Multi-self-moving device avoidance method and device, self-moving device, and storage medium

Abstract

Embodiments of the present application provide a multi-self-moving device avoidance method and device, a self-moving device and a storage medium. The method comprises: in response to an avoidance strategy generation instruction, obtaining position information and a task type corresponding to each of a plurality of self-moving devices in a preset congestion area; determining a game payoff value corresponding to each of the plurality of self-moving devices according to the position information and the task type corresponding to each of the plurality of self-moving devices; generating an avoidance strategy according to the game payoff value corresponding to each of the plurality of self-moving devices, the avoidance strategy indicating a target self-moving device that needs to perform an avoidance behavior in the preset congestion area; and sending the avoidance strategy to the target self-moving device to enable the target self-moving device to avoid other self-moving devices in the preset congestion area. Based on the method, path conflicts of multiple robots during operation can be avoided, and the passing efficiency of the robots can be improved.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a method, apparatus, self-moving device, and storage medium for obstacle avoidance by multiple self-moving devices. Background Technology

[0002] As the complexity of work environments and the difficulty of tasks increase, the application of multi-robot systems is expanding. When multiple robots are running in a scene, congestion can easily occur. Currently, robot scheduling algorithms in congested areas generally employ avoidance schemes. In practical applications, appropriate avoidance points are pre-set on a built map. When a robot encounters a path conflict during task execution, the lower-priority robot will move to the avoidance point to wait for the higher-priority robot to leave the conflict area before continuing its task.

[0003] However, in scenarios with multiple robots, setting avoidance points results in poor coordination and obstacle avoidance capabilities among the robots, leading to path conflicts and low passage efficiency. Summary of the Invention

[0004] This application provides a method, apparatus, self-moving device, and storage medium for avoiding collisions among multiple self-moving devices in a multi-robot scenario through multi-machine collaboration, thereby improving the robot's passage efficiency.

[0005] In a first aspect, embodiments of this application provide a method for avoiding collisions between multiple self-moving devices, the method comprising:

[0006] In response to the avoidance strategy generation command, the location information and task type of multiple self-moving devices within the preset congestion area are obtained;

[0007] Based on the location information of each of the multiple self-moving devices and the task type, the game payoff value corresponding to each of the multiple self-moving devices is determined. The game payoff value includes the distance payoff value determined based on the location information and the task priority payoff value determined based on the task type.

[0008] An avoidance strategy is generated based on the game payoff value corresponding to each of the plurality of self-moving devices, and the avoidance strategy indicates the target self-moving device that needs to perform avoidance behavior in the preset congestion area.

[0009] The avoidance strategy is sent to the target mobile device so that the target mobile device can avoid other mobile devices in the preset congestion area.

[0010] Secondly, embodiments of this application provide a multi-automobile device for obstacle avoidance, the device comprising:

[0011] The response module is used to respond to the avoidance strategy generation command and obtain the location information and task type of each of the multiple self-moving devices in the preset congestion area;

[0012] The determining module is used to determine the game payoff value corresponding to each of the plurality of self-moving devices based on the location information corresponding to each of the plurality of self-moving devices and the task type. The game payoff value includes a distance payoff value determined based on the location information and a task priority payoff value determined based on the task type.

[0013] The generation module is used to generate an avoidance strategy based on the game payoff value corresponding to each of the plurality of self-moving devices. The avoidance strategy indicates the target self-moving device that needs to perform avoidance behavior in the preset congestion area.

[0014] The sending module is used to send the avoidance strategy to the target self-moving device, so that the target self-moving device can avoid other self-moving devices in the preset congestion area.

[0015] Thirdly, embodiments of this application provide a self-moving device, including: a memory, a processor, and a communication interface; wherein, the memory stores executable code, and when the executable code is executed by the processor, the processor executes the multi-self-moving device avoidance method as described in the first aspect.

[0016] Fourthly, embodiments of this application provide a non-transitory machine-readable storage medium storing executable code, which, when executed by a processor of an electronic device, causes the processor to execute the multi-automobile device avoidance method as described in the first aspect.

[0017] This application provides a method for multiple autonomous mobile devices to avoid collisions. Based on this method, an avoidance strategy can be generated using the location information and task type of multiple autonomous mobile devices within a preset congestion area. This aims to avoid path conflicts among multiple robots in a multi-robot scenario, thereby improving robot mobility. In practical applications, after receiving the avoidance strategy generation instruction, the location information and task type of multiple autonomous mobile devices within the preset congestion area can be obtained. Based on these information, a game theory payoff value, including distance payoff and task priority payoff, is determined for each autonomous mobile device. Then, an avoidance strategy is generated based on the game theory payoff value, instructing the target autonomous mobile device to perform avoidance behavior within the preset congestion area. This avoidance strategy can then be sent to the target autonomous mobile device, enabling it to avoid other autonomous mobile devices within the preset congestion area.

[0018] In the solution provided in this application embodiment, by introducing multiple factors including the location information of the self-moving device and the task type, an avoidance strategy is generated for the target self-moving device that needs to perform avoidance behavior in a preset congestion area. This can avoid path conflicts between multiple robots during operation in scenarios with multiple robots and dynamic and complex environments, thereby improving the passage efficiency of robots. Attached Figure Description

[0019] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments of this application and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0020] Figure 1 A flowchart illustrating a multi-automobile device avoidance method provided for an exemplary embodiment of this application;

[0021] Figure 2 A schematic diagram of the target distance and safety distance provided for an exemplary embodiment of this application;

[0022] Figure 3 An application diagram illustrating a multi-automobile device avoidance method provided in an exemplary embodiment of this application;

[0023] Figure 4 A flowchart illustrating a strategy generation instruction generation method provided in an exemplary embodiment of this application;

[0024] Figure 5 A schematic diagram of the structure of a multi-automobile device avoidance device provided for an exemplary embodiment of this application;

[0025] Figure 6 A schematic diagram of the structure of a self-moving device provided as an exemplary embodiment of this application;

[0026] Figure 7 This is a schematic diagram of the structure of another self-moving device provided as an exemplary embodiment of this application. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0028] Currently, self-moving devices (such as intelligent service robots and automated warehouse handling robots) are used in various application scenarios. With increasing complexity of working environments and task difficulty, many application scenarios require the simultaneous use of multiple self-moving devices. This necessitates the ability to coordinate and cooperate between individual self-moving devices and groups of devices in dynamic environments. To address this, this application provides a method, apparatus, self-moving device, and storage medium for avoiding obstacles among multiple self-moving devices. In this application embodiment, based on the location information and task type of multiple self-moving devices within a preset congestion area, the distance gain value and task priority gain value of each self-moving device are determined. An avoidance strategy is generated, instructing the target self-moving device to perform avoidance behavior within the preset congestion area. This avoidance strategy enables the target self-moving device to avoid other self-moving devices within the preset congestion area. Therefore, in scenarios with multiple robots and dynamic, complex environments, path conflicts during operation can be avoided, thereby improving robot mobility.

[0029] The multi-autonomous-moving-device obstacle avoidance method provided in this application can be applied to autonomous-moving devices. In this application, the autonomous-moving device can be any mechanical device capable of highly autonomous spatial movement within its environment. Examples of autonomous-moving devices include, but are not limited to, intelligent purification robots, intelligent water purifiers, intelligent lawnmowers, intelligent inspection robots, intelligent disinfection robots, and intelligent handling robots. The explanation of "autonomous-moving device" herein applies to all embodiments of this application and will not be repeated in subsequent embodiments.

[0030] To enable the multi-automobile device avoidance method provided in this application embodiment to be applied to automobile devices, the automobile devices are equipped with LiDAR, odometer, depth camera, ultrasonic sensor, and infrared sensor. The automobile devices can acquire their own motion state, position, and other information based on these sensors, and share this information with other automobile devices, so that each automobile device can process its own and other automobile devices' motion state, position, and other information.

[0031] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0032] Figure 1 This is a flowchart illustrating a multi-automobile device obstacle avoidance method provided as an exemplary embodiment of this application. See also... Figure 1 The method specifically includes the following steps:

[0033] 101. In response to the avoidance strategy generation command, obtain the location information and task type of each of the multiple self-moving devices within the preset congestion area.

[0034] 102. Based on the location information and task type of each of the multiple self-moving devices, determine the game payoff value of each of the multiple self-moving devices. The game payoff value includes the distance payoff value determined based on the location information and the task priority payoff value determined based on the task type.

[0035] 103. Generate an avoidance strategy based on the game payoff values ​​of multiple self-moving devices. The avoidance strategy indicates the target self-moving device that needs to perform avoidance behavior in a preset congestion area.

[0036] 104. Send the avoidance strategy to the target mobile device so that the target mobile device can avoid other mobile devices in the preset congestion area.

[0037] The multi-automatic-moving-device obstacle avoidance method provided in this application can be applied to different types of automated-moving devices. As mentioned above, automated-moving devices can include automated warehouse handling robots, intelligent service robots, and so on. Taking an automated warehouse handling robot as an example, in practical application scenarios, there may be multiple automated warehouse handling robots working together in the same area. In such scenarios, coordination and cooperation of the movement paths among the automated warehouse handling robots are required to improve their passage efficiency.

[0038] The multi-automobile device avoidance method provided in this embodiment can be executed by any one of the multiple automobile devices. It should be noted that each automobile device can interact with other automobile devices through its own communication module. Specifically, the communication module may include a Bluetooth communication module, a Long Range Radio (LoRa) communication module, etc.

[0039] In this embodiment of the application, after obtaining the avoidance strategy generation instruction, it is necessary to first obtain the location information and task type of each of the multiple self-moving devices within the preset congestion area.

[0040] In this embodiment, the preset congestion area can refer to areas with low mobility of self-mobile devices or narrow areas. For example, the preset congestion area can include areas with many conflicting movement paths of multiple self-mobile devices, or it can include areas that allow at most two self-mobile devices to pass side by side. In practical applications, the preset congestion area can be custom-marked on a map of the self-mobile device's working scenario, or it can be automatically generated based on the movement path of the self-mobile device.

[0041] Location information of a self-moving device can include the coordinates of the self-moving device on a map. These coordinates can be obtained through sensors such as LiDAR and ultrasonic sensors installed on the self-moving device.

[0042] The task type of a self-operated mobile device can be determined based on the urgency and importance of the task. For example, if the task type is determined according to its importance, the task type of a self-operated mobile device can include urgent tasks, temporary tasks, routine tasks, and so on.

[0043] In one optional embodiment, the task type of the self-moving device can be set according to the application scenario of the self-moving device. For example, taking a warehouse automated handling robot as an example, the task type of each warehouse automated handling robot can be determined according to the type of goods it handles.

[0044] After obtaining the location information and task type of multiple automated devices within a preset congestion area, the game payoff value for each automated device can be determined. Specifically, the game payoff value includes a distance payoff value and a task priority payoff value. The distance payoff value can be determined based on the location information of the automated device, while the task priority payoff value can be determined based on the task type of the automated device.

[0045] In this embodiment, the distance gain value may include a target distance gain value and a safe distance gain value. Specifically, for any one of multiple self-moving devices, the target distance gain value can be determined based on the location information of any self-moving device and the location information of a preset target point within a preset congestion area. The safe distance gain value can be determined based on the location information of any self-moving device and the location information of other self-moving devices within the preset congestion area. It should be noted that, in this embodiment, the preset target point within the preset congestion area can be determined based on factors such as the shape of the preset congestion area; for example, the preset target point may include the center point within the preset congestion area.

[0046] In this embodiment, for the target distance benefit value, the target distance between the self-moving device and the preset target point can be determined first by using the location information of the self-moving device and the location information of the preset target point in the preset congestion area, and then the target distance benefit value of the self-moving device can be determined based on the target distance.

[0047] Specifically, assume the coordinates of the self-moving device are (x... i y i The preset target point coordinates are (x, y). t y t The target distance between the self-moving device and the preset target point can be calculated based on the following formula (1):

[0048]

[0049] Among them, D d Indicates the target distance.

[0050] The smaller the target distance between the self-mobile device and the preset target point, the closer the self-mobile device is to the preset target point. In other words, the smaller the target distance, the greater the competitive advantage of the self-mobile device in the game among multiple self-mobile devices. Therefore, the target distance payoff value can be determined by the reciprocal of the target distance, that is, the target distance payoff value can be calculated based on the following formula (2):

[0051]

[0052] Among them, M d D represents the target distance reward value. d Indicates the target distance.

[0053] In this embodiment, the safe distance benefit value can be determined by first using the location information of the self-moving device and the location information of other self-moving devices in a preset congestion area to determine the safe distance between the self-moving device and other self-moving devices, and then determining the safe distance benefit value of the self-moving device based on the safe distance.

[0054] Specifically, assuming the pre-defined congestion area includes a first self-moving device and a second self-moving device, with the coordinates of the first self-moving device being (x1, y1) and the coordinates of the second self-moving device being (x2, y2), the safe distance between the first self-moving device and the second self-moving device can be calculated based on the following formula (3):

[0055]

[0056] Among them, D S(1，2) This indicates the safe distance between the first self-moving device and the second self-moving device.

[0057] Based on the aforementioned safe distances, the security benefit value of the self-moving device can be determined. Specifically, the greater the safe distance between the self-moving device and other self-moving devices, the farther the distance between them, and in this case, the higher the security benefit value of the self-moving device.

[0058] In an optional embodiment, a preset safety distance can be set for each self-mobile device, and this preset safety distance can be used to determine whether the self-mobile device has a safety benefit value. For example, taking a preset safety distance of 5m for a certain self-mobile device as an example, if the safety distance between this self-mobile device and other self-mobile devices is greater than 5m, it indicates that the self-mobile device has a safety benefit value; if the safety distance between this self-mobile device and other self-mobile devices is less than 5m, it indicates that the distance between this self-mobile device and other self-mobile devices is too close, and in this case, the safety benefit value of this self-mobile device is zero. It should be noted that the preset safety distance for each self-mobile device can be the same or different, and the preset safety distance for each self-mobile device can be set individually according to actual needs.

[0059] Taking the first and second self-moving devices mentioned above as an example, let's assume that the preset safe distance between the first and second self-moving devices is D. z The security benefits of the first and second self-moving devices can be calculated based on the following formula (4):

[0060]

[0061] Where, m S(1，2) D represents the security benefit value between the first and second self-moving devices. S(1，2) This indicates the safe distance between the first self-moving device and the second self-moving device.

[0062] After calculating the safety benefit values ​​of the first and second automated mobile devices, the safety benefit values ​​can be determined as the safety distance benefit values ​​between the first and second automated mobile devices. In practical applications, multiple (more than two) automated mobile devices may be operating simultaneously within a pre-defined congested area. In this case, for a target automated mobile device among the multiple automated mobile devices, the average of the safety benefit values ​​of the target automated mobile device and other automated mobile devices can be used as the safety distance benefit value of the target automated mobile device.

[0063] To facilitate understanding, the following will be combined with... Figure 2 The target distance and safe distance provided in the embodiments of this application will be explained. For example... Figure 2 As shown, assume that the preset congestion area is a rectangular area that allows a maximum of two self-moving devices to pass side by side, and the preset target point is the center point A of the rectangular area. The rectangular area includes the first self-moving device and the second self-moving device.

[0064] For the first self-moving device, the target distance is the distance between the first self-moving device and the center point A; for the second self-moving device, the target distance is the distance between the second self-moving device and the center point A. For both the first and second self-moving devices, the safe distance is the distance between the first and second self-moving devices.

[0065] In this embodiment, for determining the task priority benefit value, for any self-mobile device among multiple self-mobile devices, a target task priority corresponding to the task type of any self-mobile device can be determined from a preset set of multiple task priorities, and then the task priority benefit value of any self-mobile device is determined based on the target task priority.

[0066] Specifically, each of the aforementioned task priorities can have a corresponding preset task priority benefit value. As mentioned above, after determining the target task priority corresponding to the task type of the mobile device, the preset task priority benefit value corresponding to the target task priority can be determined as the task priority benefit value of the mobile device.

[0067] For example, taking tasks categorized into urgent, temporary, and regular tasks, the task priorities for these tasks are, respectively, first priority, second priority, and third priority. This means that urgent tasks have a higher priority than temporary tasks, and temporary tasks have a higher priority than regular tasks. Based on this scenario, the preset task priority benefit value for the first priority task can be set to 0.5, for the second priority task priority to 0.3, and for the third priority task priority to 0.2.

[0068] In this embodiment, different task priorities correspond to different preset task priority benefit values. Optionally, the sum of the preset task priority benefit values ​​corresponding to each task priority is 1.

[0069] After obtaining the game payoff values, an avoidance strategy can be generated for the target mobile device that needs to perform avoidance behavior within a preset congestion area, based on the game payoff values ​​corresponding to each of the multiple mobile devices. Finally, the avoidance strategy can be sent to the target mobile device so that it can avoid other mobile devices within the preset congestion area.

[0070] In an optional embodiment, before generating the avoidance strategy, a corresponding weight value can be set for each game payoff value. Specifically, as described above, the game payoff values ​​include distance payoff values ​​and task priority payoff values; therefore, each of the distance payoff value and task priority payoff value has a preset weight value. It should be noted that the distance payoff value includes a target distance payoff value and a safe distance payoff value, and correspondingly, the target distance payoff value and the safe distance payoff value each have different preset weight values. It should be noted that in this embodiment, the preset weight values ​​corresponding to the target distance payoff value, the safe distance payoff value, and the task priority payoff value can be set according to the specific application scenario; this application does not limit the magnitude of the preset weight values ​​for the aforementioned game payoff values.

[0071] When generating an avoidance strategy, for a target self-mobile device among multiple self-mobile devices, the distance gain value and task priority gain value corresponding to the target self-mobile device can be weighted and summed according to a preset weight value to determine the total gain value of the target self-mobile device. Then, an avoidance strategy is generated based on the total gain value corresponding to each of the multiple self-mobile devices.

[0072] The total revenue can be calculated based on the following formula (5):

[0073] M = w1M d +w2M s +w3M t (5)

[0074] Where M represents the total revenue; M d M represents the target distance reward value; s M represents the benefit value of safe distance; t This represents the task priority reward value; w1, w2, and w3 represent the preset weight values, and w1 + w2 + w3 = 1.

[0075] After obtaining the total revenue value for each self-moving device, an avoidance strategy can be generated based on the magnitude of the total revenue value for each self-moving device. Specifically, self-moving devices with lower total revenue values ​​can avoid self-moving devices with higher total revenue values.

[0076] For example, consider a pre-defined congested area containing a first, second, and third automated mobile device. Assume the total reward value for the first automated mobile device is 20, the total reward value for the second automated mobile device is 10, and the total reward value for the third automated mobile device is 40. In this case, the generated avoidance strategy can instruct the second automated mobile device to avoid the first and third automated mobile devices, and the first automated mobile device to avoid the third automated mobile device.

[0077] As mentioned above, the following section uses a self-moving robot as an example of an automated warehouse handling robot, combined with... Figure 3 This example illustrates a method for avoiding collisions between multiple self-moving devices in this application scenario.

[0078] like Figure 3 As shown, assume that the preset congestion area includes mobile device A and mobile device B, and the preset target point is the center point C of the preset congestion area. Mobile device A and mobile device B can exchange information based on their own communication modules and through base stations.

[0079] First, after receiving the avoidance strategy generation instruction, the location information and task type of each of the self-moving device A and self-moving device B within the preset congestion area are obtained.

[0080] Then, based on the location information of self-mobile device A and self-mobile device B respectively, the target distance gain value and the safe distance gain value corresponding to self-mobile device A and self-mobile device B are determined. In this embodiment, it is assumed that the target distance between self-mobile device A and the center point C is 2m, the target distance between self-mobile device B and the center point C is 5m, the safe distance between self-mobile device A and self-mobile device B is 10m, and the preset safe distance between self-mobile device A and self-mobile device B is 5m.

[0081] Calculations show that the target distance gain value for mobile device A is 0.5, the target distance gain value for mobile device B is 0.2, and the safe distance gain value for both mobile devices A and B is 0.5.

[0082] Simultaneously, based on the task types corresponding to self-mobile device A and self-mobile device B, the task priority reward values ​​corresponding to self-mobile device A and self-mobile device B are determined. In this embodiment, it is assumed that the task priority reward value corresponding to the task type of self-mobile device A is 0.6, and the task priority reward value corresponding to the task type of self-mobile device B is 0.4.

[0083] Then, the total reward value for each of the self-mobile devices A and B can be determined based on their respective target distance reward value, safe distance reward value, and task priority reward value. In this embodiment, the weight values ​​for the target distance reward value, safe distance reward value, and task priority reward value are 0.5, 0.3, and 0.2, respectively.

[0084] Calculations show that the total revenue of mobile device A is 0.52, and the total revenue of mobile device B is 0.33.

[0085] Based on the total revenue values ​​of the aforementioned self-moving device A and self-moving device B, an avoidance strategy can be generated, which identifies self-moving device B as the target self-moving device, that is, instructs self-moving device B to avoid self-moving device A within the preset congestion area.

[0086] Finally, the avoidance strategy can be sent to self-mobile device B so that self-mobile device B can avoid self-mobile device A.

[0087] It should be noted that, in this embodiment, the self-moving device used to generate the avoidance strategy can be either self-moving device A or self-moving device B (self-moving device A is used as an example in this embodiment).

[0088] In an optional embodiment, if it is found that there are self-moving devices with the same total benefit value, the target game benefit value to be given priority can be determined according to the weight values ​​corresponding to the target distance benefit value, the safe distance benefit value, and the task priority benefit value. Then, the target self-moving device can be determined based on the target game benefit value of the self-moving devices with the same total benefit.

[0089] For example, let's assume the target distance gain, safe distance gain, and task priority gain have weights of 0.5, 0.3, and 0.2, respectively. If the total gain values ​​of mobile device A and mobile device B are the same, the target mobile device can be determined by comparing their target distance gain values. Assuming the target distance gain value for mobile device A is 0.5 and the target distance gain value for mobile device B is 0.2, then mobile device B can be identified as the target mobile device.

[0090] In one optional embodiment, different types of avoidance strategies can be generated for different application scenarios. Specifically, the avoidance strategy may include a target self-moving device that needs to perform avoidance behavior within a preset congestion area, or the avoidance strategy may include not only the target self-moving device, but also motion state adjustment information corresponding to the target self-moving device.

[0091] For example, consider automated mobile devices (such as automated warehouse robots) used for moving goods in a warehouse. In this application scenario, since the factors within the scenario are relatively simple and the changes in these factors are minimal, to reduce the computational power consumption of the automated mobile devices, a server that establishes communication connections with multiple automated mobile devices can determine the target automated mobile device that needs to perform avoidance behavior and the corresponding motion state adjustment information of the target automated mobile device.

[0092] Specifically, firstly, based on the total revenue value corresponding to each of the multiple self-mobile devices, the target self-mobile device that needs to perform avoidance behavior is determined among the multiple self-mobile devices. Then, based on the motion state corresponding to the target self-mobile device and the other self-mobile devices among the multiple self-mobile devices, the motion state adjustment information corresponding to the target self-mobile device is determined.

[0093] In this embodiment, the motion state may include information such as the movement speed and angle of the mobile device. Before generating an avoidance strategy, the server can also obtain information such as the movement speed and angle of the target mobile device and other mobile devices among the multiple mobile devices to calculate the movement routes of the target mobile device and the other mobile devices. Then, based on the above movement routes, the location where the target mobile device and other mobile devices collide is determined. Based on this location, the motion state adjustment information corresponding to the target mobile device can be determined. By using this motion state adjustment information, the movement speed and angle of the target mobile device can be adjusted to achieve avoidance of other mobile devices by the target mobile device.

[0094] Alternatively, consider self-moving devices (such as intelligent service robots) providing services in complex settings like hospitals and restaurants. In these scenarios, due to their complexity and the numerous changes in various factors, to ensure real-time obstacle avoidance by the target self-moving device, it can adjust its own motion based on the status information of other self-moving devices to achieve obstacle avoidance.

[0095] Specifically, firstly, based on the total revenue value corresponding to each of the multiple self-moving devices, the target self-moving device that needs to perform avoidance behavior is determined. Then, an avoidance strategy carrying the identification information of the other self-moving devices is sent to the target self-moving device, so that the target self-moving device adjusts its motion state according to the acquired state information of the other self-moving devices. Here, "other self-moving devices" refers to the self-moving devices other than the target self-moving device among the multiple self-moving devices.

[0096] In this embodiment, each mobile device can interact with other mobile devices based on a communication module. Specifically, the target mobile device can obtain information such as the motion status of other mobile devices through the communication module. This communication module may include a Bluetooth communication module, a Long Range Radio (LoRa) communication module, or similar devices.

[0097] Figure 4 A flowchart of a strategy generation instruction generation method provided for an exemplary embodiment of this application is shown below. Figure 4As shown, the method specifically includes:

[0098] 401. In response to any self-moving device entering a preset congestion area, determine the number of self-moving devices in the preset congestion area.

[0099] 402. If the number of self-moving devices in the preset congestion area reaches the set threshold, an avoidance strategy generation instruction will be generated.

[0100] In this embodiment, by acquiring the location information of each mobile device in real time, it can be determined whether the mobile device has entered a preset congestion area. When a mobile device enters a preset congestion area, the number of mobile devices in the preset congestion area can be obtained. Different preset congestion areas can be set with different thresholds for the number of mobile devices. When the number of mobile devices in a preset congestion area reaches the set threshold, an avoidance strategy generation instruction is generated.

[0101] For example, taking a pre-defined congestion area as one where only two mobile devices are allowed to pass side-by-side, an avoidance strategy needs to be generated when there are two mobile devices in this area. Therefore, the threshold for the number of mobile devices in this pre-defined congestion area can be set to two.

[0102] It should be noted that the execution subject of each step in the method provided in the above embodiments can be the same self-moving device, or the method can be executed by different self-moving devices. For example, the execution subject of steps 101 to 103 can be self-moving device A; or the execution subject of steps 101 and 102 can be self-moving device A, and the execution subject of step 103 can be self-moving device B; and so on.

[0103] Furthermore, some processes described in the above embodiments and accompanying drawings include multiple operations appearing in a specific order. However, it should be clearly understood that these operations may not be executed in the order they appear herein, or they may be executed in parallel. The operation numbers, such as 101, 102, etc., are merely used to distinguish different operations and do not represent any execution order. Additionally, these processes may include more or fewer operations, and these operations may be executed sequentially or in parallel. It should be noted that the descriptions such as "first" and "second" in this document are used to distinguish different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit "first" and "second" to different types.

[0104] The following will describe in detail one or more embodiments of the multi-automobile obstacle avoidance device of this application. Those skilled in the art will understand that these devices can all be configured using commercially available hardware components through the steps taught in this solution.

[0105] Figure 5A schematic diagram of the structure of a multi-automobile device obstacle avoidance device provided for an exemplary embodiment of this application is shown below. Figure 5 As shown, the device includes: a response module 501, a determination module 502, a generation module 503, and a sending module 504.

[0106] The response module 501 is used to respond to the avoidance strategy generation command and obtain the location information and task type of each of the multiple self-moving devices in the preset congestion area.

[0107] The determining module 502 is used to determine the game payoff value corresponding to each of the multiple self-moving devices based on their respective location information and task type. The game payoff value includes the distance payoff value determined based on the location information and the task priority payoff value determined based on the task type.

[0108] The generation module 503 is used to generate an avoidance strategy based on the game payoff values ​​of multiple self-moving devices. The avoidance strategy indicates the target self-moving device that needs to perform avoidance behavior in a preset congestion area.

[0109] The sending module 504 is used to send the avoidance strategy to the target self-moving device so that the target self-moving device can avoid other self-moving devices in the preset congestion area.

[0110] Optionally, the determining module 502 is specifically used to determine, for any one of the multiple self-moving devices, a target task priority corresponding to the task type of any one of the multiple self-moving devices from a set of preset task priorities, each of the multiple task priorities having a preset task priority benefit value; and to determine the preset task priority benefit value corresponding to the target task priority as the task priority benefit value of any one of the self-moving devices.

[0111] Optionally, the distance gain value includes a target distance gain value and a safe distance gain value. Accordingly, the determining module 502 is specifically used to determine, for any one of the multiple self-moving devices, the target distance gain value corresponding to any one of the self-moving devices based on the location information of any one of the self-moving devices and the location information of a preset target point within a preset congestion area; and to determine the safe distance gain value corresponding to any one of the self-moving devices based on the location information of any one of the self-moving devices and the location information of other self-moving devices within the preset congestion area.

[0112] Optionally, the distance gain value and the task priority gain value each have a preset weight value. Accordingly, the generation module 503 is specifically used to perform weighted summation of the distance gain value and the task priority gain value corresponding to the target self-mobile device among multiple self-mobile devices, according to the preset weight value, to determine the total gain value of the target self-mobile device; and to generate an avoidance strategy based on the total gain value corresponding to each of the multiple self-mobile devices.

[0113] Optionally, the generation module 503 is specifically used to determine the target self-mobile device among the multiple self-mobile devices that needs to perform avoidance behavior based on the total revenue value corresponding to each of the multiple self-mobile devices; and to determine the motion state adjustment information corresponding to the target self-mobile device based on the motion state corresponding to the target self-mobile device and the other self-mobile devices among the multiple self-mobile devices. Accordingly, the sending module 504 is specifically used to send the avoidance strategy carrying the motion state adjustment information corresponding to the target self-mobile device to the target self-mobile device.

[0114] Optionally, the generation module 503 is specifically used to determine the target self-mobile device among the multiple self-mobile devices that needs to perform avoidance behavior based on the total revenue value corresponding to each of the multiple self-mobile devices. Correspondingly, the sending module 504 is specifically used to send the avoidance strategy carrying the identification information corresponding to each of the other self-mobile devices to the target self-mobile device, so that the target self-mobile device adjusts its motion state according to the obtained state information of the other self-mobile devices, where the other self-mobile devices refer to the self-mobile devices other than the target self-mobile device among the multiple self-mobile devices.

[0115] Optionally, the response module 501 is further configured to determine the number of self-moving devices within the preset congestion area in response to any self-moving device entering the preset congestion area. Correspondingly, the generation module 503 is further configured to generate an avoidance strategy generation instruction if the number of self-moving devices within the preset congestion area reaches a set threshold.

[0116] In one possible design, the above Figure 5 The structure of the multi-self-moving device shown can be implemented as a single self-moving device. For example... Figure 6 As shown, the self-moving device may include: a processor 61, a memory 62, and a communication interface 63. The memory 62 stores executable code, which, when executed by the processor 61, enables the processor 61 to at least implement the multi-self-moving device avoidance method provided in the foregoing embodiments.

[0117] In addition, embodiments of this application provide a non-transitory machine-readable storage medium storing executable code, which, when executed by a processor of an electronic device, enables the processor to at least implement the multi-automobile device avoidance method provided in the foregoing embodiments.

[0118] The device embodiments described above are merely illustrative. The network elements described as separate components may or may not be physically separate. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0119] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of a necessary general-purpose hardware platform, or by a combination of hardware and software. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a computer product. This application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0120] Figure 7 A schematic diagram of the structure of another self-moving device provided as an exemplary embodiment of this application. For example... Figure 7 As shown, the self-moving device includes: a device body 70, on which a memory 71 and a processor 72 are disposed.

[0121] The memory 71 is primarily used to store computer programs, which can be executed by the processor 72, causing the processor 72 to control the self-moving device to perform corresponding tasks. In addition to storing computer programs, the memory 71 can also be configured to store various other data to support operations on the self-moving device. Examples of this data include instructions for any application or method used to operate on the self-moving device, map data of the environment / scene in which the self-moving device is located, operating modes, operating parameters, etc.

[0122] The memory 71 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0123] In this embodiment, the implementation of processor 72 is not limited; it can be, for example, but not limited to, a CPU, GPU, or MCU. Processor 72 can be considered a control system for the self-moving device, capable of executing computer programs stored in memory 71 to control the self-moving device to perform corresponding functions, actions, or tasks. It is worth noting that, depending on the implementation of the self-moving device and the context in which it operates, the required functions, actions, or tasks will differ; correspondingly, the computer programs stored in memory 71 will also differ, and processor 72 can control the self-moving device to perform different functions and complete different actions or tasks by executing different computer programs.

[0124] The processor 72, coupled to the memory 71, is used to execute the computer program in the memory 71 to: in response to an avoidance strategy generation instruction, acquire the location information and task type of each of multiple self-moving devices within a preset congestion area; determine the game payoff value of each of the multiple self-moving devices based on the location information and task type, the game payoff value including a distance payoff value determined based on the location information and a task priority payoff value determined based on the task type; generate an avoidance strategy based on the game payoff value of each of the multiple self-moving devices, the avoidance strategy indicating the target self-moving device that needs to perform avoidance behavior within the preset congestion area; and send the avoidance strategy to the target self-moving device so that the target self-moving device avoids other self-moving devices within the preset congestion area.

[0125] Further optionally, when the processor 72 determines the game payoff value for each of the multiple self-moving devices based on their respective location information and task type, it is specifically used for:

[0126] For any one of multiple self-moving devices, determine the target task priority corresponding to the task type of any one self-moving device from a set of preset task priorities. Each of the multiple task priorities has a preset task priority benefit value. The preset task priority benefit value corresponding to the target task priority is determined as the task priority benefit value of any one self-moving device.

[0127] Further optionally, the distance payoff value includes a target distance payoff value and a safe distance payoff value. When the processor 72 determines the game payoff value for each of the multiple self-moving devices based on their respective location information and task type, it is specifically used for:

[0128] For any one of multiple self-moving devices, the target distance benefit value corresponding to any self-moving device is determined based on the location information of any self-moving device and the location information of a preset target point in a preset congestion area; the safe distance benefit value corresponding to any self-moving device is determined based on the location information of any self-moving device and the location information of other self-moving devices in the preset congestion area.

[0129] Optionally, the distance payoff value and the task priority payoff value each have a preset weight value. When the processor 72 generates an avoidance strategy based on the game payoff values ​​corresponding to the multiple self-moving devices, it is specifically used for:

[0130] For a target self-mobile device among multiple self-mobile devices, the distance gain value and task priority gain value corresponding to the target self-mobile device are weighted and summed according to preset weight values ​​to determine the total gain value of the target self-mobile device; an avoidance strategy is generated based on the total gain value corresponding to each of the multiple self-mobile devices.

[0131] Further optionally, when the processor 72 generates an avoidance strategy based on the total revenue value corresponding to each of the multiple self-moving devices, it is specifically used for:

[0132] Based on the total revenue value of each of the multiple self-moving devices, the target self-moving device that needs to perform avoidance behavior is determined among the multiple self-moving devices; based on the motion state of the target self-moving device and the other self-moving devices among the multiple self-moving devices, the motion state adjustment information of the target self-moving device is determined.

[0133] Accordingly, when processor 72 sends the avoidance strategy to the target self-moving device, it is specifically used for:

[0134] The avoidance strategy, which carries motion state adjustment information corresponding to the target mobile device, is sent to the target mobile device.

[0135] Further optionally, when the processor 72 generates an avoidance strategy based on the total revenue value corresponding to each of the multiple self-moving devices, it is specifically used for:

[0136] Based on the total revenue value corresponding to each of the multiple self-moving devices, the target self-moving device that needs to perform avoidance behavior is determined among the multiple self-moving devices.

[0137] Accordingly, when the target moves automatically, the processor 72 sends the avoidance strategy, specifically for:

[0138] The avoidance strategy, which carries the identification information of each of the other self-moving devices, is sent to the target self-moving device so that the target self-moving device can adjust its motion state according to the state information of the other self-moving devices. The other self-moving devices refer to the self-moving devices other than the target self-moving device among the multiple self-moving devices.

[0139] Further optionally, the processor 72 is also configured to, in response to any self-moving device entering a preset congestion area, determine the number of self-moving devices in the preset congestion area; if the number of self-moving devices in the preset congestion area reaches a set threshold, generate an avoidance strategy generation instruction.

[0140] In some alternative embodiments, the self-moving device may also include some basic components, such as communication component 75, power supply component 76, etc. In this embodiment, these components are only shown as a partial example and do not mean that the self-moving device only includes these components. Depending on different application requirements, the self-moving device may also include other components, depending on the product form of the self-moving device.

[0141] The aforementioned communication components are configured to facilitate wired or wireless communication between the device containing the communication components and other devices. The device containing the communication components can access wireless networks based on communication standards, such as Wi-Fi, 2G or 3G, 4G, 5G, or combinations thereof. In one exemplary embodiment, the communication components receive broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communication components may further include a Near Field Communication (NFC) module, Radio Frequency Identification (RFID) technology, Infrared Data Association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, etc.

[0142] The aforementioned power supply components provide power to various components within the device in which they reside. These power supply components may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power to the device in which they reside.

[0143] Accordingly, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed, can implement the steps that can be executed by the self-moving device in the above method embodiments.

[0144] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A multi-self-moving device avoidance method, characterized by, The method comprises: in response to the avoidance strategy generation instruction, obtaining position information and task types corresponding to each of a plurality of self-moving devices in a preset congestion area; determining a game payoff value corresponding to each of the plurality of self-moving devices according to the position information and the task types, wherein the game payoff value comprises a distance payoff value determined according to the position information and a task priority payoff value determined according to the task types, the distance payoff value comprises a target distance payoff value and a safety distance payoff value, the target distance payoff value is determined based on the position information of any one of the plurality of self-moving devices and the position information of a preset target point in the preset congestion area, and the safety distance payoff value is determined based on the position information of the any one of the plurality of self-moving devices and the position information corresponding to each of other self-moving devices in the preset congestion area; generating an avoidance strategy according to the game payoff value corresponding to each of the plurality of self-moving devices, wherein the avoidance strategy indicates a target self-moving device that needs to perform an avoidance behavior in the preset congestion area; sending the avoidance strategy to the target self-moving device, so that the target self-moving device avoids other self-moving devices in the preset congestion area.

2. The method of claim 1, wherein, The method further comprises: for any one of the plurality of self-moving devices, determining a target task priority corresponding to the task type of the any one of the plurality of self-moving devices in a plurality of preset task priorities, wherein each of the plurality of task priorities corresponds to a preset task priority payoff value; determining the preset task priority payoff value corresponding to the target task priority as the task priority payoff value of the any one of the plurality of self-moving devices.

3. The method according to claim 1 or 2, characterized in that, The distance payoff value and the task priority payoff value each correspond to a preset weight value. The method further comprises: for a target self-moving device of the plurality of self-moving devices, performing weighted summation processing on the distance payoff value and the task priority payoff value corresponding to the target self-moving device according to the preset weight value, to determine a total payoff value of the target self-moving device; generating the avoidance strategy according to the total payoff value corresponding to each of the plurality of self-moving devices.

4. The method of claim 3, wherein, The method further comprises: determining a target self-moving device that needs to perform an avoidance behavior in the plurality of self-moving devices according to the total payoff value corresponding to each of the plurality of self-moving devices; determining motion state adjustment information corresponding to the target self-moving device according to the motion state of the target self-moving device and the motion state of each of other self-moving devices in the plurality of self-moving devices; The method further comprises: sending the avoidance strategy carrying the motion state adjustment information corresponding to the target self-moving device to the target self-moving device.

5. The method of claim 3, wherein, The generating the avoidance strategy according to the total benefit values corresponding to the plurality of self-moving devices respectively comprises: determining target self-moving devices in the plurality of self-moving devices that need to perform avoidance behaviors according to the total benefit values corresponding to the plurality of self-moving devices respectively; The sending the avoidance strategy to the target self-moving device comprises: sending the avoidance strategy carrying the identification information of the other self-moving devices respectively to the target self-moving device, so that the target self-moving device adjusts the motion state of the target self-moving device according to the state information of the other self-moving devices, the other self-moving devices being self-moving devices in the plurality of self-moving devices except the target self-moving device.

6. The method of claim 1, wherein, The method further comprises: in response to any self-moving device entering the preset congestion area, determining the number of self-moving devices in the preset congestion area; if the number of self-moving devices in the preset congestion area reaches a set threshold, generating the avoidance strategy generation instruction.

7. A multi-self-moving device evading apparatus characterized by comprising: The device comprises: a response module configured to, in response to the avoidance strategy generation instruction, acquire position information and task types corresponding to a plurality of self-moving devices in a preset congestion area respectively; a determination module configured to determine game benefit values corresponding to the plurality of self-moving devices respectively according to the position information and the task types corresponding to the plurality of self-moving devices respectively, the game benefit values comprising distance benefit values determined according to the position information and task priority benefit values determined according to the task types, the distance benefit values comprising target distance benefit values and safety distance benefit values, the target distance benefit values being determined based on the position information of any self-moving device in the plurality of self-moving devices and the position information of a preset target point in the preset congestion area, and the safety distance benefit values being determined based on the position information of the any self-moving device and the position information of the other self-moving devices in the preset congestion area respectively; a generation module configured to generate an avoidance strategy according to the game benefit values corresponding to the plurality of self-moving devices respectively, the avoidance strategy indicating target self-moving devices that need to perform avoidance behaviors in the preset congestion area; a sending module configured to send the avoidance strategy to the target self-moving devices, so that the target self-moving devices avoid the other self-moving devices in the preset congestion area.

8. A self-moving device, characterized in that comprises: a memory, a processor, and a communication interface; wherein the memory stores executable code, and when the executable code is executed by the processor, the processor executes the multi-self-moving device avoidance method according to any one of claims 1 to 6.

9. A non-transitory machine-readable storage medium, comprising: The non-transitory machine-readable storage medium stores executable code, and when the executable code is executed by the processor of the electronic device, the processor executes the multi-self-moving device avoidance method according to any one of claims 1 to 6.

Images