Walking control method of robot and robot

Abstract

The invention relates to the technical field of robots, in particular to a walking control method of a robot and the robot, and the walking control method comprises the steps of determining an easy-to-collide area, counting historical collision records of the robot walking in the easy-to-collide area, updating the walking speed of the robot in the easy-to-collide area according to the historical collision records, and updating the easy-to-collide area. On one hand, according to the embodiment, the next walking speed of the robot in the easy-to-collide area can be flexibly adjusted according to the collision condition when the robot walks in the easy-to-collide area, so that the risk that the robot collides with the obstacle can be reduced, the robot can be prevented from frequently colliding with the obstacle, and the cleaning smoothness and the cleaning effect are improved; and on the other hand, the change condition of the easy-to-collide area can be dynamically perceived, so that the phenomenon that the robot pauses due to the change of the easy-to-collide area when walking in the easy-to-collide area next time can be avoided, and then the walking smoothness of the robot can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of robots, and in particular to a walking control method of a robot and the robot. Background Art

[0002] When cleaning complex home environments, existing robots usually rely on sensors to detect obstacles in front of the robot in real time, and when an obstacle is detected, the robot slows down and circumvents the obstacle to avoid collision with the obstacle. However, due to the detection frequency of the sensor, the robot detects the obstacle area only when it is very close to the obstacle. If the robot speed has not been switched, or the robot fails to avoid the obstacle in time after slowing down, it is easy to collide with the obstacle. Especially in an environment with many obstacles, the robot is prone to frequent speed switching and frequent collisions with obstacles. Or, due to the detection angle of the sensor, the robot is prone to frequent collisions with undetectable obstacles. When the robot frequently collides with obstacles, it will not only cause damage to the robot, but also affect the cleaning efficiency. Summary of the invention

[0003] An object of the present invention is to provide a walking control method of a robot and a robot, so as to solve the technical problem of frequent collisions between the robot and obstacles in the related art.

[0004] In a first aspect, an embodiment of the present invention provides a walking control method of a robot, comprising:

[0005] Identify collision-prone areas;

[0006] Collecting historical collision records of the robot while walking in the collision-prone area;

[0007] Update the walking speed of the robot in the collision-prone area according to the historical collision record;

[0008] The collision-prone area is updated.

[0009] Optionally, updating the walking speed of the robot in the collision-prone area according to the historical collision record includes:

[0010] Determining a speed level of the collision-prone area according to the historical collision record;

[0011] The walking speed of the robot in the collision-prone area is updated according to the speed level.

[0012] Optionally, after updating the walking speed of the robot in the collision-prone area according to the speed level, the method further includes:

[0013] Determining whether the robot enters the collision-prone area;

[0014] If the robot enters the easy-collision area, the robot is controlled to walk in the easy-collision area at the updated walking speed.

[0015] Optionally, the historical collision record includes the number of historical collisions, and determining the speed level of the collision-prone area according to the historical collision record includes:

[0016] The speed grade of the collision-prone area is determined according to the number of historical collisions, wherein the historical collision records are negatively correlated with the speed of the speed grade.

[0017] Optionally, the historical collision record further includes a historical passing event sequence, and the statistical historical collision record of the robot walking in the collision-prone area includes:

[0018] When the robot passes through the easy-collision area, a current passing event is recorded, where the current passing event is an event that occurs when the robot currently passes through the easy-collision area;

[0019] According to the current passing event and the historical passing event sequence, historical collision records of the robot walking in the collision-prone area are counted.

[0020] Optionally, the counting of historical collision records of the robot walking in the collision-prone area according to the current passing event and the historical passing event sequence includes:

[0021] Updating the historical passing event sequence according to the current passing event;

[0022] Determining an event type of the current passing event;

[0023] Determining a target historical passing event from the updated historical passing event sequence according to the event type;

[0024] Update the historical collision count according to the target historical passing events;

[0025] According to the updated historical event sequence and the historical collision times, historical collision records of the robot walking in the collision-prone area are counted.

[0026] Optionally, the event type includes a collision event, and determining the target historical passing event from the updated historical passing event sequence according to the event type includes:

[0027] If the event type is the collision event, determining the most recent first preset number of the historical passing events in the updated historical passing event sequence as the target historical passing events;

[0028] Then, updating the historical collision number according to the target historical passing event includes:

[0029] Determine the first number of the first preset number of historical passing events whose event type is a collision event;

[0030] The historical number of collisions is updated according to the first number.

[0031] Optionally, updating the historical collision count according to the first number includes:

[0032] Determining whether the first number is equal to the first preset number;

[0033] If it is equal to the first preset number, updating the historical collision number according to the sum of the historical collision number and the first preset number, where the first preset number is a natural number greater than or equal to 1;

[0034] If it is not equal to the first preset number, the historical number of collisions is maintained unchanged.

[0035] Optionally, the event type includes a non-collision event, and determining a target historical passing event from the updated historical passing event sequence according to the event type includes:

[0036] If the event type is the non-collision event, determining the most recent second preset number of historical passing events in the updated historical passing event sequence as the target historical passing event;

[0037] Then, updating the historical collision number according to the target historical passing event includes:

[0038] Determine a second number of the second preset number of historical passing events whose event type is non-collision events;

[0039] The historical number of collisions is updated according to the second number.

[0040] Optionally, updating the historical number of collisions according to the second number includes:

[0041] Determining whether the second number is equal to the second preset number;

[0042] If it is equal to the second preset number, the historical collision number is updated according to the difference between the historical collision number and the first preset number, where the first preset number is a natural number greater than or equal to 1.

[0043] If it is not equal to the second preset number, the historical number of collisions is maintained unchanged.

[0044] Optionally, determining the collision-prone area includes:

[0045] Obtain target environment obstacle detection data;

[0046] Determining obstacle distribution information of the target environment according to the obstacle detection data;

[0047] Determining the number of obstacles in the target area according to the obstacle distribution information;

[0048] Determining whether the number of obstacles is greater than or equal to a preset number threshold;

[0049] If it is greater than or equal to the preset quantity threshold, the target area is determined to be a collision-prone area.

[0050] Optionally, after determining the collision-prone area, the method further includes:

[0051] Determining the area type of the collision-prone area;

[0052] Determining an initial collision record of the collision-prone area according to the area type;

[0053] The initial collision record is configured as a historical collision record of the robot walking in the collision-prone area.

[0054] In a second aspect, an embodiment of the present invention provides a robot, comprising a memory and a processor, wherein the memory is connected to the processor, and the processor is used to execute one or more computer programs stored in the memory, and when the processor executes the one or more computer programs, the robot implements the robot walking control method as described above.

[0055] Compared with the prior art, the embodiment of the present invention provides a walking control method of a robot and a robot, the walking control method comprising: determining a collision-prone area, counting historical collision records of the robot walking in the collision-prone area, updating the walking speed of the robot in the collision-prone area according to the historical collision records, and updating the collision-prone area. Therefore, on the one hand, the embodiment can flexibly adjust the walking speed of the robot in the collision-prone area next time according to the collision situation when walking in the collision-prone area, thereby reducing the risk of collision between the robot and obstacles, thereby avoiding frequent collisions between the robot and obstacles, and improving the cleaning fluency and cleaning effect. On the other hand, the embodiment can dynamically sense the changes in the collision-prone area, thereby avoiding the feeling of frustration caused by the changes in the collision-prone area when the robot walks in the collision-prone area next time, thereby improving the smoothness of the robot's walking. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0057] Figure 1 A schematic diagram of the structure of a robot provided by an embodiment of the present invention;

[0058] Figure 2 A schematic diagram of a flow chart of a robot walking control method provided by an embodiment of the present invention;

[0059] Figure 3 A schematic diagram of a collision-prone area provided by an embodiment of the present invention;

[0060] Figure 4 A schematic diagram of a collision scenario provided by an embodiment of the present invention;

[0061] Figure 5 A schematic diagram of a collision scenario provided by another embodiment of the present invention;

[0062] Figure 6 A schematic diagram of a risk map provided by an embodiment of the present invention;

[0063] Figure 7 A schematic diagram of the flow of S23 in a walking control method of a robot provided by an embodiment of the present invention;

[0064] Figure 8 A schematic diagram of the structure of a walking control device of a robot provided by an embodiment of the present invention;

[0065] Fig. 9 A schematic diagram of the structure of a first updating module in a walking control device of a robot provided by an embodiment of the present invention;

[0066] Fig.10 A schematic diagram of the structure of a statistical module in a walking control device of a robot provided by another embodiment of the present invention;

[0067] Fig.11 A schematic diagram of the structure of a first determination module in a walking control device of a robot provided by an embodiment of the present invention;

[0068] Fig.12 A schematic structural diagram of a walking control device for a robot provided by another embodiment of the present invention;

[0069] Fig.13 A schematic diagram of the hardware structure of a controller provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0070] In order to make the purpose, technical scheme and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0071] It should be noted that, if there is no conflict, the various features in the embodiments of the present invention can be combined with each other, all within the scope of protection of the present invention. In addition, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in a different order from the module division in the device or the flow chart. Furthermore, the words "first", "second", "third", etc. used in the present invention do not limit the data and execution order, but only distinguish the same items or similar items with basically the same functions and effects.

[0072] An embodiment of the present invention provides a robot, which may be a cleaning robot, a transport robot, a guiding robot, a food delivery robot, etc. The cleaning robot includes a sweeping robot, a floor washing robot, a mopping robot, a sweeping and mopping robot, a vacuuming robot, etc.

[0073] See also Figure 1 The robot 100 includes a controller 11, a driving component 12, a cleaning component 13, a wall detection sensor 14, a ground detection sensor 15, an inertial measurement unit 16, a laser radar 17 and a collision sensor 18.

[0074] The controller 11 serves as the control core of the robot 100 and is used to control the robot 100 to complete relevant logical operations and execute the walking control method of the robot as described below.

[0075] The drive assembly 12 is electrically connected to the controller 11. In the present embodiment, the drive assembly 12 is controlled by the controller 11 to drive the robot 100 forward or backward to complete cleaning operations or recharging operations, etc. In some embodiments, the drive assembly 12 includes a left-wheel drive unit and a right-wheel drive unit. Taking the left-wheel drive unit as an example, the left-wheel drive unit includes a motor, a wheel drive mechanism and a left wheel. The shaft of the motor is connected to the wheel drive mechanism, the left wheel is connected to the wheel drive mechanism, the motor is electrically connected to the controller 11, the motor receives the control command sent by the controller 11 and rotates its shaft, and transmits the torque to the left wheel through the wheel drive mechanism, thereby realizing the rotation of the left wheel. Therefore, with the cooperation of the left-wheel drive unit and the right-wheel drive unit, the robot 100 can be driven forward or backward.

[0076] The cleaning assembly 13 is electrically connected to the controller 11. In the present embodiment, the cleaning assembly 13 is used to clean the floor and can be configured into any suitable cleaning structure. For example, in some embodiments, the cleaning assembly 13 includes a cleaning motor and a roller brush. The surface of the roller brush is provided with a cleaning portion. The roller brush is connected to the cleaning motor through a driving mechanism. The cleaning motor is electrically connected to the controller 11. The controller 11 can send instructions to the cleaning motor to control the cleaning motor to drive the roller brush to rotate so that its cleaning portion can effectively clean the floor. In some embodiments, the cleaning assembly 13 also includes a dust box and a dust suction fan. The dust box is connected to the dust suction fan, and the dust suction fan is electrically connected to the controller 11. The dust suction fan receives the control instruction of the controller 11 and generates suction so as to suck the dust or garbage stirred up when the roller brush rotates into the dust box.

[0077] The wall detection sensor 14 is arranged on the side of the robot 100, and is used to detect the distance between the robot 100 and the wall. The wall detection sensor 14 is electrically connected to the controller 11, and can transmit the distance information to the controller 11, so as to ensure that the controller 11 can control the robot 100 to always walk along the edge of the wall, or control the robot 100 to always keep a certain distance from the wall during the process of cleaning the gaps along the wall, for example, 10 mm. In this way, the robot 100 can better clean the gaps along the wall and clean up the dust in the gaps along the wall.

[0078] The ground detection sensor 15 is arranged at the bottom of the robot 100. It is a very important sensor in the robot 100 and plays a very critical role in the navigation and obstacle avoidance functions of the robot 100. It is mainly used to detect obstacles and potholes on the ground by detecting the height between the robot 100 and the ground. The ground detection sensor 15 is electrically connected to the controller 11 and can transmit the height information to the controller 11 so that the controller 11 can control the robot 100 to avoid these obstacles or prevent the robot 100 from falling when encountering steps. For example, when the robot 100 moves to the edge of the step, if it is detected that the height between the robot 100 and the ground exceeds the preset height threshold, a signal is sent to the controller 11, and the controller 11 controls the robot 100 to turn and change the forward direction of the robot 100, thereby achieving the purpose of preventing falling.

[0079] The ground detection sensor 15 can be a sensor that adopts any suitable ranging method, such as infrared ranging or laser ranging, etc., wherein the ground detection sensor 15 that adopts infrared ranging is usually composed of a reflective infrared detector and an infrared LED lamp. The reflective infrared detector can detect the light emitted by the infrared LED. When the light is reflected by an obstacle on the ground, the reflective infrared detector will receive the reflected light signal, thereby detecting the height between the robot 100 and the ground; the ground detection sensor 15 that adopts laser ranging uses ultrasonic waves to measure the height between the robot 100 and the ground.

[0080] The inertial measurement unit 16 is electrically connected to the controller 11. Its main function in the robot 100 is to detect the motion change information of the robot 100 in real time, such as angular velocity, acceleration, orientation, etc., and after providing this information to the controller 11 for processing, the position and posture of the robot 100 can be solved, thereby realizing the positioning, obstacle avoidance, path planning, navigation, etc. of the robot 100. In some embodiments, the inertial measurement unit 16 includes a 3-axis accelerometer and a 3-axis gyroscope, and the 3-axis accelerometer and the 3-axis gyroscope are used to measure the acceleration and angular velocity of the robot 100 in three-dimensional space, respectively, so as to solve the position and posture of the robot 100. The inertial measurement unit 16 can also detect the tilt and sudden collision of the robot 100, so as to prevent the robot 100 from falling or other accidents.

[0081] The laser radar 17 is electrically connected to the controller 11. It can emit lasers to the surrounding environment and calculate the distance between the laser radar 17 and the object based on the time difference of the signal reflected from the object, and give the distance information to the controller 11 for processing, so as to ensure that the controller 11 controls the robot 100 to avoid the obstacle in time when it walks in front of the obstacle, so as to prevent the robot 100 from colliding with the obstacle. The laser radar 17 can also collect real-time environmental data of the robot 100's surrounding environment by continuous rotation and scanning, and transmit it to the controller 11. The controller 11 can perform environmental perception and positioning based on the real-time environmental data, and generate a map by processing the real-time environmental data through a map building algorithm, wherein the map building algorithm can be any type of algorithm such as SLAM (Simultaneous Localization and Mapping) algorithm. The controller 11 can also continuously obtain real-time environmental data from the laser radar 17 to continuously update and optimize the map, which is conducive to the robot 100 gradually learning and optimizing the cleaning path and improving the cleaning efficiency.

[0082] The collision sensor 18 is one of the most basic sensors in the robot 100. It can detect collisions when the robot 100 is moving and immediately stop the robot 100 to prevent the robot 100 from hitting furniture or other objects. The collision sensor 18 is usually located at the front end or side of the robot 100 and is triggered mechanically or electronically. When the robot 100 hits an object, the collision sensor 18 generates a collision signal and sends the collision signal to the controller 11 so that the controller 11 controls the robot 100 to stop or turn.

[0083] The map provided in this embodiment may be a grid map or other graphical map. When the map is a grid map, the map is composed of multiple grids. In order to reflect the distribution of objects in the environment, a corresponding occupancy probability value may be set for each grid. The occupancy probability value is the probability value of the area corresponding to the grid being occupied. The larger the occupancy probability value, the greater the probability that the area corresponding to the grid is occupied. The smaller the occupancy probability value, the smaller the probability that the area corresponding to the grid is occupied. Therefore, the occupancy probability value can reflect the state of the corresponding grid, and the state of the grid is used to represent the situation of the corresponding pixel in the environment. The state of a single grid may be one of the following: idle state, occupied state, and unknown state. Among them, the idle state is used to indicate that the corresponding pixel belongs to a pixel in an area without obstacles in the environment, the occupied state is used to indicate that the corresponding pixel belongs to a pixel in an area occupied by obstacles in the environment, and the unknown state is used to indicate that the corresponding pixel belongs to a pixel in an unknown area in the environment. For the convenience of description, the grid type corresponding to the idle state, the grid type corresponding to the occupied state, and the grid type corresponding to the unknown state can be determined as an idle grid, an occupied grid, and an unknown grid, respectively. In some embodiments, the occupancy probability value corresponding to the idle grid, the occupancy probability value corresponding to the occupied grid, and the occupancy probability value corresponding to the unknown grid are 0.49, 0.99, and 0, respectively.

[0084] See also Figure 2 , an embodiment of the present invention provides a walking control method of a robot, the walking control method comprising:

[0085] S21. Determine a collision-prone area.

[0086] In this step, the collision-prone area is an area where the robot is likely to collide with obstacles during walking. In some embodiments, the collision-prone area may include two types of areas: dense obstacle areas and recognition blind areas. The dense obstacle area is an area where obstacles are concentrated. Figure 3 , the obstacles can be tables, chairs, children's toys and other obstacles; the blind area is the area where the robot cannot be identified and has obstacles due to the limited detection angle of the robot, please refer to Figure 4 , such obstacles can be hollow obstacles such as sofas, beds, etc., please refer to Figure 5Such obstacles may also be low obstacles such as thresholds, and such obstacles may also be other obstacles, such as room corners, narrow corridors, etc.

[0087] In some embodiments, the controller can obtain obstacle detection data of the target environment, determine the obstacle distribution information of the target environment based on the obstacle detection data, determine the number of obstacles in the target area based on the obstacle distribution information, and determine whether the number of obstacles is greater than or equal to a preset number threshold. If it is greater than or equal to the preset number threshold, the target area is determined to be a collision-prone area.

[0088] In this embodiment, the obstacle detection data may be data collected by scanning or photographing obstacles in the target environment through a laser radar, a camera or other sensor. The target environment is the spatial environment that the robot needs to clean. The controller may determine the position of each obstacle in the target environment based on the obstacle detection data, thereby determining the obstacle distribution information of the target environment. The controller may divide the target environment into multiple areas of the same area, and then the controller traverses each area in turn and counts the number of obstacles that fall into the target area. The target area is the area currently traversed by the robot. When the number of obstacles in the target area is greater than or equal to a preset number threshold, it indicates that the target area is an area where multiple obstacles gather. As mentioned above, the robot is prone to collide with obstacles in dense obstacle areas, so the controller may determine that the target area is an area prone to collision. The preset number threshold can be set according to actual needs.

[0089] In some embodiments, when the robot collides with an obstacle, the controller can determine the collision point position and judge whether the collision point position is an obstacle position recognizable by the robot. If it is not an obstacle position recognizable by the robot, the controller determines the blind spot based on the collision point position.

[0090] In this embodiment, the collision point position is the position where the robot and the obstacle contact each other when they collide. If the grid corresponding to the collision point position is an idle grid or an unknown grid, the controller can determine that the collision point position is an obstacle position that the robot cannot recognize. At this time, the controller can set an area in front of the collision point position and use the area as a blind spot for recognition. The size and shape of the blind spot can be set according to actual needs. For example, the area is a rectangular area of ​​0.5 meters * 0.5 meters.

[0091] In some embodiments, the controller can mark the collision-prone areas on a preset environment map to obtain a risk map. The preset environment map is a map generated by the robot performing environmental perception and positioning of the target environment based on real-time environmental data and processing the real-time environmental data through a map building algorithm. The risk map is a map with collision-prone areas marked. Please refer to Figure 6The risk map is marked with the first collision-prone area A, the second collision-prone area B, the third collision-prone area C and the fourth collision-prone area D. Different collision-prone areas may overlap partially or not, such as Figure 6 As shown, the second easy-collision area B, the third easy-collision area C and the fourth easy-collision area D partially overlap, and the first easy-collision area A does not overlap with the second easy-collision area B, the third easy-collision area C and the fourth easy-collision area D.

[0092] In some embodiments, the collision-prone area may also be an area specified by the user. The controller may receive area information specified by the user, determine the collision-prone area according to the area information, and mark the collision-prone area on a preset environmental map to obtain a risk map.

[0093] S22. Count the historical collision records of the robot when it walks in the collision-prone area.

[0094] In this step, the historical collision record is a record of whether the robot collides or does not collide with an obstacle when the robot passes through a collision-prone area according to the risk map.

[0095] In some embodiments, the historical collision record includes a historical passing event sequence and a historical collision number.

[0096] The historical passing event sequence is an event sequence used to record whether a collision occurs each time the robot passes through a prone-collision area. When the robot determines a prone-collision area, if the robot has not passed through the prone-collision area, the historical passing event sequence of the prone-collision area is empty. If the robot passes through the prone-collision area, the historical passing event sequence of the prone-collision area may include at least one historical passing event. The historical passing events include collision events and non-collision events. A collision event refers to an event in which the robot collides with an obstacle when passing through the prone-collision area. A non-collision event refers to an event in which the robot does not collide with an obstacle when passing through the prone-collision area. Assume that the robot has passed through the first prone-collision area A three times, and did not collide with an obstacle when passing through the first prone-collision area A for the first time. A collision occurs when the vehicle passes through the first collision-prone area A for the second time, but no collision occurs when the vehicle passes through the first collision-prone area A for the third time. Then, the historical passing event sequence of the collision-prone area is (N, N, Y), wherein Y represents a collision event and N represents a non-collision event. It can be understood that the historical passing events in the historical passing event sequence can be arranged from right to left in chronological order, or can be arranged in other ways, such as from left to right in chronological order. As mentioned above, the historical passing events in the historical passing event sequence (N, N, Y) are arranged in this way, and the most recent historical passing event is a collision event, and the two most recent historical passing events are a collision event and a non-collision event, respectively.

[0097] The number of historical collisions is the number of collisions counted based on the collisions that occurred between the robot and obstacles in the prone-collision area when the robot recently passed through the prone-collision area. It is worth noting that the number of historical collisions is not necessarily the number of actual collisions between the robot and obstacles when the robot recently passed through the prone-collision area. For example, when the robot has not entered the prone-collision area, if the robot collides with obstacles in the area multiple times when walking in the prone-collision area for the first time, the number of historical collisions can be counted as 1.

[0098] It can be understood that, the greater the number of historical collisions in a certain collision-prone area, the more frequently the robot collides with obstacles in the area when passing through the collision-prone area recently.

[0099] S23. Update the walking speed of the robot in the collision-prone area according to the historical collision records.

[0100] In this step, it can be understood that when the robot walks in the easy-collision area, the walking speed of the robot remains unchanged. After the robot passes through the easy-collision area, the historical collision records can be counted according to the collision with obstacles in the easy-collision area, and then the walking speed of the robot next time in the easy-collision area can be updated according to the historical collision records. Therefore, when the robot enters the easy-collision area again next time, the controller can directly walk in the easy-collision area according to the updated walking speed.

[0101] Therefore, in some embodiments, after S23, it also includes: determining whether the robot enters a collision-prone area, and if so, controlling the robot to walk in the collision-prone area at an updated walking speed.

[0102] In this embodiment, the controller can determine whether the current position of the robot falls into the easy-collision area according to the risk map. If it falls into the easy-collision area, it is determined that the robot enters the easy-collision area.

[0103] In some embodiments, the controller can update the walking speed of the robot in the collision-prone area based on the historical event sequence. For example, if the robot collided with an obstacle the last two times it passed through the first collision-prone area A, the controller can set the walking speed of the first collision-prone area A to a low speed. Then, the next time the robot enters the first collision-prone area A, the controller can control the robot to walk at a low speed in the first collision-prone area A.

[0104] The controller can also update the robot's walking speed in the easy-collision area according to the number of historical collisions. For example, the more historical collisions a certain easy-collision area has, the slower the robot's walking speed in the first easy-collision area A will be when the robot enters the first easy-collision area A next time.

[0105] S24. Update the collision-prone area.

[0106] In this embodiment, the controller can update the collision-prone area when the collision-prone area changes. For example, when the controller detects that there is no obstacle in a collision-prone area or the formation conditions of the collision-prone area are not met, the controller can remove the collision-prone area and its historical collision records from the risk map, thereby updating the collision-prone area to avoid affecting the normal cleaning of the subsequent robot in the area.

[0107] Therefore, on the one hand, the present embodiment can flexibly adjust the robot's walking speed in the easy-collision area next time according to the collision situation when walking in the easy-collision area, thereby reducing the risk of the robot colliding with obstacles, and further avoiding frequent collisions between the robot and obstacles, thereby improving the cleaning smoothness and cleaning effect. On the other hand, the present embodiment can dynamically sense the changes in the easy-collision area, thereby avoiding the feeling of frustration caused by changes in the easy-collision area when the robot walks in the easy-collision area next time, thereby improving the smoothness of the robot's walking.

[0108] In some embodiments, see Figure 7 , S23 includes:

[0109] S231. Determine the speed level of the collision-prone area according to historical collision records.

[0110] In this step, the speed level is used to distinguish different speeds. The speed level may include multiple different levels. For example, the speed level includes normal speed, deceleration and low speed. Normal speed refers to the speed of the robot during normal cleaning, for example, the normal speed is 0.2m / s, the deceleration is a speed slightly lower than the normal speed, for example, the deceleration is 0.15m / s, and the low speed is a speed slightly lower than the deceleration, for example, the low speed is 0.1m / s. Of course, the speed level may also include a speed level higher than the normal speed or a speed level lower than the low speed.

[0111] In some embodiments, the controller may determine a speed level of the collision-prone area based on a number of historical collisions, wherein the historical collision records are negatively correlated with the speed of the speed level.

[0112] In this embodiment, the controller can search a preset speed configuration table based on the number of historical collisions. The preset speed configuration table is configured with a correspondence between the number of historical collisions and the speed level. The controller can determine that the speed level corresponding to the number of historical collisions in the preset speed configuration table is the speed level of the collision-prone area.

[0113] For example, the preset speed configuration table is shown in Table 1 below:

[0114] Table 1

[0115] Historical collision times Speed ​​Rating 0 Normal speed 1 slow down 2 Low speed

[0116] According to Table 1 above, the more historical collision times, the lower the speed of the corresponding speed level, and the fewer historical collision times, the higher the speed of the corresponding speed level, that is, the historical collision times are negatively correlated with the speed of the speed level.

[0117] S232: Update the walking speed of the robot in the collision-prone area according to the speed level.

[0118] In this step, as mentioned above, when the speed level is normal speed, the controller can update the walking speed of the robot in the collision-prone area to 0.2m / s; when the speed level is deceleration, the controller can update the walking speed of the robot in the collision-prone area to 0.15m / s; when the speed level is low speed, the controller can update the walking speed of the robot in the collision-prone area to 0.1m / s.

[0119] Therefore, this embodiment can flexibly adjust the speed level of the robot in each collision-prone area according to the historical number of collisions in each collision-prone area, and the historical collision records are negatively correlated with the speed level. This can ensure that the robot avoids frequent collisions with obstacles in the collision-prone area and walks in the collision-prone area at the optimal speed, thereby increasing the service life of the robot and avoiding the robot from frequently switching speeds in areas with dense obstacles, thereby improving the cleaning effect.

[0120] In some embodiments, after S21, the method further includes: determining the area type of the collision-prone area, determining an initial collision record of the collision-prone area according to the area type, and using the initial collision record as a historical collision record of the collision-prone area.

[0121] In this embodiment, the initial collision record is a collision record configured when determining a collision-prone area. The initial collision record includes an initial passing event and an initial collision number. As mentioned above, the area types of collision-prone areas include dense obstacle areas and identification blind areas. When determining a dense obstacle area, since the robot has not collided with the obstacle in the dense obstacle area, the controller can configure the initial passing event of the dense obstacle area as a non-collision event. When determining an identification blind area, since the robot has collided with the obstacle in the identification blind area, the controller can configure the initial passing event of the identification blind area as a collision event. Since the dense obstacle area and the recognition blind area are both easy-to-collision areas, if the robot walks at a normal speed in the easy-to-collision area next time, the robot is likely to collide with obstacles in the easy-to-collision area. Therefore, the controller can configure the initial collision number of the dense obstacle area or the recognition blind area to be 1, and configure the initial collision number as the historical collision number. As mentioned above, since the historical collision number is 1, the robot's next walking speed in the easy-to-collision area is decelerated, which can reduce the risk of the robot colliding with obstacles in the easy-to-collision area when walking in the easy-to-collision area next time, thereby avoiding frequent collisions between the robot and obstacles. Therefore, the area types of easy-to-collision areas are different. Although the initial collision number is the same, the initial passing events are different, and the historical collision records are also different. In some embodiments, in the historical collision record of the dense obstacle area, the historical passing event sequence is (N), and the historical collision number is 1. In the historical collision record of the recognition blind area, the historical passing event sequence is (Y), and the historical collision number is 1.

[0122] Therefore, this embodiment can configure reasonable historical collision records for collision-prone areas of different area types, which is beneficial for subsequently providing basic collision records and walking speeds for the robot when walking in collision-prone areas of different area types, thereby facilitating the robot to accurately update historical collision records on this basis, and further facilitating the robot to more reliably adjust the walking speed in collision-prone areas.

[0123] In some embodiments, S22 includes: when determining that the robot passes through a collision-prone area, recording the current passing event, the current passing event being an event that occurs when the robot currently passes through the collision-prone area, and based on the current passing event and the historical passing event sequence, counting the historical collision records of the robot walking in the collision-prone area.

[0124] In this embodiment, the current passing event includes a collision event and a non-collision event. If the robot currently passes through a collision-prone area and collides with an obstacle in the area, the current passing event is a collision event. If the robot currently passes through a collision-prone area and does not collide with an obstacle in the area, the current passing event is a non-collision event. In some embodiments, the controller can simultaneously update the historical passing event sequence and the historical collision count of the collision-prone area according to the current passing event, thereby counting the historical collision records of the robot walking in the collision-prone area.

[0125] In some embodiments, the current passing event is different, and the method of counting the historical collision records of the robot walking in the easy-collision area is also different. In some embodiments, the controller can update the historical passing event sequence according to the current passing event, determine the event type of the current passing event, determine the target historical passing event from the updated historical passing event sequence according to the event type, update the historical collision count according to the target historical passing event, and count the historical collision records of the robot walking in the easy-collision area according to the updated historical passing event sequence and the historical collision count.

[0126] In this embodiment, as mentioned above, the historical passing event sequence of the first collision-prone area A is (N, N, Y), and the event type of the current passing event includes a collision event and a non-collision event. If the event type of the current passing event is a collision event, the historical passing event sequence of the first collision-prone area A can be updated to (N, N, Y, Y). If the event type of the current passing event is a non-collision event, the historical passing event sequence of the first collision-prone area A can be updated to (N, N, Y, N). The target historical passing event is the most recent one or more historical passing events in the historical passing event sequence. If the event type of the current passing event is different, the target historical passing events can be the same or different.

[0127] In some embodiments, if the event type is a collision event, a first preset number of most recent historical passing events in the updated historical passing event sequence are determined as target historical passing events.

[0128] In this embodiment, the first preset number can be set according to actual needs. For example, the first preset number is 2. As mentioned above, the updated historical passing event sequence is (N, N, Y, Y). If the first preset number is 2, the target historical passing event is the two most recent historical passing events in the historical passing event sequence, Y and Y, that is, the two most recent historical passing events are two consecutive collision events.

[0129] In some embodiments, if the event type is a non-collision event, a second preset number of most recent historical passing events in the updated historical passing event sequence is determined as the target historical passing event.

[0130] In this embodiment, the second preset number can be set according to actual needs. For example, the second preset number is 3. As mentioned above, the updated historical passing event sequence is (N, N, Y, N). If the first preset number is 3, the target historical passing event is the three most recent historical passing events in the historical passing event sequence, namely N, Y and N, that is, the three most recent historical passing events are a non-collision event, a collision event and a non-collision event, respectively.

[0131] In some embodiments, the controller may determine the first number of the first preset number of historical passing events whose event type is a collision event, and update the number of historical collisions according to the first number.

[0132] For example, as mentioned above, the first preset number is 2, the event type of the current passing event is a collision event, and the historical passing event sequence of the first collision-prone area A is updated to (N, N, Y, Y). For the updated historical passing event sequence, the two most recent historical passing events are Y and Y. Since two of the two historical passing events have the event type of a collision event, the first number is 2. The controller may compare the first number with the preset number and update the number of historical collisions according to the comparison result.

[0133] In some embodiments, the controller can determine whether the first number is equal to a first preset number. If it is equal to the first preset number, the historical collision number can be updated according to the sum of the historical collision number and the first preset number. The first preset number is a natural number greater than or equal to 1. If it is not equal to the first preset number, the historical collision number is maintained unchanged.

[0134] In this embodiment, the first preset number can be set according to actual needs, as long as the first preset number is a natural number greater than or equal to 1, for example, the first preset number is 1.

[0135] As mentioned above, in the updated historical collision record of the first collision-prone area A, the historical event sequence is (N, N, Y, Y), and the historical collision number is 1. Since the first preset number is 2, and the event types of the two most recent historical passing events in the historical passing event sequence are both collision events, that is, the first number is also 2, the controller can determine that the first number is equal to the first preset number. At this time, the controller can add the historical collision number 1 to the first preset number 1 to obtain a sum of 2, and update the historical collision number from 1 to 2. As mentioned above, since the historical collision number is 2, the robot's walking speed will be low the next time it enters the first collision-prone area.

[0136] Therefore, if the robot has collided with obstacles in a prone-collision area twice in the last two times it passed through the area, adjusting the walking speed of the robot to a lower level the next time it enters the prone-collision area can reduce the risk of the robot colliding with obstacles in the area the next time it passes through the prone-collision area.

[0137] It is understandable that a maximum number of historical collisions is generally set, that is, the number of historical collisions is always less than or equal to the maximum number. Therefore, in some embodiments, before determining whether the first number is equal to the first preset number, the controller first determines whether the number of historical collisions is equal to the maximum number. If the number of historical collisions is equal to the maximum number, there is no need to enter the step of determining whether the first number is equal to the first preset number, and the number of historical collisions is directly maintained unchanged. If the number of historical collisions is not equal to the maximum number, it is necessary to enter the step of determining whether the first number is equal to the first preset number.

[0138] In some embodiments, the controller may determine a second number of the event types of non-collision events among a second preset number of historical passing events, and update the number of historical collisions according to the second number.

[0139] For example, as mentioned above, the second preset number is 3, the event type of the current passing event is a non-collision event, and the historical passing event sequence of the first collision-prone area A is updated to (N, N, Y, N). For the updated historical passing event sequence, the three most recent historical passing events N, Y, and N, since two of the three historical passing events have the event type of non-collision events, the second number is 2. The controller can compare the second number with the preset number and update the number of historical collisions according to the comparison result.

[0140] In some embodiments, the controller can determine whether the second number is equal to a second preset number. If it is equal to the second preset number, the historical collision number can be updated according to the difference between the historical collision number and the first preset number. The first preset number is a natural number greater than or equal to 1. If it is not equal to the second preset number, the historical collision number is maintained unchanged.

[0141] In this embodiment, as mentioned above, the first preset number is 1. In the updated historical collision record of the first collision-prone area A, the historical event sequence is (N, N, Y, N), and the historical collision number is 1. Since the second preset number is 3, and the three most recent historical events in the historical event sequence have two event types of non-collision events and one event type of collision event, that is, the second number is 2, the controller can determine that the second number is not equal to the second preset number. At this time, the controller can maintain the historical collision number of 1 unchanged.

[0142] It can be understood that, assuming that in the historical collision record of a certain collision-prone area, the historical passing event sequence is (Y, N, N), the historical collision number is 1, and the event type of the current passing event when the robot currently passes through the collision-prone area is a non-collision event, then the historical passing event sequence of the collision-prone area is updated to (Y, N, N, N). Since the event types of the three most recent historical passing events in the historical passing event sequence are all non-collision events, that is, the second number is 3, the controller can determine that the second number is equal to the second preset number. At this time, the controller can subtract the first preset number 1 from the historical collision number 1 to obtain a difference of 0, and update the historical collision number from 1 to 0. As mentioned above, since the historical collision number is 0, the walking speed of the robot the next time it enters the first collision-prone area is normal.

[0143] Therefore, if the robot has not collided with any obstacles in a collision-prone area during the three most recent times it has passed through the area, the robot's walking speed will be adjusted higher the next time it enters the collision-prone area. This can improve the robot's cleaning efficiency in the collision-prone area while avoiding any collision with any obstacles in the area the next time the robot enters the collision-prone area for cleaning.

[0144] It is understandable that the number of historical collisions is generally set to a minimum number, that is, the number of historical collisions is always greater than or equal to the minimum number. Therefore, in some embodiments, before determining whether the second number is equal to the second preset number, the controller first determines whether the number of historical collisions is equal to the minimum number. If the number of historical collisions is equal to the minimum number, there is no need to enter the step of determining whether the second number is equal to the second preset number, and the number of historical collisions is directly maintained unchanged. If the number of historical collisions is not equal to the minimum number, it is necessary to enter the step of determining whether the second number is equal to the second preset number.

[0145] It should be noted that, in each of the above-mentioned embodiments, there is not necessarily a certain order between the above-mentioned steps. A person of ordinary skill in the art can understand, based on the description of the embodiments of the present invention, that in different embodiments, the above-mentioned steps may have different execution orders, that is, they may be executed in parallel, may be executed interchangeably, and so on.

[0146] As another aspect of an embodiment of the present invention, an embodiment of the present invention provides a walking control device for a robot. The walking control device for the robot may be a software module, which includes a number of instructions stored in a memory, and a processor may access the memory and call the instructions for execution to complete the walking control method of the robot described in each of the above embodiments.

[0147] In some embodiments, the walking control device of the robot can be constructed by hardware devices, for example, the walking control device of the robot can be constructed by one or more chips, and each chip can work in coordination with each other to complete the walking control method of the robot described in each of the above embodiments. For another example, the walking control device of the robot can also be constructed by a general processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), a single-chip microcomputer, an ARM (Acorn RISC Machi ne), a programmable logic device, a discrete gate or transistor logic, a discrete hardware component, or any combination of these components.

[0148] In some embodiments, see Figure 8 The robot walking control device 800 provided in the embodiment of the present invention includes a first determination module 81, a statistics module 82, a first updating module 83 and a second updating module 84.

[0149] The first determination module 81 is used to determine the easy-to-collision area, the statistical module 82 is used to count the historical collision records of the robot walking in the easy-to-collision area, the first update module 83 is used to update the walking speed of the robot in the easy-to-collision area according to the historical collision records, and the second update module 84 is used to update the easy-to-collision area.

[0150] In some embodiments, see Fig. 9 The first updating module 83 includes a first determining unit 831 and an updating unit 832 .

[0151] The first determining unit 831 is used to determine the speed level of the easy-collision area according to the historical collision records, and the updating unit 832 is used to update the walking speed of the robot in the easy-collision area according to the speed level.

[0152] In some embodiments, the historical collision record includes the number of historical collisions, and the first determining unit 831 is specifically used to determine the speed level of the collision-prone area according to the number of historical collisions, wherein the historical collision record is negatively correlated with the speed level.

[0153] In some embodiments, see Fig.10 The statistical module 82 includes a recording unit 821 and a statistical unit 822.

[0154] The recording unit 821 is used to determine when the robot passes through a collision-prone area and record the current passing event. The current passing event is an event that occurs when the robot currently passes through the collision-prone area. The statistical unit 822 is used to count the historical collision records of the robot walking in the collision-prone area based on the current passing event and the historical passing event sequence.

[0155] In some embodiments, the statistical unit 822 is specifically used to: update the historical passing event sequence according to the current passing event, determine the event type of the current passing event, determine the target historical passing event from the updated historical passing event sequence according to the event type, update the historical collision number according to the target historical passing event, and count the historical collision records of the robot walking in the collision-prone area according to the updated historical passing event sequence and the historical collision number.

[0156] In some embodiments, see Fig.11 The first determination module 81 includes an acquisition unit 811, a second determination unit 812, a third determination unit 813, a judgment unit 814 and a fourth determination unit 815.

[0157] The acquisition unit 811 is used to acquire obstacle detection data of the target environment, the second determination unit 812 is used to determine the obstacle distribution information of the target environment according to the obstacle detection data, the third determination unit 813 is used to determine the number of obstacles in the target area according to the obstacle distribution information, the judgment unit 814 is used to judge whether the number of obstacles is greater than or equal to a preset number threshold, and the fourth determination unit 815 is used to determine that the target area is a collision-prone area when the number of obstacles is greater than or equal to the preset number threshold.

[0158] In some embodiments, see Fig.12 The robot walking control device 800 also includes a second determination module 85, a third determination module 86 and a configuration module 87.

[0159] The second determination module 85 is used to determine the area type of the easy-collision area, the third determination module 86 is used to determine the initial collision record of the easy-collision area according to the area type, and the configuration module 87 is used to configure the initial collision record as the historical collision record of the robot walking in the easy-collision area.

[0160] It should be noted that the walking control device of the robot can execute the walking control method of the robot provided in the embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not fully described in the embodiment of the walking control device of the robot, please refer to the walking control method of the robot provided in the embodiment of the present invention.

[0161] See also Fig.13 , Fig.13 A schematic diagram of the hardware structure of a controller is provided in accordance with an embodiment of the present invention. Fig.13 As shown, the controller 11 includes one or more processors 111 and a memory 112. Fig.13 A processor 111 is taken as an example.

[0162] The processor 111 is configured to support the computer device to perform the corresponding functions in the method in the above method embodiment. The processor 111 can be a central processing unit (CPU), a network processor (NP), a hardware chip or any combination thereof. The above hardware chip can be an application specific integrated circuit (ASIC), a programmable logic device (PLD) or a combination thereof. The above PLD can be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL) or any combination thereof.

[0163] The memory 112 is used to store program codes. The memory 112 may include a volatile memory (VM), such as a random access memory (RAM); the memory may also include a non-volatile memory (NVM), such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD); the memory 112 may also include a combination of the above-mentioned types of memory.

[0164] The memory 112 can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as program instructions / modules corresponding to the walking control method of the robot in the embodiment of the present invention. The processor 111 executes the various functional applications and data processing of the walking control method of the robot and the walking control device of the robot by running the non-volatile software programs, instructions and modules stored in the memory 112, that is, realizes the functions of the various modules or units of the walking control method of the robot and the walking control device of the robot provided in the above method embodiment.

[0165] The memory 112 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function. The data storage area may store data created according to the use of the robot's walking control device, etc. In some embodiments, the memory 112 may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the robot's walking control device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0166] The one or more modules are stored in the memory 112, and when executed by the one or more processors 111, the walking control method of the robot in any of the above-mentioned method embodiments is executed, for example, the method steps described in the above-mentioned method embodiments are executed to realize the functions of the modules described in the above-mentioned device embodiments.

[0167] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a computer, the computer executes the method described in the above embodiment.

[0168] It is understood by those skilled in the art that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0169] Finally, it should be noted that the present invention can be implemented in many different forms and is not limited to the embodiments described in this specification. These embodiments are not intended to be additional limitations on the content of the present invention. The purpose of providing these implementations is to make the understanding of the disclosure of the present invention more thorough and comprehensive. And under the idea of ​​the present invention, the above-mentioned technical features continue to be combined with each other, and there are many other changes in different aspects of the present invention as described above, which are all considered to be within the scope of the present invention. Further, for those of ordinary skill in the art, improvements or changes can be made according to the above description, and all these improvements and changes should belong to the scope of protection of the claims attached to the present invention.

Claims

1. A walking control method of a robot, characterized in that: include: Identify collision-prone areas; Collecting historical collision records of the robot while walking in the collision-prone area; Update the walking speed of the robot in the collision-prone area according to the historical collision record; The collision-prone area is updated.

2. The robot walking control method according to claim 1, characterized in that: The updating of the walking speed of the robot in the collision-prone area according to the historical collision record comprises: Determining a speed level of the collision-prone area according to the historical collision record; The walking speed of the robot in the collision-prone area is updated according to the speed level.

3. The walking control method of the robot according to claim 2, characterized in that: After updating the walking speed of the robot in the collision-prone area according to the speed level, the method further includes: Determining whether the robot enters the collision-prone area; If the robot enters the easy-collision area, the robot is controlled to walk in the easy-collision area at the updated walking speed.

4. The walking control method of the robot according to claim 2, characterized in that: The historical collision record includes the number of historical collisions, and determining the speed level of the collision-prone area according to the historical collision record includes: The speed grade of the collision-prone area is determined according to the number of historical collisions, wherein the historical collision records are negatively correlated with the speed of the speed grade.

5. The robot walking control method according to claim 4, characterized in that: The historical collision record also includes a historical event sequence, and the historical collision record of the robot walking in the collision-prone area includes: When the robot passes through the easy-collision area, a current passing event is recorded, where the current passing event is an event that occurs when the robot currently passes through the easy-collision area; According to the current passing event and the historical passing event sequence, historical collision records of the robot walking in the collision-prone area are counted.

6. The robot walking control method according to claim 5, characterized in that: The counting of historical collision records of the robot walking in the collision-prone area according to the current passing event and the historical passing event sequence includes: Updating the historical passing event sequence according to the current passing event; Determining an event type of the current passing event; Determining a target historical passing event from the updated historical passing event sequence according to the event type; Update the historical collision count according to the target historical passing events; According to the updated historical event sequence and the historical collision times, historical collision records of the robot walking in the collision-prone area are counted.

7. The robot walking control method according to claim 6, characterized in that: The event type includes a collision event, and determining a target historical passing event from the updated historical passing event sequence according to the event type includes: If the event type is the collision event, determining the most recent first preset number of the historical passing events in the updated historical passing event sequence as the target historical passing events; Then, updating the historical collision number according to the target historical passing event includes: Determine the first number of the first preset number of historical passing events whose event type is a collision event; The historical number of collisions is updated according to the first number.

8. The robot walking control method according to claim 7, characterized in that: The updating of the historical collision times according to the first number comprises: Determining whether the first number is equal to the first preset number; If it is equal to the first preset number, updating the historical collision number according to the sum of the historical collision number and the first preset number, where the first preset number is a natural number greater than or equal to 1; If it is not equal to the first preset number, the historical number of collisions is maintained unchanged.

9. The robot walking control method according to claim 6, characterized in that: The event type includes a non-collision event, and determining a target historical passing event from the updated historical passing event sequence according to the event type includes: If the event type is the non-collision event, determining the most recent second preset number of historical passing events in the updated historical passing event sequence as the target historical passing event; Then, updating the historical collision number according to the target historical passing event includes: Determine a second number of the second preset number of historical passing events whose event type is non-collision events; The historical number of collisions is updated according to the second number.

10. The robot walking control method according to claim 9, characterized in that: The updating of the historical collision times according to the second number comprises: Determining whether the second number is equal to the second preset number; If it is equal to the second preset number, updating the historical collision number according to the difference between the historical collision number and the first preset number, where the first preset number is a natural number greater than or equal to 1; If it is not equal to the second preset number, the historical number of collisions is maintained unchanged.

11. The robot walking control method according to claim 1, characterized in that: Determining the collision-prone area comprises: Obtain obstacle detection data of the target environment; Determining obstacle distribution information of the target environment according to the obstacle detection data; Determining the number of obstacles in the target area according to the obstacle distribution information; Determining whether the number of obstacles is greater than or equal to a preset number threshold; If it is greater than or equal to the preset quantity threshold, the target area is determined to be a collision-prone area.

12. The robot walking control method according to any one of claims 1 to 11, characterized in that: After determining the collision-prone area, the method further includes: Determining the area type of the collision-prone area; Determining an initial collision record of the collision-prone area according to the area type; The initial collision record is configured as a historical collision record of the robot walking in the collision-prone area.

13. A robot, characterized in that: It includes a memory and a processor, the memory is connected to the processor, the processor is used to execute one or more computer programs stored in the memory, and when the processor executes the one or more computer programs, the robot implements the robot walking control method as described in any one of claims 1 to 12.

Images