, when the lidar 30 rotates along a set plane, the photoelectric receiving array can form a scanning cylinder, thereby increasing the scanning area, facilitating the identification of the morphological details of obstacles, and reducing the occurrence of collisions. When the lidar 30 is a single-line lidar, the lidar 30 only includes a single photoelectric receiving unit and a single laser emitting unit. After the lidar 30 rotates along the set plane, it can only measure the morphological information of an object in one circumference and cannot obtain the morphology of complex objects in a timely manner, which is prone to collisions and endangers personal and property safety. Therefore, it can be combined with other sensors such as a binocular vision camera, an odometer, a stereo vision sensor, and an infrared sensor to detect the surrounding environment. It should be noted that the above set plane can be a horizontal plane to facilitate the robot to detect objects during movement. Of course, other set planes such as a vertical plane can also be selected according to requirements, and the present invention does not limit this.

[0096] According to a preferred embodiment of the present invention, at least one turn signal unit 110 is provided at the bottom of the mobile chassis 10, and each turn signal unit 110 includes at least one turn signal 111; at least two sets of drive wheels 120 are provided in the traveling mechanism, and each set of drive wheels 120 is located on one side of the mobile chassis 10 respectively; the component controller controls the traveling speed of the drive wheels 120; and controls the turn signals 111 in the turn signal unit 110 to be lit in a preset manner when the robot turns to remind pedestrians to pay attention.

[0097] Among the drive wheels 120, at least one set of drive wheels 120 is used as the left drive wheel, and at the same time, at least one set of drive wheels 120 is used as the right drive wheel. The left drive wheel and the right drive wheel are located on opposite sides of the mobile chassis 10. Optionally, the traveling mechanism may further include at least two sets of driven wheels, and one set of drive wheels corresponds to one set of driven wheels. Among them, at least one set of driven wheels is used as the left driven wheel, and at the same time, at least one set of driven wheels is used as the right driven wheel. The left driven wheel and the right driven wheel are used to assist the left drive wheel and the right drive wheel to drive the housing 20 and the mobile chassis 10 of the robot to move, so as to reduce the load pressure on the drive wheels 120.

[0098] On the basis of the above technical solution, optionally, when the speed difference between the drive wheels 120 on both sides of the mobile chassis 10 is greater than a preset value, the component controller controls the turn signals 111 in the turn signal unit 110 to be lit in a preset manner.

[0099] Optionally, the robot 200 further includes a voice module, which is electrically connected to the component controller; when the robot turns, the component controller controls the voice module to send out voice prompt information to alert pedestrians or other robots.

[0100] The above describes the robot 200. In addition, the present invention also provides a computer-readable storage medium, including computer-executable instructions stored thereon and a grid map, and the executable instructions, when executed by a processor, implement the method 100 as described above. The storage medium includes, but is not limited to, floppy disks, optical disks, DVDs, hard disks, flash memories, USB flash drives, CF cards, SD cards, MMC cards, SM cards, Memory Sticks, xD cards, etc. Popular storage media are based on flash memory (Nand flash), such as USB flash drives, CF cards, SD cards, SDHC cards, MMC cards, SM cards, Memory Sticks, xD cards, etc.

[0101] Finally, it should be noted that the above are only the preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for dynamically adjusting the obstacle avoidance sensitivity of a robot, the method comprises: Obtaining the target movement path of the robot in the grid map; Selecting multiple positions on the target movement path; Determining the distances between the robot and obstacles at the multiple positions; Adjusting the obstacle avoidance sensitivity of the robot based on the distances; and Controlling the robot to perform obstacle avoidance operations based on the adjusted obstacle avoidance sensitivity; Wherein the step of adjusting the obstacle avoidance sensitivity of the robot based on the distances comprises: determining the smoothness level of the target movement path based on the magnitude relationship between the distances and a threshold, and adjusting the obstacle avoidance sensitivity of the robot according to the smoothness level of the target movement path; Wherein the step of determining the smoothness level of the target movement path based on the magnitude relationship between the distances and the threshold comprises: determining the average value and the minimum value of the distances, and determining the smoothness level of the target movement path based on the magnitude relationship between the average value and the minimum value and the threshold.

2. The method according to claim 1, wherein the step of obtaining the target movement path of the robot in the grid map comprises: Determining the current position and the target position of the robot in the grid map, and obtaining the target movement path based on the current position and the target position.

3. The method according to claim 1, wherein the step of determining the distances between the robot and obstacles at multiple positions comprises: Measuring the distances of the obstacles at the multiple positions.

4. The method according to any one of claims 1-3, wherein the threshold comprises a first threshold and a second threshold; the smoothness level comprises a high level, a medium level and a low level.

5. The method according to any one of claims 1-3, wherein the obstacle avoidance sensitivity comprises a first sensitivity, a second sensitivity and a third sensitivity, and the first sensitivity < the second sensitivity < the third sensitivity.

6. The method according to any one of claims 1-3, the step of determining the smoothness level of the target movement path based on the magnitude relationship between the average value and the minimum value and the threshold comprises: When the average value is greater than the first threshold and the minimum value is greater than the second threshold, determining that the smoothness level of the target movement path is a high level; The step of adjusting the obstacle avoidance sensitivity of the robot according to the smoothness level of the target movement path comprises: when determining that the smoothness level of the target movement path is a high level, adjusting the current obstacle avoidance sensitivity of the robot to the first sensitivity.

7. The method according to any one of claims 1-3, the step of determining the smoothness level of the target movement path based on the magnitude relationship between the average value and the minimum value and the threshold further comprises: When the average value is greater than the first threshold and the minimum value is less than the second threshold, determining that the smoothness level of the target movement path is a medium level; The step of adjusting the obstacle avoidance sensitivity of the robot according to the smoothness level of the target movement path comprises: when determining that the smoothness level of the target movement path is a medium level, adjusting the current obstacle avoidance sensitivity of the robot to the second sensitivity.

8. The method according to any one of claims 1-3, wherein the step of determining the passability level of the target movement path based on the magnitude relationship between the average value, the minimum value and the threshold further comprises: When the average value is less than the first threshold and the minimum value is less than the second threshold, determining that the passability level of the target movement path is a low level; The step of adjusting the obstacle avoidance sensitivity of the robot according to the passability level of the target movement path includes: when it is determined that the passability level of the target movement path is a low level, adjusting the current obstacle avoidance sensitivity of the robot to a third sensitivity.

9. The method according to any one of claims 1-3, wherein the obstacle avoidance sensitivity is the grid map resolution. The step of adjusting the obstacle avoidance sensitivity of the robot according to the passability level of the target movement path further comprises: Updating the grid state of the grid map, where the grid state includes two states: occupied and free.

10. The method according to claim 9, wherein the step of controlling the robot to perform obstacle avoidance operations based on the adjusted obstacle avoidance sensitivity comprises: Controlling the robot to bypass the obstacle with a certain movement step size, where the certain movement step size is the same as the size of the adjusted grid size.

11. A robot, comprising: A housing; A mobile chassis with a walking mechanism; A sensor installed on the robot and configured to detect the surrounding environment of the robot; A controller coupled to the walking mechanism and the sensor and configured to execute the method according to any one of claims 1-10.

12. The robot according to claim 11, wherein the sensor includes one or more of a lidar, a binocular vision camera, an odometer, a stereo vision sensor, and an infrared sensor.

13. A computer-readable storage medium, including computer-executable instructions stored thereon and a grid map, where the executable instructions, when executed by a processor, implement the method according to any one of claims 1-10.

Images