Multi-robot obstacle avoidance control method and device and robot obstacle avoidance control system

Abstract

The invention provides a multi-robot obstacle avoidance control method and device and a robot obstacle avoidance control system. The method comprises the following steps: acquiring first real-time position information of a first robot and second real-time position information of a second robot; according to the first initial path, the second initial path, the first real-time position information and the second real-time position information, whether the first robot and the second robot will collide or not is determined; under the condition that the first robot and the second robot can collide, at least updating a first initial path of the first robot, so that the first robot avoids the second robot, and obtaining a first target path of the first robot; and the first robot is controlled to continue carrying operation along the first target path. According to the scheme, the problem that in the prior art, multiple transfer robots collide with one another easily when working cooperatively is solved.

Description

Technical Field

[0001] The present application relates to the field of intelligent robot control technology, and more specifically, to a multi-robot obstacle avoidance control method, device, computer program product, and robot obstacle avoidance control system. Background Art

[0002] A handling robot is an automated device that is specifically used to carry and transport objects or goods in industries such as industry, warehousing, and logistics. A handling robot is usually equipped with various sensors, actuators, and control systems, and can autonomously move, grab, carry, and place objects in a working environment and complete corresponding handling tasks according to preset tasks and instructions.

[0003] In the field of modern logistics and manufacturing, the control scheme and system of intelligent handling robots play a vital role. In addition, intelligent handling robots also have unparalleled advantages over manual labor in some heavy or dangerous handling tasks. For example, in the intelligent storage management of explosive warehouses, the use of intelligent handling robots can improve the automation level of industrial handling tasks and reduce labor costs and work risks.

[0004] Since the number of explosives to be transported is generally large, it is usually necessary to arrange multiple transport robots to work together to complete the operation efficiently. Therefore, when controlling multiple transport robots simultaneously, it is necessary to consider the problem of mutual collision between multiple transport robots. Since the items to be transported are flammable and explosive, even a small collision may lead to serious consequences. Summary of the invention

[0005] The main purpose of the present application is to provide a multi-robot obstacle avoidance control method, device, computer program product and robot obstacle avoidance control system, so as to at least solve the problem in the prior art that multiple transport robots are prone to collision when working together.

[0006] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a multi-robot obstacle avoidance control method is provided, including: obtaining a first initial path of a first robot and a second initial path of a second robot; when the first robot starts to perform a handling operation along the first initial path and the second robot starts to perform a handling operation along the second initial path, obtaining the first real-time position information of the first robot and the second real-time position information of the second robot; determining whether the first robot and the second robot will collide based on the first initial path, the second initial path, the first real-time position information and the second real-time position information; when the first robot and the second robot are about to collide, at least updating the first initial path of the first robot so that the first robot avoids the second robot and obtains the first target path of the first robot; and controlling the first robot to continue the handling operation along the first target path.

[0007] Optionally, obtaining a first initial path of the first robot includes: obtaining task information, wherein the task information is information about transporting items to a warehouse; obtaining warehouse location information of the warehouse and initial location information of the first robot; and generating the first initial path based on the warehouse location information and the initial location information of the first robot, wherein the first initial path is an optimal path for the first robot to transport the items to the warehouse.

[0008] Optionally, obtaining the first real-time position information of the first robot includes: obtaining a positioning signal, wherein the positioning signal is a signal transmitted between the first robot and a positioning beacon, and the positioning beacon is located in a warehouse; determining the relative distance between the first robot and the positioning beacon based on the strength of the positioning signal; and determining the first real-time position information of the first robot in the warehouse based on the relative distance.

[0009] Optionally, determining whether the first robot and the second robot will collide based on the first initial path, the second initial path, the first real-time position information and the second real-time position information includes: determining that the first robot and the second robot will collide when the first initial path and the second initial path have an intersection, and / or the distance between the first real-time position information and the second real-time position information is less than or equal to a preset distance threshold; and determining that the first robot and the second robot will not collide when the first initial path and the second initial path do not intersect and the distance between the first real-time position information and the second real-time position information is greater than the preset distance threshold.

[0010] Optionally, in the event that the first robot and the second robot are about to collide, at least the first initial path of the first robot is updated so that the first robot avoids the second robot and obtains the first target path of the first robot, including: constructing a virtual potential field, wherein the coordinate origin of the virtual potential field is a warehouse, and the virtual potential field includes gravity and repulsion, the gravity is the gravity field between the first robot and the warehouse, and the gravity is used to attract the first robot to move toward the warehouse, and the repulsion is the repulsion field between the first robot and the second robot, and the repulsion is used to repel the first robot and the second robot; calculating the total force value applied to the first robot at each position in the virtual potential field, wherein the total force value is the sum of the gravity and the repulsion; according to the total force value, adjusting the first initial path by a gradient descent method until the position of the first robot reaches the warehouse, and determining that the adjusted path is the first target path.

[0011] Optionally, after controlling the first robot to continue the transport operation along the first target path, the method further includes: obtaining the temperature of the goods transported by the first robot and the gas concentration of the goods; when the temperature is greater than a first preset temperature threshold and / or the gas concentration is greater than a preset concentration threshold, generating a first warning information, and sending the first warning information to a monitoring device.

[0012] Optionally, after controlling the first robot to continue to perform the handling operation along the first target path, the method also includes: acquiring an image of the goods being handled by the first robot and a sound of the goods; determining whether the goods being handled by the first robot have exploded based on the image and / or the sound; in the event that the goods being handled by the first robot have exploded, generating a second warning message, and sending the second warning message to a monitoring device; controlling the first robot to evacuate the handled goods from the warehouse; updating the second initial path of the second robot so that the second robot avoids the first robot and obtains the second target path of the second robot; and controlling the second robot to continue to perform the handling operation along the second target path.

[0013] According to another aspect of the present application, a multi-robot obstacle avoidance control device is provided, including: a first acquisition unit, used to acquire a first initial path of a first robot and a second initial path of a second robot; a second acquisition unit, used to acquire first real-time position information of the first robot and second real-time position information of the second robot when the first robot starts to perform a handling operation along the first initial path and the second robot starts to perform a handling operation along the second initial path; a first determination unit, used to determine whether the first robot and the second robot will collide based on the first initial path, the second initial path, the first real-time position information and the second real-time position information; a first update unit, used to update at least the first initial path of the first robot when the first robot and the second robot are about to collide, so that the first robot avoids the second robot and obtains the first target path of the first robot; and a first control unit, used to control the first robot to continue the handling operation along the first target path.

[0014] According to another aspect of the present application, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the steps of any one of the multi-robot obstacle avoidance control methods are implemented.

[0015] According to another aspect of the present application, a robot obstacle avoidance control system is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for executing any one of the multi-robot obstacle avoidance control methods described.

[0016] By applying the technical solution of the present application, when multiple robots are working in collaboration, if a collision between robots is predicted, the paths of the robots are adjusted in time to avoid the collision between the robots, thereby achieving dynamic obstacle avoidance for the collaborative work of multiple robots. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings constituting part of the present application are used to provide a further understanding of the present application. The exemplary embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0018] Figure 1 A hardware structure block diagram of a mobile terminal for executing a multi-robot obstacle avoidance control method provided in an embodiment of the present application is shown;

[0019] Figure 2A schematic flow chart of a multi-robot obstacle avoidance control method provided according to an embodiment of the present application is shown;

[0020] Figure 3 A structural block diagram of a multi-robot obstacle avoidance control device provided according to an embodiment of the present application is shown.

[0021] The above drawings include the following reference numerals:

[0022] 102, processor; 104, memory; 106, transmission device; 108, input and output devices. DETAILED DESCRIPTION

[0023] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0024] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0025] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0026] As introduced in the background technology, in the prior art, multiple transport robots are prone to collision with each other when working together. To solve the above problem, the embodiments of the present application provide a multi-robot obstacle avoidance control method, device, computer program product and robot obstacle avoidance control system.

[0027] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0028] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 FIG. 1 is a hardware structure block diagram of a mobile terminal of a multi-robot obstacle avoidance control method according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0029] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the display method of device information in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The transmission device 106 is used to receive or send data via a network. The above-mentioned specific examples of the network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0030] In this embodiment, a multi-robot obstacle avoidance control method running on a mobile terminal, a computer terminal or a similar computing device is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0031] Figure 2 FIG. 1 is a flow chart of a multi-robot obstacle avoidance control method according to an embodiment of the present application. Figure 2 As shown, the method comprises the following steps:

[0032] Step S201, obtaining a first initial path of the first robot and a second initial path of the second robot;

[0033] Specifically, in the intelligent handling robot system, once the task information is determined by the intelligent warehouse management platform, the system will generate respective initial paths according to the task requirements of each handling robot (eg, the first robot and the second robot) and the warehouse layout.

[0034] Specifically, the first initial path is to generate a shortest or optimal path from the current position to the target position (usually a specific location in the warehouse) under the condition of a given task (such as transporting specific explosives to a designated warehouse). This path is the route that the first robot will follow when it starts to perform the task.

[0035] Similarly, the second initial path is the path generated for the second robot from its current position to the target position for performing the task. This path is also planned for the second robot at the beginning of the task to ensure that it can complete the handling task efficiently and safely.

[0036] Suppose that in a large explosive warehouse, there are two intelligent handling robots that need to perform warehousing tasks at the same time. The first robot needs to carry a batch of detonators to area A of the warehouse, while the second robot needs to carry a batch of explosives to area B of the warehouse. The intelligent warehouse management platform first plans an initial path for the first robot based on the task information and the layout of the explosive warehouse. This path starts from the first robot's stop point, passes through the entrance of the warehouse, and follows the aisles between the shelves inside the warehouse to the designated location in area A. Similarly, another initial path is planned for the second robot, which will guide the second robot from its stop point, through the entrance of the warehouse, along another different aisle, to the designated location in area B.

[0037] Step S202, when the first robot starts to perform the transport operation along the first initial path and the second robot starts to perform the transport operation along the second initial path, obtaining first real-time position information of the first robot and second real-time position information of the second robot;

[0038] Specifically, when the first robot starts to carry out the handling operation along the first initial path, the real-time position tracking of the first robot will be started. This can be achieved through the cooperation of sensors installed on the robot (such as Bluetooth beacon receivers, laser radars or cameras, etc.) and positioning devices in the warehouse (such as Bluetooth beacons). The sensors will collect data regularly or continuously and send it to the intelligent warehouse management platform, which will update the real-time position information of the first robot based on this data.

[0039] Similarly, when the second robot starts to carry out the transport operation along the second initial path, the real-time position information of the second robot will also be collected and updated. This real-time position information will be used in the subsequent dynamic obstacle avoidance strategy to ensure that the robot can intelligently avoid obstacles during the transport process, including other robots that are working.

[0040] Step S203, determining whether the first robot and the second robot will collide based on the first initial path, the second initial path, the first real-time position information, and the second real-time position information;

[0041] Specifically, once the first robot and the second robot start to perform the handling tasks along their respective initial paths, the intelligent warehouse management platform will continue to receive the real-time location information of each robot. This location information includes the precise coordinates of the robot inside the warehouse, which can be obtained through Bluetooth beacons, lidar or other positioning technologies. The platform combines the real-time location information with the pre-planned first initial path and second initial path, analyzes their movement trajectories and directions, and evaluates the relative positions and movement trends between the robots.

[0042] If it is predicted based on the first real-time position information and the second real-time position information that the first robot and the second robot may meet at a certain point or area during future movement, and the distance at the time of meeting is less than a preset obstacle avoidance distance threshold, it will be determined that there is a risk of collision between the two.

[0043] Step S204, in the case where the first robot and the second robot are about to collide, at least updating the first initial path of the first robot so that the first robot avoids the second robot, thereby obtaining a first target path of the first robot;

[0044] Specifically, in an environment where multiple robots work together, the intelligent warehouse management platform continuously monitors and analyzes the real-time location information of all participating robots (e.g., the first robot and the second robot). If the platform determines through a prediction algorithm that the first robot and the second robot will collide if they continue along their current path, it will take action to avoid this situation. To avoid a collision, the robot path will be updated, giving priority to adjusting the path of the first robot and generating a first target path that allows it to avoid the second robot.

[0045] Specifically, the process of updating the path involves calculating new path planning information, which usually includes adjusting the robot's direction, speed, or a combination of the two. Based on the relationship between the real-time position information and the target position (the designated area of ​​the warehouse), as well as the relative distance between the robots and the obstacle avoidance potential field parameters, a new path will be planned to avoid potential collision areas.

[0046] Step S205 , controlling the first robot to continue the transport operation along the first target path.

[0047] Specifically, in a multi-robot collaborative handling operation, when a collision risk is detected between the first robot and the second robot, the intelligent warehouse management platform will adjust the path planning of the first robot according to the actual situation and the preset obstacle avoidance strategy. The newly generated first target path will avoid possible collision points to ensure that the first robot can continue the handling task safely. Once the first target path is determined, the updated path information will be sent to the first robot, instructing it to continue along this path.

[0048] Specifically, the intelligent handling robot system usually has a high degree of automation and autonomy, which means that the first robot can receive new path information, automatically adjust the direction and speed of travel, and continue the handling operation according to the first target path without human intervention.

[0049] Through this embodiment, when multiple robots are working in collaboration, if a collision between robots is predicted, the paths of the robots are adjusted in time to avoid the collision between the robots, thereby achieving dynamic obstacle avoidance for the collaborative work of multiple robots.

[0050] Specifically, when multiple handling robots currently work together, their control method is mainly to determine the position through the positioning device of each handling robot itself, determine the position of the truck in combination with machine vision, and then determine the warehouse number that needs to be operated according to the operation information. Then, the explosive warehouse position corresponding to the truck position and the warehouse number is used to generate path planning information according to the truck position and the explosive warehouse position. Then the handling robot is controlled according to the generated path planning information, and then the handling robot will realize the centralized handling of explosives according to this path planning information. However, such path planning information is obviously shared by multiple handling robots, which means that multiple handling robots may meet at some point in the path during the handling process. The current obstacle avoidance scheme may have a better avoidance effect for static obstacles, but for two handling robots in relative motion, a collision is likely to occur. If a collision of handling robots occurs, on the one hand, it may cause equipment damage, and on the other hand, the collision may generate sparks, which is a huge safety hazard for explosive warehouses. It can be seen that the current control scheme of intelligent handling robots for explosive warehouses needs to be improved.

[0051] Therefore, the solution of the present application can dynamically avoid obstacles among multiple transport robots based on the dynamic position of each transport robot on the basis of conventional obstacle avoidance.

[0052] In the specific implementation process, obtaining the first initial path of the first robot can be achieved through the following steps: obtaining task information, wherein the task information is information about transporting items to the warehouse; obtaining warehouse location information of the warehouse and initial location information of the first robot; generating the first initial path based on the warehouse location information and the initial location information of the first robot, wherein the first initial path is the optimal path for the first robot to transport the items to the warehouse.

[0053] In this solution, through this precise task information analysis and optimal path planning, the item handling task can be completed efficiently and safely in a complex warehouse environment, significantly improving the degree of automation and safety of explosives storage management.

[0054] Specifically, task information may be obtained, the task information including task category and explosive warehouse number information. According to the explosive warehouse number information, the operation warehouse location information is obtained, according to the task category, the number N of handling robots involved in handling is obtained, the initial location information of the N handling robots is obtained, and according to the initial location information of the N handling robots and the operation warehouse location information, the corresponding path planning information, i.e., the initial path, is generated.

[0055] Specifically, in the current application of intelligent handling robots, there is an existing system, namely, an intelligent warehouse management platform, which needs to uniformly manage the handling work of intelligent robots and the warehouse's outbound and inbound. When a truck carrying explosives arrives at the warehouse area, the platform determines the type of explosives carried on the truck and which corresponding warehouse should be stored according to the operation ticket. Since different types of explosives need to be stored in different warehouses in isolation from each other in terms of management, the intelligent warehouse management platform will determine which warehouse the goods should be stored in or which warehouse should be shipped out based on the goods information recorded in the operation ticket, that is, the type of goods, packaging volume and operator information after receiving the request for inbound or outbound. In this process, the task category generally includes at least outbound, inbound or outbound, and the explosive warehouse number corresponds to the warehouse of different types of explosives. Therefore, obtaining task information is the task information generated by the intelligent warehouse management platform after receiving the outbound or inbound request. In this step, after the intelligent handling robot obtains the warehouse number where the truck is about to stop, since the warehouse number can determine the unique location information, and the docking position of the intelligent handling robot is also a pre-set docking position. Therefore, according to the warehouse location determined by the warehouse number and the docking position of the intelligent handling robot, the preset path information can be successfully confirmed. This path only refers to the path information from the docking position to the truck docking at the transfer platform outside the warehouse. This step of the path is fixed and there is no obstacle avoidance.

[0056] The number of robots involved in the transportation is also determined by the number of goods to be transported in the task information. Based on efficiency factors, rules can be manually specified. When the number is less than a certain number a, one intelligent transportation robot is arranged, and when the number is greater than a but less than b, two intelligent transportation robots are arranged. And so on.

[0057] Specifically, when the intelligent warehouse management platform receives the task information of transporting items to the warehouse, the platform will parse the task information and extract key data, including the warehouse number information and the type and quantity of items to be transported. Next, the platform will obtain the precise location information of the warehouse, which usually includes the entrance coordinates and internal layout of the warehouse, as well as the specific location coordinates where the items need to be placed. At the same time, the platform will obtain the initial position information of the first robot involved in the transport, that is, the position of the robot when it receives the task instruction, which can be the robot's stop point or the end point of the previous task.

[0058] Specifically, after obtaining the above information, the system will use the path planning algorithm to generate the first initial path based on the warehouse location information and the robot's initial position information. This path is the route that the first robot needs to follow to complete the handling task. The path planning algorithm will consider factors such as warehouse layout, shelf distribution, channel width, size and weight of the items being handled, the robot's own speed and carrying capacity, and possible obstacles to generate the shortest or optimal path from the robot's initial position to the designated location in the warehouse. The definition of the optimal path may be based on a comprehensive consideration of multiple dimensions such as time, distance, energy consumption or risk.

[0059] For example, in a large explosives warehouse, the intelligent warehouse management platform receives a task to move a batch of detonators from the transfer platform outside the warehouse to storage in Area A inside the warehouse. The platform first parses the number of the warehouse in Area A from the task information, and then calls the warehouse layout database to obtain the entrance coordinates of the warehouse in Area A and the internal layout information, including the location of the shelves storing detonators. At the same time, the platform obtains the initial position information of the first robot currently available, assuming that it is docked somewhere outside the warehouse.

[0060] Next, the first initial path is generated. A path planning algorithm, such as the A* algorithm or the Dijkstra algorithm, is used to calculate the shortest path from the initial position of the first robot to the designated location of the warehouse in zone A, combined with the layout information of the warehouse, including aisles, shelf locations, and obstacle distribution. The algorithm also considers the robot's ability to carry detonators and safety requirements to avoid planning paths through narrow aisles or high-risk areas.

[0061] After determining the optimal path, the first initial path information is sent to the first robot. After receiving the path information, the robot will automatically start the handling program, follow the planned first initial path, start from the stop point, pass through the warehouse entrance, and follow the passage to the designated shelf position in Area A to complete the detonator handling task. During the entire handling process, the first robot will continue to collect and upload its own location information so that the system can monitor its movement trajectory in real time to ensure the safety and smooth progress of the handling task.

[0062] Specifically, the steps of obtaining the second initial path of the second robot are the same as the steps of obtaining the first initial path of the first robot, which will not be repeated here.

[0063] In the specific implementation process, obtaining the first real-time position information of the above-mentioned first robot can be achieved through the following steps: obtaining a positioning signal, wherein the above-mentioned positioning signal is a signal transmitted between the above-mentioned first robot and a positioning beacon, and the above-mentioned positioning beacon is located in a warehouse; according to the intensity of the above-mentioned positioning signal, determining the relative distance between the above-mentioned first robot and the above-mentioned positioning beacon; according to the above-mentioned relative distance, determining the above-mentioned first real-time position information of the above-mentioned first robot in the above-mentioned warehouse.

[0064] In this solution, positioning beacon signals can be used to achieve high-precision positioning of the robot in a warehouse environment, further improving the automation and safety of handling operations.

[0065] Specifically, the initial position information of N handling robots is actually obtained directly from the intelligent warehouse management platform. That is to say, after the task information is determined, the initial position and warehouse position of the handling robots involved in the handling are determined, and the corresponding path planning information is generated by the initial position information of the N handling robots and the position information of the operation warehouse. When further obtaining the real-time position information of the N handling robots, this solution sets corresponding Bluetooth positioning beacons at the entrances of multiple different explosive warehouses. Each Bluetooth positioning beacon has a unique device identifier, which corresponds to a different explosive warehouse. And each Bluetooth positioning beacon broadcasts iBeacon data packets to the surrounding area as a sending device, and each handling robot can receive iBeacon data packets as a trusted device. It can be understood that each corresponding Bluetooth positioning beacon actually constitutes a different positioning node. By evaluating the signal strength, the handling robot can determine its own location.

[0066] Specifically, the intelligent handling robot system usually sets up multiple positioning beacons at key locations inside the warehouse in advance. Each beacon has a unique identity and can continuously transmit positioning signals to the surrounding area. The positioning signal can be in the form of Bluetooth, Wi-Fi, RFID or other wireless signals. The relative distance between the robot and the beacon is estimated mainly based on the change in signal strength, thereby determining the robot's position in the warehouse.

[0067] The receiver on the robot will continuously monitor the surrounding positioning signals. Once it receives the signal transmitted by the positioning beacon, it will estimate the distance based on the signal strength. Generally, there is a certain inverse relationship between signal strength and distance, that is, the closer the distance, the stronger the signal strength, and the farther the distance, the weaker the signal strength. Based on the change in signal strength, the system will apply the pre-calibrated signal strength-distance relationship curve to calculate the relative distance between the robot and each positioning beacon.

[0068] By obtaining the relative distance information between the robot and multiple positioning beacons, the system can use positioning algorithms, such as triangulation or polygon positioning, to determine the real-time position coordinates of the robot in the warehouse. This position information is crucial for robot path planning, obstacle avoidance, and task execution.

[0069] For example, in an explosives warehouse, the intelligent warehouse management platform assigns the first robot the task of moving a batch of explosives to Area C. To ensure that the robot can accurately locate itself during the moving process, Bluetooth positioning beacons are placed at the entrance, exit, key channels and near the shelves inside the warehouse, and each beacon has a unique device ID.

[0070] When the first robot starts to perform the task, it will continue to receive iBeacon packets sent by these Bluetooth beacons. The Bluetooth receiver on the robot will estimate the relative distance between the robot and each beacon based on the received signal strength. For example, if the robot is close to the positioning beacon at the entrance of the warehouse, it will receive a strong signal, and the system can calculate the distance between the robot and the beacon based on this signal strength. It is about 2 meters.

[0071] By continuously collecting and analyzing the signal strength between the robot and multiple positioning beacons, the system can calculate the robot's precise position in the entire warehouse in real time. For example, if the robot receives signals from three positioning beacons, the system will use a triangulation algorithm to combine the strength of each signal and the position of the beacon to calculate the coordinates (X, Y) of the robot at a certain point in time in the warehouse. This forms the first real-time location information.

[0072] The real-time position information is combined with the robot's current task information and preset path planning to dynamically adjust the robot's motion trajectory. For example, if the robot approaches another robot that is working during a task, the robot's path will be adjusted based on the real-time position information to avoid collision. During the entire handling process, the first robot will ensure that it completes the handling task safely along the established path based on the real-time updated positioning information.

[0073] Specifically, the steps of acquiring the second real-time position information of the second robot are the same as the steps of acquiring the first real-time position information of the first robot, which will not be repeated here.

[0074] In a specific implementation process, determining whether the first robot and the second robot will collide can be achieved by the following steps based on the first initial path, the second initial path, the first real-time position information and the second real-time position information: when the first initial path and the second initial path have an intersection, and / or the distance between the first real-time position information and the second real-time position information is less than or equal to a preset distance threshold, determining that the first robot and the second robot will collide; when the first initial path and the second initial path do not have an intersection and the distance between the first real-time position information and the second real-time position information is greater than the preset distance threshold, determining that the first robot and the second robot will not collide.

[0075] In this solution, by implementing a monitoring and prediction mechanism for collision risks, it is possible to effectively prevent collision accidents in a multi-robot collaborative environment, further ensuring the safety and efficiency of handling tasks.

[0076] Specifically, in an intelligent handling robot system, when multiple robots perform tasks in a warehouse environment at the same time, collision avoidance is one of the key safety considerations. First, an initial path is generated for each robot (such as the first robot and the second robot) based on the task information and the warehouse layout. At the same time, the system continuously receives and updates the real-time location information of each robot.

[0077] If the initial path of the first robot and the initial path of the second robot intersect somewhere, that is, the two paths overlap at certain points or areas inside the warehouse, it is considered that there is a potential risk of collision. Even if the paths do not intersect, if the distance displayed in the real-time position information of the first robot and the second robot is less than or equal to the preset distance threshold (this is a safety distance, set according to the specific situation, such as 0.5 meters or 1 meter), it is also considered that there is a risk of collision.

[0078] On the contrary, if the initial path of the first robot and the initial path of the second robot do not intersect, and according to the real-time position information, the distance between the two robots is greater than the preset distance threshold, it will be determined that the two robots will not collide and can safely continue to perform their respective tasks.

[0079] For example, in a scenario of an explosives warehouse, the first robot and the second robot are assigned to carry different types of explosives to different areas of the warehouse. The first robot's initial path is from the warehouse entrance to area A, while the second robot's initial path is from another entrance to area B. The warehouse monitors the location information of the two robots in real time through Bluetooth positioning beacons and receivers on the robots.

[0080] During the task execution, the real-time position information of the first robot and the second robot is continuously monitored. Assume that at a certain moment, the first robot is moving from the entrance to area A, while the second robot is moving from a different entrance to area B. The paths of the two robots intersect in a passage inside the warehouse, and their real-time position information shows that the distance between the first robot and the second robot has been reduced to 0.5 meters, which is equal to or less than the preset safety distance threshold.

[0081] In this case, the risk of collision is immediately determined and the obstacle avoidance mechanism is activated. It may generate a new target path by adjusting the path of the first robot to make it take a detour to avoid the intersection with the second robot. At the same time, the system may also send a deceleration instruction to the second robot to increase the safe distance between the two.

[0082] On the contrary, if at another time point, the real-time position information of the first robot and the second robot is monitored, and it is found that the distance between them is 2 meters, which is much larger than the preset safety distance threshold, and their initial paths do not intersect (i.e., they go to area A and area B respectively), it will be determined that the two robots will not collide. In this case, the first robot and the second robot can continue to carry the explosives safely according to their respective initial paths until the task is completed.

[0083] In some embodiments, in the event that the first robot and the second robot collide, at least the first initial path of the first robot is updated so that the first robot avoids the second robot and obtains the first target path of the first robot, which can be specifically achieved through the following steps: constructing a virtual potential field, wherein the coordinate origin of the virtual potential field is a warehouse, the virtual potential field includes gravity and repulsion, the gravity is the gravity field of the first robot and the warehouse, and the gravity is used to attract the first robot to move toward the warehouse, the repulsion is the repulsion field between the first robot and the second robot, and the repulsion is used to repel the first robot and the second robot; calculating the total force value received by the first robot at each position in the virtual potential field, wherein the total force value is the sum of the gravity and the repulsion; adjusting the first initial path by the gradient descent method according to the total force value until the position of the first robot reaches the warehouse, and determining that the adjusted path is the first target path.

[0084] In this scheme, by constructing a virtual potential field and using gravity and repulsion to dynamically adjust the path, this scheme can effectively prevent collisions and further improve work efficiency in an environment where multiple robots work together.

[0085] Specifically, the operation is started according to the above-mentioned path planning information, the real-time position information of the N transport robots is obtained, and the real-time position information of the N transport robots is projected into a two-dimensional coordinate system, and the two-dimensional coordinate system takes the explosive warehouse as the coordinate origin; an artificial potential field (i.e., a virtual potential field) is constructed according to the two-dimensional coordinate system, and it is set that there is a repulsive force between the N transport robots in the artificial potential field, and there is an attractive force between each transport robot and the coordinate origin; according to the real-time position information of the N transport robots, the resultant force Ftotal received by the transport robot in the artificial potential field is calculated in real time, and according to the above-mentioned resultant force, the movement direction of each transport robot on its respective path planning is updated.

[0086] Specifically, when it is determined that a handling task requires multiple handling robots, multiple handling robots avoid collisions in the warehouse. Specifically, in this scheme, collision detection is performed by constructing an artificial potential field. In the artificial potential field method, two types of virtual potential fields need to be defined, one is the gravitational field and the other is the repulsive field. Since the handling robot has a certain destination, it can be tried that each handling robot receives the attraction of the destination point, and the attraction guides the handling robot to the destination. In order to avoid collisions between different handling robots, the repulsive field existing between multiple handling robots will generate repulsion between two handling robots whose distance values ​​reach a preset value. The repulsive field is also a virtual potential field. The repulsive force generated by the repulsive field will prevent the two handling robots from being too close. Therefore, after the scene modeling is completed, a coordinate system is constructed with the scene entrance and exit as the coordinate origin. The positioning device of the handling robot itself will obtain its real-time position, project the real-time position into the coordinate system, and construct an artificial potential field in the coordinate system, namely the gravitational field and the repulsive field. The formulas corresponding to the control algorithm are expressed as follows:

[0087] F 引力 =k a *d1,

[0088] Among them, F 引力 is the gravitational force vector of the gravitational field, k a is the gravitational coefficient, which is a manually specified constant that can adjust the speed of the transport robot moving toward the destination. The larger the value, the greater the gravitational force and the faster the transport robot's travel speed; d1 is the distance between the transport robot and the destination, which is calculated by the coordinate conversion of the robot's real-time position information and the destination's preset position information:

[0089] F 斥力 =k b / d2,

[0090] Among them, F 斥力 is the repulsive force vector of the repulsive field, k bis the repulsion coefficient, which is used to adjust the safe distance for obstacle avoidance between transport robots. The larger the value, the larger the safe distance generated by the repulsion. d2 is the obstacle avoidance distance between transport robots, that is, the radius of the repulsion field.

[0091] The obstacle avoidance distance is pre-set by the intelligent warehouse management platform. After multiple handling robots report their positions in real time, the management platform can determine whether they have entered the repulsive field range based on the real-time positions of the multiple handling robots. If it is determined that they have entered the repulsive field range, an obstacle avoidance instruction will be issued to the relevant handling robots. The obstacle avoidance instruction at least includes the vector of repulsion. At this time, the two handling robots that may collide will calculate the gravitational field potential energy and the repulsive field potential energy according to the vector value containing the magnitude and direction of gravity, and then calculate the total potential energy after the gravitational field potential energy and the repulsive field potential energy are superimposed, and then the total potential energy is calculated by gradient calculation to obtain the force received by the handling robot at each point. The purpose of the gradient calculation is to determine in which direction the robot is subjected to the least force, that is, the shortest path.

[0092] The gradient calculation of the minimum potential energy specifically adopts the gradient descent method, and its steps are basically as follows: initialize the position of the robot and calculate the potential energy field gradient at the current position; update the position of the robot according to the negative direction of the gradient; repeat the steps until the stopping condition is met (such as determining that the robot has left the radius range of the repulsive field based on the real-time position).

[0093] Specifically, the purpose of constructing an artificial potential field is to resolve possible collisions between multiple transport robots. It can be understood that each transport robot in a working state is regarded as a particle with the same charge, and the magnitude of the mutual repulsion between them is inversely proportional to the distance between them. Each transport robot and the explosive warehouse are regarded as particles with different charges and have gravitational forces. In this way, the minimum safe distance that should be maintained between each transport robot can be quantified in the potential field, so as to achieve the purpose of adjusting the movement direction in real time.

[0094] In the above method of this solution, the problem of two transport robots is discussed. Similarly, when there are multiple transport robots, the situation is relatively complicated, but the principle is similar. Specifically, the repulsive force on each transport robot i among the N transport robots can be expressed as F i , then the resultant force F total It can be obtained by summing the repulsive force of each robot, that is:

[0095]

[0096] For each robot i, its repulsive force F iThe calculation of is usually determined based on the positions of the surrounding obstacles and other robots. A common calculation method is to express the repulsion between robots based on the inverse relationship of the distance, that is:

[0097]

[0098] Among them, k is a constant, indicating the strength of repulsion; r i represents the position of handling robot i; represents the distance vector between handling robot i and robot j, that is, the direction vector from handling robot i to handling robot j; In this way, the direction of the repulsive force will point robot i away from other robots, thus achieving the effect of avoiding collision.

[0099] Specifically, the handling robot is connected to the intelligent warehouse management platform for communication and obtains task information from the intelligent warehouse management platform. The task information includes task category information such as warehousing in, out, and return, as well as the number information of the explosive warehouse corresponding to the operation to be performed.

[0100] Specifically, in the intelligent handling robot system, the warehouse is regarded as the coordinate origin of the virtual potential field, and the robot is subject to two forces in the potential field: gravity and repulsion. Gravity comes from the attraction between the robot and the warehouse, which prompts the robot to move along a predetermined path to the warehouse to complete the handling task; repulsion comes from between the robots, which is used to prevent multiple robots from colliding when performing tasks inside the warehouse.

[0101] The process of constructing a virtual potential field involves setting the warehouse as the coordinate origin of the potential field, and setting a gravitational field and a repulsive field for each robot. The strength of the gravitational field is inversely proportional to the distance between the robot and the warehouse, that is, the closer the robot is to the warehouse, the smaller the gravitational force; conversely, the greater the gravitational force. The strength of the repulsive field is inversely proportional to the distance between the robots, that is, the closer the two robots are, the greater the repulsive force; conversely, the smaller the repulsive force. This design ensures that the robot can be attracted to the warehouse when performing tasks, while avoiding getting too close to other robots.

[0102] The robot path is dynamically adjusted by calculating the total force value, i.e. the sum of the attraction and repulsion, at each position of the robot in the virtual potential field. The total force value reflects the potential field environment of the robot's current position, including the attraction from the warehouse and the repulsion from other robots. The system uses the gradient descent method to analyze the trend of the total force value change, adjust the robot's movement direction, and move it in the direction of decreasing force value, and finally find an optimal path to avoid collision and reach the warehouse.

[0103] For example, in a scenario of an explosive warehouse, the first robot and the second robot are responsible for carrying different types of explosives to different areas of the warehouse. When the two robots start to perform tasks, the system constructs a virtual potential field centered on the warehouse. The warehouse, as the origin of the coordinates, exerts gravitational force on the two robots, while there is repulsion between the robots.

[0104] Assume that at a certain moment, an intersection area appears in the path prediction of the first robot and the second robot, and at the same time, according to the real-time position information, the distance between the two robots is less than the preset safety distance threshold, and the system immediately detects the risk of collision. At this time, the system starts to calculate the total force value of the first robot at each position in the virtual potential field, which is the combination of gravity and repulsion.

[0105] At the current position, the total force value of the first robot points to a slightly offset direction, which indicates that continuing to move in a straight line at the current position will increase the risk of collision with the second robot. Using the gradient descent method, the trend of the total force value is analyzed to find the path direction with the minimum force value. After multiple iterations and calculations, a new path is finally determined. This path can not only avoid the second robot, but also maintain the efficiency of the original path as much as possible while ensuring safety.

[0106] The adjusted path is sent to the first robot as the first target path, instructing it to continue the handling operation along the new path. After receiving the updated path information, the first robot begins to move along the first target path, and finally arrives at the warehouse safely to complete the handling task. During the entire process, the real-time position information is continuously monitored, and the path is dynamically adjusted to ensure a safe distance between robots and avoid collisions, while maintaining the efficiency and safety of warehouse operations.

[0107] Specifically, the path of the second robot may also be updated so that the second robot avoids the first robot and obtains the second target path of the second robot. The specific steps are the same as those for updating the path of the first robot and are not repeated here.

[0108] In some embodiments, after controlling the first robot to continue the transport operation along the first target path, the method further includes the following steps: obtaining the temperature of the goods transported by the first robot and the gas concentration of the goods; when the temperature is greater than a first preset temperature threshold and / or the gas concentration is greater than a preset concentration threshold, generating a first warning information, and sending the first warning information to a monitoring device.

[0109] In this solution, when transporting high-risk goods, such as explosives or chemicals, the environmental status of the goods, especially the temperature and gas concentration, is monitored. When the safety threshold is exceeded, early warning information is generated in time, and relevant personnel are notified in time to take countermeasures to ensure safety during the transportation process.

[0110] Specifically, in the intelligent handling robot system, the handling robot is not only responsible for the physical handling task, but may also be equipped with temperature and humidity sensors and gas concentration detectors to monitor the environmental status of the goods being handled in real time. This is because, for explosives or certain chemicals, temperature and gas concentration (such as oxygen concentration, flammable gas concentration) are important factors affecting their stability. Too high or too low temperature, as well as inappropriate gas concentration, may cause safety problems such as explosions.

[0111] Continuously collect and analyze temperature data and gas concentration data, and compare them with the preset safety thresholds. If the monitored temperature data exceeds the first preset temperature threshold, or the gas concentration data exceeds the preset concentration threshold, the system will immediately generate the first warning information. These warning messages contain potential safety risk information, as well as the real-time status of the robot and cargo, such as specific temperature values ​​and gas concentration values.

[0112] The warning information is then sent to the monitoring device, which can be the control center of the intelligent warehouse management platform, the staff's mobile device or a dedicated security monitoring system. After receiving the warning information, the monitoring personnel can take immediate measures, such as adjusting the warehouse environment, suspending the robot handling operation or initiating emergency procedures to prevent safety accidents.

[0113] For example, in an explosives warehouse, the first robot is responsible for carrying a batch of temperature-sensitive explosives. A temperature sensor and a gas concentration detector are installed on the robot to monitor the temperature environment of the explosives and the concentration of the surrounding gas, especially the oxygen concentration, in real time.

[0114] When the first robot starts to carry the explosives, the system continuously monitors the temperature and gas concentration data. Assuming that at a certain point in time, due to the excessive temperature of a local area inside the warehouse (such as exceeding 35°C), exceeding the preset first temperature threshold (for example, 30°C), or the oxygen concentration around the explosives is abnormally high, exceeding the preset concentration threshold (such as oxygen concentration exceeding 21%), the system immediately detects a potential safety risk.

[0115] The first warning information is then generated, which includes the specific values ​​of temperature and gas concentration, as well as the possible threat to the stability of the explosives. The warning information is sent to the control center of the intelligent warehouse management platform and to the mobile devices of the staff responsible for warehouse safety supervision.

[0116] After receiving the warning information, the monitoring personnel will take immediate action. They may first suspend the handling operation of the first robot through remote control to avoid potential danger. At the same time, the staff will start the emergency procedure to check whether the temperature control system and ventilation system of the warehouse are operating normally, and make adjustments if necessary to restore normal safety conditions. After ensuring that the environmental conditions are stable, the system will allow the first robot to continue to complete the handling task.

[0117] In some embodiments, after controlling the first robot to continue the transporting operation along the first target path, the method further includes the following steps: acquiring images of the goods transported by the first robot and sounds of the goods; determining whether the goods transported by the first robot explode according to the images and / or sounds; in the event that the goods transported by the first robot explode, generating second warning information, and sending the second warning information to a monitoring device; controlling the first robot to evacuate the transported goods from the warehouse; updating the second initial path of the second robot so that the second robot avoids the first robot and obtains the second target path of the second robot; and controlling the second robot to continue the transporting operation along the second target path.

[0118] In this solution, when dangerous explosives are being transported, image and sound monitoring technology is used to detect whether the cargo has exploded. When a potential explosion risk is detected, a second warning message is generated and emergency response measures are initiated, including evacuating the threatened cargo, adjusting the paths of other robots, and maintaining the continuity of warehouse operations, thereby reducing potential accident risks and further improving the safety and reliability of warehouse operations.

[0119] Specifically, in the intelligent handling robot system, when the robot is carrying dangerous goods, such as explosives, it will be equipped with image sensors and sound sensors to monitor the status of the goods in real time. Image sensors can capture changes in the appearance of goods, such as damaged packaging, smoke, and other visual clues that may indicate an explosion; sound sensors can capture abnormal sounds, such as popping sounds, unusual noises, etc., which may be precursors to explosions.

[0120] Continuously analyze image and sound data, and use advanced image recognition and sound recognition algorithms to determine whether the cargo shows signs of explosion. If smoke, fire, or explosion in the sound is detected, a second warning message will be generated immediately, which will include the robot ID, cargo information, a description of the specific abnormal situation, and the possible explosion risk level.

[0121] The warning information is then sent to the monitoring device, which may include the control center of the intelligent warehouse management platform, the mobile device of the warehouse security manager, or a dedicated security monitoring system. After receiving the warning information, the monitoring personnel will take immediate measures according to the severity of the warning and the emergency procedures.

[0122] If it is determined that the cargo has an explosion risk, the first robot will be controlled to immediately stop the handling operation, start the emergency evacuation procedure, and quickly evacuate the cargo to a safe area. At the same time, in order to ensure the safety of other robots in the warehouse, the second initial path of the second robot will be updated to generate a second target path to avoid the evacuation route of the first robot and possible explosion areas. After receiving the updated path, the second robot will continue the handling operation according to the second target path to ensure the continuity and safety of the entire warehouse operation.

[0123] For example, in an explosives warehouse, the first robot is responsible for carrying a batch of detonators. The system installs a high-definition camera and a high-sensitivity microphone on the robot to monitor the appearance changes of the detonators and the sounds of the surrounding environment in real time. When the first robot starts to carry the detonators, the system continuously monitors the image and sound data.

[0124] Assume that at a certain point in time, the system finds through image monitoring that the detonator packaging is slightly damaged, and the sound monitoring captures a slight popping sound, which may indicate that the detonator is at risk of explosion. The system immediately generates a second warning message, which includes the detonator ID, a description of the damage, detailed information on the abnormal sound, and a possible explosion risk assessment.

[0125] The warning information is sent to the control center of the intelligent warehouse management platform and the equipment of the warehouse safety supervisor. After receiving the warning information, the monitoring personnel quickly start the emergency procedure. Through the system command, the first robot immediately stops the transportation and starts the emergency evacuation procedure to quickly evacuate the detonator to an isolation area far away from the warehouse.

[0126] At the same time, in order to ensure the safety of other robots in the warehouse (such as the second robot), the system updates the second initial path of the second robot and generates a new second target path, which will avoid the evacuation route of the first robot and the possible explosion area. The second robot receives the updated path information and starts to continue to move other goods according to the second target path, ensuring that the entire warehouse operation can remain safe and continuous under emergency response.

[0127] In summary, the solution of this application achieves high automation, flexibility and safety. The system's autonomous navigation and path planning technology enables the robot to automatically complete the handling task, reducing the need for human intervention and improving production efficiency. The in-and-out control system uses real-time data analysis and optimization to improve work efficiency. By setting up a Bluetooth beacon corresponding to the explosive warehouse, it has a more accurate positioning effect compared to traditional GPS positioning.

[0128] The embodiment of the present application also provides an obstacle avoidance control device for multiple robots. It should be noted that the obstacle avoidance control device for multiple robots in the embodiment of the present application can be used to execute the obstacle avoidance control method for multiple robots provided in the embodiment of the present application. The device is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0129] The following is an introduction to the multi-robot obstacle avoidance control device provided in an embodiment of the present application.

[0130] Figure 3 is a structural block diagram of a multi-robot obstacle avoidance control device according to an embodiment of the present application. Figure 3 As shown, the device comprises:

[0131] A first acquisition unit 10 is used to acquire a first initial path of the first robot and a second initial path of the second robot;

[0132] A second acquisition unit 20 is used to acquire first real-time position information of the first robot and second real-time position information of the second robot when the first robot starts to perform the transport operation along the first initial path and the second robot starts to perform the transport operation along the second initial path;

[0133] A first determining unit 30, configured to determine whether the first robot and the second robot will collide based on the first initial path, the second initial path, the first real-time position information, and the second real-time position information;

[0134] A first updating unit 40 is configured to update at least the first initial path of the first robot when the first robot and the second robot collide, so that the first robot avoids the second robot and obtains a first target path of the first robot;

[0135] The first control unit 50 is used to control the first robot to continue the transport operation along the first target path.

[0136] Through this embodiment, when multiple robots are working in collaboration, if a collision between robots is predicted, the paths of the robots are adjusted in time to avoid the collision between the robots, thereby achieving dynamic obstacle avoidance for the collaborative work of multiple robots.

[0137] During the specific implementation process, the first acquisition unit includes a first acquisition module, a second acquisition module and a generation module, the first acquisition module is used to acquire task information, wherein the task information is information about transporting items to the warehouse; the second acquisition module is used to acquire warehouse location information of the warehouse and initial position information of the first robot; the generation module is used to generate the first initial path according to the warehouse location information and the initial position information of the first robot, wherein the first initial path is the optimal path for the first robot to transport the items to the warehouse.

[0138] In this solution, through this precise task information analysis and optimal path planning, the item handling task can be completed efficiently and safely in a complex warehouse environment, significantly improving the degree of automation and safety of explosives storage management.

[0139] During the specific implementation process, the second acquisition unit includes a third acquisition module, a first determination module and a second determination module, the third acquisition module is used to acquire a positioning signal, wherein the positioning signal is a signal transmitted between the first robot and the positioning beacon, and the positioning beacon is located in the warehouse; the first determination module is used to determine the relative distance between the first robot and the positioning beacon according to the strength of the positioning signal; the second determination module is used to determine the first real-time position information of the first robot in the warehouse according to the relative distance.

[0140] In this solution, positioning beacon signals can be used to achieve high-precision positioning of the robot in a warehouse environment, further improving the automation and safety of handling operations.

[0141] During the specific implementation process, the first determination unit includes a third determination module and a fourth determination module. The third determination module is used to determine that the first robot and the second robot will collide when the first initial path and the second initial path have an intersection, and / or the distance between the first real-time position information and the second real-time position information is less than or equal to a preset distance threshold; the fourth determination module is used to determine that the first robot and the second robot will not collide when the first initial path and the second initial path do not have an intersection and the distance between the first real-time position information and the second real-time position information is greater than the preset distance threshold.

[0142] In this solution, by implementing a monitoring and prediction mechanism for collision risks, it is possible to effectively prevent collision accidents in a multi-robot collaborative environment, further ensuring the safety and efficiency of handling tasks.

[0143] In some embodiments, the first update unit includes a construction module, a calculation module and an adjustment module, the construction module is used to construct a virtual potential field, wherein the coordinate origin of the above-mentioned virtual potential field is the warehouse, the above-mentioned virtual potential field includes gravity and repulsion, the above-mentioned gravity is the gravity field between the above-mentioned first robot and the above-mentioned warehouse, the above-mentioned gravity is used to attract the above-mentioned first robot to move toward the above-mentioned warehouse, the above-mentioned repulsion is the repulsive field between the above-mentioned first robot and the above-mentioned second robot, and the above-mentioned repulsion is used to repel the above-mentioned first robot and the above-mentioned second robot; the calculation module is used to calculate the total force value exerted on the above-mentioned first robot at each position in the above-mentioned virtual potential field, wherein the above-mentioned total force value is the sum of the above-mentioned gravity and the above-mentioned repulsion; the adjustment module is used to adjust the above-mentioned first initial path by gradient descent method according to the above-mentioned total force value until the position of the above-mentioned first robot reaches the above-mentioned warehouse, and determine that the adjusted path is the above-mentioned first target path.

[0144] In this scheme, by constructing a virtual potential field and using gravity and repulsion to dynamically adjust the path, this scheme can effectively prevent collisions and further improve work efficiency in an environment where multiple robots work together.

[0145] In some embodiments, the above-mentioned device also includes a third acquisition unit and a first processing unit. The third acquisition unit is used to obtain the temperature of the goods transported by the above-mentioned first robot and the gas concentration of the above-mentioned goods after controlling the above-mentioned first robot to continue the transport operation along the above-mentioned first target path; the first processing unit is used to generate a first warning information when the above-mentioned temperature is greater than a first preset temperature threshold and / or the above-mentioned gas concentration is greater than a preset concentration threshold, and send the above-mentioned first warning information to the monitoring device.

[0146] In this solution, when transporting high-risk goods, such as explosives or chemicals, the environmental status of the goods, especially the temperature and gas concentration, is monitored. When the safety threshold is exceeded, early warning information is generated in time, and relevant personnel are notified in time to take countermeasures to ensure safety during the transportation process.

[0147] In some embodiments, the device further includes a fourth acquisition unit, a second determination unit, a second processing unit, a second control unit, a second updating unit and a third control unit. The fourth acquisition unit is used to acquire the image of the goods being transported by the first robot and the sound of the goods after controlling the first robot to continue the transport operation along the first target path; the second determination unit is used to determine whether the goods being transported by the first robot have exploded based on the image and / or the sound; the second processing unit is used to generate a second warning message in the event that the goods being transported by the first robot have exploded, and send the second warning message to the monitoring device; the second control unit is used to control the first robot to evacuate the transported goods from the warehouse; the second updating unit is used to update the second initial path of the second robot so that the second robot avoids the first robot and obtains the second target path of the second robot; the third control unit is used to control the second robot to continue the transport operation along the second target path.

[0148] In this solution, when dangerous explosives are being transported, image and sound monitoring technology is used to detect whether the cargo has exploded. When a potential explosion risk is detected, a second warning message is generated and emergency response measures are initiated, including evacuating the threatened cargo, adjusting the paths of other robots, and maintaining the continuity of warehouse operations, thereby reducing potential accident risks and further improving the safety and reliability of warehouse operations.

[0149] The obstacle avoidance control device for multiple robots includes a processor and a memory. The first acquisition unit, the second acquisition unit, the first determination unit, the first update unit and the first control unit are all stored in the memory as program units, and the processor executes the program units stored in the memory to implement corresponding functions. The modules are all located in the same processor; or, the modules are located in different processors in any combination.

[0150] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be provided, and the problem of multiple handling robots easily colliding with each other when working together in the prior art can be solved by adjusting kernel parameters.

[0151] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0152] An embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored program, wherein when the program is run, the device where the computer-readable storage medium is located is controlled to execute the obstacle avoidance control method for multiple robots.

[0153] An embodiment of the present invention provides a processor, which is used to run a program, wherein the obstacle avoidance control method of multiple robots is executed when the program is run.

[0154] An embodiment of the present invention provides a device, the device includes a processor, a memory, and a program stored in the memory and executable on the processor, and when the processor executes the program, at least the steps of the obstacle avoidance control method of multiple robots are implemented. The device in this article can be a server, a PC, a PAD, a mobile phone, etc.

[0155] A computer program product includes a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the obstacle avoidance control method for multiple robots in various embodiments of the present application are implemented.

[0156] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0157] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0158] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0159] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0160] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0161] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0162] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0163] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0164] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0165] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0166] 1) The multi-robot obstacle avoidance control method of the present application, when multiple robots are working in collaboration, if a collision between robots is predicted, the paths of the robots are adjusted in time to avoid collision between robots, thereby realizing dynamic obstacle avoidance for the collaborative work of multiple robots.

[0167] 2) The multi-robot obstacle avoidance control device of the present application, when the multiple robots are working in collaboration, if a collision between the robots is predicted, promptly adjusts the paths of the robots to avoid the collision between the robots, thereby realizing dynamic obstacle avoidance for the collaborative work of the multiple robots.

[0168] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A multi-robot obstacle avoidance control method, characterized in that: include: Acquire a first initial path of the first robot and a second initial path of the second robot; When the first robot starts to perform a transport operation along the first initial path and the second robot starts to perform a transport operation along the second initial path, acquiring first real-time position information of the first robot and second real-time position information of the second robot; determining whether the first robot and the second robot will collide according to the first initial path, the second initial path, the first real-time position information, and the second real-time position information; In the case where the first robot and the second robot are about to collide, at least updating the first initial path of the first robot so that the first robot avoids the second robot, thereby obtaining a first target path of the first robot; The first robot is controlled to continue the transport operation along the first target path.

2. The method according to claim 1, characterized in that Obtaining a first initial path of a first robot includes: Acquiring task information, wherein the task information is information on transporting items to a warehouse; Acquire warehouse location information of the warehouse and initial location information of the first robot; The first initial path is generated according to the warehouse position information and the initial position information of the first robot, wherein the first initial path is an optimal path for the first robot to transport the article to the warehouse.

3. The method according to claim 1, characterized in that Acquiring first real-time position information of the first robot, including: Acquiring a positioning signal, wherein the positioning signal is a signal transmitted between the first robot and a positioning beacon, and the positioning beacon is located in a warehouse; Determining the relative distance between the first robot and the positioning beacon according to the strength of the positioning signal; The first real-time position information of the first robot in the warehouse is determined according to the relative distance.

4. The method according to claim 1, characterized in that Determining whether the first robot and the second robot will collide according to the first initial path, the second initial path, the first real-time position information, and the second real-time position information includes: When the first initial path and the second initial path intersect, and / or the distance between the first real-time position information and the second real-time position information is less than or equal to a preset distance threshold, determining that the first robot and the second robot will collide; When the first initial path and the second initial path have no intersection and the distance between the first real-time position information and the second real-time position information is greater than the preset distance threshold, it is determined that the first robot and the second robot will not collide.

5. The method according to claim 1, characterized in that In the case where the first robot and the second robot are about to collide, at least updating the first initial path of the first robot so that the first robot avoids the second robot, and obtaining a first target path of the first robot, comprises: Constructing a virtual potential field, wherein the coordinate origin of the virtual potential field is the warehouse, and the virtual potential field includes attraction and repulsion, the attraction is the attraction field between the first robot and the warehouse, and the attraction is used to attract the first robot to move toward the warehouse, and the repulsion is the repulsion field between the first robot and the second robot, and the repulsion is used to repel the first robot and the second robot; Calculating a total force value applied to the first robot at each position in the virtual potential field, wherein the total force value is the sum of the attraction and the repulsion; According to the total force value, the first initial path is adjusted by a gradient descent method until the position of the first robot reaches the warehouse, and the adjusted path is determined to be the first target path.

6. The method according to any one of claims 1 to 5, characterized in that After controlling the first robot to continue the transport operation along the first target path, the method further includes: obtaining a temperature of a cargo carried by the first robot and a gas concentration of the cargo; When the temperature is greater than a first preset temperature threshold and / or the gas concentration is greater than a preset concentration threshold, a first warning message is generated and sent to a monitoring device.

7. The method according to any one of claims 1 to 5, characterized in that After controlling the first robot to continue the transport operation along the first target path, the method further includes: acquiring images of goods carried by the first robot and sounds of the goods; determining, according to the image and / or the sound, whether the cargo carried by the first robot explodes; In the event that the cargo carried by the first robot explodes, generating second warning information, and sending the second warning information to a monitoring device; Controlling the first robot to evacuate the transported goods from the warehouse; updating the second initial path of the second robot so that the second robot avoids the first robot, thereby obtaining a second target path of the second robot; The second robot is controlled to continue the transport operation along the second target path.

8. A multi-robot obstacle avoidance control device, characterized in that: include: A first acquisition unit, configured to acquire a first initial path of the first robot and a second initial path of the second robot; a second acquisition unit, configured to acquire first real-time position information of the first robot and second real-time position information of the second robot when the first robot starts to perform the transport operation along the first initial path and the second robot starts to perform the transport operation along the second initial path; a first determining unit, configured to determine whether the first robot and the second robot will collide according to the first initial path, the second initial path, the first real-time position information, and the second real-time position information; A first updating unit, configured to update at least the first initial path of the first robot when the first robot and the second robot are likely to collide, so that the first robot avoids the second robot and obtains a first target path of the first robot; The first control unit is used to control the first robot to continue the transport operation along the first target path.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the obstacle avoidance control method for multiple robots described in any one of claims 1 to 7 are implemented.

10. A robot obstacle avoidance control system, characterized in that: include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for executing the obstacle avoidance control method of a multi-robot according to any one of claims 1 to 7.

Images