Robot escape and obstacle crossing method and apparatus

Abstract

A robot escape and obstacle crossing method. The robot comprises a body (11) and a robotic arm (12), wherein the robotic arm (12) is arranged on the body (11). The method comprises: acquiring the current pose of the robotic arm (12); when the current pose of the robotic arm (12) indicates that the robotic arm (12) is in an extended state, detecting environmental information of a scene where the robotic arm (12) is currently located; and then on the basis of the current pose of the robotic arm (12) in combination with the environmental information, controlling the robot to perform escape and obstacle-crossing processing. In this way, when the robotic arm (12) of the robot is in an extended state, different escape and obstacle-crossing processing can be performed on the basis of different environments in which the robotic arm (12) is currently located, thereby improving the adaptability of the escape and obstacle-crossing processing to the current pose of the robotic arm (12) and the environment in which the robotic arm (12) is located, and further reducing damage to the robotic arm (12) and / or objects surrounding the robotic arm caused by the robot performing the escape and obstacle-crossing processing. Further provided are a robot escape and obstacle crossing apparatus, a robot, a computer-readable storage medium, and a computer program product.

Description

Methods and devices for robots to escape obstacles Technical Field

[0001] This disclosure is based on and claims priority to Chinese Patent Application No. 202510305708.6, filed on March 14, 2025, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This disclosure relates to, but is not limited to, the field of mobile robots, and particularly to a method and apparatus for a robot to escape from obstacles. Background Technology

[0003] With the rapid development of technology, mobile robots with foldable or retractable robotic arms are being used more and more widely. Summary of the Invention

[0004] This disclosure provides a method for a robot to escape from obstacles. The mobile robot includes a body and a robotic arm, with the robotic arm mounted on the body. The method includes: acquiring the current posture of the robotic arm; when the current posture of the robotic arm indicates that the robotic arm is extended, detecting environmental information of the scene in which the robotic arm is currently located; and controlling the mobile robot to perform obstacle-avoidance processing based on the current posture of the robotic arm and the environmental information.

[0005] In some embodiments, controlling a mobile robot to perform obstacle avoidance and obstacle traversal based on the current posture of the robotic arm and environmental information includes: predicting the safety level of the mobile robot performing the target obstacle avoidance and obstacle traversal action based on environmental information and the current posture information of the robotic arm; and controlling the mobile robot to perform obstacle avoidance and obstacle traversal based on the safety level.

[0006] In some embodiments, controlling a mobile robot to perform obstacle avoidance and obstacle crossing based on the level of safety includes at least one of the following: when the level of safety meets the target safety conditions, controlling the mobile robot to perform the target obstacle avoidance and obstacle crossing action; when the level of safety does not meet the target safety conditions, controlling the mobile robot to perform obstacle avoidance and obstacle crossing based on the load state of the robotic arm.

[0007] In some embodiments, based on the load state of the robotic arm, controlling the mobile robot to perform obstacle avoidance and obstacle crossing operations includes at least one of the following: when the robotic arm is in a loaded state, controlling the mobile robot to perform a preset departure action to attempt to leave the current obstacle avoidance and obstacle crossing area, and / or marking the current obstacle avoidance and obstacle crossing area as a loaded, impassable area in the environment map corresponding to the current scene; when the robotic arm is in an unloaded state, controlling the robotic arm to retract, and controlling the mobile robot to perform the target obstacle avoidance and obstacle crossing action.

[0008] In some embodiments, the mobile robot further includes a lifting mechanism disposed at the bottom of the body; when the safety level meets the target safety conditions, the mobile robot is controlled to perform the target obstacle escape action, including: controlling the lifting mechanism to lift the body to perform the target obstacle escape action; when the safety level does not meet the target safety conditions, the mobile robot is controlled to perform obstacle escape processing based on the load state of the robotic arm, including: controlling the lifting mechanism to lower the body during the obstacle escape processing.

[0009] In some embodiments, the method further includes: controlling the mobile robot to perform a target escape and obstacle-crossing action when the current posture of the robotic arm indicates that the robotic arm has retracted.

[0010] This disclosure provides a robot obstacle avoidance and escaping device. The mobile robot includes a body and a robotic arm, with the robotic arm mounted on the body. The device includes: an acquisition module for acquiring the current posture of the robotic arm; a detection module for detecting environmental information of the current scene where the robotic arm is located when the current posture of the robotic arm indicates that the robotic arm is extended; and a control module for controlling the mobile robot to perform obstacle avoidance and escaping processing based on the current posture of the robotic arm and the environmental information.

[0011] In some embodiments, the control module is further configured to: predict the safety level of the mobile robot performing the target obstacle avoidance action based on environmental information and the current pose information of the robotic arm; and control the mobile robot to perform obstacle avoidance processing based on the safety level.

[0012] In some embodiments, the control module is further configured to: control the mobile robot to perform a target obstacle avoidance action when the safety level meets the target safety conditions; or control the mobile robot to perform obstacle avoidance processing based on the load state of the robotic arm when the safety level does not meet the target safety conditions.

[0013] In some embodiments, the control module is further configured to: when the robotic arm is in a loaded state, control the mobile robot to perform a preset departure action to attempt to leave the current obstacle-crossing area, and / or mark the current obstacle-crossing area as a loaded, impassable area in the environment map corresponding to the current scene; when the robotic arm is in an unloaded state, control the robotic arm to retract and control the mobile robot to perform the target obstacle-crossing action.

[0014] In some embodiments, the mobile robot further includes a lifting mechanism disposed at the bottom of the body; the control module is also configured to: control the lifting mechanism to lift the body to perform the target obstacle escape action when the safety level meets the target safety conditions; and control the lifting mechanism to lower the body during the obstacle escape process when the safety level does not meet the target safety conditions.

[0015] In some embodiments, the control module is further configured to: control the mobile robot to perform target escape and obstacle-crossing actions when the current posture of the robotic arm indicates that the robotic arm has retracted.

[0016] This disclosure provides a mobile robot, including a memory and a processor. The memory stores a computer program that can run on the processor. When the processor executes the program, it implements the steps in the above-described robot obstacle avoidance and obstacle crossing method.

[0017] This disclosure provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps in the above-described robot obstacle avoidance and evasion method.

[0018] This disclosure provides a processor that is communicatively connected to a memory. The memory stores a computer program that can run on the processor. When the processor executes the computer program, it implements the steps in the above-described robot obstacle avoidance method. Attached Figure Description

[0019] Figure 1 illustrates a robot obstacle avoidance method provided in an embodiment of this disclosure;

[0020] Figure 2 is a schematic diagram of the posture of a robot provided in an embodiment of this disclosure;

[0021] Figure 3 is a schematic diagram of the posture of a robot provided in an embodiment of this disclosure;

[0022] Figure 4 is a schematic diagram of the posture of a robot provided in an embodiment of this disclosure;

[0023] Figure 5 is a flowchart of a robot obstacle avoidance and treacherous crossing method provided in an embodiment of this disclosure;

[0024] Figure 6 is a structural schematic diagram of a robot obstacle-avoiding device provided in an embodiment of this disclosure;

[0025] Figure 7 is a schematic diagram of the structure of a robot provided in an embodiment of this disclosure. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of this disclosure clearer, the technical solutions of this disclosure are further described in detail below with reference to the accompanying drawings and embodiments. The described embodiments should not be regarded as limitations on this disclosure. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0027] In the following description, references to "some embodiments" describe a subset of all possible embodiments; however, it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict. The terms "first / second / third" are used merely to distinguish similar objects and do not represent a specific ordering of objects. It is understood that "first / second / third" may be interchanged in a specific order or sequence where permitted, so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein.

[0028] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure pertains. The terminology used herein is for descriptive purposes only and is not intended to limit the scope of this disclosure.

[0029] With the rapid development of technology, mobile robots with foldable or retractable robotic arms are becoming increasingly widely used. During application, mobile robots with robotic arms may encounter situations where they get stuck or need to overcome obstacles. When the mobile robot is escaping or overcoming obstacles, the robotic arm and / or objects around it may be damaged.

[0030] Therefore, this disclosure provides a method for a robot to escape obstacles. This method can be applied to a robot, which includes a body and a robotic arm. The robotic arm is mounted on the body (e.g., installed in a compartment on the top of the body, folded into the top of the body, etc.). Here, "robot" refers to a robot capable of autonomous movement. For example, the robot may include, but is not limited to, at least one of cleaning robots (such as sweeping robots, floor scrubbers, mopping robots, and combined washing and mopping robots), guiding robots, and service robots. As shown in Figure 1, the method includes the following steps S101 to S103:

[0031] Step S101: Obtain the current posture of the robotic arm.

[0032] In embodiments of the present invention, the robotic arm can be used for at least one of grasping, handling, positioning, assembly, and inspection.

[0033] For example, a robotic arm can use connected gripping components to grasp objects and complete a transport task.

[0034] For example, a robotic arm can use precise motion to help a robot overcome obstacles and complete a positioning task.

[0035] In some implementations, the robot can detect obstacles to obtain the current posture of the robotic arm. The robot's detection of obstacles can indicate at least one of the following: the robot is currently in a scenario where it is stuck by an obstacle or needs to cross an obstacle.

[0036] For example, during the robot's movement, there may be situations where the wheels or the robot body get stuck by surrounding obstacles.

[0037] For example, during the robot's movement, there may be situations where it needs to pass through or cross obstacles such as thresholds or steps.

[0038] In some implementations, the robot may include a first acquisition component, which can be used to acquire environmental information about the robot's current location. The first acquisition component may include, but is not limited to, at least one of a ranging component, an image acquisition component, etc.; the ranging component may include, but is not limited to, at least one of a lidar ranging component, an infrared ranging component, a time-of-flight (TOF) ranging component, an ultrasonic ranging component, etc.; the image acquisition component may include, but is not limited to, at least one of a red-green-blue (RGB) image acquisition component, a depth image acquisition component, an infrared image acquisition component, etc.

[0039] In some implementations, the type of the first acquisition component may differ, and the type of environmental information acquired may also differ. For example, the environmental information may include, but is not limited to, at least one of point cloud information, image information, etc.

[0040] In some implementations, the robot can perform obstacle detection in real time during movement. When the environmental information collected by the first acquisition component indicates that the robot has detected an obstacle, it can determine whether the robot is currently stuck by an obstacle or needs to cross an obstacle. Furthermore, in the current scenario, the robot arm's current posture can be obtained.

[0041] For example, during movement, the robot can use radar ranging components to collect point cloud information of its surroundings in real time. Based on this point cloud information, if the robot detects a point cloud in the direction of travel that is less than a distance threshold from the robot body, it determines that the robot needs to cross the obstacle and obtain the current posture of the robotic arm when it continues to move in that direction.

[0042] In some implementations, the current posture of the robotic arm can be detected based on the currently collected environmental information including the robotic arm, thus obtaining the current posture of the robotic arm.

[0043] In some implementations, the current posture of the robotic arm can be determined based on the current angles of its joints.

[0044] In some implementations, the current posture of the robotic arm can characterize at least one of the following states: whether the robotic arm is carrying a load, the position of the robotic arm, or whether the robotic arm is folded. For example, the current posture of the robotic arm may include, but is not limited to, at least one of the following states: robotic arm carrying a load, robotic arm unloaded, or robotic arm retracted.

[0045] For example, as shown in Figure 2, when the robotic arm is in a retracted position, it can be folded inside the body 11 of the robot 10. In this case, the movement of the robot 10 will not affect the robotic arm.

[0046] For example, as shown in Figure 3, the current posture of the robotic arm is that it is unloaded, with the robotic arm 12 extending from the top of the body 11 but not carrying any object. At this time, the movement of the robot 10 will drive the robotic arm 12.

[0047] For example, as shown in FIG4, when the current posture of the robotic arm is that the robotic arm 12 extends from the top of the body 11 and carries an object 13, the movement of the robot 10 will move the robotic arm 12 and the object 13 carried by the robotic arm 12.

[0048] Step S102: When the current posture of the robotic arm indicates that the robotic arm is extended, detect the environmental information of the scene in which the robotic arm is currently located.

[0049] Here, the environmental information of the current scene of the robotic arm can represent at least one of the following: obstacles around the robotic arm in its current posture, whether the robotic arm is carrying an object, and object parameters of the object carried by the robotic arm; wherein, object parameters can include, but are not limited to, at least one of the following: object type, quantity, weight, volume, etc.

[0050] The term "extended" indicates that the current posture of the robotic arm is extended, which may include, but is not limited to, at least one of the following: extending from the housing, extending relative to the top plane of the body.

[0051] In some implementations, the robot may include a second acquisition component, which can be used to acquire environmental information about the scene in which the robotic arm is currently located. The second acquisition component may include, but is not limited to, at least one of a ranging component, an image acquisition component, etc.; the ranging component may include, but is not limited to, at least one of a lidar ranging component, an infrared ranging component, a TOF ranging component, an ultrasonic ranging component, etc.; the image acquisition component may include, but is not limited to, at least one of an RGB image acquisition component, a depth image acquisition component, an infrared image acquisition component, etc.

[0052] In some implementations, the type of the second acquisition component may vary, and the type of environmental information about the current scene of the robotic arm acquired may also vary. For example, the environmental information may include, but is not limited to, at least one of point cloud information, image information, etc.

[0053] In some implementations, a map of the robot's current environment can be created using a second acquisition component. For example, a three-dimensional map of the robot's current environment can be created using a Time-of-Flight (TOF) ranging component or a camera via the Simultaneous Localization and Mapping (SLAM) method.

[0054] In some implementations, the created map can be updated in real time, and the distance between the robotic arm and objects in the map can be detected in real time to prevent collisions.

[0055] In some implementations, the map may be stored in the robot's local memory and / or in the cloud, etc.

[0056] Step S103: Based on the current posture of the robotic arm and environmental information, control the robot to perform obstacle avoidance and obstacle crossing.

[0057] Here, obstacle avoidance and obstacle crossing can include, but is not limited to, at least one of the following: removing the robot from a stuck position, passing through obstacles, or crossing obstacles.

[0058] For example, when the robotic arm is extended and there are low obstacles in front of the robot, if there are no obstacles above the robotic arm in the surrounding environment corresponding to the robot's location, the robot can overcome obstacles by crossing them.

[0059] For example, when the robotic arm extends and the robot is stuck in its current position, if the environmental information indicates that there are no objects in the surrounding environment corresponding to the robot's position that can collide with the robotic arm after the robotic arm rotates, the robot can escape the obstacle by rotating its chassis.

[0060] In this embodiment, when the robot detects an obstacle, the current posture of the robot's robotic arm is acquired. If the current posture indicates that the robotic arm is extended, environmental information about the current scene in which the robotic arm is located is detected. Then, based on the current posture of the robotic arm and the environmental information, the robot is controlled to perform obstacle-avoidance processing. In this way, when the robot detects an obstacle and the robotic arm is extended, different obstacle-avoidance processing can be executed depending on the different environments in which the robotic arm is located. This improves the adaptability of obstacle-avoidance processing to the current posture of the robotic arm and the surrounding environment, further reducing damage to the robotic arm and / or objects around the robotic arm caused by the robot's obstacle-avoidance processing.

[0061] In some embodiments, step S103 may include the following steps S111 to S112:

[0062] Step S111: Based on environmental information and the current pose information of the robotic arm, predict the safety level of the robot's target escape and obstacle crossing actions.

[0063] Here, the target escape and obstacle-crossing action can include at least one of the following: escape action that enables the robot to get out of the stuck position, obstacle-crossing action that enables the robot to pass through the obstacle, and obstacle-crossing action that enables the robot to cross the obstacle.

[0064] For example, a robot can pass through low obstacles such as thresholds by performing at least one of the following actions: acceleration, twisting, or leaping.

[0065] For example, a robot can break free from its current stuck position by performing at least one of the following actions: rotating, moving forward, or moving backward.

[0066] Safety level can characterize at least one of the following: the safety level of the robot, the safety level of the robotic arm, the safety level of objects loaded on the robotic arm, the safety level of objects around the robot, and the safety level of objects around the robotic arm.

[0067] For example, when the environment around the robotic arm is open and the robotic arm is loaded, it can be predicted that the robot is relatively safe in performing target escape and obstacle crossing actions.

[0068] For example, if the robot arm is carrying a heavy object and the robot is about to pass through a low obstacle, and it is predicted that the robot may experience instability or the object may fall off the robot arm after performing the target obstacle-crossing action, then the safety level of the robot performing the target obstacle-crossing action is determined to be low.

[0069] In some implementations, environmental information may include the distance between the robotic arm and surrounding objects. If the distance between the robotic arm and surrounding objects is greater than a distance threshold, the safety level of the robot performing the target escape and obstacle crossing action can be predicted as safe.

[0070] In some implementations, the safety level of the robot performing the target escape and obstacle crossing action can be predicted to be unsafe if the robot arm is carrying a load and the weight of the load exceeds a weight threshold.

[0071] Step S112: Based on the level of safety, control the robot to perform obstacle removal and evasion procedures.

[0072] Here, the robot can be controlled to perform obstacle-crossing actions based on different safety levels, either through target obstacle-crossing actions or non-target obstacle-crossing actions.

[0073] For example, if the safety level indicates that the robot will not cause damage to the robotic arm, the robot, or the surrounding environment after accelerating forward, it can be used to overcome obstacles by accelerating forward.

[0074] For example, if the robot's ability to cross an obstacle would damage the robotic arm, it can be used to overcome obstacles without crossing them, given that the safety level indicates that the robot would be unable to cross the obstacle.

[0075] In this embodiment, the safety level of the robot performing the target obstacle-crossing action is first predicted based on environmental information and the current pose of the robotic arm; then, based on the safety level, the robot is controlled to perform the obstacle-crossing process. In this way, after predicting the safety level of the robot performing the target obstacle-crossing action based on environmental information and the current pose of the robotic arm, the most suitable obstacle-crossing action for the current scenario (e.g., the target obstacle-crossing action, or an obstacle-crossing action that is not the target obstacle-crossing action) is selected based on the safety level for the obstacle-crossing process, thereby further improving the adaptability and safety of the obstacle-crossing process in the current scenario.

[0076] In some embodiments, step S112 may include at least one of steps S121 to S122:

[0077] Step S121: When the safety level meets the target safety conditions, control the robot to perform the target escape and obstacle crossing actions.

[0078] Here, target safety conditions can characterize the target conditions under which the robotic arm, robot, and / or surrounding objects are in a safe state after the robot performs target escape and obstacle-crossing actions.

[0079] For example, if the distance between the robotic arm and / or the robot and surrounding objects is greater than a distance threshold after the robot performs the target escape and obstacle crossing action, it can be determined that the safety level meets the target safety conditions.

[0080] For example, if the distance between the object carried by the robotic arm and the surrounding objects is greater than a distance threshold after the robot performs the target escape and obstacle crossing action, it can be determined that the safety level meets the target safety conditions.

[0081] Step S122: If the safety level does not meet the target safety conditions, control the robot to perform obstacle avoidance and obstacle crossing based on the load state of the robotic arm.

[0082] Here, the load state of the robotic arm can characterize at least one of the following: whether the robotic arm is carrying a load, the state of the object carried by the robotic arm, etc., including but not limited to at least one of the following: unloaded, loaded, the weight of the loaded object is large, the weight of the loaded object is small, the volume of the loaded object is large, the volume of the loaded object is small.

[0083] For example, when the robotic arm is carrying a load, and the load is a light object such as a sock, a crumpled piece of paper, or a plastic toy, the load state of the robotic arm can be determined to be "carried and lightly loaded".

[0084] When the robotic arm is carrying a load, and the load consists of relatively heavy objects such as shoes, furniture, or electronic devices, the load state of the robotic arm can be determined as "carrying a load and having a relatively heavy load".

[0085] For example, when the target's obstacle-crossing action is shaking, rotating, twisting, etc., and the robotic arm is under load and the load is heavy, obstacle-crossing can be carried out by moving forward or backward.

[0086] In this embodiment, when the safety level meets the target safety conditions, the robot is controlled to perform the target obstacle-crossing action; when the safety level does not meet the target safety conditions, the robot is controlled to perform obstacle-crossing processing based on the load state of the robotic arm. In this way, the final obstacle-crossing processing method can be determined based on the different safety levels of the target obstacle-crossing action and the load state of the robotic arm, thereby further improving the adaptability of the obstacle-crossing processing to the current scene and the load state of the robotic arm, and further improving the safety of the robotic arm, the robot, and / or surrounding objects.

[0087] It is understandable that when there are multiple target escape and obstacle crossing actions, each target escape and obstacle crossing action can correspond to its own safety level and target safety conditions. If the safety level corresponding to some target escape and obstacle crossing actions meets the target safety conditions, the final escape and obstacle crossing method can be further determined based on the target escape and obstacle crossing actions and the load state of the robotic arm.

[0088] In some embodiments, controlling the mobile robot to perform obstacle avoidance and evasion based on the load state of the robotic arm in step S122 above may include at least one of the following steps S131 to S132:

[0089] Step S131: When the robotic arm is in a loaded state, control the robot to perform a preset departure action to attempt to leave the current area to be freed from obstacles and / or mark the current area to be freed from obstacles as a loaded, impassable area in the environmental map corresponding to the current scene.

[0090] Here, the preset departure action can be pre-configured by the user, and may include, but is not limited to, attempting to leave the current obstacle-crossing area based on a preset speed, preset rotation angle, and preset distance. This embodiment of the disclosure does not limit this. The preset speed may be less than a preset speed threshold, the preset rotation angle may be less than a preset angle threshold, or the preset distance may be less than a preset distance threshold. The speed threshold, angle threshold, and distance threshold can be upper limits for distance, speed, and rotation angle, respectively, determined by those skilled in the art based on the actual application scenario, to enable the robot to gently leave the current obstacle-crossing area.

[0091] In some implementations, the environment map corresponding to the current scene may include, but is not limited to, at least one of a 3D point cloud map, a 2D planar map, etc.

[0092] For example, the environmental map corresponding to the current scene may include the three-dimensional map established by the acquisition component in the above embodiments.

[0093] It is understandable that when the robotic arm is under load, leaving the area where it needs to escape from obstacles can reduce the risk of damage to the robotic arm and the object it is carrying if it is forced to perform an escape and obstacle-crossing action.

[0094] Marking corresponding areas on the environment map as areas that cannot be traversed while carrying a load allows devices moving in the current environment based on the environment map to determine in advance whether to leave the area while carrying a load, thereby improving the processing efficiency of devices performing load-carrying movement tasks.

[0095] Step S132: When the robotic arm is in an unloaded state, control the robotic arm to retract and control the robot to perform the target escape and obstacle crossing action.

[0096] Here, controlling the retraction of the robotic arm can include, but is not limited to, retracting the robotic arm into the receiving compartment, retracting the robotic arm to fit against the top of the machine body, retracting and folding the robotic arm, etc.

[0097] When the robotic arm is in an unloaded state, it can be determined that there is no object being carried on the robotic arm. Retracting the robotic arm will not cause damage to it. Therefore, the robotic arm can be retracted without considering the impact of performing the target obstacle-crossing action on the robotic arm. The robot can then be further controlled to perform the target obstacle-crossing action.

[0098] In this embodiment, when the robotic arm is in a loaded state, the robot is controlled to perform a preset departure action to attempt to leave the area to be extricated from the obstacle, and / or to mark the area to be extricated from the obstacle as a non-passable area with a load in the environmental map corresponding to the current scene. When the robotic arm is in an unloaded state, the robotic arm is controlled to retract, and the robot is controlled to perform the target obstacle-crossing action. Thus, on the one hand, considering that performing obstacle-crossing actions may cause damage to the loaded robotic arm, the object carried by the robotic arm, and objects in the surrounding environment, performing the preset departure action can improve the safety of the robot performing obstacle-crossing operations while the robotic arm is loaded. On the other hand, by marking the non-passable area with a load in the environmental map corresponding to the current scene, other devices, including the current robot, can improve the processing efficiency of performing loaded tasks in the current environment, reducing the possibility of re-entering the area with a load. Furthermore, by controlling the robot to perform the target obstacle-crossing action after the unloaded robotic arm is retracted, the robot's ability to complete obstacle-crossing is improved without affecting the robotic arm's function and safety, further improving the robot's performance.

[0099] In some embodiments, the robot further includes a lifting mechanism disposed at the bottom of the body, and step S121 may include the following step S141:

[0100] Step S141: When the safety level meets the target safety conditions, control the lifting mechanism to raise the body to perform the target escape and obstacle crossing action.

[0101] Here, the lifting mechanism can raise the robot's body, thereby increasing its position and allowing it to cross obstacles or escape from a stuck position.

[0102] For example, the lifting mechanism may include at least one of a lifting servo motor, a lifting bracket, etc.

[0103] In some implementations, after the lifting mechanism is controlled to raise the body and complete the target escape and obstacle crossing action, the lifting mechanism can be controlled to lower the body to the target position; wherein, the target position may include, but is not limited to, at least one of the positions corresponding to the original height, the positions corresponding to the preset height, etc.

[0104] In this embodiment, when the safety level meets the target safety conditions, the mobile robot is controlled to perform a target escape and obstacle-crossing action. During the execution of the target escape and obstacle-crossing action, a lifting mechanism located at the bottom of the robot body is controlled to raise the robot body. In this way, by increasing the height of the robot body, the likelihood of the robot successfully escaping and overcoming obstacles by performing the target escape and obstacle-crossing action is increased, thereby further improving the success rate of the robot in successfully escaping and overcoming obstacles.

[0105] In some embodiments, step S122 may include the following step S151:

[0106] Step S151: If the safety level does not meet the target safety conditions, based on the load state of the robotic arm, control the robot to perform obstacle escape and obstacle crossing, and control the lifting mechanism to lower the robot body during the obstacle escape and obstacle crossing process.

[0107] Here, the lifting mechanism can lower the robot's body, thereby lowering the robot's position and reducing the center of gravity and position of the robotic arm and the robot.

[0108] For example, if there are obstacles above the robotic arm during the robot's obstacle-crossing process, the robotic arm may be damaged. Therefore, by controlling the lifting mechanism to lower the robot body, damage to the robotic arm can be reduced.

[0109] In this embodiment, when the safety level does not meet the target safety conditions, the robot is controlled to perform obstacle avoidance and evasion based on the load state of the robotic arm, and during the obstacle avoidance and evasion process, the lifting mechanism is controlled to lower the robot body. In this way, by lowering the center of gravity and position of the robotic arm and the robot, the safety level of the robot's obstacle avoidance and evasion process can be improved while reducing the possibility of damage to the robotic arm, the robot, and / or surrounding objects.

[0110] In some embodiments, the above-described robot obstacle avoidance method may further include the following step S161:

[0111] Step S161: When the current posture of the robotic arm indicates that the robotic arm has retracted, control the robot to perform the target escape and obstacle crossing action.

[0112] Here, with the robotic arm retracted, it can be determined that the robot's current objective obstacle avoidance operation has little impact on the robotic arm. Therefore, the robot can be directly controlled to perform the objective obstacle avoidance operation.

[0113] In this embodiment, the robot is controlled to perform the target obstacle-crossing action while its current posture indicates that it is retracting. This allows the robot to directly execute the target obstacle-crossing action without affecting its current posture, thus improving the robot's efficiency in overcoming obstacles while considering the safety of the robot and surrounding objects.

[0114] In related technologies, robots with foldable or retractable robotic arms can perform grasping operations, and further, with a movable body, can carry the grasped object along with them.

[0115] This disclosure provides a method for a robot to escape obstacles and overcome difficulties. The method can be applied to a robot, which includes a body and a robotic arm, the robotic arm being mounted in a compartment on top of the body. As shown in Figure 5, the method includes the following steps S501 to S509:

[0116] Step S501: Determine the strategy for getting out of trouble and overcoming obstacles.

[0117] Here, when the robot is triggered to overcome obstacles, it can perform obstacle-avoidance processing according to different obstacle-avoidance strategies.

[0118] In some implementations, escape and obstacle-crossing strategies can be divided into strict escape and obstacle-crossing strategies and lenient escape and obstacle-crossing strategies.

[0119] In some implementations, the robot's obstacle avoidance strategy can be determined based on the robot arm's current posture and / or load status.

[0120] For example, when a robotic arm grasps a heavy object, a strict obstacle avoidance strategy can be determined for the robot. This can improve the safety of the robotic arm, the object it grasps, the robot itself, and / or surrounding objects.

[0121] For example, when the robotic arm is grasping a light object, is unloaded, is close to the top of the robot body, or is retracted, a relaxed obstacle avoidance strategy can be determined. This reduces the restrictions on the robot's obstacle avoidance processing and improves its efficiency.

[0122] In some implementations, for robots with lifting mechanisms, when implementing a strict obstacle avoidance strategy, the mechanism is not used to lift the robot body when the robotic arm is outside the robot body; when implementing a relaxed obstacle avoidance strategy, the mechanism may or may not be used to lift the robot body.

[0123] Step S502: Under the strict obstacle-avoidance strategy, the robot detects the obstacle.

[0124] Here, when the robot is executing a strict obstacle-avoidance strategy, step S503 is executed after an obstacle is detected.

[0125] Step S503: Determine whether the robotic arm is under load.

[0126] Here, the current posture and / or load state of the robotic arm in the above-mentioned robot obstacle avoidance method can be determined.

[0127] If the robotic arm is determined to be loaded, proceed to step S504; if the robotic arm is determined to be unloaded, proceed to step S505.

[0128] Step S504: Gently leave, add a load-incompatible area.

[0129] Here, under a strict obstacle-avoidance strategy, when in an area where the robot is to be freed from obstacles, it does not perform any obstacle-avoidance actions. If it detects a stuck or obstacle-crossing location, it adds that location as an area that cannot be passed while carrying a load and then gently leaves that area.

[0130] A gentle departure can include leaving the current obstacle-crossing area based on at least one of a preset speed, a preset rotation angle, and a preset distance. This can correspond to the execution of a preset departure action in the robot obstacle-crossing method described above.

[0131] After leaving and adding the load-inaccessible area, proceed to step S509.

[0132] Step S505: Retract the robotic arm.

[0133] Step S506: Perform the obstacle-crossing and escaping maneuvers.

[0134] This can be equated to the target's obstacle-avoidance action in the above-mentioned robot obstacle-avoidance method.

[0135] After performing the escape and obstacle-crossing maneuvers, proceed to step S509.

[0136] Step S507: Under a relaxed obstacle-avoidance strategy, the robot detects an obstacle.

[0137] Here, when the robot is implementing a relaxed obstacle-avoidance strategy, step S508 is executed after an obstacle is detected.

[0138] Step S508: Detection is performed using sensors in conjunction with a 3D map.

[0139] Here, corresponding to the robot obstacle avoidance and obstacle crossing methods mentioned above, the safety level of the robot performing the target obstacle avoidance and obstacle crossing action can be predicted based on environmental information and the current pose information of the robotic arm.

[0140] In some implementations, sensors and 3D maps can be used to detect the distance between the robotic arm and obstacles above, in front of, and to the sides of the robotic arm, i.e., to detect whether there are obstacles in the robotic arm's operating space; and to detect parameters such as the volume, weight, and type of the object grasped by the robotic arm, i.e., to detect whether the object grasped by the robotic arm will affect the robot's obstacle-crossing and obstacle-crossing processes.

[0141] If the detection result is safe, which corresponds to the situation where the safety level of the robot's obstacle avoidance and obstacle crossing method meets the target safety conditions, then step S506 is executed; if the detection result is unsafe, which corresponds to the situation where the safety level of the robot's obstacle avoidance and obstacle crossing method does not meet the target safety conditions, then the obstacle avoidance and obstacle crossing strategy is switched to a strict obstacle avoidance and obstacle crossing strategy, and step S502 is executed.

[0142] Step S509: Execute the target task.

[0143] This can be either the task the robot was performing before it escaped the obstacle or the next task before it escaped the obstacle.

[0144] In this embodiment of the present disclosure, when the robotic arm is outside the robot body, the robot selects different escape and obstacle-crossing strategies based on the loading status of the robotic arm and environmental information, thereby reducing the problem of damage to the robotic arm, robot, and surrounding objects caused by excessive body movements.

[0145] This disclosure provides a robot obstacle avoidance and traversal device, wherein the robot includes a body and a robotic arm, the robotic arm being mounted on the body. As shown in Figure 6, the device 600 includes:

[0146] The acquisition module 610 is used to acquire the current posture of the robotic arm;

[0147] The detection module 620 is used to detect the environmental information of the scene in which the robotic arm is currently located when the current posture of the robotic arm indicates that the robotic arm is extended.

[0148] The control module 630 is used to control the robot to perform obstacle avoidance and evasion processing based on the current posture of the robotic arm and the environmental information.

[0149] In some embodiments, the control module is further configured to: predict the safety level of the robot performing the target obstacle escape action based on the environmental information and the current pose information of the robotic arm; and control the robot to perform obstacle escape processing based on the safety level.

[0150] In some embodiments, the control module is further configured to: control the robot to perform the target obstacle avoidance action when the safety level meets the target safety conditions; and control the robot to perform obstacle avoidance processing based on the load state of the robotic arm when the safety level does not meet the target safety conditions.

[0151] In some embodiments, the control module is further configured to: control the robot to perform a preset departure action to attempt to leave the current obstacle-crossing area when the robot arm is in a loaded state, and / or mark the current obstacle-crossing area as a loaded, impassable area in the environment map corresponding to the current scene; control the robot arm to retract when the robot arm is in an unloaded state, and control the robot to perform the target obstacle-crossing action.

[0152] In some embodiments, the robot further includes a lifting mechanism disposed at the bottom of the body; the control module is further configured to: control the lifting mechanism to lift the body to perform the target obstacle escape action when the safety level meets the target safety conditions; and control the lifting mechanism to lower the body during the obstacle escape process when the safety level does not meet the target safety conditions.

[0153] In some embodiments, the control module is further configured to: control the robot to perform a target escape and obstacle-crossing action when the current posture of the robotic arm indicates that the robotic arm is retracted.

[0154] The description of the robot obstacle avoidance and hurdle-crossing device embodiments above is similar to the description of the method embodiments above, and has similar beneficial effects. For technical details not disclosed in the robot obstacle avoidance and hurdle-crossing device embodiments of this disclosure, please refer to the description of the method embodiments of this disclosure for understanding.

[0155] It should be noted that, in the embodiments of this disclosure, if the above-described robot obstacle avoidance method is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiments of this disclosure, or the part that contributes to related technologies, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this disclosure. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, external hard drive, read-only memory (ROM), magnetic disk, or optical disk. Thus, the embodiments of this disclosure are not limited to any specific hardware and software combination.

[0156] This disclosure provides a robot, as shown in FIG7. The robot 700 includes a memory 710 and a processor 720. The memory 710 stores a computer program that can run on the processor 720. When the processor 720 executes the program, it implements some or all of the steps in the above method.

[0157] This disclosure provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements some or all of the steps in the above-described method. The computer-readable storage medium may be transient or non-transient.

[0158] This disclosure provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program. When the computer program is read and executed by a computer, it implements some or all of the steps in the above-described method. This computer program product can be implemented specifically through hardware, software, or a combination thereof. In one optional embodiment, the computer program product is specifically embodied as a computer storage medium; in another optional embodiment, the computer program product is specifically embodied as a software product, such as a software development kit (SDK), etc.

[0159] This disclosure provides a computer program product, including a computer program or instructions, which, when executed by a processor, implement some or all of the steps in the above-described method.

[0160] This disclosure provides a processor that is communicatively connected to a memory storing a computer program that can run on the processor. When the processor executes the computer program, it implements the steps in the method described above.

[0161] It should be noted that the descriptions of the above-described storage media, computer program products, and device embodiments are similar to the descriptions of the above-described method embodiments, and have similar beneficial effects. For technical details not disclosed in the embodiments of the storage media, computer program products, and devices of this disclosure, please refer to the descriptions of the method embodiments of this disclosure for understanding.

[0162] It should be understood that the phrase "an embodiment" or "one embodiment" throughout the specification means that a specific feature, structure, or characteristic related to the embodiment is included in at least one embodiment of this disclosure. Therefore, "in one embodiment" or "one embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It should be understood that in the various embodiments of this disclosure, the sequence numbers of the above-described processes do not imply a sequential order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this disclosure. The sequence numbers of the above-described embodiments are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0163] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0164] In the several embodiments provided in this disclosure, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components may be combined, or integrated into another system, or some features may be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0165] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0166] In addition, each functional unit in the various embodiments of this disclosure can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0167] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as mobile storage devices, read-only memory (ROM), magnetic disks, or optical disks.

[0168] Alternatively, if the integrated units described above are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this disclosure, or the part that contributes to related technologies, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this disclosure. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, magnetic disks, or optical disks.

[0169] The above description is merely an embodiment of this disclosure, but the scope of protection of this disclosure is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for a robot to escape from obstacles, wherein, The robot includes a body and a robotic arm, the robotic arm being mounted on the body; the method includes: Obtain the current posture of the robotic arm; When the current posture of the robotic arm indicates that the robotic arm is extended, detect the environmental information of the scene in which the robotic arm is currently located; Based on the current posture of the robotic arm and the environmental information, the robot is controlled to perform obstacle avoidance and evasion procedures.

2. The robot obstacle avoidance method according to claim 1, wherein, Based on the current posture of the robotic arm and the environmental information, the robot is controlled to perform obstacle avoidance and evasion procedures, including: Based on the environmental information and the current pose information of the robotic arm, the safety level of the robot performing the target escape and obstacle crossing action is predicted; Based on the stated level of safety, the robot is controlled to perform obstacle avoidance and rescue operations.

3. The robot obstacle avoidance method according to claim 2, wherein, Based on the aforementioned safety level, controlling the robot to perform obstacle avoidance and evasion procedures includes at least one of the following: When the safety level meets the target safety conditions, control the robot to perform the target obstacle avoidance and obstacle crossing actions; If the safety level does not meet the target safety conditions, the robot is controlled to perform obstacle avoidance and evasion based on the load state of the robotic arm.

4. The robot obstacle avoidance method according to claim 3, wherein, Controlling the robot to perform obstacle avoidance and evasion based on the load state of the robotic arm includes at least one of the following: When the robotic arm is in a loaded state, control the robot to perform a preset departure action to attempt to leave the current area to be extricated from the obstacle, and / or mark the current area to be extricated from the obstacle as a loaded, impassable area in the environmental map corresponding to the current scene; When the robotic arm is in an unloaded state, control the robotic arm to retract and control the robot to perform the target escape and obstacle crossing action.

5. The robot obstacle avoidance method according to claim 3 or 4, wherein, The robot also includes a lifting mechanism located at the bottom of the body; When the safety level meets the target safety conditions, controlling the robot to perform the target escape and obstacle crossing action includes: controlling the lifting mechanism to lift the robot body to perform the target escape and obstacle crossing action; If the safety level does not meet the target safety conditions, based on the load state of the robotic arm, controlling the robot to perform obstacle avoidance and obstacle crossing includes: controlling the lifting mechanism to lower the robot body during the obstacle avoidance and obstacle crossing process.

6. The robot obstacle avoidance method according to any one of claims 1 to 5, further comprising: When the current posture of the robotic arm indicates that the robotic arm is retracted, the robot is controlled to perform a target escape and obstacle crossing action.

7. A robot obstacle avoidance and traversal device, wherein, The robot includes a body and a robotic arm, the robotic arm being mounted on the body; the device includes: An acquisition module is used to acquire the current posture of the robotic arm; The detection module is used to detect the environmental information of the scene in which the robotic arm is currently located when the current posture of the robotic arm indicates that the robotic arm is extended. The control module is used to control the robot to perform obstacle avoidance and evasion based on the current posture of the robotic arm and the environmental information.

8. The robot obstacle avoidance device according to claim 7, wherein, The control module is also used for: Based on the environmental information and the current pose information of the robotic arm, the safety level of the robot performing the target escape and obstacle crossing action is predicted; Based on the stated level of safety, the robot is controlled to perform obstacle avoidance and rescue operations.

9. The robot obstacle avoidance device according to claim 8, wherein, The control module is also used for at least one of the following: When the safety level meets the target safety conditions, control the robot to perform the target obstacle avoidance and obstacle crossing actions; If the safety level does not meet the target safety conditions, the robot is controlled to perform obstacle avoidance and evasion based on the load state of the robotic arm.

10. The robot obstacle avoidance device according to claim 9, wherein, The control module is also used for at least one of the following: When the robotic arm is in a loaded state, control the robot to perform a preset departure action to attempt to leave the current area to be extricated from the obstacle, and / or mark the current area to be extricated from the obstacle as a loaded, impassable area in the environmental map corresponding to the current scene; When the robotic arm is in an unloaded state, control the robotic arm to retract and control the robot to perform the target escape and obstacle crossing action.

11. The robot obstacle avoidance device according to claim 9 or 10, wherein, The robot also includes a lifting mechanism located at the bottom of the body; The control module is also used for: When the safety level meets the target safety conditions, the lifting mechanism is controlled to raise the body to perform the target escape and obstacle crossing action; If the safety level does not meet the target safety conditions, the lifting mechanism is controlled to lower the fuselage during the obstacle avoidance process.

12. The robot obstacle avoidance device according to any one of claims 7 to 11, wherein, The control module is also used for: When the current posture of the robotic arm indicates that the robotic arm is retracted, the robot is controlled to perform a target escape and obstacle crossing action.

13. A robot comprising a memory and a processor, the memory storing a computer program executable on the processor, the processor executing the program to implement the steps of the method as claimed in any one of claims 1 to 6.

14. A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method as claimed in any one of claims 1 to 6.

15. A computer program product comprising a computer program or instructions, which, when executed by a processor, implement the steps of the method according to any one of claims 1 to 6.

Images