Warehouse system, robot and obstacle avoidance method thereof and computer readable storage medium

Abstract

The application relates to the technical field of intelligent warehousing, and discloses a warehousing system, a robot, an obstacle avoidance method thereof and a computer readable storage medium. The warehousing system comprises: a plurality of sensing sensors, which are arranged at different positions of the warehousing system and are used for collecting environmental data of the warehousing system; and a robot, which is used for: locating a current position of the robot itself; determining a target sensing sensor located in a current area where the robot is from the plurality of sensing sensors according to the current position; acquiring environmental data collected by the target sensing sensor; generating an obstacle map according to the environmental data collected by the target sensing sensor; and performing obstacle avoidance planning according to the current position and the obstacle map. The application reduces the obstacle avoidance cost, improves the obstacle avoidance reliability and resource utilization rate.

Description

Technical Field

[0001] This application relates to the field of intelligent warehousing technology, specifically to a warehousing system, a robot and its obstacle avoidance method, and a computer-readable storage medium. Background Technology

[0002] In dynamic environments such as warehouse aisles, multiple robots need to share passageways, as well as between robots and workers, and there is a risk of unexpected situations such as goods falling. To ensure the safe and efficient operation of robots in complex environments, warehousing systems need to meet robot obstacle avoidance requirements.

[0003] In existing single-robot autonomous obstacle avoidance systems, LiDAR, depth cameras, or multi-sensor fusion systems are integrated into the robot body to achieve obstacle recognition and path planning through local environmental perception and SLAM technology. However, this type of distributed perception architecture suffers from problems such as high deployment costs, difficulty in eliminating perception blind spots, and sensor failures affecting system reliability. Summary of the Invention

[0004] In view of the above problems, this application provides a warehousing system, a robot and its obstacle avoidance method and a computer-readable storage medium to solve the problems of high deployment cost, difficulty in eliminating perception blind spots and sensor failure affecting system reliability in the existing obstacle avoidance schemes.

[0005] According to one aspect of the embodiments of this application, a warehousing system is provided, comprising: Multiple sensing sensors are deployed at different locations within the warehousing system to collect environmental data of the warehousing system; and Robots, used for: Determine the robot's current position; Based on the current location, determine the target sensing sensor located within the current area where the robot is located from among the multiple sensing sensors; Acquire the environmental data collected by the target perception sensor; An obstacle map is generated based on the environmental data collected by the target perception sensor. Obstacle avoidance planning is performed based on the current location and the obstacle map.

[0006] In one alternative approach, multiple of the sensing sensors are deployed on one or more of the shelves, columns, and walls of the warehousing system.

[0007] In one alternative approach, the ground intervals of the warehousing system that allow the robot to pass through are equipped with multiple positioning markers. The robot is equipped with a recognition device, and the robot is specifically used for: The robot's current position is determined by identifying the positioning marker using the identification device.

[0008] In one alternative approach, the robot stores installation information for multiple of the sensing sensors, the installation information including installation location and scanning angle information; The robot is specifically used for: The continuous area formed by all geographical locations whose distance from the current location is less than or equal to a preset distance threshold is defined as the current area; Based on the installation information and the robot's forward path, the target sensing sensor whose installation location is within the current area and whose scanning range covers the forward path is determined from among the plurality of sensing sensors.

[0009] In one alternative approach, the installation information further includes identification codes for multiple sensing sensors, the identification codes being bound to the installation location and the scanning angle information; The plurality of the sensing sensors are further configured to: broadcast a data packet containing the environmental data, wherein the data packet carries the identification code of the sensing sensor broadcasting the data packet; The robot is specifically used for: Listen to the data packets broadcast by the multiple sensing sensors; The data packets carrying the identification code of the target perception sensor are retained from the monitored data packets, and the remaining data packets are discarded to obtain the environmental data collected by the target perception sensor.

[0010] In one alternative approach, the robot stores a map of the warehousing system; The robot is specifically used to: identify obstacles in the map and generate the obstacle map based on the environmental data collected by the target perception sensor.

[0011] In one alternative embodiment, the robot is specifically used for: Determine whether there is a target obstacle on the robot's forward path among the obstacles marked in the obstacle map; If the target obstacle exists, determine whether there is an obstacle avoidance path that can bypass the target obstacle; If there is an obstacle avoidance path that can avoid the target obstacle, proceed according to the obstacle avoidance path.

[0012] In one alternative embodiment, the robot is further specifically used for: If no obstacle avoidance path exists that can bypass the target obstacle, wait at the current position; Continue to monitor the data packets broadcast by the multiple sensing sensors; From the continuously monitored data packets, retain the data packets carrying the identification code of the target perception sensor, discard the remaining data packets, and obtain the updated environmental data collected by the target perception sensor; Based on the updated environmental data, obstacles are identified in the map to obtain an updated obstacle map; Determine whether the target obstacle is still on the robot's path based on the updated obstacle map; Repeat the steps of continuing to listen to the data packets broadcast by the multiple sensing sensors until determining whether the target obstacle is still on the robot's forward path based on the updated obstacle map, until the target obstacle is no longer on the robot's forward path; Follow the described path forward.

[0013] In one alternative approach, the warehousing system further includes a server; The plurality of the sensing sensors are also used to: upload the environmental data to the server; The robot is specifically used to: obtain the environmental data collected by the target perception sensor from the server.

[0014] According to another aspect of the embodiments of this application, a robot obstacle avoidance method is provided, which is applied to a robot in a warehousing system. The warehousing system includes multiple sensing sensors deployed at different locations in the warehousing system, and the sensing sensors are used to collect environmental data of the warehousing system. The method includes: Determine the robot's current position; Based on the current location, determine the target sensing sensor located within the current area where the robot is located from multiple sensing sensors; Acquire the environmental data collected by the target perception sensor; An obstacle map is generated based on the environmental data collected by the target perception sensor. Obstacle avoidance planning is performed based on the current location and the obstacle map.

[0015] In one alternative, the warehousing system has multiple positioning markers arranged at intervals on the ground that the robot can pass through, and the robot is equipped with an identification device. Locating the robot's current position includes: The robot's current position is determined by identifying the positioning marker using the identification device.

[0016] In one alternative approach, the robot stores installation information for multiple of the sensing sensors, the installation information including installation location and scanning angle information; The step of determining the target sensing sensor located within the current area of ​​the robot from multiple sensing sensors based on the current position includes: The continuous area formed by all geographical locations whose distance from the current location is less than or equal to a preset distance threshold is defined as the current area; Based on the installation information and the robot's forward path, the target sensing sensor whose installation location is within the current area and whose scanning range covers the forward path is determined from among the plurality of sensing sensors.

[0017] In one alternative approach, the installation information further includes identification codes for multiple sensing sensors, the identification codes being bound to the installation location and the scanning angle information; The acquisition of the environmental data collected by the target perception sensor includes: Listen to data packets containing environmental data broadcast by multiple of the sensing sensors, wherein the data packets carry the identification code of the sensing sensor broadcasting the data packet; The data packets carrying the identification code of the target perception sensor are retained from the monitored data packets, and the remaining data packets are discarded to obtain the environmental data collected by the target perception sensor.

[0018] In one alternative approach, the robot stores a map of the warehousing system; The step of generating an obstacle map based on the environmental data collected by the target perception sensor includes: marking obstacles in the map based on the environmental data collected by the target perception sensor, and generating the obstacle map.

[0019] In one alternative approach, the obstacle avoidance planning based on the current location and the obstacle map includes: Determine whether there is a target obstacle on the robot's forward path among the obstacles marked in the obstacle map; If the target obstacle exists, determine whether there is an obstacle avoidance path that can bypass the target obstacle; If there is an obstacle avoidance path that can avoid the target obstacle, proceed according to the obstacle avoidance path.

[0020] In an alternative approach, the method further includes: If no obstacle avoidance path exists that can bypass the target obstacle, wait at the current position; Continue to monitor the data packets broadcast by the multiple sensing sensors; From the continuously monitored data packets, retain the data packets carrying the identification code of the target perception sensor, discard the remaining data packets, and obtain the updated environmental data collected by the target perception sensor; Based on the updated environmental data, obstacles are identified in the map to obtain an updated obstacle map; Determine whether the target obstacle is still on the robot's path based on the updated obstacle map; Repeat the steps of continuing to listen to the data packets broadcast by the multiple sensing sensors until determining whether the target obstacle is still on the robot's forward path based on the updated obstacle map, until the target obstacle is no longer on the robot's forward path; Follow the described path forward.

[0021] In one alternative approach, the warehousing system further includes a server; The step of acquiring the environmental data collected by the target perception sensor includes: acquiring the environmental data collected and uploaded by the target perception sensor from the server.

[0022] According to another aspect of the embodiments of this application, a robot is provided, including: a processor and a memory, wherein the memory stores executable instructions, and the processor is capable of executing the executable instructions to implement the robot obstacle avoidance method as described in any of the preceding embodiments.

[0023] According to another aspect of the embodiments of this application, a computer-readable storage medium is provided, wherein the storage medium stores executable instructions, which, when executed on a robot, cause the robot to perform the robot obstacle avoidance method as described in any of the preceding embodiments.

[0024] This application embodiment deploys multiple sensing sensors at different locations within the warehousing system. As the robot moves to different locations, it acquires environmental data collected by the target sensing sensors within its current area and performs obstacle avoidance planning based on this data. This approach eliminates the need for independently configuring sensing sensors on each robot, reducing deployment costs. By deploying sensors at different locations, environmental data collected by adjacent sensors can be combined and used, reducing blind spots and improving obstacle avoidance reliability. Environmental data collected by sensing sensors within the same area can be provided to multiple robots passing through that area, improving resource utilization through information sharing and utilizing environmental sensing resources.

[0025] The above description is merely an overview of the technical solutions of the embodiments of this application. In order to better understand the technical means of the embodiments of this application and to implement them in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the embodiments of this application more obvious and understandable, specific implementation methods of this application are described below. Attached Figure Description

[0026] The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of this application. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 A structural block diagram of the warehousing system provided in an embodiment of this application is shown; Figure 2 A schematic diagram illustrating the deployment of sensing sensors in a warehousing system provided in an embodiment of this application is shown. Figure 3A This paper shows a schematic diagram of the horizontal coverage area of ​​a sensing sensor in a local area in a specific embodiment of this application. Figure 3B This illustration shows a schematic diagram of the horizontal coverage area of ​​a sensing sensor within a local area in another specific embodiment of this application; Figure 3C This illustration shows a schematic diagram of the vertical coverage area of ​​a sensing sensor in a local area in yet another specific embodiment of this application. Figure 4 A flowchart illustrating the robot obstacle avoidance method provided in an embodiment of this application is shown; Figure 5 A schematic diagram of a target perception sensor used to determine the current area where the robot is located is shown in an embodiment of this application; Figure 6A A schematic diagram of an obstacle map is shown; Figure 6B A schematic diagram of another obstacle map is shown; Figure 7A Showing the target Figure 6A A schematic diagram illustrating obstacle avoidance planning based on the obstacle map shown; Figure 7B A schematic diagram of another obstacle avoidance plan is shown; Figure 8 A flowchart illustrating a robot obstacle avoidance method according to other embodiments of this application is shown; Figure 9 This application shows a structural block diagram of a warehousing system provided in some other embodiments; Figure 10 A schematic diagram of the robot obstacle avoidance device provided in an embodiment of this application is shown; Figure 11 A schematic diagram of the structure of the robot provided in an embodiment of this application is shown.

[0027] The attached figures are labeled as follows: Warehouse system 100, sensing sensor 10, robot 20, identification device 21, exterior wall 31, interior wall 32, column 40, shelf 50, first shelf 51, second shelf 52, container 60, aisle 70, first aisle 71, second aisle 72, server 80, positioning marker 90. Detailed Implementation

[0028] Exemplary embodiments of the present application will now be described in more detail with reference to the accompanying drawings. Although exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application may be implemented in various forms and should not be limited to the embodiments set forth herein.

[0029] With the rapid development of intelligent warehousing and automated logistics technologies, warehouse robots have become key execution units for cargo handling and scheduling, mainly including Automated Guided Vehicles (AGVs) and Autonomous Mobile Robots (AMRs). In intelligent warehousing systems, warehouse robots need to move between shelves or in aisles between shelves and workstations, where workers often pass through, and goods occasionally fall from the robots to the ground, creating a complex and dynamic operating environment. To ensure their safe and efficient operation, obstacle avoidance is one of the core functions of warehouse robots. Currently, the mainstream solution is to integrate obstacle avoidance sensors, such as LiDAR, depth cameras, and ultrasonic sensors, into the robot body to achieve autonomous obstacle detection and avoidance, i.e., single-robot autonomous obstacle avoidance.

[0030] Existing single-robot autonomous obstacle avoidance solutions mainly fall into the following categories: one is based on local perception, which uses depth vision devices such as forward-facing or 360° LiDAR, structured light, or Time-of-flight (TOF) cameras installed on the robot to achieve obstacle detection and local path planning; another relies on visual perception, using cameras and AI algorithms for obstacle recognition, but this method has shortcomings in recognition accuracy, real-time performance, and occlusion robustness, and is easily affected by ambient lighting; and a third uses a multi-sensor fusion system (such as radar + vision + infrared), which can improve perception accuracy, but also brings higher costs and computational load, and is mostly used in scenarios with extremely strict obstacle avoidance accuracy requirements.

[0031] All of the above solutions require each robot to be independently equipped with an obstacle avoidance sensor, relying on these sensors to perceive the surrounding environment in real time and combining them with Simultaneous Localization and Mapping (SLAM) algorithms to achieve navigation and obstacle avoidance. This distributed architecture has the following limitations: First, large-scale deployment leads to high total system costs; second, the perception ranges of multiple robots overlap, but there is a lack of information sharing mechanisms, resulting in duplication and waste of perception resources; in addition, due to limitations in sensor installation location and angle, there may still be blind spots, posing safety hazards; once a sensor malfunctions or deviates, it will directly affect the robot's obstacle avoidance capabilities and the system's reliability. Finally, warehouses, as static and structured environments, have favorable conditions for deploying global perception facilities, but existing single-robot obstacle avoidance solutions fail to fully reuse environmental perception resources, and overall efficiency has not been optimized.

[0032] To address the aforementioned issues, this application provides an obstacle avoidance solution for warehouse robots. Figure 1 A structural block diagram of a warehousing system 100 provided in an embodiment of this application is shown. Figure 1 As shown, the warehousing system 100 includes multiple sensing sensors 10 and a robot 20. The multiple sensing sensors 10 are deployed at different locations within the warehousing system 100 to collect environmental data. When the robot 20 moves within the warehousing system 100, it locates its current position and, based on this position, identifies a target sensing sensor within its current area from among the multiple sensing sensors 10. The robot 20 then acquires the environmental data collected by the target sensing sensor, generates an obstacle map based on the environmental data collected by the target sensing sensor, and performs obstacle avoidance planning based on its current position and the obstacle map.

[0033] The warehouse system 100 has multiple positioning markers 90 arranged at intervals on the ground (e.g., the floor of an alley) that the robot 20 can pass through. The robot 20 is equipped with an identification device 21. The robot 20 identifies the positioning markers 90 through the identification device 21 to locate its current position.

[0034] Figure 2 This diagram illustrates the deployment of sensing sensors 10 in a warehousing system 100 provided in an embodiment of this application. Figure 2As shown, the warehousing system 100 includes walls, divided into outer walls 31 and inner walls 32. The outer walls 31 are the enclosure structure of the warehouse building, defining the boundaries of the warehouse, and forming the storage and operating spaces of the warehousing system 100 within them. The layout of the shelves and aisles inside the warehousing system 100 must be ultimately bounded by the walls, with sufficient safety distances maintained. The inner walls 32 are used to divide the large warehouse into several zones. The warehousing system 100 also includes columns 40 (also called building columns, warehouse columns, or structural columns), which are the load-bearing structure of the warehouse.

[0035] Shelves 50 and robots 20 are arranged within the space inside the wall. Shelves 50 are used to store containers 60, which can be containers loaded with goods or temporarily empty containers. Robots 20 are used to move containers 60, for example, moving containers 60 to shelves 50 for warehousing operations, or retrieving containers 60 from shelves 50 for outbound operations.

[0036] The warehousing system 100 includes a server 80 on which the software systems of the warehousing system 100 are installed, such as the Intelligent Equipment Scheduling System (ESS), the Order Management System (OMS), the Warehouse Management System (WMS), the Warehouse Control System (WCS), and the Warehouse Execution System (WES).

[0037] The warehousing system 100 may also include other facilities or equipment, such as workstations, which are not limited in this application.

[0038] The shelves 50, uprights 40, and walls (external wall 31 and internal wall 32) have a certain height, which can be used to install sensing sensors 10. The sensing sensors 10 can be deployed on one or more of the shelves 50, uprights 40, and walls of the storage system 100.

[0039] Due to the limitation of the field of view (FOV) of the sensing sensor 10, the coverage area of ​​a single sensing sensor 10 is limited. The field of view is the angular range of the external world that the sensing sensor 10 can detect, including the horizontal field of view (HFOV, the angular range that the sensor can cover in the horizontal direction) and the vertical field of view (VFOV, the angular range that the sensor can cover in the vertical direction). When deploying the sensing sensor 10, by deploying the sensing sensor 10 in multiple locations, the coverage areas of the multiple sensing sensors 10 can be stitched together to cover the entire passage path of the robot 20, thereby eliminating obstacle avoidance blind spots. The deployment location of the sensing sensor 10 can be selected based on its field of view so that the coverage areas of the deployed multiple sensing sensors 10 can be stitched together to cover the entire passage path of the robot 20. In the horizontal plane, the horizontal installation position of the sensing sensor 10 can be determined based on its horizontal field of view. Multiple sensing sensors 10 can be deployed at intervals on one or more of the shelf 50, column 40, and wall. In the vertical direction, the vertical installation position, i.e., its installation height, of the sensing sensor 10 can be determined based on its vertical field of view, ensuring that the sensing area of ​​the sensing sensor 10 covers the ground area where the robot 20 walks. Since the ground height at which the robot 20 walks within the storage system 100 is basically consistent, the installation height of each sensing sensor 10 can be the same, only the horizontal installation position differs. This embodiment defines the storage system 100 coordinate system as XYZ, where the X direction is the length direction of the shelf 50, the Y direction is the depth direction of the shelf 50, and the Z direction is the height direction of the shelf 50. Therefore, when deploying the sensing sensors 10, the Z coordinate of each sensing sensor 10 can be the same, while the (X, Y) coordinates can be different.

[0040] The deployment of the sensing sensor 10 is further illustrated below with a specific example. Figure 3A This diagram illustrates the horizontal coverage area of ​​the sensing sensor 10 within a local area in a specific embodiment of this application. Figure 3B This illustration shows a schematic diagram of the horizontal coverage area of ​​the sensing sensor 10 within a local area in another specific embodiment of this application. Figure 3C This paper shows a schematic diagram of the vertical coverage area of ​​the sensing sensor 10 in a local area in another specific embodiment of this application.

[0041] like Figure 3AAs shown in the figure, the dashed line represents the horizontal field of view (HFOV) of the sensing sensor 10. Four sensing sensors 10 are deployed at intervals on the first shelf 51, so that the horizontal sensing area of ​​the sensing sensors 10 can cover the aisle 70 (the path of the robot 20) between the first shelf 51 and the second shelf 52. It is understood that, for ease of illustration, the size of the sensing sensor 10 has been enlarged. The area not covered by the sensing sensor 10, filled with dots in the figure, is actually only a very narrow area close to the edge of the shelf 50. The robot 20 is usually not located in this area when traveling in the aisle 70, and obstacles are usually other robots 20, workers, fallen goods, etc. Obstacles located in this area usually also enter the coverage area of ​​the sensing sensor 10. Therefore, this uncovered area does not affect the obstacle avoidance scheme of this embodiment, and it can be considered that the horizontal sensing area of ​​the sensing sensor 10 has covered the aisle 70 between the first shelf 51 and the second shelf 52. Of course, to achieve full coverage in a physical sense, it can also be done as follows... Figure 3B As shown, four sensing sensors 10 are deployed at similar intervals on the second shelf 52 to eliminate the aforementioned small uncovered areas within the aisle 70.

[0042] like Figure 3C As shown in the figure, the horizontal coordinates (X, Y) of the sensing sensor 10 have been determined. The dashed line in the figure shows the vertical field of view (VFOV) of the sensing sensor 10. The sensing sensor 10 is deployed at the height shown in the figure (that is, the vertical coordinate Z of the sensing sensor 10 is determined) so that the sensing area of ​​the sensing sensor 10 in the vertical direction can cover the ground area where the robot 20 walks in the aisle 70 between the first shelf 51 and the second shelf 52.

[0043] The perception sensor 10 can be one or more of the following: LiDAR, depth camera, ultrasonic sensor, and camera. For example, all of the perception sensors 10 may be LiDAR, all may be cameras, or some of the perception sensors 10 may use LiDAR and some may use ultrasonic sensors. LiDAR has precise three-dimensional ranging capabilities, can directly output point cloud data with three-dimensional coordinates, and is unaffected by ambient light. When all of the perception sensors 10 deployed within the warehouse system 100 are LiDAR, the multiple LiDARs collect environmental point cloud data of the warehouse system 100 to provide to the robot 20 for obstacle avoidance.

[0044] The positioning marker 90 can be any item that can store location information and be recognized by the identification device 21 of the robot 20, such as visual markers, electromagnetic / physical markers, etc. Accordingly, if visual markers are placed on the ground, the identification device 21 on the robot 20 is a camera; if electromagnetic / physical markers are placed on the ground, a dedicated sensor on the robot 20 serves as the identification device 21. Visual markers include QR codes, April tags, ARUC codes, custom patterns, custom lines, etc. Electromagnetic / physical markers include magnetic nails / strips, Radio Frequency Identification (RFID) tags, etc. The robot 20 can be equipped with magnetic sensors (such as Hall effect sensors) to identify magnetic nails / strips and RFID readers to read RFID tags. Among these, QR codes are highly versatile, simple to generate, and low in cost, and can achieve centimeter-level positioning accuracy, making them suitable for large-scale deployment in the warehouse system 100.

[0045] The following section uses a QR code as an example to explain in detail how to identify the current position of the robot 20 using a positioning identifier 90 (i.e., using a QR code for positioning). When using a QR code for positioning, location information (such as coordinates) can be stored in the QR code itself. Alternatively, an identifier can be stored in the QR code, and the location information associated with the identifier can be stored in a database (such as the robot's local database, or the database of a backend server or cloud server).

[0046] If the QR code itself stores location information, when generating the QR code, the coordinates of the current location (e.g., location A) of the QR code (e.g., x:100, y:50, z:0, or excluding the z coordinate) are encoded as text into the QR code, printed, and then pasted at location A. When robot 20 moves to location 1, its camera captures the QR code. The program inside robot 20 (e.g., using an OpenCV QR code recognition library) decodes the QR code content, directly obtaining the string "x:100, y:50", allowing robot 20 to know that it is currently at coordinates (x: 100, y: 50).

[0047] The above method requires no network connection or database query, and can complete the location instantly with extremely low latency; since it does not rely on external systems, it has high reliability. However, if the coordinates of each location need to be modified later (e.g., a 100-map update for a warehouse system), the physical QR code needs to be regenerated and replaced, resulting in poor flexibility; moreover, the QR code has limited capacity and can only carry a limited amount of information, making it unfriendly for application scenarios with complex coordinate information or those that require more data (such as map version numbers).

[0048] If a QR code is used to store the identifier, and the location information associated with the identifier is stored on server 80, then each QR code stores only one unique identifier, such as a number or string (e.g., "tag_001" or "7A3B9C"). Server 80 stores the coordinate information corresponding to each identifier. First, a QR code is generated and a database is built. For example, a QR code with the content "tag_001" is pasted at position 1. Simultaneously, the identifier "tag_001" is associated with the coordinates (x: 100, y: 50) in the database (which can be the robot 20's local database or the database on server 80). When robot 20 moves to position 1, its camera captures the QR code, decodes it to obtain the string "tag_001," and then uses the identifier "tag_001" to query the database. The database returns the coordinates (x: 100, y: 50) corresponding to "tag_001," allowing robot 20 to know its current coordinates (x: 100, y: 50).

[0049] The above method offers high deployment flexibility. If coordinates need to be modified, only the database record needs to be updated; there's no need to replace the physical QR code. Furthermore, if the physical location of the QR code moves, only its coordinate mapping needs to be updated in the database. Moreover, the database can store far more information than just coordinates, such as the semantics of the location, associated task instructions, and information about neighboring points. However, this method requires a network connection to query a remote database, or the entire database needs to be pre-stored locally on the robot 20. Querying a remote database via the network increases the consumption of communication bandwidth.

[0050] In actual deployment, the appropriate deployment method can be selected according to the application scenario. In some embodiments, the above two methods can also be combined. For example, the QR code can store both the identifier and coordinates. During positioning, the robot 20 prioritizes the coordinates built into the QR code, while sending the identifier to the server 80 for verification and to obtain updated information, thus combining the advantages of offline capability and online updates.

[0051] The obstacle avoidance process of robot 20 is explained in detail below. Figure 4 This paper illustrates a flowchart of an obstacle avoidance method for a robot 20 provided in an embodiment of this application. This method is applied to the aforementioned robot 20, such as... Figure 4 As shown, the method includes the following steps.

[0052] S110, locate the current position of robot 20.

[0053] In this embodiment, a QR code is placed on the ground as a positioning marker 90. A camera is placed on the robot 20 at a location where the QR code can be captured (e.g., the bottom of the robot 20's chassis), with the camera lens facing the ground, so that the image of the QR code can be captured. When the robot 20 walks to a location with a QR code, it recognizes the QR code through the camera to obtain the robot 20's current coordinates (x1, y1), which are used to indicate the robot 20's current position.

[0054] S120, based on the current position, determine the target sensing sensor located in the current area where the robot 20 is located from among the multiple sensing sensors 10.

[0055] Robot 20 stores installation information for multiple sensing sensors 10, including installation location and scanning angle information. The installation location can be coordinate information, such as (x2, y2), and the scanning angle refers to the horizontal field of view of the sensing sensor 10, such as 120°. In this step, the continuous area formed by all geographical locations whose distance from the current location is less than or equal to a preset distance threshold is defined as the current area. Then, based on the installation information and the robot 20's forward path, the target sensing sensor whose installation location is within the current area and whose scanning range covers the forward path is determined from the multiple sensing sensors 10.

[0056] Figure 5 A schematic diagram of a target perception sensor determining the current area where robot 20 is located is shown in an embodiment of this application. For example... Figure 5 As shown, the current position of robot 20, located by S110, is (x1, y1). Based on this, a circle R is drawn with (x1, y1) as the center and a preset distance threshold r as the radius. The area within circle R is the current area where robot 20 is located. According to the installation positions of the multiple sensing sensors 10 stored by robot 20, sensing sensors S1, S2, and S3 located within circle R can be identified. Further combining this with the robot 20's forward path P, and based on the scanning angle information of the multiple sensing sensors 10 stored by robot 20, it can be seen that the scanning range of sensing sensors S1 and S2 covers the robot 20's forward path P, but the scanning range of sensing sensor S3 does not cover the robot 20's forward path P. Therefore, sensing sensors S1 and S2 are ultimately identified as the target sensing sensors, and the environmental data they collect can be used for obstacle avoidance.

[0057] S130: Acquire environmental data collected by the target perception sensor.

[0058] The installation information of multiple sensing sensors 10 stored in robot 20 also includes the identification codes (IDs) of multiple sensing sensors 10. The identification codes are bound to the installation position and scanning angle information. For example, in the installation information stored in robot 20, the identification code of sensing sensor S1 is S1, the installation position is (x2, y2), and the scanning angle is 120°. Then, S1, (x2, y2), and 120° are bound together, and the installation position and scanning angle of the sensing sensor 10 can be queried based on S1.

[0059] After each sensing sensor 10 collects environmental data from the storage system 100, it can broadcast the collected environmental data and / or upload the environmental data to the server 80. When the sensing sensor 10 broadcasts environmental data, it includes the environmental data and the identification code of the sensing sensor 10 that broadcast the data in its broadcast data packet.

[0060] Robot 20 can obtain environmental data collected by the target perception sensor by listening to data packets broadcast by multiple perception sensors 10, retaining data packets carrying the identification code of the target perception sensor, and discarding the remaining data packets. The target perception sensor is installed within the current area and its scanning range covers the robot 20's forward path; therefore, the environmental data it collects can be used for obstacle avoidance by the robot 20 and can be retained. Environmental data collected by other perception sensors 10 is useless for obstacle avoidance by the robot 20 and can be discarded to avoid occupying the robot 20's storage space.

[0061] For example, robot 20 listens to data packets broadcast by sensing sensors S1, S2, S3, S4, and S5 that are relatively close to it. Since the target sensing sensors identified by S120 are sensing sensors S1 and S2, robot 20 retains the data packets with identification codes S1 and S2 of shoelace sensing sensors S1 and S2, and discards the data packets carrying identification codes S3, S4, and S5.

[0062] Data acquisition via broadcasting can reduce the consumption of communication bandwidth, especially when there are a large number of sensing sensors 10 and robots 20, thereby improving data transmission efficiency and thus improving obstacle avoidance efficiency.

[0063] In some embodiments, if each sensing sensor 10 uploads environmental data to the server 80, the robot 20 can also obtain the environmental data collected and uploaded by the target sensing sensor from the server 80.

[0064] S140 generates an obstacle map based on environmental data collected by the target perception sensor.

[0065] Robot 20 locally stores the map of warehouse system 100, thus eliminating the need to rely on the map stored on server 80. Robot 20 can quickly generate obstacle maps and avoid obstacles locally. After acquiring environmental data from target perception sensors, robot 20 can mark obstacles in its locally stored map based on this data, generating an obstacle map.

[0066] The environmental data collected by the sensing sensor 10 is in its own coordinate system, and each sensing sensor 10 has a different coordinate system due to its different installation location. After acquiring the environmental data collected by the target sensing sensor and before generating the obstacle map, coordinate transformation of the data is required. The robot 20 can transform the acquired environmental data from the coordinate system of the sensing sensor 10 to the robot coordinate system based on the installation location of the sensing sensor 10 and the current position of the robot 20. The robot coordinate system is the coordinate system of the robot 20 at its current position. The coordinate transformation of each data point in the environmental data can be performed using the following formula 1: Formula 1 in, These are the coordinates of data points in the environment data within the robot's coordinate system. To collect the coordinates of the data points in the environmental data in the sensor coordinate system, T is the coordinate of the origin of the sensor coordinate system in the robot coordinate system, and R is the rotation matrix required to rotate the data points from the sensor coordinate system to align with the robot coordinate system. Based on the installation position of the sensor 10 collecting the environmental data and the current position of the robot 20, i.e., their relative positional relationship (relative pose), the above R and T are determined, and coordinate transformation can be performed according to Formula 1.

[0067] S150 performs obstacle avoidance planning based on the current location and obstacle map.

[0068] In this step, robot 20 first determines whether there is a target obstacle on the robot's forward path among the obstacles marked in the obstacle map; if there is a target obstacle, it determines whether there is an obstacle avoidance path that can avoid the target obstacle; if there is an obstacle avoidance path that can avoid the target obstacle, it moves according to the obstacle avoidance path.

[0069] Figure 6A and Figure 6B Several schematic diagrams of obstacle maps are shown. Figure 6A In this case, neither obstacle O1 nor obstacle O2 is located on the forward path of robot 20, so there is no target obstacle and no subsequent obstacle avoidance operation is required. Figure 6BIn the equation, obstacle O1 is on the forward path of robot 20, while obstacle O2 is not on the forward path of robot 20. Therefore, it is determined that there is a target obstacle, which is obstacle O1.

[0070] Figure 7A Showing the target Figure 6A The diagram illustrates obstacle avoidance planning based on the obstacle map shown. QR codes are arranged along the dotted lines in the diagram, allowing robot 20 to travel along the paths indicated by these lines. The first alleyway 71 is wider, containing two rows of QR codes arranged side-by-side, forming two paths for robot 20 to travel on. This means that two robots 20 can travel side-by-side simultaneously within the first alleyway 71. The second alleyway 72 is narrower, containing only one row of QR codes, forming a single path for robot 20 to travel on. This means that only one robot 20 can travel in the Y direction within the second alleyway 72 at a time.

[0071] like Figure 7A As shown, due to the presence of the target obstacle O1, the robot cannot continue along the original walking path (the local path P1 passing through obstacle O1, with points A and B as its two endpoints), otherwise the robot 20 will collide with obstacle O1. Based on the obstacle map, it can be determined that there is an obstacle avoidance path P2 that can avoid the target obstacle O1. Therefore, obstacle avoidance path P2 is used to replace the local path P1. The robot 20 walks from point A to point B according to the obstacle avoidance path P2, and then continues along the original walking path. Both obstacle avoidance path P2 and local path P1 are paths within the first aisle 71.

[0072] Figure 7B A schematic diagram of another obstacle avoidance plan is shown. (For example...) Figure 7B As shown, the target obstacles are O1 and O2. Since both obstacles O1 and O2 are within the first aisle 71, it is impossible to bypass them using other parallel paths within the first aisle 71. When the bottom of the shelf 50 is accessible to the robot 20, it can bypass obstacles O1 and O2 using obstacle avoidance path P3, which passes through the bottom of the shelf 50.

[0073] Furthermore, the obstacle avoidance path can also be a path that passes through other lanes 70. The planning method for the obstacle avoidance path can be implemented using existing technologies, which will not be described in detail in this application.

[0074] This embodiment of the application deploys multiple sensing sensors 10 at different locations within the warehousing system 100. When the robot 20 moves to different locations, it acquires environmental data collected by the target sensing sensors within its current area and performs obstacle avoidance planning based on this environmental data. This method eliminates the need to independently configure a sensing sensor 10 on each robot 20, reducing deployment costs. By deploying sensors at different locations, environmental data collected by adjacent sensors can be combined and used, reducing blind spots and improving obstacle avoidance reliability. Environmental data collected by sensing sensors 10 within the same area can be provided to multiple robots 20 passing through that area, improving resource utilization through information sharing and utilizing environmental sensing resources.

[0075] Figure 8 A flowchart illustrating obstacle avoidance methods for robot 20 according to other embodiments of this application is shown. For example... Figure 8 As shown, the method includes the following steps.

[0076] S210, locate the current position of robot 20.

[0077] S220, based on the current position, determine the target sensing sensor located in the current area where the robot 20 is located from among the multiple sensing sensors 10.

[0078] S230: Acquire environmental data collected by the target perception sensor.

[0079] S240 generates an obstacle map based on environmental data collected by the target perception sensor.

[0080] The implementation methods of steps S210 to S240 are the same as those of steps S110 to S140 in the aforementioned embodiments, and can be referred to the previous description, which will not be repeated here.

[0081] S250: Determine if there is a target obstacle on the robot 20's forward path among the obstacles marked on the obstacle map; if so, execute S260; otherwise, end the current obstacle avoidance process until the next QR code location is reached, and then start the next round of obstacle avoidance process.

[0082] S260, determine if there is an obstacle avoidance path that can avoid the target obstacle; if yes, proceed to step S270, otherwise proceed to step S280.

[0083] If a target obstacle exists, further determine whether there is an obstacle avoidance path that can bypass the target obstacle.

[0084] S270, follow the obstacle avoidance path.

[0085] If there is an obstacle avoidance path that can bypass the target obstacle, follow the obstacle avoidance path to avoid the target obstacle.

[0086] S280, waiting at the current location.

[0087] If there is no obstacle avoidance path that can bypass the target obstacle, robot 20 waits at its current position. If the target obstacle is subsequently removed, robot 20 can continue to walk along the original path.

[0088] S290, continue to listen for data packets broadcast by multiple sensing sensors 10.

[0089] S300 retains the data packets carrying the identification code of the target perception sensor from the continuously monitored data packets, discards the remaining data packets, and obtains the updated environmental data collected by the target perception sensor.

[0090] S310: Based on the updated environmental data, mark obstacles on the map to obtain an updated obstacle map.

[0091] S320: Determine whether the target obstacle is still on the robot 20's forward path based on the updated obstacle map; if yes, return to step S290; otherwise, proceed to step S330.

[0092] S330, proceed according to the forward path.

[0093] By continuously listening to the data packets broadcast by multiple sensing sensors 10, it can determine whether the target obstacle is still on the robot 20's forward path. If the target obstacle has not left the robot 20's forward path, the robot 20 remains in its current position and continues to listen until the target obstacle leaves the robot 20's forward path, at which point the robot 20 can continue to move along the forward path.

[0094] In this way, when the target obstacle cannot be avoided by using the obstacle avoidance path, the robot 20 can continue to pass normally after the target obstacle is removed by waiting in place.

[0095] Figure 9 A structural block diagram of a warehousing system 100 provided in some embodiments of this application is shown. For example... Figure 9As shown, the warehousing system 100 includes multiple sensing sensors 10, a robot 20, and a server 80. The sensing sensors 10 are deployed at different locations within the warehousing system 100 to collect environmental data. When the robot 20 moves within the warehousing system 100, it locates its current position and sends this position to the server 80. Based on the robot's current position, the server 80 identifies the target sensing sensor located within the current area of ​​the robot 20 from among the multiple sensing sensors 10. The server 80 acquires the environmental data collected by the target sensing sensor, generates an obstacle map based on this data, and performs obstacle avoidance planning based on the current position and the obstacle map. After obtaining the obstacle avoidance path for the robot 20 through obstacle avoidance planning, the server 80 sends the obstacle avoidance path to the robot 20, which can then follow the obstacle avoidance path.

[0096] The warehouse system 100 has multiple positioning markers 90 arranged at intervals on the ground (e.g., the ground of the aisle 70) that the robot 20 can pass through. The robot 20 is equipped with an identification device 21. The robot 20 identifies the positioning markers 90 through the identification device 21 to locate its current position.

[0097] Server 80 stores installation information for multiple sensing sensors 10, including installation location and scanning angle information. Server 80 can determine the target sensing sensor based on the installation information of the sensing sensors 10 and the current position of robot 20.

[0098] Similar to the aforementioned embodiments, after each sensing sensor 10 collects environmental data from the warehouse system 100, it can broadcast the collected environmental data. The server 80 can obtain the environmental data collected by the target sensing sensor by listening to the data packets broadcast by multiple sensing sensors 10, retaining the data packets carrying the identification code of the target sensing sensor, and discarding the remaining data packets.

[0099] In other embodiments, the sensing sensor 10 may also upload environmental data to the server 80, and the server 80 may directly obtain the environmental data collected by the target sensing sensor from the environmental data uploaded by the sensing sensor 10.

[0100] Server 80 stores a map of the warehouse system 100 and, based on environmental data collected by the target perception sensor, marks obstacles in the map and generates an obstacle map.

[0101] Server 80 determines whether any of the obstacles marked on the obstacle map are located on the forward path of robot 20. If a target obstacle exists, it determines whether there is an obstacle avoidance path. If an obstacle avoidance path exists, it sends the path to robot 20 so that robot 20 can follow it. When determining the obstacle avoidance path, because server 80 has access to the current position of all robots globally, it can combine this information with the positions of other robots in a larger area surrounding robot 20 to find more accurate obstacle avoidance paths.

[0102] If no obstacle avoidance path exists to avoid the target obstacle, server 80 sends the judgment result to robot 20 so that robot 20 waits at its current position. Then, server 80 continues to listen to the data packets broadcast by multiple sensing sensors 10. From the continuously listened data packets, it retains the data packets carrying the identification code of the target sensing sensor and discards the remaining data packets to obtain the updated environmental data collected by the target sensing sensor. Based on the updated environmental data, it marks the obstacle on the map to obtain an updated obstacle map. Based on the updated obstacle map, it determines whether the target obstacle is still on the robot 20's forward path. It repeats the steps of continuing to listen to the data packets broadcast by multiple sensing sensors 10 until it determines whether the target obstacle is still on the robot 20's forward path based on the updated obstacle map, until the target obstacle is no longer on the robot 20's forward path. Then, it sends this judgment result to robot 20 so that robot 20 can move according to its original forward path.

[0103] In addition to the robot 20 itself locating its current position, the other steps in the robot obstacle avoidance method embodiment that were performed by the robot 20 are all performed by the server 80 in this embodiment. For specific implementation details and principles, please refer to the description of the aforementioned embodiment, which will not be repeated here.

[0104] Figure 10 A schematic diagram of the robot obstacle avoidance device 400 provided in an embodiment of this application is shown. As shown, the robot obstacle avoidance device 400 is applied to the robot 20 in the aforementioned warehousing system 100. The warehousing system includes multiple sensing sensors deployed at different locations within the warehousing system, which are used to collect environmental data of the warehousing system.

[0105] The robot obstacle avoidance device 400 includes: The positioning module 410 is used to locate the current position of the robot itself.

[0106] The determination module 420 is used to determine, based on the current position, the target sensing sensor located within the current area where the robot is located from among multiple sensing sensors.

[0107] The acquisition module 430 is used to acquire the environmental data collected by the target perception sensor.

[0108] The generation module 440 is used to generate an obstacle map based on the environmental data collected by the target perception sensor.

[0109] The planning module 450 is used to perform obstacle avoidance planning based on the current position and the obstacle map.

[0110] The robot obstacle avoidance device 400 of this application embodiment also includes other modules for performing the steps of the robot obstacle avoidance method embodiment performed by the robot 20 described above, which will not be described in detail here.

[0111] Figure 11 A schematic diagram of the robot provided in an embodiment of this application is shown. Figure 8 As shown, the robot 20 may include a processor 21 and a memory 22.

[0112] The memory 22 is used to store the computer program 23. The memory 22 may include high-speed RAM, and may also include non-volatile memory, such as at least one disk storage device. The computer program 23 may include computer-executable instructions.

[0113] The processor 21 is used to execute the computer program 23 to implement the robot obstacle avoidance method embodiment described above, which is executed by the robot 20.

[0114] The processor 21 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application. The robot 20 may include one or more processors of the same type, such as one or more CPUs; or it may include processors of different types, such as one or more CPUs and one or more ASICs.

[0115] This application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described robot obstacle avoidance method embodiment.

[0116] This application provides a computer program that can be executed by a processor to implement the above-described robot obstacle avoidance method embodiments.

[0117] This application provides a computer program product, which includes a computer program that, when executed by a processor, implements the above-described robot obstacle avoidance method embodiment.

[0118] In the several embodiments provided in this application, any function, if implemented as a software functional module / unit and sold or used as an independent product, can be stored in a computer-readable storage medium. Based on this understanding, all or part of the technical solution of this application 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 other electronic device) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing computer program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0119] The algorithms or displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used in conjunction with the teachings herein. The required structure for constructing such systems is apparent from the above description. Furthermore, the embodiments of this application are not directed to any particular programming language. It should be understood that the content of this application described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing the best mode of implementation of this application.

[0120] It should be noted that the above embodiments are illustrative of this application and not restrictive, and those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. This application can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In claims enumerating several means, several units or modules of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be construed as limiting the order of execution.

[0121] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A warehousing system, characterized in that, include: Multiple sensing sensors are deployed at different locations within the warehousing system to collect environmental data from the warehousing system. as well as The robot, equipped with a recognition device, is used for: The robot's current position is located using the identification device; Based on the current location, determine the target sensing sensor located within the current area where the robot is located from among the multiple sensing sensors; Acquire the environmental data collected by the target perception sensor; An obstacle map is generated based on the environmental data collected by the target perception sensor. Obstacle avoidance planning is performed based on the current location and the obstacle map; The robot stores installation information for multiple sensing sensors, including installation location and scanning angle information. The robot is specifically used for: The continuous area formed by all geographical locations whose distance from the current location is less than or equal to a preset distance threshold is defined as the current area; Based on the installation information and the robot's forward path, determine from among the multiple sensing sensors the target sensing sensor whose installation location is within the current area and whose scanning range covers the forward path; The installation information also includes identification codes for multiple sensing sensors, and the identification codes are bound to the installation location and the scanning angle information; The plurality of the sensing sensors are further configured to: broadcast a data packet containing the environmental data, wherein the data packet carries the identification code of the sensing sensor broadcasting the data packet; The robot is specifically used for: Listen to the data packets broadcast by the multiple sensing sensors; The data packets carrying the identification code of the target perception sensor are retained from the monitored data packets, and the remaining data packets are discarded to obtain the environmental data collected by the target perception sensor.

2. The warehousing system according to claim 1, characterized in that, Multiple of the aforementioned sensing sensors are deployed on one or more of the shelves, columns, and walls of the warehousing system.

3. The warehousing system according to claim 1, characterized in that, The warehousing system has multiple positioning markers arranged at intervals on the ground that allow the robot to pass through. The robot is specifically used for: The robot's current position is determined by identifying the positioning marker using the identification device.

4. The warehousing system according to claim 1, characterized in that, The robot stores a map of the warehousing system; The robot is specifically used to: identify obstacles in the map and generate the obstacle map based on the environmental data collected by the target perception sensor.

5. The warehousing system according to claim 4, characterized in that, The robot is specifically used for: Determine whether there is a target obstacle on the robot's forward path among the obstacles marked in the obstacle map; If the target obstacle exists, determine whether there is an obstacle avoidance path that can bypass the target obstacle; If there is an obstacle avoidance path that can avoid the target obstacle, proceed according to the obstacle avoidance path.

6. The warehousing system according to claim 5, characterized in that, The robot is also specifically used for: If no obstacle avoidance path exists that can bypass the target obstacle, wait at the current position; Continue to monitor the data packets broadcast by the multiple sensing sensors; From the continuously monitored data packets, retain the data packets carrying the identification code of the target perception sensor, discard the remaining data packets, and obtain the updated environmental data collected by the target perception sensor; Based on the updated environmental data, obstacles are identified in the map to obtain an updated obstacle map; Determine whether the target obstacle is still on the robot's path based on the updated obstacle map; Repeat the steps of continuing to listen to the data packets broadcast by the multiple sensing sensors until determining whether the target obstacle is still on the robot's forward path based on the updated obstacle map, until the target obstacle is no longer on the robot's forward path; Follow the described path forward.

7. The warehousing system according to claim 1, characterized in that, The warehousing system also includes a server; The plurality of the sensing sensors are also used to: upload the environmental data to the server; The robot is specifically used to: obtain the environmental data collected by the target perception sensor from the server.

8. A robot obstacle avoidance method, applied to a robot, characterized in that, The robot is a robot in a warehousing system. The warehousing system includes multiple sensing sensors deployed at different locations in the warehousing system. The sensing sensors are used to collect environmental data of the warehousing system. The robot is equipped with a recognition device. The method includes: The robot's current position is located using the identification device; Based on the current location, determine the target sensing sensor located within the current area where the robot is located from multiple sensing sensors; Acquire the environmental data collected by the target perception sensor; An obstacle map is generated based on the environmental data collected by the target perception sensor. Obstacle avoidance planning is performed based on the current location and the obstacle map; The robot stores installation information for multiple sensing sensors, including installation location and scanning angle information. The step of determining the target sensing sensor located within the current area of ​​the robot from multiple sensing sensors based on the current position includes: The continuous area formed by all geographical locations whose distance from the current location is less than or equal to a preset distance threshold is defined as the current area; Based on the installation information and the robot's forward path, determine from among the multiple sensing sensors the target sensing sensor whose installation location is within the current area and whose scanning range covers the forward path; The installation information also includes identification codes for multiple sensing sensors, and the identification codes are bound to the installation location and the scanning angle information; The acquisition of the environmental data collected by the target perception sensor includes: Listen to data packets containing environmental data broadcast by multiple of the sensing sensors, wherein the data packets carry the identification code of the sensing sensor broadcasting the data packet; The data packets carrying the identification code of the target perception sensor are retained from the monitored data packets, and the remaining data packets are discarded to obtain the environmental data collected by the target perception sensor.

9. The method according to claim 8, characterized in that, The warehousing system has multiple positioning markers arranged at intervals on the ground that allow the robot to pass through. The step of locating the robot's current position using the identification device includes: The robot's current position is determined by identifying the positioning marker using the identification device.

10. The method according to claim 8, characterized in that, The robot stores a map of the warehousing system; The step of generating an obstacle map based on the environmental data collected by the target perception sensor includes: marking obstacles in the map based on the environmental data collected by the target perception sensor, and generating the obstacle map.

11. The method according to claim 10, characterized in that, The obstacle avoidance planning based on the current location and the obstacle map includes: Determine whether there is a target obstacle on the robot's forward path among the obstacles marked in the obstacle map; If the target obstacle exists, determine whether there is an obstacle avoidance path that can bypass the target obstacle; If there is an obstacle avoidance path that can avoid the target obstacle, proceed according to the obstacle avoidance path.

12. The method according to claim 11, characterized in that, The method further includes: If no obstacle avoidance path exists that can bypass the target obstacle, wait at the current position; Continue to monitor the data packets broadcast by the multiple sensing sensors; From the continuously monitored data packets, retain the data packets carrying the identification code of the target perception sensor, discard the remaining data packets, and obtain the updated environmental data collected by the target perception sensor; Based on the updated environmental data, obstacles are identified in the map to obtain an updated obstacle map; Determine whether the target obstacle is still on the robot's path based on the updated obstacle map; Repeat the steps of continuing to listen to the data packets broadcast by the multiple sensing sensors until determining whether the target obstacle is still on the robot's forward path based on the updated obstacle map, until the target obstacle is no longer on the robot's forward path; Follow the described path forward.

13. The method according to claim 8, characterized in that, The warehousing system also includes a server; The step of acquiring the environmental data collected by the target perception sensor further includes: acquiring the environmental data collected and uploaded by the target perception sensor from the server.

14. A robot comprising: A processor and a memory, wherein the memory stores executable instructions, characterized in that the processor is capable of executing the executable instructions to implement the robot obstacle avoidance method as described in any one of claims 8-13.

15. A computer-readable storage medium, characterized in that, The storage medium stores executable instructions, which, when executed on the robot, cause the robot to perform the robot obstacle avoidance method as described in any one of claims 8-13.

Images