Robot control method and device and storage medium

Abstract

The invention provides a robot control method and device and a storage medium, and the method comprises the steps: carrying out the obstacle detection analysis of first environment data collected by a first environment sensor disposed on a target robot, and determining a first size detection result of an obstacle; determining a first control strategy of the target robot according to the first size detection result of the obstacle; if the first control strategy does not include the direct obstacle avoidance strategy, performing obstacle detection analysis on second environment data collected by a second environment sensor arranged on the target robot, determining a second size detection result of the obstacle, and determining a second control strategy of the target robot according to the second size detection result, and motion control is carried out on the target robot. Therefore, according to the invention, the two environment sensors are used for carrying out secondary recognition on the obstacle, so that the accuracy of an obstacle detection result can be effectively improved, and the driving safety and the task completion degree of the robot can be ensured.

Description

Technical Field

[0001] The present application relates to the technical field of robots, and in particular, to a control method, device, and storage medium for a robot. Background Art

[0002] With the development of robot technology, robots are increasingly widely used in industrial manufacturing, item delivery, home service, hotel cleaning and other fields, involving various robots, such as cleaning robots, delivery robots, cruising robots, etc. However, due to the complexity of the working environment, robots will inevitably encounter various obstacles during the working process. In order to ensure the smooth execution of the robot's tasks and ensure the safe and efficient movement of the robot, it is necessary for the robot to accurately avoid obstacles during the autonomous navigation process.

[0003] At present, in order for a robot to identify surrounding obstacles earlier or in a larger range for effective obstacle avoidance, an obstacle detection sensor with a relatively long detection distance or a large detection range, such as stereo vision, is usually set on the robot to obtain the spatial information of the surrounding environment and analyze and determine the existing obstacles. However, such sensors often have accuracy errors. If stable identification is desired, the obstacle threshold needs to be adjusted, which will cause the robot to be unable to accurately identify some obstacles, especially low obstacles (such as the base of a shopping mall shelf) during the driving process, and thus there may be a situation where the robot collides with the obstacle, and even the robot may be damaged. Summary of the Invention

[0004] In view of this, the purpose of the present application is to provide a control method, device, and storage medium for a robot. By using the obstacle detection result of the second environment sensor to perform secondary verification on the obstacle detection result of the first environment sensor, the accuracy of the obstacle detection result can be effectively improved, thereby further ensuring the driving safety and task completion degree of the robot.

[0005] The embodiment of the present application provides a control method for a robot, and the control method includes: Performing obstacle detection and analysis on the first environment data collected by the first environment sensor set on the target robot to determine the first size detection result of the obstacle; Determining the first control strategy of the target robot according to the first size detection result of the obstacle, and performing motion control on the target robot according to the first control strategy; If the first control strategy does not include a direct obstacle avoidance strategy, analyze the second environmental data collected by the second environmental sensor set on the target robot for obstacle detection to determine the second size detection result of the obstacle, and determine the second control strategy of the target robot according to the second size detection result; the maximum detection distance of the first environmental sensor along the moving direction of the target robot is greater than that of the second environmental sensor, and the detection accuracy of the second environmental sensor is higher than that of the first environmental sensor; Perform motion control on the target robot according to the second control strategy.

[0006] Optionally, the determining the first control strategy of the target robot according to the first size detection result of the obstacle includes: Determine whether the first size detection result of the obstacle is within the range of the suspected dangerous obstacle size; If it is within, determine that the first control strategy is a deceleration strategy; If it is not within, when the first size detection result of the obstacle is greater than the upper limit of the suspected dangerous obstacle size range, determine that the first control strategy is a direct obstacle avoidance strategy; If it is not within, when the first size detection result of the obstacle is less than the lower limit of the suspected dangerous obstacle size range, determine that the first control strategy is a strategy of controlling the movement of the target robot according to the planned driving data.

[0007] Optionally, the analyzing the second environmental data collected by the second environmental sensor set on the target robot for obstacle detection to determine the second size detection result of the obstacle includes: Perform partition processing on the second environmental data to determine the obstacle area data and the non-obstacle area data; Process the non-obstacle area data to determine the mean value and the noise standard deviation of the non-obstacle area; Use the mean value of the non-obstacle area to perform compensation processing on the obstacle area data, and calculate the signal mean value of the compensated obstacle area data; Determine the signal-to-noise ratio of the second environmental data according to the signal mean value and the noise standard deviation; Determine the second size detection result of the obstacle according to the determined signal-to-noise ratio and the preset evaluation rule.

[0008] Optionally, the determining the second control strategy of the target robot according to the second size detection result includes: If the second size detection result indicates the existence of a dangerous obstacle, determine that the second control strategy is a braking strategy of performing corresponding braking with reference to the first control strategy of the target robot; If the second dimension detection result indicates the absence of a dangerous obstacle, determine that the second control strategy is the strategy of controlling the movement of the target robot according to the planned driving data.

[0009] Optionally, when the first control strategy is the strategy of controlling the movement of the target robot according to the planned driving data and the second dimension detection result indicates the presence of a dangerous obstacle, the second control strategy is: controlling the target robot to initiate an emergency brake; When the first control strategy is a deceleration strategy and the second dimension detection result indicates the presence of a dangerous obstacle, the second control strategy is: Determine the current braking change curve of the target robot according to the current driving speed of the target robot under the deceleration strategy and the current distance between the target robot and the obstacle; Control the target robot to smoothly decelerate to a stop according to the current braking change curve.

[0010] Optionally, both the first environmental sensor and the second environmental sensor are arranged on the surface of the target robot facing the moving direction. The installation position of the first environmental sensor on the surface of the target robot facing the moving direction is: installed at a position where the first space range in front of the target robot can be monitored. The installation position of the second environmental sensor on the surface of the target robot facing the moving direction is: installed at a position where the second space range in front of the target robot can be monitored; the first environmental sensor is located above the second environmental sensor, and the first space range includes the second space range; the first environmental sensor is a stereo vision sensor, and the second environmental sensor is a line laser sensor.

[0011] Optionally, when the target robot is a cleaning robot and both the first control strategy and the second control strategy are the strategies of controlling the movement of the target robot according to the planned driving data, the control method includes: Perform ground information recognition processing on the first environmental data to determine the second ground information in the area to be cleaned; Determine the current cleaning strategy for the second ground area according to at least one of the second ground information and the current cleaning mode of the target robot; wherein, the current cleaning strategy includes a mode switching strategy; Determine the target cleaning mode according to the current cleaning strategy, and control the target robot to clean the second ground area according to the target cleaning mode.

[0012] Optionally, after determining the first dimension detection result of the obstacle, the control method further includes: When the first size detection result of the obstacle is within the range of the suspected dangerous obstacle size, identify the current position of the obstacle, determine that the first control strategy is a deceleration strategy, and control the target robot to decelerate according to the first control strategy; When it is determined that the obstacle is within the monitoring range of the second environmental sensor according to the identified current position of the obstacle, obtain the second environmental data collected by the second environmental sensor, and determine the second size detection result; Determine the second control strategy of the target robot according to the second size detection result, and perform motion control on the target robot according to the second control strategy.

[0013] An embodiment of the present application also provides a control device for a robot, and the control device includes: An analysis module, configured to perform obstacle detection and analysis on the first environmental data collected by the first environmental sensor provided on the target robot, and determine the first size detection result of the obstacle; A first determination module, configured to determine the first control strategy of the target robot according to the first size detection result of the obstacle, and perform motion control on the target robot according to the first control strategy; A second determination module, configured to, if the first control strategy does not include a direct obstacle avoidance strategy, perform obstacle detection and analysis on the second environmental data collected by the second environmental sensor provided on the target robot, determine the second size detection result of the obstacle, and determine the second control strategy of the target robot according to the second size detection result; the maximum detection distance of the first environmental sensor along the movement direction of the target robot is greater than that of the second environmental sensor, and the detection accuracy of the second environmental sensor is higher than that of the first environmental sensor; A control module, configured to perform motion control on the target robot according to the second control strategy.

[0014] An embodiment of the present application also provides an electronic device, including: a processor, a memory, and a bus, where the memory stores machine-readable instructions executable by the processor. When the electronic device runs, the processor communicates with the memory through the bus, and when the machine-readable instructions are executed by the processor, the steps of the control method as described above are executed.

[0015] An embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is run by a processor, the steps of the control method as described above are executed.

[0016] A control method, device and storage medium for a robot provided by an embodiment of the present application. The control method includes: performing obstacle detection and analysis on first environmental data collected by a first environmental sensor set on a target robot to determine a first size detection result of an obstacle; determining a first control strategy for the target robot according to the first size detection result of the obstacle, and performing motion control on the target robot according to the first control strategy; if the first control strategy does not include a direct obstacle avoidance strategy, performing obstacle detection and analysis on second environmental data collected by a second environmental sensor set on the target robot to determine a second size detection result of the obstacle, and determining a second control strategy for the target robot according to the second size detection result; a maximum detection distance of the first environmental sensor along the moving direction of the target robot is greater than that of the second environmental sensor, and a detection accuracy of the second environmental sensor is higher than that of the first environmental sensor; performing motion control on the target robot according to the second control strategy.

[0017] In this way, two environmental sensors (a first environmental sensor and a second environmental sensor) are set on the target robot in the present application. During the movement of the target robot, first, the first environmental sensor with a large field of view is used to identify obstacles in the surrounding environment, which can improve the speed of obstacle determination, so as to timely adjust the motion state of the robot, that is, determine the first control strategy. This method can effectively ensure driving safety. Further, when it is determined that the first control strategy does not include a direct obstacle avoidance strategy, it means that it cannot be accurately determined according to the first size detection result that there are dangerous obstacles affecting the driving of the target robot on its driving path. At this time, the second environmental sensor with high detection accuracy is used for secondary verification of the obstacle, which can effectively improve the accuracy of the obstacle detection result, so as to determine a second control strategy suitable for the current state of the target robot, and control the target robot to move according to this strategy, which can further ensure the driving safety and task completion degree of the robot.

[0018] In order to make the above objects, features and advantages of the present application more obvious and understandable, the following specific embodiments are given, and detailed descriptions are made in conjunction with the accompanying drawings as follows. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required to be used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0020] Figure 1A flowchart of a control method for a robot provided by an embodiment of the present application; Figure 2 A schematic structural diagram of a robot provided by the present application, which is provided with a first environmental sensor and a second environmental sensor; Figure 3 A schematic diagram of the detection ranges of the first environmental sensor and the second environmental sensor provided by the present application; Figure 4 A schematic structural diagram of a control device for a robot provided by an embodiment of the present application; Figure 5 A schematic structural diagram of another control device for a robot provided by an embodiment of the present application; Figure 6 A schematic structural diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0021] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Usually, the components of the embodiments of the present application described and illustrated in the accompanying drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application that is required to be protected, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, every other embodiment obtained by those skilled in the art without creative efforts belongs to the scope of protection of the present application.

[0022] First, the applicable application scenarios of the present application are introduced. The present application can be applied to the field of robots, specifically to intelligent robots equipped with two environmental sensors. The intelligent robots can be applied in fields such as industrial manufacturing, item delivery, home service, hotel cleaning, etc., such as cleaning robots, delivery robots, cruise robots, etc.

[0023] However, through research, it is found that due to the complexity of the working environment of the robots applied to the above scenarios, the robots will inevitably encounter various obstacles during the working process. In order to ensure the smooth execution of the tasks of the robots and ensure the safe and efficient movement of the robots, it is necessary for the robots to accurately avoid obstacles during the autonomous navigation process.

[0024] For this reason, the following solutions for obstacle avoidance of robots have been proposed in the prior art: First, in order for robots to identify surrounding obstacles in advance or within a larger range for effective obstacle avoidance, obstacle detection sensors with a relatively long detection distance or a large detection range are usually set on the robots, such as stereo vision, to obtain the spatial information of the surrounding environment and analyze to determine the existing obstacles. However, such sensors often have accuracy errors. If stable identification is desired, the obstacle threshold needs to be adjusted, which will cause the robot to be unable to accurately identify some obstacles during driving, especially low obstacles (such as the base of a shopping mall shelf), and thus there may be a situation where the robot collides with the obstacle, even causing damage to the robot. Second, in order to improve the detection accuracy, line lasers with a relatively short detection distance are set on the robot. After detecting a low obstacle, the robot brakes and detours. However, although this method can accurately detect the obstacle, when the obstacle is detected, the distance between the obstacle and the robot is relatively close, and the robot cannot brake in time when driving fast, so there is a risk of collision. Third, due to the risk of collision when using line lasers with a relatively short detection distance, the prior art sets line lasers with a relatively long detection distance obliquely downward on the robot, marks the obstacle and detours. However, although this method realizes the early detection of obstacles to a certain extent and ensures that the robot brakes in time in front of the obstacle, the long-distance line laser can only detect a single line, and obstacles occasionally located between the line laser and the robot cannot be stably identified. Therefore, the detection accuracy of obstacles by this method is relatively low, and it cannot effectively ensure the safety of the robot during driving. Fourth, AI technology is used to identify ground obstacles. However, when the existing AI is used to identify obstacles, the accuracy rate is relatively low, generally only about 70%, and there is a situation where patterned floor tiles are misidentified as obstacles. This low-accuracy method of obstacle identification will increase the risk of collision between the robot and the obstacle, thus affecting the completion of the robot's tasks.

[0025] Based on this, the embodiments of the present application provide a control method for a robot to improve the accuracy of obstacle detection results and ensure the driving safety and task completion rate of the robot.

[0026] Please refer to Figure 1 , Figure 1 which is a flowchart of a control method for a robot provided by the embodiments of the present application. As Figure 1 shown in S101. Perform obstacle detection and analysis on the first environmental data collected by the first environmental sensor set on the target robot to determine the first size detection result of the obstacle.

[0027] In this step, the first environmental sensor set on the target robot monitors the surrounding environment in real time or periodically, and obtains the first environmental data. Then, the collected first environmental data is identified to determine whether there are obstacles. If it is determined that there are obstacles, the size of the identified obstacles is further determined to obtain the first size detection result. Among them, to ensure the recognition accuracy, the first environmental sensor can monitor the surrounding environment in real time.

[0028] S102. Determine the first control strategy of the target robot according to the first size detection result of the obstacle, and perform motion control on the target robot according to the first control strategy.

[0029] In this step, according to the specific size of the obstacle recorded in the first size detection result of the identified obstacle and the pre-determined mapping relationship between size and strategy, the first control strategy for currently controlling the movement of the target robot is determined, and the target robot is controlled to perform corresponding movement according to the determined first control strategy.

[0030] S103. If the first control strategy does not include a direct obstacle avoidance strategy, perform obstacle detection and analysis on the second environmental data collected by the second environmental sensor set on the target robot to determine the second size detection result of the obstacle, and determine the second control strategy of the target robot according to the second size detection result.

[0031] Here, the maximum detection distance of the first environmental sensor along the movement direction of the target robot is greater than that of the second environmental sensor, and the detection accuracy of the second environmental sensor is higher than that of the first environmental sensor.

[0032] S104. Perform motion control on the target robot according to the second control strategy.

[0033] For the robot scheduling method provided by the implementation of this application, first, the first environmental sensor set on the robot monitors the surrounding environment of the target robot and analyzes the monitored environmental data, and determines the first control strategy of the current target robot according to the first size detection result of the obstacle determined by the analysis. Then, when the determined first control strategy is not a direct obstacle avoidance strategy, perform secondary verification of the obstacle on the second environmental data obtained by monitoring the surrounding environment by the second environmental sensor set on the target robot to obtain the second size detection result of the obstacle. Finally, determine the second control strategy for re-controlling the target robot moving according to the first control strategy according to the second size detection result, and perform motion control on the target robot according to the second control strategy.

[0034] In this way, two types of environmental sensors (the first environmental sensor and the second environmental sensor) are set on the target robot. During the movement of the target robot, first, the first environmental sensor with a large field of view is used to identify obstacles in the surrounding environment, which can improve the speed of obstacle determination, so as to adjust the motion state of the robot in time, that is, determine the first control strategy. This method can effectively ensure driving safety. Further, when it is determined that the first control strategy does not include direct obstacle avoidance, it means that based on the first size detection result, it is not possible to accurately determine that there are obstacles affecting the driving path of the target robot. At this time, the second environmental sensor with high detection accuracy is used for secondary verification of the obstacles, which can effectively improve the accuracy of the obstacle detection result, so as to determine the second control strategy suitable for the current state of the target robot, and control the movement of the target robot with this strategy, which can further ensure the driving safety and task completion degree of the robot.

[0035] The following describes the exemplary steps of the embodiments of the present application: Regarding step S101, in this step, the number of the first environmental sensors set on the target robot can be 1 or more. When there are multiple ones, the first environmental data is the fusion result of the data collected by multiple first environmental sensors. Here, in order to make the first environmental sensor have the characteristic of a large field of view detection range, for example, the first environmental sensor can be a stereo vision sensor.

[0036] Among them, when the first environmental sensor is a stereo vision sensor, the first environmental sensor is set on the surface of the target robot facing the moving direction, and the installation position of the first environmental sensor on the surface of the target robot facing the moving direction is: installed at a position where the first space range in front of the target robot can be monitored, and the specific size of the first space range can be set adaptively.

[0037] In this step, when performing obstacle detection and analysis on the first environmental data, if no obstacle is detected, the target robot is controlled to continue moving according to the preset planned driving data.

[0038] In an implementation manner provided by the present application, the performing obstacle detection and analysis on the first environmental data collected by the first environmental sensor set on the target robot to determine the first size detection result of the obstacle includes: S1011. Preprocess the first environmental data to determine the target point cloud data.

[0039] S1012. Perform point cloud clustering processing on the target point cloud data to determine the ground point cloud and the obstacle point cloud.

[0040] S1013. Process the ground point cloud to determine the ground height information; S1014. Determine the first size detection result of the obstacle based on the obstacle point cloud and the ground height information.

[0041] Regarding step S1011, the first environmental data may be the first raw environmental point cloud data of the environment around the target robot collected by the first environmental sensor.

[0042] Assuming that the first raw environmental point cloud data includes obstacles, this step may specifically include: performing filtering processing on the first raw environmental point cloud data, and determining the remaining point cloud after filtering as the target point cloud data.

[0043] Here, after determining the target point cloud data, the type of each point cloud can be classified to support the execution of step S1012.

[0044] Regarding step S1012, this step may specifically include: clustering the point clouds of the ground type in the target point cloud data to obtain the ground point cloud; clustering the point clouds of the obstacle type in the target point cloud data to obtain the obstacle point cloud.

[0045] Regarding step S1013, this step may specifically include: processing the ground point cloud, extracting the ground plane, and determining the ground height according to the extracted ground plane.

[0046] Regarding step S1014, the first size detection result of the obstacle may specifically be the first height detection result of the obstacle. When it is the height detection result, this step may specifically include: determining the height of the obstacle point cloud according to the obstacle point cloud, comparing the height of the obstacle point cloud with the ground height information, and obtaining the height of the obstacle detected by the first environmental sensor, that is, the first size detection result of the obstacle.

[0047] In this way, by sequentially performing filtering - clustering - extracting the ground plane - comparing the obstacle height with the ground height for height calculation, the accuracy of the obstacle height detection result can be effectively improved.

[0048] Regarding step S102, in this step, when the obstacle heights included in the first size detection result are different, the specific control methods of the corresponding first control strategy will also be different.

[0049] Exemplarily, in the present application, the first control strategy may be a deceleration strategy, a direct obstacle avoidance strategy, or a strategy of controlling the movement of the target robot according to the planned driving data.

[0050] Here, when specifically determining which strategy is the implementation method of the first control strategy according to the first size detection result, determining the first control strategy of the target robot according to the first size detection result of the obstacle includes: S1021. Determine whether the first size detection result of the obstacle is within the size range of the suspected dangerous obstacle; S1022. Determine that the first control strategy is a deceleration strategy.

[0051] S1023. Determine that the first control strategy is a direct obstacle avoidance strategy.

[0052] S1024. Determine that the first control strategy is a strategy of controlling the movement of the target robot according to the planned driving data.

[0053] For steps S1021 to S1024, this embodiment may specifically include: determining whether the first size detection result of the obstacle is within the size range of the suspected dangerous obstacle. If it is, execute step S1022; if it is not within the size range of the suspected dangerous obstacle, but the first size detection result of the obstacle is greater than the upper limit of the size range of the suspected dangerous obstacle, execute step S1023; if it is not within the size range of the suspected dangerous obstacle, but the first size detection result of the obstacle is less than the lower limit of the size range of the suspected dangerous obstacle, execute step S1024.

[0054] Here, the direct obstacle avoidance strategy is a strategy of performing path replanning and bypassing the obstacle. The size range of the suspected dangerous obstacle may specifically be the height range of the suspected dangerous obstacle. The determination of the height range of the suspected dangerous obstacle is based on the passing ability of the target robot to the ground height change and the accuracy of the detection result of the obstacle by the first environmental sensor on the target robot.

[0055] Exemplarily, when the target robot can drive normally within the ground height of 0 - A cm, the first environmental sensor can accurately identify obstacles with a height of B cm (B > A, A > 0) and above, but when it is lower than B cm, misidentification will occur. At this time, the determined height range of the suspected dangerous obstacle is [A cm, B cm].

[0056] Among them, the reason why the first environmental sensor misidentifies when the obstacle is lower than B cm is that when the stereo vision sensor identifies low obstacles, due to the influence of the fluctuations of the scene point clouds such as uneven ground, sunlight, and dark environment, the point cloud recognition result will feedback that there are objects with a height above the ground height, and it is considered that there are obstacles (but actually they are not obstacles). Therefore, misidentification of low obstacles occurs. The low obstacle refers to an obstacle that is higher than the passing height requirement of the robot and for which the first environmental sensor will have misidentification, that is, an obstacle with a height within the height range of the suspected dangerous obstacle is determined as a low obstacle.

[0057] In another example, when the target robot can travel normally at a ground height within -M cm to A cm, the first environmental sensor can accurately identify obstacles at a height of B cm (B > A, A > 0) and above, or at a depth of N cm (N > M, M > 0) and above. However, in other cases, misidentifications may occur. At this time, the determined height range / depth range of the suspected dangerous obstacles is [A cm, B cm], [-N cm, -M cm].

[0058] It should be noted that the reason for describing the size detection result in terms of the height detection result is that, compared with the width detection result or others, the height of the obstacle is the main factor affecting the movement of the robot. For example, when the target robot is a cleaning robot in a shopping mall, during the cleaning operation, low obstacles such as paper balls and the bases of shelves in the shopping mall will affect the normal travel of the cleaning robot (exceeding the passable height). However, the existing environmental perception devices on the robot often cannot accurately detect such low obstacles, resulting in the risk of crashing or jamming. By determining the obstacle based on the height detection result, it can be more accurately identified compared to determining whether there is an obstacle based on other types of size information, thus better ensuring the safe travel of the robot.

[0059] In this way, the present application adopts different control strategies based on different height results of the obstacles detected by the first environmental sensor. This can not only ensure that the target robot timely avoids dangerous obstacles and prevent the risk of crashing, but also, when a suspected dangerous obstacle is detected, through the deceleration control strategy, while reducing the risk of crashing, ensure the completion of the task.

[0060] Regarding step S103, this step may specifically include: identifying whether the first control strategy determined according to the detection result of the first environmental sensor includes a direct obstacle avoidance strategy. If it does not include a direct obstacle avoidance strategy, then perform obstacle detection and analysis on the second environmental data collected by the second environmental sensor set on the target robot, that is, perform a secondary verification to determine the second size detection result of the obstacle; finally, determine the second control strategy of the target robot according to the second size detection result and the strategy determination rule.

[0061] Here, the reason for identifying whether the first control strategy determined according to the detection result of the first environmental sensor includes a direct obstacle avoidance strategy is that when the first control strategy includes a direct obstacle avoidance strategy, it indicates that the first environmental sensor has accurately identified the obstacle and there is no need for secondary verification by the second environmental sensor. When the first control strategy does not include a direct obstacle avoidance strategy, it indicates that the detected height of the obstacle in the first size detection result of the obstacle is lower than B cm.

[0062] Among them, one or more second environmental sensors can be set. When multiple second environmental sensors are set, the second environmental data is the fusion data of the environmental data collected by multiple second environmental sensors.

[0063] The second environmental sensor is used when the detection result of the first environmental sensor is uncertain. Therefore, the detection accuracy of the second environmental sensor is higher than that of the first environmental sensor. When the first environmental sensor is a stereo vision sensor, the second environmental sensor can be a line laser sensor. The second environmental sensor is arranged on the surface of the target robot facing the moving direction, and the installation position of the second environmental sensor on the surface of the target robot facing the moving direction is: installed at a position where the second space range in front of the target robot can be monitored; the first environmental sensor is located above the second environmental sensor, and the first space range includes the second space range.

[0064] Exemplarily, in order to further understand the relative relationship between the installation positions and the field of view ranges of the first environmental sensor and the second environmental sensor, please refer to Figure 2 、 Figure 3 , Figure 2 which is a schematic structural diagram of a robot provided with a first environmental sensor and a second environmental sensor according to the present application, Figure 3 which is a schematic diagram of the detection ranges of the first environmental sensor and the second environmental sensor provided by the present application respectively.

[0065] As Figure 2 shown, one first environmental sensor and two second environmental sensors are arranged on the target robot. Exemplarily, the first environmental sensor can specifically be an anti-fall stereo vision sensor, that is, this stereo vision sensor can simultaneously perform anti-fall and ground protrusion obstacle detection, and the second environmental sensor can be a line laser sensor. As Figure 2 shown, the anti-fall stereo vision sensor is located below the touch screen in front of the robot and is placed downward. Among them, the anti-fall stereo vision sensor can use a large-angle module of structured light to cover the area in front of and obliquely in front of the robot, achieving the effect of preventing the robot from falling and being crushed by the feet. The determination of the specific values of the placement position requirements (height from C cm to D cm) and the forward tilt angle from directly below (angle from E° to F°) is determined by the requirement of accurately detecting obstacles above B cm in advance. Therefore, the installation position of the first environmental sensor should ensure a small blind area and be able to cover the range above X cm in front, so as to enable the robot to sense obstacles above B cm in advance and avoid them. In addition, when the robot is a cleaning robot, this stereo vision sensor can be equipped with an RGB module to identify the material of obstacles through AI, so as to detect different obstacles and identify stains to modify the cleaning strategy.

[0066] Continue to refer to Figure 2 Two second environmental sensors are set on the robot, that is, two line laser sensors are set for detecting low obstacles. The line laser sensors are set at a position slightly above the front radar layer of the robot and are inclined downward. The specific setting position is such that the optical path of the line laser can cover the front of the robot, and the distance from the robot is not less than Y cm (Y < X), and objects above G cm (0 < G ≤ A) can be detected. Preferably, 10 ≤ Y ≤ 20, which can not only detect obstacles at a relatively short distance from the robot, but also avoid difficulties in installation and emergency stop of the robot caused by too small Y value. Preferably, G ≤ 1 to ensure accurate identification of low obstacles. The two line laser sensors are symmetrically arranged along the central axis of the robot, and the distance from the sensor to the axis of symmetry is 13 cm to 15 cm. The installation height of the line laser sensor is 22 cm to 26 cm, and the installation height of the stereo vision sensor is 45 cm to 50 cm.

[0067] Wherein, when Y < X, it indicates that the monitoring range of the first environmental sensor is larger than and includes the monitoring range of the second environmental sensor.

[0068] Exemplarily, please refer to Figure 3 , Figure 3 The large field of view range in Figure 3 is the monitoring range of the first environmental sensor, that is, the first spatial range; Figure 3 The small field of view range in

[0069] is the monitoring range of the second environmental sensor, that is, the second spatial range. Preferably, referring to

[0070] Continue to refer to step S103. In an implementation manner provided by the present application, the obstacle detection and analysis of the second environmental data collected by the second environmental sensor set on the target robot to determine the second size detection result of the obstacle includes: S10311. Perform zoning processing on the second environmental data to determine obstacle area data and non-obstacle area data.

[0071] S10312. Process the non-obstacle area data to determine the mean value and noise standard deviation of the non-obstacle area.

[0072] S10313. Use the mean value of the non-obstacle area to perform compensation processing on the obstacle area data, and calculate the signal mean value of the obstacle area data after compensation processing.

[0073] S10314. Determine the signal-to-noise ratio of the second environmental data based on the signal mean value and the noise standard deviation.

[0074] S10315. Determine the second size detection result of the obstacle according to the determined signal-to-noise ratio and the preset evaluation rule.

[0075] Regarding step S10311, when the second environmental sensor is a line laser sensor, the second environmental data can be line laser data. At this time, this step can specifically include: filtering the entire second environmental data to remove single-point noise, and then using, for example, the ransac algorithm for straight line fitting processing to obtain the data with obstacles, that is, determining the obstacle area data, and then determining the remaining data in the second environmental data except the obstacle area data as the non-obstacle area data.

[0076] Regarding step S10312, the non-obstacle area data divided by the second environmental data is usually mainly the ground or an open area, and its data is usually relatively uniform. However, because the ground is not absolutely flat, it may contain some noise. Therefore, it is necessary to calculate the noise standard deviation to reflect the noise level of this area.

[0077] Regarding step S10313, when using the mean value of the non-obstacle area to perform compensation processing on the obstacle area data, it can specifically be: subtracting the mean value of the non-obstacle area from each data in the obstacle area data.

[0078] Regarding step S10314, this step specifically includes: determining the value obtained by dividing the signal mean value by the noise standard deviation as the signal-to-noise ratio of the second environmental data.

[0079] Regarding step S10315, a signal-to-noise ratio threshold is set in the preset evaluation rule, and the second size detection result is the detection result of whether the dangerous obstacle size requirement is met.

[0080] Here, if the determined signal-to-noise ratio is greater than the signal-to-noise ratio threshold, the determined second size detection result is a detection result that meets the dangerous obstacle size requirement, that is, the second size detection result indicates the existence of a dangerous obstacle.

[0081] If the determined signal-to-noise ratio is not greater than the signal-to-noise ratio threshold, the determined second size detection result is a detection result that does not meet the dangerous obstacle size requirement, that is, the second size detection result indicates the non-existence of a dangerous obstacle.

[0082] In this way, in the present application, the data collected by the second environmental sensor is divided into obstacle area data and non-obstacle area data, the mean and standard deviation are calculated based on the divided data, the signal-to-noise ratio of the second environmental data is determined based on the calculated mean and standard deviation, and finally, based on the determined signal-to-noise ratio, a secondary verification of the obstacle is performed, thereby improving the accuracy of the obstacle recognition result. And through this embodiment, it is also possible to reduce the misjudgment of obstacle recognition caused by interference such as uneven ground.

[0083] Continuing to refer to step S103, in another embodiment provided by the present application, determining the second control strategy of the target robot according to the second size detection result includes: if the second size detection result indicates the existence of a dangerous obstacle, determining the second control strategy as a braking strategy of corresponding braking with reference to the first control strategy of the target robot; if the second size detection result indicates the non-existence of a dangerous obstacle, determining the second control strategy as a strategy of controlling the movement of the target robot according to the planned driving data.

[0084] Here, the braking strategy of corresponding braking with reference to the first control strategy of the target robot can be understood as a strategy of braking according to the current driving speed of the target robot and the distance from the obstacle to ensure that there is no collision with the obstacle.

[0085] When the second size detection result indicates the non-existence of a dangerous obstacle, determining the second control strategy as a strategy of controlling the movement of the target robot according to the planned driving data can specifically be: when the target robot is driving according to a deceleration strategy, controlling it to stop decelerating and resume the preset speed, and continue to drive along the planned path; when the target robot is already driving according to the planned driving data (preset speed, planned path, etc.), continue to maintain the current driving state.

[0086] In this way, by adopting different control strategies for different second size detection results to control the movement of the robot, the safety of the robot's driving can be effectively ensured, and the completion degree of the robot's task can also be ensured.

[0087] Further, for the specific implementation manner of the above second control strategy, the present application provides the following implementation manners: When the first control strategy is a strategy of controlling the movement of the target robot according to the planned driving data, and the second dimension detection result indicates the existence of a dangerous obstacle, the second control strategy is: controlling the target robot to initiate an emergency brake.

[0088] Here, controlling the target robot to initiate an emergency brake means controlling the target robot to perform an emergency brake at the current speed, so as to ensure avoiding a collision with the obstacle.

[0089] When the first control strategy is a deceleration strategy, and the second dimension detection result indicates the existence of a dangerous obstacle, the second control strategy is: determining the current braking change curve of the target robot according to the current driving speed of the target robot under the deceleration strategy and the current interval distance between the target robot and the obstacle; controlling the target robot to smoothly decelerate to a stop according to the current braking change curve.

[0090] Here, the determined current braking change curve records the deceleration change value of the target robot during the process of approaching the obstacle from the current position, and the robot that brakes according to the determined deceleration change value can stop before colliding with the obstacle, and because it performs a non-emergency brake (sudden brake), but a slow brake, it also plays a certain role in protecting the relevant moving parts of the robot.

[0091] In this way, by adopting different braking strategies according to the different speeds of the robot, it can not only effectively ensure avoiding a collision with the obstacle, but also effectively avoid damage to the relevant moving parts of the robot because a slow brake is adopted when the robot speed is relatively slow.

[0092] Regarding step S104, when performing motion control on the target robot according to the second control strategy, specifically, it can be: adjusting the working parameters of the corresponding motion components of the target robot according to the motion adjustment parameters of the robot set in the second control strategy, so as to achieve motion control of the target robot.

[0093] In addition, when this solution is applied to the cleaning field, that is, the target robot is a cleaning robot. At this time, when both the first control strategy and the second control strategy are strategies of controlling the movement of the target robot according to the planned driving data, in an implementation manner provided by the present application, the control method includes: S201. Performing ground information recognition processing on the first environmental data to determine the second ground information in the area to be cleaned.

[0094] S202. Determine the current cleaning strategy for the second floor area based on at least one of the second floor information and the current cleaning mode of the target robot; wherein, the current cleaning strategy includes a mode switching strategy.

[0095] S203. Determine the target cleaning mode according to the current cleaning strategy, and control the target robot to clean the second floor area according to the target cleaning mode.

[0096] For step S201, this step may specifically include: extracting the floor data from the first environmental data, and determining the included floor information (specifically, it may be floor type information) according to the extracted floor data; then, according to the identified floor information, determine whether it includes the second floor information in the area to be cleaned.

[0097] Here, the second floor information can be set according to the relevant performance of the cleaning robot. For example, when the cleaning robot is cleaning a carpet and cleaning other floors, the operating parameters are different. At this time, the second floor information can be set as the carpet, and the floors other than the carpet are determined as the first floor information.

[0098] For step S202, this step may specifically include: when it is determined that the area to be cleaned includes a carpet, identify the current cleaning mode of the target robot, and determine whether it is suitable for cleaning the carpet; and determine the current cleaning strategy according to the judgment result, that is, determine whether to perform a cleaning mode switch.

[0099] For step S203, in this step, determining the target cleaning mode according to the current cleaning strategy may, for example, include: determining the current cleaning mode as the target cleaning module, or switching the current cleaning mode, and determining the switched cleaning mode as the target cleaning mode.

[0100] Here, the target cleaning mode stipulates the working components required for the cleaning robot to currently perform the cleaning task and the working parameters of each working component.

[0101] In this way, on the premise that no obstacle that needs to directly avoid an obstacle is detected, the robot can continue to plan the path movement. At this time, by identifying the floor information from the first environmental data, the distinction and identification between the carpet and other floor materials are realized, the accuracy of carpet identification is improved, and different cleaning modes are adopted for the carpet, so that the determined cleaning mode is more accurate, thereby improving the cleaning effect and efficiency.

[0102] Further, in another embodiment provided in the present application, after determining the first size detection result of the obstacle, the control method further includes: S301. When the first size detection result of the obstacle is within the range of the suspected dangerous obstacle size, mark the current position of the obstacle, determine the first control strategy as the deceleration strategy, and control the target robot to decelerate according to the first control strategy.

[0103] S302. When it is determined that the obstacle is within the monitoring range of the second environmental sensor according to the marked current position of the obstacle, obtain the second environmental data collected by the second environmental sensor and determine the second size detection result.

[0104] S303. Determine the second control strategy of the target robot according to the second size detection result, and perform motion control on the target robot according to the second control strategy.

[0105] Regarding step S301, in this step, when the first size detection result of the obstacle is within the range of the suspected dangerous obstacle size, it indicates that the first environmental sensor cannot completely determine the existence of a dangerous obstacle. At this time, according to the first environmental data, determine the position of the obstacle in the robot coordinate system and control the target robot to decelerate.

[0106] Here, the specific speed during deceleration can be set according to the specific distance between the robot and the marked obstacle.

[0107] Regarding step S302, since the monitoring range of the second environmental sensor is smaller than that of the first environmental sensor, when marking the obstacle, the second environmental data may not include the obstacle data yet. Therefore, the second environmental data analysis can be skipped first, which can reduce the data processing pressure of the processor. When the current position of the marked obstacle appears within the monitoring range of the second environmental sensor, obtaining the second environmental data and performing obstacle recognition to obtain the second size detection result can ensure the effectiveness of data processing.

[0108] Among them, the processing process of determining the second size detection result can refer to the description of step S103 and will not be elaborated here.

[0109] Regarding step S303, the implementation process of this step can refer to the descriptions of steps S103 and S104 and will not be elaborated here.

[0110] In this way, by using the data collected by the first environmental sensor to mark the position of the suspected dangerous obstacle, when the marked obstacle is within the monitoring range of the second environmental sensor, then perform the analysis of the second environmental data and obstacle recognition. This can not only reduce the data processing pressure but also ensure the effectiveness of data processing. And through the secondary verification of the second environmental sensor, the accuracy of the obstacle detection result can be improved, thus ensuring the safe driving of the robot and the timely completion of the task.

[0111] Based on the same inventive concept, a control device corresponding to the control method is also provided in the embodiments of the present application. Since the principle of solving problems by the device in the embodiments of the present application is similar to that of the above control method in the embodiments of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0112] Please refer to Figure 4 、 Figure 5 , Figure 4 which is a schematic structural diagram of a control device for a robot provided by an embodiment of the present application. Figure 5 which is a schematic structural diagram of another control device for a robot provided by an embodiment of the present application. As Figure 4 shown in the control device 400 includes: an analysis module 410, configured to perform obstacle detection and analysis on first environmental data collected by a first environmental sensor provided on a target robot, and determine a first size detection result of the obstacle; a first determination module 420, configured to determine a first control strategy of the target robot according to the first size detection result of the obstacle, and perform motion control on the target robot according to the first control strategy; a second determination module 430, configured to, if the first control strategy does not include a direct obstacle avoidance strategy, perform obstacle detection and analysis on second environmental data collected by a second environmental sensor provided on the target robot, determine a second size detection result of the obstacle, and determine a second control strategy of the target robot according to the second size detection result; the maximum detection distance of the first environmental sensor along the moving direction of the target robot is greater than that of the second environmental sensor, and the detection accuracy of the second environmental sensor is higher than that of the first environmental sensor;

[0113] Optionally, when the first determination module 420 is configured to determine the first control strategy of the target robot according to the first size detection result of the obstacle, the first determination module 420 is configured to: determine whether the first size detection result of the obstacle is within the range of the size of a suspected dangerous obstacle; if it is within, determine that the first control strategy is a deceleration strategy; if it is not within, when the first size detection result of the obstacle is greater than the upper limit of the range of the size of the suspected dangerous obstacle, determine that the first control strategy is a direct obstacle avoidance strategy; if it is not within, when the first size detection result of the obstacle is less than the lower limit of the range of the size of the suspected dangerous obstacle, determine that the first control strategy is a strategy of controlling the movement of the target robot according to the planned driving data.

[0114] Optionally, when the second determination module 430 is used to perform obstacle detection and analysis on the second environmental data collected by the second environmental sensor set on the target robot to determine the second size detection result of the obstacle, the second determination module 430 is configured to: Perform partition processing on the second environmental data to determine obstacle area data and non-obstacle area data; Process the non-obstacle area data to determine the mean value and noise standard deviation of the non-obstacle area; Use the mean value of the non-obstacle area to perform compensation processing on the obstacle area data, and calculate the signal mean value of the obstacle area data after the compensation processing; Determine the signal-to-noise ratio of the second environmental data according to the signal mean value and the noise standard deviation; Determine the second size detection result of the obstacle according to the determined signal-to-noise ratio and the preset evaluation rule.

[0115] Optionally, when the second determination module 430 is used to determine the second control strategy of the target robot according to the second size detection result, the second determination module 430 is configured to: If the second size detection result indicates the existence of a dangerous obstacle, determine that the second control strategy is a braking strategy for corresponding braking with reference to the first control strategy of the target robot; If the second size detection result indicates the non-existence of a dangerous obstacle, determine that the second control strategy is a strategy for controlling the movement of the target robot according to the planned driving data.

[0116] Optionally, when the first control strategy is a strategy for controlling the movement of the target robot according to the planned driving data and the second size detection result indicates the existence of a dangerous obstacle, the second control strategy is: controlling the target robot to start emergency braking; When the first control strategy is a deceleration strategy and the second size detection result indicates the existence of a dangerous obstacle, the second control strategy is: Determine the current braking change curve of the target robot according to the current driving speed of the target robot under the deceleration strategy and the current interval distance between the target robot and the obstacle; Control the target robot to smoothly decelerate to a stop according to the current braking change curve.

[0117] Optionally, both the first environmental sensor and the second environmental sensor are disposed on the surface of the target robot facing the moving direction. The installation position of the first environmental sensor on the surface of the target robot facing the moving direction is: installed at a position where the first space range in front of the target robot can be monitored. The installation position of the second environmental sensor on the surface of the target robot facing the moving direction is: installed at a position where the second space range in front of the target robot can be monitored; the first environmental sensor is located above the second environmental sensor, and the first space range includes the second space range; the first environmental sensor is a stereo vision sensor, and the second environmental sensor is a line laser sensor.

[0118] Optionally, as Figure 5 shown, when the target robot is a cleaning robot, both the first control strategy and the second control strategy are strategies for controlling the movement of the target robot according to the planned driving data. The control device 400 further includes a cleaning module 450, and the cleaning module 450 is configured to: Perform ground information recognition processing on the first environmental data to determine the second ground information in the area to be cleaned; Determine the current cleaning strategy for the second ground area according to at least one of the second ground information and the current cleaning mode of the target robot; wherein, the current cleaning strategy includes a mode switching strategy; Determine the target cleaning mode according to the current cleaning strategy, and control the target robot to clean the second ground area according to the target cleaning mode.

[0119] Optionally, the control device 400 is further configured to: After determining the first size detection result of the obstacle, when the first size detection result of the obstacle is within the range of the suspected dangerous obstacle size, mark the current position of the obstacle, and determine the first control strategy as the deceleration strategy, and control the target robot to decelerate according to the first control strategy; When it is determined that the obstacle is within the monitoring range of the second environmental sensor according to the marked current position of the obstacle, obtain the second environmental data collected by the second environmental sensor, and determine the second size detection result; Determine the second control strategy of the target robot according to the second size detection result, and perform motion control on the target robot according to the second control strategy.

[0120] Please refer to Figure 6 , Figure 6 which is a schematic structural diagram of an electronic device provided by an embodiment of the present application. As Figure 6 shown in, the electronic device 600 includes a processor 610, a memory 620, and a bus 630.

[0121] The memory 620 stores machine-readable instructions executable by the processor 610. When the electronic device 600 runs, the processor 610 communicates with the memory 620 via the bus 630. When the machine-readable instructions are executed by the processor 610, the steps in the method embodiments as described above can be executed. For the specific implementation manners, reference can be made to the method embodiments and will not be elaborated herein. Figure 1 shown in the method embodiments, and for the specific implementation manners, reference can be made to the method embodiments and will not be elaborated herein.

[0122] The embodiments of the present application further provide a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, the steps in the method embodiments as described above can be executed. For the specific implementation manners, reference can be made to the method embodiments and will not be elaborated herein. Figure 1 shown in the method embodiments, and for the specific implementation manners, reference can be made to the method embodiments and will not be elaborated herein.

[0123] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0124] In several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there can be other division manners in actual implementation. For another example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the couplings, direct couplings, or communication connections shown or discussed with each other can be through some communication interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0125] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0126] In addition, in each embodiment of the present application, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0127] When the above-mentioned functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The foregoing storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical discs.

[0128] ​

Claims

1. A control method for a robot, characterized in that, The control method includes: Performing obstacle detection and analysis on the first environmental data collected by the first environmental sensor set on the target robot to determine the first size detection result of the obstacle; Determining the first control strategy of the target robot according to the first size detection result of the obstacle, and performing motion control on the target robot according to the first control strategy; If the first control strategy does not include a direct obstacle avoidance strategy, performing obstacle detection and analysis on the second environmental data collected by the second environmental sensor set on the target robot to determine the second size detection result of the obstacle, and determining the second control strategy of the target robot according to the second size detection result; the maximum detection distance of the first environmental sensor along the moving direction of the target robot is greater than that of the second environmental sensor, and the detection accuracy of the second environmental sensor is higher than that of the first environmental sensor; Performing motion control on the target robot according to the second control strategy.

2. The control method according to claim 1, characterized in that The determining the first control strategy of the target robot according to the first size detection result of the obstacle includes: Determining whether the first size detection result of the obstacle is within the range of the suspected dangerous obstacle size; If it is within, determining the first control strategy as a deceleration strategy; If it is not within, when the first size detection result of the obstacle is greater than the upper limit of the suspected dangerous obstacle size range, determining the first control strategy as a direct obstacle avoidance strategy; If it is not within, when the first size detection result of the obstacle is less than the lower limit of the suspected dangerous obstacle size range, determining the first control strategy as a strategy for controlling the motion of the target robot according to the planned driving data.

3. The control method according to claim 1, characterized in that, The performing obstacle detection and analysis on the second environmental data collected by the second environmental sensor set on the target robot to determine the second size detection result of the obstacle includes: Performing partition processing on the second environmental data to determine the obstacle area data and the non-obstacle area data; Processing the non-obstacle area data to determine the mean value and the noise standard deviation of the non-obstacle area; Compensating the obstacle area data by using the mean value of the non-obstacle area, and calculating the signal mean value of the compensated obstacle area data; Determining the signal-to-noise ratio of the second environmental data according to the signal mean value and the noise standard deviation; Determining the second size detection result of the obstacle according to the determined signal-to-noise ratio and the preset evaluation rule.

4. The control method according to claim 3, wherein The determining the second control strategy of the target robot according to the second size detection result includes: If the second size detection result indicates the existence of a dangerous obstacle, determining the second control strategy as a braking strategy of referring to the first control strategy of the target robot for corresponding braking; If the second size detection result indicates the non-existence of a dangerous obstacle, determining the second control strategy as a strategy for controlling the motion of the target robot according to the planned driving data.

5. The control method according to claim 4, wherein When the first control strategy is a strategy of controlling the movement of the target robot according to the planned driving data, and the second size detection result indicates the existence of a dangerous obstacle, the second control strategy is: controlling the target robot to initiate an emergency brake; When the first control strategy is a deceleration strategy and the second size detection result indicates the existence of a dangerous obstacle, the second control strategy is: Determining the current braking change curve of the target robot according to the current driving speed of the target robot under the deceleration strategy and the current distance between the target robot and the obstacle; Controlling the target robot to smoothly decelerate to a stop according to the current braking change curve.

6. The control method according to claim 1, wherein Both the first environmental sensor and the second environmental sensor are arranged on the surface of the target robot facing the moving direction. The installation position of the first environmental sensor on the surface of the target robot facing the moving direction is: installed at a position where the first space range in front of the target robot can be monitored. The installation position of the second environmental sensor on the surface of the target robot facing the moving direction is: installed at a position where the second space range in front of the target robot can be monitored; the first environmental sensor is located above the second environmental sensor, and the first space range includes the second space range; the first environmental sensor is a stereo vision sensor, and the second environmental sensor is a line laser sensor.

7. The control method according to claim 1, wherein When the target robot is a cleaning robot, and both the first control strategy and the second control strategy are strategies of controlling the movement of the target robot according to the planned driving data, the control method includes: Performing ground information recognition processing on the first environmental data to determine the second ground information in the area to be cleaned; Determining the current cleaning strategy for the second ground area according to at least one of the second ground information and the current cleaning mode of the target robot; wherein, the current cleaning strategy includes a mode switching strategy; Determining the target cleaning mode according to the current cleaning strategy, and controlling the target robot to clean the second ground area according to the target cleaning mode.

8. The control method according to claim 1, characterized in that After determining the first size detection result of the obstacle, the control method further includes: When the first size detection result of the obstacle is within the size range of a suspected dangerous obstacle, marking the current position of the obstacle, determining the first control strategy as a deceleration strategy, and controlling the target robot to decelerate according to the first control strategy; When it is determined that the obstacle is within the monitoring range of the second environmental sensor according to the marked current position of the obstacle, obtaining the second environmental data collected by the second environmental sensor and determining the second size detection result; Determining the second control strategy of the target robot according to the second size detection result, and performing motion control on the target robot according to the second control strategy.

9. A control device for a robot, characterized in that, The control device includes: An analysis module for performing obstacle detection and analysis on the first environmental data collected by the first environmental sensor provided on the target robot to determine the first size detection result of the obstacle; The first determination module is configured to determine a first control strategy for the target robot according to the first size detection result of the obstacle, and perform motion control on the target robot according to the first control strategy; The second determination module is configured to, if the first control strategy does not include a direct obstacle avoidance strategy, perform obstacle detection and analysis on the second environmental data collected by the second environmental sensor provided on the target robot, determine a second size detection result of the obstacle, and determine a second control strategy for the target robot according to the second size detection result; the maximum detection distance of the first environmental sensor along the moving direction of the target robot is greater than that of the second environmental sensor, and the detection accuracy of the second environmental sensor is higher than that of the first environmental sensor; The control module is configured to perform motion control on the target robot according to the second control strategy.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is run by a processor, it executes the steps of the control method according to any one of claims 1 to 8.

Images