Robot moving path planning method and device, electronic equipment and storage medium

Abstract

The invention discloses a robot moving path planning method and device, electronic equipment and a storage medium. The method comprises the following steps: receiving a first control instruction for a robot, and obtaining an actual position of the robot and a global grid map of a preset activity area of the robot; determining a target advancing path according to the first control instruction, the actual position and the global grid map, and controlling the robot to move along the target advancing path; in the advancing process of the robot, space information of the robot is collected through a data collection module installed on the robot, and the space information comprises environment information and pose information; and determining an environment state vector according to the space information, and updating the target advancing path of the robot according to the environment state vector and the global grid map, so that autonomous navigation and dynamic path planning of the robot can be realized, and the moving efficiency, the environment adaptability and the target arrival accuracy are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of robot navigation, and in particular to a robot movement path planning method and device, electronic equipment and a storage medium. BACKGROUND

[0002] With the wide application of mobile robots (such as service robots, AGVs, drones, etc.) in complex environments (such as warehouses, hospitals, outdoor scenes), the real-time and robustness requirements of autonomous navigation are significantly improved.

[0003] In related technologies, robot navigation systems mostly rely on static maps and preset paths, which are prone to path failure or collision risks when facing dynamic obstacles or environmental mutations. When the position of obstacles in the environment changes (such as moving objects or newly added obstacles) or the pose error of the robot itself accumulates, the fixed initial path may cause collision risks or task failures. In addition, the system usually lacks dynamic assessment of environmental risks, making it difficult to quickly adjust the path in emergency situations. SUMMARY

[0004] The present application provides a robot movement path planning method, device, electronic equipment and storage medium to solve the problem of inaccurate path planning and inability to adapt to environmental changes in real time for robots in dynamic and complex environments.

[0005] According to an aspect of the present application, a robot movement path planning method is provided, comprising:

[0006] receiving a first control instruction for the robot, obtaining the actual position of the robot and the global grid map of the preset activity area of the robot, wherein the first control instruction is used to control the robot to move to a target endpoint;

[0007] determining a target travel path according to the first control instruction, the actual position and the global grid map, and controlling the robot to move along the target travel path;

[0008] In the process of the robot traveling, a data acquisition module installed on the robot is used to collect spatial information of the robot, wherein the spatial information includes environmental information and pose information;

[0009] determining an environmental state vector according to the spatial information, and updating the target travel path of the robot according to the environmental state vector and the global grid map.

[0010] According to another aspect of the present application, a robot movement path planning device is provided, characterized in that it comprises:

[0011] The global grid map acquisition module is configured to receive a first control instruction for the robot, acquire an actual position of the robot and a global grid map of a preset activity area of the robot, wherein the first control instruction is used to control the robot to move to a target end point.

[0012] The robot movement module is configured to determine a target travel path according to the first control instruction, the actual position and the global grid map, and control the robot to move along the target travel path.

[0013] The spatial information acquisition module is configured to acquire spatial information of the robot by a data acquisition module installed on the robot during movement of the robot, wherein the spatial information includes environment information and pose information.

[0014] The path update module is configured to determine an environment state vector according to the spatial information, and update the target travel path of the robot according to the environment state vector and the global grid map.

[0015] According to another aspect of the present application, an electronic device is provided, which comprises:

[0016] at least one processor; and

[0017] a memory connected to the at least one processor in communication; wherein

[0018] the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the path planning method for robot movement according to any one of the embodiments of the present application.

[0019] According to another aspect of the present application, a computer readable storage medium is provided, which stores computer instructions for enabling a processor to implement the path planning method for robot movement according to any one of the embodiments of the present application when executed by the processor.

[0020] The technical scheme of the embodiment of the present application receives a first control instruction of a robot, obtains an actual position of the robot and a global grid map of a preset activity area of the robot, and since the first control instruction is used to control the robot to move to a target end point, the robot can quickly respond to the instruction, accurately position and plan a path to the target end point. Then, a target travel path is determined according to the first control instruction, the actual position and the global grid map, and the robot is controlled to move along the target travel path, so that the path planning of the robot from the actual position to the target end point can be determined, thereby providing a basis for subsequent path updating. Then, during the travel of the robot, spatial information of the robot is collected by a data collection module installed on the robot, wherein the spatial information includes environment information and pose information, so that the robot can realize real-time environment perception and accurate positioning, thereby providing accurate data support for path planning and navigation. Finally, an environment state vector is determined according to the spatial information, and the target travel path of the robot is updated according to the environment state vector and the global grid map, so that the travel path of the robot can be dynamically adjusted, the problem that the path planning of the robot is inaccurate and cannot adapt to the change of the environment in real time in a dynamic and complex environment can be solved, autonomous navigation and dynamic path planning of the robot can be realized, and the moving efficiency, environment adaptability and target arrival accuracy are improved.

[0021] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0023] Figure 1 is a flowchart of a path planning method for robot movement according to an embodiment of the present application;

[0024] Figure 2 is a flowchart of a path planning method for robot movement according to an embodiment of the present application;

[0025] Figure 3 is a flowchart of a path planning method for robot movement according to an embodiment of the present application;

[0026] Figure 4Fig. 1 is a structural schematic diagram of a path planning device for robot movement according to an embodiment of the present application;

[0027] Figure 5 Fig. 2 is a structural schematic diagram of an electronic device implementing a path planning method for robot movement according to an embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to make the personnel in the technical field better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should belong to the scope of protection of the present application.

[0029] It should be noted that the terms "first", "second", and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0030] It should be noted that the modification of "one" or "multiple" mentioned in the present disclosure is illustrative but not restrictive, and those skilled in the art should understand that unless otherwise explicitly indicated in the context, it should be understood as "one or more".

[0031] The names of the messages or information exchanged between the multiple devices in the embodiments of the present disclosure are only for illustrative purposes, and are not intended to limit the scope of the messages or information.

[0032] It can be understood that before using the technical solutions disclosed in the embodiments of the present disclosure, the type, scope of use, use scenario, etc. of the personal information involved in the present disclosure should be informed to the user and the authorization of the user should be obtained in accordance with relevant laws and regulations.

[0033] For example, in response to receiving an active request of a user, prompt information is sent to the user to explicitly prompt the user that the operation requested to be performed will require obtaining and using personal information of the user. Thus, the user can autonomously select whether to provide personal information to the software or hardware, such as an electronic device, an application program, a server or a storage medium, etc. performing the operation of the technical solution of the present disclosure according to the prompt information.

[0034] As an optional but non-limiting implementation manner, in response to receiving an active request of a user, the manner of sending prompt information to the user may, for example, be a pop-up window manner, and the prompt information may be presented in the form of text in the pop-up window. In addition, the pop-up window may also carry selection controls for the user to select “agree” or “disagree” to provide personal information to the electronic device.

[0035] It can be understood that the above notification and obtaining user authorization process is only illustrative and does not limit the implementation manner of the present disclosure, and other manners meeting relevant laws and regulations can also be applied to the implementation manner of the present disclosure.

[0036] It can be understood that the data (including but not limited to the data itself, the obtaining or use of the data) involved in the technical solution should comply with the requirements of relevant laws and regulations and relevant provisions.

[0037] Embodiment one

[0038] Figure 1 A flowchart of a robot moving path planning method is provided for the first embodiment of the present application. The present embodiment can be applied to autonomous navigation, obstacle avoidance and path planning scenarios in a complex dynamic environment. The method can be executed by a robot moving path planning device, which can be realized in the form of hardware and / or software. Optionally, the robot moving path planning device can be realized by an electronic device, which can be a mobile terminal, a PC terminal or a server, etc.

[0039] As shown in Figure 1 , the method specifically can include:

[0040] S110, receiving a first control instruction for a robot, obtaining an actual position of the robot and a global grid map of a preset activity area of the robot, wherein the first control instruction is used to control the robot to move to a target endpoint.

[0041] The first control instruction can be understood as an initial instruction issued by a user or a control system to the robot, instructing the robot to move from an actual position to a target endpoint. The first control instruction triggers the starting point of the robot's path planning, and explicitly indicates the task target of the robot (such as reaching a certain coordinate point). The first control instruction includes but is not limited to the target endpoint position, the movement speed requirement or other constraint conditions, etc. The actual position can be understood as the geographical coordinates of the robot in the current environment (including but not limited to position and direction, etc.), which provides the starting point coordinates for path planning, ensuring the real-time and accuracy of path calculation. The preset active area can be understood as the area range in which the robot is allowed to move freely, which can be a set map boundary or a work area, etc. The global grid map can be understood as a map representation method that divides the environment into a two-dimensional grid, and each grid cell represents a space state, which is used to provide global cognition of the environment, and is used for obstacle avoidance and selection of feasible paths during path planning.

[0042] S120, determining a target travel path according to the first control instruction, the actual position and the global grid map, and controlling the robot to move along the target travel path.

[0043] The target travel path can be understood as the initial movement route of the robot from the actual position to the target endpoint.

[0044] S130, during the travel of the robot, acquiring spatial information of the robot by a data acquisition module installed on the robot, wherein the spatial information includes environment information and pose information.

[0045] The data acquisition module can be understood as a combination of sensors carried by the robot. The data acquisition module includes but is not limited to a visual sensor, a laser radar sensor, a depth sensor and an inertial measurement unit, etc., which is used to acquire the environment information (such as obstacle distance, terrain change, etc.) around the robot and the state (such as speed, angle, etc.) of the robot in real time, providing a basis for dynamic path adjustment. The spatial information can be understood as the data about the space where the robot is perceived. The spatial information includes but is not limited to environment information and pose information, etc. The environment information can be understood as the obstacles or terrain around the robot, etc. The pose information can be understood as the position (x, y) and orientation (θ) of the robot, which is used to construct a local map, correct the position and update the path.

[0046] On the basis of the above scheme, optionally, the spatial information at least includes visual image information, three-dimensional point cloud data, depth information and pose information; the spatial information of the robot is collected by the data collection module mounted on the robot, including: collecting visual image information around the robot by the visual sensor; receiving a reflection signal of a target object in the environment by the laser radar sensor, and constructing three-dimensional point cloud data according to the reflection signal; obtaining depth information of the target object in the environment by the depth sensor; collecting pose information of the robot by the inertial measurement unit.

[0047] The visual sensor can be understood as an RGB camera, a binocular camera, etc., which is used to capture visual image information of the environment. The visual image information can be understood as two-dimensional image information (such as RGB color, texture or object contour, etc.) obtained by the visual sensor. The laser radar sensor can be understood as a sensor that measures distance by emitting a laser beam and receiving a reflection signal. The reflection signal can be understood as an electromagnetic wave signal reflected back to the radar after the laser beam irradiates the target object, which contains intensity and time information, etc. The three-dimensional point cloud data can be understood as a three-dimensional coordinate set of the surface points of the objects in the environment generated by the laser radar by emitting a laser beam and receiving a reflection signal, which is used to construct a high-precision three-dimensional map and identify the shape and position of the target object. The target object can be understood as an object in the environment where the robot is located, including but not limited to obstacles, pedestrians or vehicles, etc. The depth sensor can be understood as outputting the distance of the target object to the sensor. The depth information can be understood as the straight-line distance data measured from the robot to the target object, which is used to assist in filling the missing areas of the three-dimensional point cloud data (such as low reflectivity objects such as glass). The inertial measurement unit can be understood as a sensor containing an accelerometer, a gyroscope and a magnetometer, which is used to measure the motion attitude (such as acceleration and angular velocity, etc.) of the robot. The pose information can be understood as the position and attitude information of the robot collected by the inertial measurement unit. The position usually refers to the coordinates (such as X, Y, Z) of the robot in space, and the attitude includes the heading angle, pitch angle and roll angle of the robot, etc. The pose information can determine the specific position and orientation of the robot in space, so that the robot can determine its own state, accurately move according to the planned path, and adjust its own position and attitude in real time during the movement.

[0048] By using the technical scheme, the spatial information of the robot is collected by fusing multiple sensors, which can comprehensively perceive the visual features, three-dimensional structure, target distance and self attitude of the surrounding environment, improve the environmental modeling and positioning accuracy of the robot, and enhance the autonomous navigation and obstacle avoidance capability.

[0049] S140, determine an environment state vector according to the space information, and update the target travel path of the robot according to the environment state vector and the global grid map.

[0050] The environment state vector can be understood as a feature representation of the quantized space information (such as obstacle distance, direction, robot speed, etc.), which is used to evaluate whether the current environment is safe or whether the path needs to be re-planned.

[0051] The technical scheme of the embodiment of the application receives a first control instruction for the robot, obtains the actual position of the robot and the global grid map of the preset activity area of the robot. Since the first control instruction is used to control the robot to move to a target endpoint, the robot can quickly respond to the instruction, accurately position and plan a path to the target endpoint. Then, the target travel path is determined according to the first control instruction, the actual position and the global grid map, and the robot is controlled to move along the target travel path, so that the path planning of the robot from the actual position to the target endpoint can be determined, thereby providing a basis for subsequent path updating. During the travel of the robot, the space information of the robot is collected by the data acquisition module installed on the robot, wherein the space information includes environment information and pose information, so that real-time environment perception and accurate positioning of the robot can be realized, thereby providing accurate data support for path planning and navigation. Finally, the environment state vector is determined according to the space information, and the target travel path of the robot is updated according to the environment state vector and the global grid map, so that the travel path of the robot can be dynamically adjusted, the problem of inaccurate path planning and inability to adapt to environmental changes in real time of the robot in a dynamic and complex environment can be solved, autonomous navigation and dynamic path planning of the robot can be realized, and the moving efficiency, environmental adaptability and target arrival accuracy can be improved.

[0052] Embodiment Two

[0053] Figure 2 A flowchart of a path planning method for robot movement is provided for the second embodiment of the application. The embodiment is further refined based on the above-mentioned embodiment. According to the space information, the environment state vector is determined. Alternatively, the environment state vector is determined according to the space information, which includes classifying the pre-processed environment information according to the types of target objects in the environment information, and determining the environment state vector according to the classification result and the preset confidence weight. The pre-processing at least includes denoising, downsampling and bilateral filtering. The specific implementation can be referred to the description of the embodiment. The same or similar technical features as the foregoing embodiments are not repeated here.

[0054] As Figure 2 shown, the method can specifically include:

[0055] S210, receiving a first control instruction for the robot, obtaining an actual position of the robot and a global grid map of a preset active area of the robot, wherein the first control instruction is used to control the robot to move to a target end point.

[0056] S220, determining a target travel path according to the first control instruction, the actual position and the global grid map, and controlling the robot to move along the target travel path.

[0057] S230, collecting spatial information of the robot by a data collection module installed on the robot during travel of the robot, wherein the spatial information includes environment information and pose information.

[0058] S240, classifying the preprocessed environment information according to a type of target object in the environment information, determining an environment state vector according to a classification result and a preset confidence weight, and updating the target travel path of the robot according to the environment state vector and the global grid map, wherein the preprocessing at least includes denoising, down-sampling and bilateral filtering.

[0059] The type of the target object can be understood as different types of objects identified in the environment. The types include but are not limited to static obstacles, dynamic obstacles, semi-static obstacles, terrain features and environmental disturbances, etc. The static obstacle can be understood as an obstacle with fixed position in the environment and cannot move, including but not limited to buildings and billboards, etc. The dynamic obstacle can be understood as an obstacle that can move or whose behavior is unpredictable in the environment, including but not limited to pedestrians, moving vehicles or animals, etc. The semi-static obstacle can be understood as an obstacle that usually maintains a fixed position in the environment, but can change its position, state or form under certain time periods or specific conditions, including but not limited to parked vehicles, temporary piles or movable devices, etc. Different types of target objects have different behavior patterns and risk levels, which are important basis for environment state modeling. The confidence weight can be understood as a numerical value representing the reliability of a certain classification result. The denoising is used to remove random errors or outliers in sensor collected data. The down-sampling is used to simplify high-density point cloud or image data to lower density to reduce computational load. The bilateral filtering is used to preserve edge details while smoothing image / point cloud data, keeping important structural information from being lost while removing noise.

[0060] On the basis of the above scheme, optionally, the environment state vector is determined according to the classification result and a preset confidence weight, comprising: updating the confidence weight according to the number of the target objects in the classification result, the state of the target objects and the distance between the target objects and the robot, wherein the state is used to represent the motion state of the target objects; determining the environment state vector according to the weighted summation result of the classification result and the confidence weight.

[0061] The number of the target objects can be understood as the total number of entities of the target objects of different categories identified in the environment. The number directly affects the environment complexity evaluation, and more target objects can increase the difficulty of obstacle avoidance or the complexity of path planning. The state of the target objects can be understood as the information of the current motion state of the target objects. The motion state includes but is not limited to static, moving direction and speed, etc.

[0062] In an optional embodiment, all target objects are traversed, it is judged whether they belong to a certain category, and the preset confidence weight is determined, and they are stored in groups according to the category, and the number, the distance from the robot, the speed and other information are recorded. Different categories of obstacles have different influences on the decision of the robot, so it is necessary to set the confidence weight to adjust the importance. For example, if the obstacle is moving (such as a pedestrian), the confidence weight is increased by a dynamic compensation coefficient, and the faster the speed is, the greater the weight is. If the obstacle can cause serious problems to the robot (such as a glass door causing collision), the risk coefficient is increased. The confidence weight of different categories of target objects is adjusted by the product of the preset confidence weight, the risk coefficient and the dynamic compensation coefficient. Finally, the confidence weight of each category is normalized to obtain the updated confidence weight.

[0063] By using the technical scheme, the confidence weight is dynamically updated by comprehensively considering the number of target objects, the motion state and the relative distance from the robot, and the environment state vector is generated based on weighted summation, which can more comprehensively and accurately represent the environmental changes, and improve the perception ability and judgment accuracy of the robot in a complex environment.

[0064] The technical scheme of the embodiment of the application can preprocess the environmental information such as denoising, downsampling and bilateral filtering, improve the data quality, and then combine the target object category classification and confidence weighting to accurately construct the environment state vector, thereby enhancing the perception accuracy and decision reliability of the robot in a complex environment.

[0065] Embodiment three

[0066] Figure 3A flowchart of a robot moving path planning method provided for the third embodiment of the present application, the embodiment is based on the above-mentioned embodiments, and further refines the target travel path of the robot according to the environment state vector and the global grid map. Optionally, updating the target travel path of the robot according to the environment state vector and the global grid map comprises: determining prompt information according to the environment state vector and a preset prompt template, inputting the prompt information into a pre-trained warning level determination model to obtain the warning level, wherein the warning level is used to represent the warning degree of the robot traveling in the target travel path; and updating the target travel path of the robot according to the environment state vector, the warning level and the global grid map. The specific implementation can be seen from the description of the embodiment. Wherein, the same or similar technical features as the foregoing embodiments are not described here.

[0067] As shown in Figure 3 , the method can specifically include:

[0068] S310, receiving a first control instruction of a robot, obtaining an actual position of the robot and a global grid map of a preset activity area of the robot, wherein the first control instruction is used to control the robot to move to a target terminal point.

[0069] S320, determining a target travel path according to the first control instruction, the actual position and the global grid map, and controlling the robot to move along the target travel path.

[0070] S330, during the travel of the robot, collecting spatial information of the robot through a data collection module installed on the robot, wherein the spatial information includes environment information and pose information.

[0071] S340, determining an environment state vector according to the spatial information, determining prompt information according to the environment state vector and a preset prompt template, inputting the prompt information into a pre-trained warning level determination model to obtain the warning level, wherein the warning level is used to represent the warning degree of the robot traveling in the target travel path.

[0072] The prompt template can be understood as a predefined information format or framework for generating specific prompt information, which is used to fill the environment state vector into the corresponding position in the template to generate the prompt information. The early warning level determination model can be understood as a pre-trained model that can receive the prompt information as input and output the corresponding early warning level, which is used to evaluate the risk level encountered by the robot on the target travel path and guide the robot to take appropriate action. The early warning level can be understood as a quantitative indicator of the risk level faced by the robot in the target travel path. The early warning level includes but is not limited to low risk, medium risk, and high risk, etc.

[0073] In an optional implementation, if it is determined that the early warning level is low risk, the robot can be instructed to continue moving forward; if it is determined that the early warning level is medium risk, the travel speed or direction of the robot needs to be adjusted, and the target travel path is still moving; if it is determined that the early warning level is high risk, it indicates that there is a greater risk, and the robot needs to completely avoid the dangerous area and find a new target travel path.

[0074] In an optional implementation, the environment state vector can be information such as "a cart is approaching 2 meters in front". The prompt information can be "be careful! There is an obstacle 2 meters in front, please slow down and prepare to detour". The model outputs a "medium" early warning level. According to the medium early warning level, combined with the global grid map, the robot temporarily stops and waits for the cart to pass before continuing to move forward.

[0075] On the basis of the above scheme, optionally, updating the target travel path of the robot according to the environment state vector, the early warning level, and the global grid map includes: determining a second control instruction of the robot according to the environment state vector, the pose information of the robot, and the early warning level, and updating the target travel path of the robot according to the second control instruction and the global grid map.

[0076] The second control instruction can be understood as a new control command generated according to real-time environmental changes on the basis of the initial target travel path, which is used to adjust the motion behavior of the robot.

[0077] By fusing the environment state vector, the early warning level, and the robot pose information, dynamically generating the second control instruction, and updating the target travel path in real time combined with the global grid map, the autonomous navigation ability and obstacle avoidance safety of the robot in a complex dynamic environment can be effectively improved.

[0078] Optionally, based on the above scheme, the second control instruction of the robot is determined according to the environmental state vector, the pose information of the robot and the warning level, comprising: determining a third control instruction according to the warning level, determining a fourth control instruction of the robot according to the environmental state vector and the pose information, and determining the second control instruction according to the third control instruction and the fourth control instruction.

[0079] The third control instruction can be understood as a corresponding emergency behavior of the robot determined according to the warning level. The third control instruction includes but is not limited to continuing to travel, avoiding and changing path, etc. The fourth control instruction can be understood as an optimized instruction for the robot to travel calculated from the environmental state vector and the pose information, including but not limited to adjusting the moving direction, the turning angle and the moving speed, etc.

[0080] By converting the warning level into the third control instruction and combining the environmental state vector and the pose information to generate the fourth control instruction, and finally fusing to generate the second control instruction, the technical scheme can realize the hierarchical response and fine control of the complex environment, improve the flexibility of path adjustment and the efficiency of task execution while ensuring the safety of the robot travel.

[0081] S350, updating the target travel path of the robot according to the environmental state vector, the warning level and the global grid map.

[0082] The technical scheme of the embodiment of the application generates prompt information through the prompt template and inputs it into the trained warning level model, accurately evaluates the path warning degree, dynamically updates the target travel path of the robot on the basis of combining the environmental state vector and the global grid map, and thus improves the autonomous decision-making ability and path planning safety of the robot in the complex environment.

[0083] Embodiment four

[0084] Figure 4 A structural schematic diagram of a path planning device for robot movement provided by the fourth embodiment of the application is shown in FIG. 4. Figure 4 As shown in the figure, the device comprises a global grid map acquisition module 410, a robot movement module 420, a spatial information acquisition module 430 and a path updating module 440.

[0085] The global grid map acquisition module 410 is configured to receive a first control instruction for the robot, acquire an actual position of the robot and a global grid map of a preset activity area of the robot, wherein the first control instruction is used to control the robot to move to a target end point.

[0086] The technical scheme of the embodiment of the application can achieve the following effects: the global grid map acquisition module receives a first control instruction for the robot, acquires an actual position of the robot and a global grid map of a preset activity area of the robot, and since the first control instruction is used to control the robot to move to a target end point, the robot can quickly respond to the instruction, accurately position and plan a path to the target end point; then, the robot movement module determines a target travel path according to the first control instruction, the actual position and the global grid map, and controls the robot to move along the target travel path, so that the path planning of the robot from the actual position to the target end point can be determined, thereby providing a basis for subsequent path updating; then, the spatial information acquisition module acquires spatial information of the robot through a data acquisition module installed on the robot during the travel of the robot, wherein the spatial information includes environmental information and pose information, so that the robot can realize real-time environmental perception and accurate positioning, and provide accurate data support for path planning and navigation; finally, the path updating module determines an environmental state vector according to the spatial information, and updates the target travel path of the robot according to the environmental state vector and the global grid map, so that the travel path of the robot can be dynamically adjusted, the problem that the path planning of the robot is inaccurate and cannot adapt to environmental changes in real time in a dynamic and complex environment can be solved, the robot can realize autonomous navigation and dynamic path planning, and the moving efficiency, environmental adaptability and target arrival accuracy can be improved.

[0087] On the basis of the above scheme, optionally, the data acquisition module includes a visual sensor, a laser radar sensor, a depth sensor and an inertial measurement unit; the spatial information at least includes visual image information, three-dimensional point cloud data, depth information and pose information; the spatial information acquisition module includes: a visual image information determination sub-module, a three-dimensional point cloud data construction sub-module, a depth information acquisition sub-module and a pose information acquisition sub-module. Among them, the visual image information determination sub-module is used to collect the visual image information around the robot through the visual sensor; the three-dimensional point cloud data construction sub-module is used to receive the reflection signal of the object in the environment through the laser radar sensor, and construct three-dimensional point cloud data according to the reflection signal; the depth information acquisition sub-module is used to acquire the depth information of the object in the environment through the depth sensor; the pose information acquisition sub-module is used to acquire the pose information of the robot through the inertial measurement unit.

[0088] On the basis of the above scheme, optionally, the path updating module includes an environment state vector determination sub-module. Among them, the environment state vector determination sub-module is used to classify the preprocessed environment information according to the category of the target object in the environment information, and determine the environment state vector according to the classification result and the preset confidence weight, wherein the preprocessing at least includes denoising, downsampling and bilateral filtering.

[0089] On the basis of the above scheme, optionally, the environment state vector determination sub-module includes an environment state vector determination unit. Among them, the environment state vector determination unit is used to update the confidence weight according to the number of target objects, the state of target objects and the distance between target objects and the robot in the classification result, wherein the state is used to represent the motion state of the target object; the environment state vector is determined according to the weighted sum result of the classification result and the confidence weight.

[0090] On the basis of the above scheme, optionally, the path updating module includes a warning level determination sub-module and a path updating sub-module. Among them, the warning level determination sub-module is used to determine the prompt information according to the environment state vector and the preset prompt template, input the prompt information into the pre-trained warning level determination model, and obtain the warning level, wherein the warning level is used to represent the warning degree of the robot in the target travel path; the path updating sub-module is used to update the target travel path of the robot according to the environment state vector, the warning level and the global grid map.

[0091] On the basis of the above scheme, optionally, the path updating submodule comprises a path updating unit. The path updating unit is configured to determine a second control instruction of the robot according to the environment state vector, the pose information of the robot and the warning level, and update a target travel path of the robot according to the second control instruction and the global grid map.

[0092] On the basis of the above scheme, optionally, the path updating unit comprises a control instruction determination subunit. The control instruction determination subunit is configured to determine a third control instruction according to the warning level, determine a fourth control instruction of the robot according to the environment state vector and the pose information, and determine the second control instruction according to the third control instruction and the fourth control instruction.

[0093] The robot movement path planning device provided in the embodiments of the present application can execute the robot movement path planning method provided in any of the embodiments of the present application, and has the corresponding function modules and beneficial effects of the execution method.

[0094] Embodiment five

[0095] Figure 5 A structural schematic diagram of an electronic device 10 that can be used to implement embodiments of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smart phones, wearable devices (e.g., headsets, glasses, watches, etc.), and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present application described and / or claimed in this document.

[0096] As shown in Figure 5 The electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which are communicatively connected to the at least one processor 11, wherein the memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0097] A plurality of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0098] The processor 11 can be various general and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs various methods and processes described above, such as a path planning method for robot movement.

[0099] In particular, the processes described above with reference to the flowcharts can be implemented as a computer software program according to embodiments of the present application. For example, embodiments of the present application include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods illustrated by the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via the communication unit 19, or installed from the storage unit 18, or installed from the ROM 12. When the computer program is executed by the processor 11, the above-described functions defined in the methods of embodiments of the present application are performed.

[0100] In some embodiments, a path planning method for robot movement can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded onto the RAM 13 and executed by the processor 11, one or more steps of a path planning method for robot movement described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform a path planning method for robot movement by any other appropriate means, such as by means of firmware.

[0101] The various embodiments of the systems and techniques described above can be implemented in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a complex programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0102] Computer programs used to implement the processes of the application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer program, when executed, can cause instructions defined in the flow charts and / or block diagrams to be implemented. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine as a standalone software package and partially on a remote machine or entirely on a remote machine or server.

[0103] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store computer programs for use by or in connection with an instruction execution system, apparatus, or device. Computer-readable storage media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0104] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0105] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0106] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. A server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0107] It should be understood that the various forms of flow shown above can be re-ordered, added to, or deleted from without departing from the scope of the present disclosure. For example, the steps recited in the present disclosure can be executed in parallel, executed in sequence, or executed in a different order, as long as the desired results of the present disclosure are achieved, and the present disclosure is not limited herein.

[0108] The specific embodiments described above are not intended to be limiting, and persons skilled in the art will appreciate that various modifications, combinations, sub-combinations and alternatives can be made to the specific embodiments without departing from the spirit and principles of the disclosure. Accordingly, the disclosure is not limited to the specific embodiments described above, but only by the scope of the appended claims.

Claims

1. A path planning method for robot movement, characterized in that: include: receiving a first control instruction for the robot, and obtaining the actual position of the robot and a global grid map of a preset activity area of ​​the robot, wherein the first control instruction is used to control the robot to move to a target end point; determining a target travel path according to the first control instruction, the actual position, and the global grid map, and controlling the robot to move along the target travel path; During the movement of the robot, spatial information of the robot is collected by a data collection module installed on the robot, wherein the spatial information includes environmental information and posture information; An environment state vector is determined according to the spatial information, and a target travel path of the robot is updated according to the environment state vector and the global grid map.

2. The method according to claim 1, wherein the data acquisition module includes a visual sensor, a lidar sensor, a depth sensor, and an inertial measurement unit; the spatial information includes at least visual image information, three-dimensional point cloud data, depth information, and posture information; and the data acquisition module installed on the robot to collect the spatial information of the robot includes: Collecting visual image information around the robot through the visual sensor; receiving, by the laser radar sensor, reflected signals from target objects in an environment, and constructing three-dimensional point cloud data according to the reflected signals; Acquiring depth information of the target object in the environment through the depth sensor; The position and posture information of the robot is collected through the inertial measurement unit.

3. The method according to claim 1, characterized in that The determining of the environment state vector according to the spatial information includes: The preprocessed environmental information is classified according to the type of target object in the environmental information, and the environmental state vector is determined according to the classification result and a preset confidence weight, wherein the preprocessing includes at least denoising, downsampling and bilateral filtering.

4. The method according to claim 3, characterized in that The step of determining the environment state vector according to the classification result and the preset confidence weight includes: Updating the confidence weight according to the number of the target objects, the state of the target objects, and the distance between the target objects and the robot in the classification result, wherein the state is used to represent the motion state of the target objects; An environment state vector is determined according to a result of weighted summation of the classification result and the confidence weight.

5. The method according to claim 1, wherein The updating of the target travel path of the robot according to the environmental state vector and the global grid map comprises: Determining prompt information based on the environmental state vector and a preset prompt template, and inputting the prompt information into a pre-trained warning level determination model to obtain the warning level, wherein the warning level is used to represent the warning degree of the robot traveling in the target travel path; The target travel path of the robot is updated according to the environmental state vector, the warning level and the global grid map.

6. The method according to claim 5, characterized in that The updating of the target travel path of the robot according to the environmental state vector, the warning level and the global grid map comprises: A second control instruction for the robot is determined according to the environmental state vector, the posture information of the robot, and the warning level, and a target travel path of the robot is updated according to the second control instruction and the global grid map.

7. The method according to claim 6, characterized in that The determining the second control instruction of the robot according to the environmental state vector, the posture information of the robot, and the warning level includes: A third control instruction is determined according to the warning level, a fourth control instruction of the robot is determined according to the environmental state vector and the posture information, and the second control instruction is determined according to the third control instruction and the fourth control instruction.

8. A path planning device for robot movement, characterized in that: include: a global grid map acquisition module, configured to receive a first control instruction for the robot, and acquire the actual position of the robot and a global grid map of a preset activity area of ​​the robot, wherein the first control instruction is used to control the robot to move to a target end point; a robot movement module, configured to determine a target travel path according to the first control instruction, the actual position, and the global grid map, and control the robot to move along the target travel path; a spatial information acquisition module, configured to acquire spatial information of the robot through a data acquisition module installed on the robot during the robot's movement, wherein the spatial information includes environmental information and posture information; A path updating module is used to determine an environment state vector according to the spatial information, and to update a target travel path of the robot according to the environment state vector and the global grid map.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor. The computer program is executed by the at least one processor to enable the at least one processor to execute the path planning method for robot movement according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the path planning method for robot movement according to any one of claims 1 to 7 when executed.

Images