Vehicle obstacle avoidance control method and device and storage medium

Abstract

The invention discloses a vehicle obstacle avoidance control method and device and a storage medium, the vehicle obstacle avoidance control method is applied to a carrying trolley comprising a visual module, and the method comprises the steps that vehicle speed information and course information are acquired, and obstacle distance information is acquired through the visual module; determining a fuzzy input set according to the vehicle speed information, the obstacle distance information and the course information; determining a target fuzzy control instruction according to the fuzzy input set and a preset fuzzy rule base; inputting the target fuzzy control instruction, the vehicle speed information, the obstacle distance information and the course information into a pre-training conversion control model to obtain a target accurate control instruction; and controlling the vehicle to avoid obstacles according to the target accurate control instruction. The target fuzzy control instruction can be determined to determine the target accurate control instruction, and the carrying trolley is controlled through the target accurate control instruction, so that the autonomous navigation and automatic obstacle avoidance capabilities of self-learning and self-adaptive control of the carrying trolley are improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a vehicle obstacle avoidance control method, device and storage medium. Background Art

[0002] Smart delivery vehicles play an increasingly important role in modern logistics and distribution services. They significantly improve delivery efficiency, reduce labor costs, and improve service quality through automated operations. However, although these smart devices have shown great potential, there is still room for improvement in autonomous navigation, automatic obstacle avoidance and other functions. In terms of autonomous navigation, although the relevant technology can enable the vehicle to travel along the preset path, its ability to adapt to complex and changing environments needs to be strengthened. Automatic obstacle avoidance technology is crucial to ensuring safety. Although existing sensor technology can detect obstacles within a certain range, the ability to control the delivery vehicle to automatically avoid obstacles needs to be improved. Summary of the invention

[0003] The following is a summary of the subject matter described in detail herein. This summary is not intended to limit the scope of the claims.

[0004] The embodiments of the present application provide a vehicle obstacle avoidance control method, device and storage medium, which can improve the autonomous navigation and obstacle avoidance capabilities of the vehicle system.

[0005] In a first aspect, an embodiment of the present application provides a vehicle obstacle avoidance control method, which is applied to a transport vehicle, wherein the transport vehicle includes a vision module, and the method includes: Acquire vehicle speed information, obstacle distance information, and heading information, wherein the obstacle distance information is acquired through a visual module, the obstacle distance information indicates the precise distance between the vehicle and the obstacle, and the heading information indicates the precise information of the deviation between the vehicle and the target direction; Determining a fuzzy input set according to the vehicle speed information, the obstacle distance information, and the heading information; Determining a target fuzzy control instruction according to the fuzzy input set and a preset fuzzy rule base; Inputting the target fuzzy control instruction, the vehicle speed information, the obstacle distance information and the heading information into a pre-trained conversion control model to obtain a target precise control instruction; The vehicle is controlled to avoid obstacles according to the target precise control instruction.

[0006] According to the vehicle obstacle avoidance control method provided by some embodiments of the present application, the preset fuzzy rule base includes obstacle avoidance rules and target approach rules; wherein the obstacle avoidance rules are rules that instruct the vehicle to avoid obstacles; and the target approach rules are rules that instruct the vehicle to control its heading.

[0007] According to the vehicle obstacle avoidance control method provided by some embodiments of the present application, the fuzzy input set includes: fuzzy vehicle speed information, fuzzy distance information and fuzzy angle information, and determining the target fuzzy control instruction according to the fuzzy input set and a preset fuzzy rule base includes: Determining an obstacle avoidance fuzzy control instruction according to the fuzzy vehicle speed information, the fuzzy distance information and the obstacle avoidance rule; Determining a target trend fuzzy control instruction according to the fuzzy angle information and the target trend rule; The target fuzzy control instruction is determined according to the obstacle avoidance fuzzy control instruction and the target approach fuzzy control instruction.

[0008] According to the vehicle obstacle avoidance control method provided by some embodiments of the present application, before determining the target fuzzy control instruction according to the fuzzy input set and the preset fuzzy rule base, the method further includes: A target location and target work information are obtained, and the preset fuzzy rule base is adjusted according to the target location and the target work information.

[0009] According to the vehicle obstacle avoidance control method provided by some embodiments of the present application, the pre-trained conversion control model is trained by the following steps: Acquire a fuzzy data training set, wherein the fuzzy data training set includes a plurality of training fuzzy control instructions and training speed information, training distance information, and training heading information corresponding to the training fuzzy control instructions; Constructing an initial conversion control model, inputting the fuzzy data training set into the initial conversion control model, and obtaining a training control instruction; Determine the loss function according to the training control instruction, and judge whether the loss function is less than a preset loss threshold. If so, use the current initial conversion control model as a pre-trained conversion control model; otherwise, adjust the initial conversion control model according to the loss function, and continue to train the initial conversion control model based on the fuzzy data training set.

[0010] According to the vehicle obstacle avoidance control method provided by some embodiments of the present application, the adjusting the initial conversion control model according to the loss function includes: Back-propagating the loss function in the initial conversion control model to determine an update gradient; The initial conversion control model is updated according to the update gradient.

[0011] According to the vehicle obstacle avoidance control method provided in some embodiments of the present application, the method further includes: Get vehicle power information; When the vehicle power information indicates that the power is low, the vehicle is controlled to search for a charging station.

[0012] In a second aspect, an embodiment of the present application provides a vehicle obstacle avoidance control device, the device comprising: An information acquisition module, used to acquire vehicle speed information, obstacle distance information, and heading information, wherein the obstacle distance information is acquired through a visual module, the obstacle distance information indicates the precise distance between the vehicle and the obstacle, and the heading information indicates the precise information of the deviation between the vehicle and the target direction; A set determination module, used to determine a fuzzy input set according to the vehicle speed information, the obstacle distance information and the angle information; A fuzzy instruction determination module, used for determining a target fuzzy control instruction according to the fuzzy input set and a preset fuzzy rule base; A precise instruction determination module, used for inputting the target fuzzy control instruction, the vehicle speed information, the obstacle distance information and the heading information into a pre-trained conversion control model to obtain a target precise control instruction; A control module is used to control the vehicle to avoid obstacles according to the target precise control instruction.

[0013] In a third aspect, an embodiment of the present application provides an electronic device, including: at least one processor; at least one memory for storing at least one program; When at least one of the programs is executed by at least one of the processors, the method described in the first aspect of the embodiment of the present application is implemented.

[0014] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program executable by a processor. When the processor-executable computer program is executed by the processor, it is used to implement the method described in the first aspect of the embodiment of the present application.

[0015] The embodiments of the present application include at least the following beneficial effects: In the embodiment of the present application, the vehicle obstacle avoidance control method provided is applied to a transport vehicle including a visual module, by obtaining vehicle speed information and heading information and obstacle distance information through the visual module, the obstacle distance information indicates the precise distance of the vehicle from the obstacle, and the heading information indicates the precise information of the deviation between the vehicle and the target direction; according to the vehicle speed information, obstacle distance information and heading information, a fuzzy input set is determined; according to the fuzzy input set and the preset fuzzy rule base, a target fuzzy control instruction is determined; the target fuzzy control instruction, vehicle speed information, obstacle distance information and heading information are input into a pre-trained conversion control model to obtain a target precise control instruction; according to the target precise control instruction, the vehicle is controlled to avoid obstacles. The target fuzzy control instruction can be determined through a fuzzy algorithm, the target fuzzy control instruction is used to determine the target precise control instruction, and the transport vehicle is controlled through the target precise control instruction, so as to improve the autonomous navigation and automatic obstacle avoidance capabilities of the transport vehicle's self-learning and adaptive control.

[0016] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or understood by practicing the present application. The purpose and other advantages of the present application can be realized and obtained through the structures particularly pointed out in the description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings are used to provide further understanding of the technical solution of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the technical solution of the present application and do not constitute a limitation on the technical solution of the present application.

[0018] Figure 1 A schematic diagram of the steps of a vehicle obstacle avoidance control method provided in an embodiment of the present application; Figure 2 A schematic diagram of the steps of a target fuzzy control instruction provided in an embodiment of the present application; Figure 3 A schematic diagram of the training steps of a pre-trained conversion control model provided in an embodiment of the present application; Figure 4 A schematic diagram of the structure of a vehicle obstacle avoidance control device provided in an embodiment of the present application; Figure 5 A schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] The present application is further described below in conjunction with the accompanying drawings and specific embodiments. The described embodiments should not be regarded as limiting the present application, and all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0020] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0022] Before further describing the embodiments of the present application in detail, the nouns and terms involved in the embodiments of the present application are explained. The nouns and terms involved in the embodiments of the present application are subject to the following interpretations.

[0023] Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines so that machines have the functions of perception, reasoning and decision-making. Artificial intelligence technology is a comprehensive discipline that covers a wide range of fields, including both hardware-level technology and software-level technology. The basic technologies of artificial intelligence generally include sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, pre-trained model technology, operation / interaction system, mechatronics, etc. Among them, the pre-trained model is also called the large model or basic model. After fine-tuning, it can be widely used in downstream tasks in various major directions of artificial intelligence. Artificial intelligence software technology mainly includes computer vision technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0024] AI intelligent obstacle avoidance is to enable robots or intelligent vehicles to autonomously identify and avoid obstacles through artificial intelligence technology, ensuring their safe and efficient operation in dynamic and complex environments. This technology integrates a variety of advanced perception algorithms, machine learning models, and real-time decision-making mechanisms, providing a solid foundation for unmanned operation. The AI ​​intelligent obstacle avoidance system first relies on high-quality perception capabilities to obtain information about the surrounding environment, which usually involves the use of various types of sensors, such as LiDAR, cameras, ultrasonic sensors, etc., which can capture different forms of data, including distance information, visual images, and sound reflections. Once a potential obstacle is perceived, the next step is how to respond correctly. This requires the obstacle avoidance system to have fast and effective path planning capabilities. Based on the collected data, the system needs to build an accurate environmental model to understand and predict the location and movement trends of possible obstacles. In practical applications, AI intelligent obstacle avoidance has been widely used in autonomous vehicles, drones, service robots and other fields.

[0025] At present, smart delivery vehicles play an increasingly important role in modern logistics and distribution services. They have significantly improved distribution efficiency, reduced labor costs, and improved service quality through automated operations. However, although these smart devices have shown great potential, there is still room for improvement in functions such as autonomous navigation and automatic obstacle avoidance. In terms of autonomous navigation, although the relevant technology can enable the vehicle to travel along the preset path, its ability to adapt to complex and changing environments needs to be strengthened. Automatic obstacle avoidance technology is crucial to ensuring safety. Although existing sensor technology can detect obstacles within a certain range, the ability to control the delivery vehicle to automatically avoid obstacles needs to be improved.

[0026] Based on this, the embodiments of the present application provide a vehicle obstacle avoidance control method, device and storage medium, which can improve the autonomous navigation and obstacle avoidance capabilities of the vehicle system.

[0027] Please refer to Figure 1 , is a schematic diagram of the steps of a vehicle obstacle avoidance control method provided in an embodiment of the present application, such as Figure 1 As shown, in the embodiment of the present application, the steps of the vehicle obstacle avoidance control method may include but are not limited to steps S110 to S150: Step S110, obtaining vehicle speed information, obstacle distance information and heading information, wherein the obstacle distance information is obtained through a visual module, the obstacle distance information indicates the precise distance between the vehicle and the obstacle, and the heading information indicates the precise information of the deviation between the vehicle and the target direction.

[0028] It should be noted that in the embodiment of the present application, the vehicle speed information, obstacle distance information and heading information in step S110 are all accurate and specific information. For example, in one embodiment of the present application, the transport vehicle includes a visual module. When the transport vehicle travels at a speed of 5 m / s in a direction 100 meters away from the destination in a straight line and coinciding with the target heading, the visual module finds the obstacle ahead and determines that the obstacle distance information is 20 meters. Then the vehicle speed information obtained at this time is 5 m / s, the obstacle distance information is 20 meters, and the heading information is consistent with the target heading; in another embodiment of the present application, the transport vehicle travels at a speed of 10 m / s in a direction 150 meters away from the destination in a straight line and 20° away from the target heading. The visual module finds the obstacle ahead and determines that the obstacle distance information is 50 meters. Then the vehicle speed information obtained at this time is 5 m / s, the obstacle distance information is 20 meters, and the heading information is 20° away from the target heading. The vehicle speed information, obstacle distance information and heading information are all accurate and specific information.

[0029] It can be understood that in the embodiment of the present application, by providing a visual module, the transport vehicle can identify objects on the road and determine whether they are obstacles that need to be avoided.

[0030] Exemplarily, in the embodiment of the present application, a multimodal fusion solution can be used to implement the visual module to measure the distance of obstacles. The visual module includes a camera unit, a radar unit and an algorithm unit. The camera unit can use a binocular camera or a depth camera, and the radar unit can use a laser radar or a sonic radar. The camera unit is used to obtain images, and the obtained images are input to the algorithm unit for image recognition to determine whether there are obstacles. The radar unit can directly obtain the distance to the obstacle to achieve the technical effect of ranging. In the embodiment of the present application, the obstacle can be an object that blocks the road or an object that may cause bumps.

[0031] Through step S110, the embodiment of the present application can obtain the vehicle speed information, obstacle distance information and heading information of the transport vehicle during driving, perform subsequent command information determination, and provide basic data for generating commands for controlling the vehicle.

[0032] Step S120: Determine a fuzzy input set according to the vehicle speed information, obstacle distance information and heading information.

[0033] It should be noted that in the embodiment of the present application, the vehicle speed information, obstacle distance information and heading information are all specific and accurate information. In the embodiment of the present application, this information needs to be converted into fuzzy information for subsequent fuzzy instruction determination.

[0034] In the embodiment of the present application, the fuzzy input set includes: fuzzy vehicle speed information, fuzzy distance information and fuzzy angle information; wherein the fuzzy vehicle speed information is correspondingly defined as "slow", "medium" and "fast", the fuzzy distance information is correspondingly defined as "near", "medium" and "far", and the fuzzy angle information is correspondingly defined as "large deviation", "no deviation" and "small deviation". After obtaining the vehicle speed information, obstacle distance information and heading information, the membership of the fuzzy vehicle speed information corresponding to the vehicle speed is determined according to the vehicle speed information to determine the fuzzy vehicle speed information corresponding to the vehicle speed information; the membership of the fuzzy distance information corresponding to the vehicle distance obstacle is determined according to the obstacle distance information to determine the fuzzy distance information corresponding to the obstacle distance information; the membership of the fuzzy angle information corresponding to the vehicle heading is determined according to the heading information to determine the fuzzy angle information corresponding to the heading information.

[0035] It should be noted that the membership degree defines how the acquired information is mapped to a membership value between 0 and 1, indicating the degree to which the information belongs to a fuzzy set. The membership degree can be determined by fuzzy statistics or example methods, and this application does not impose excessive restrictions on the method of determining the membership degree.

[0036] After the fuzzy input set is determined in step S120 , the fuzzy control instruction can be determined, and step S130 is executed.

[0037] Step S130: Determine the target fuzzy control instruction according to the fuzzy input set and the preset fuzzy rule base.

[0038] It should be noted that in the embodiment of the present application, the preset fuzzy rule library includes obstacle avoidance rules and target approach rules; among which, the obstacle avoidance rules are rules that instruct the vehicle to avoid obstacles; and the target approach rules are rules that instruct the vehicle to control its heading.

[0039] For example, in one embodiment of the present application, the obstacle avoidance rules may include but are not limited to the rules shown in the following table:

[0040] Target trend rules may include but are not limited to the rules shown in the following table:

[0041] The preset fuzzy rule base is determined according to the actual situation, and this application does not make too many restrictions on this.

[0042] It should be noted that, in the embodiment of the present application, before executing step S130 and determining the fuzzy input set according to the vehicle speed information, the obstacle distance information and the angle information, the vehicle obstacle avoidance control method further includes: Obtain target location and target work information, and adjust the preset fuzzy rule base according to the target location and target work information.

[0043] By obtaining the target location and target work information, the preset fuzzy rule base can be further adjusted to achieve better vehicle control.

[0044] For example, in one embodiment of the present application, when the transport vehicle is used for food transportation, the target location is the food delivery point. At this time, the preset fuzzy rule library needs to be adjusted so that the transport vehicle can travel as smoothly as possible to avoid spillage of the transported food. At this time, the corresponding preset fuzzy rule library can be adjusted as follows:

[0045] It should be noted that in the embodiment of the present application, the preset fuzzy rule library can also be set in combination with obstacles. As mentioned above, obstacles can be objects that block the road or objects that may cause bumps. When the transport vehicle performs tasks, facing different tasks, the adjusted preset fuzzy rule library can select the corresponding preset fuzzy rule library based on the identified obstacles to determine the target fuzzy control instructions. For example, the task does not need to keep the road flat, that is, when the obstacle is identified as an object that may cause bumps, the corresponding preset fuzzy rule library may not include instructions for turning to avoid the obstacle.

[0046] In the embodiment of the present application, after the fuzzy input set including the fuzzy vehicle speed information, the fuzzy distance information and the fuzzy angle information is determined, reasoning is performed through the determined fuzzy input set and the preset fuzzy rule base to obtain the target fuzzy control instruction.

[0047] Please refer to Figure 2 , is a schematic diagram of the steps of a target fuzzy control instruction provided in an embodiment of the present application, such as Figure 2 As shown, in the embodiment of the present application, the target fuzzy control instruction is determined according to the fuzzy input set and the preset fuzzy rule base, which may include but is not limited to steps S210 to S230: Step S210: Determine an obstacle avoidance fuzzy control instruction according to the fuzzy vehicle speed information, the fuzzy distance information and the obstacle avoidance rule.

[0048] For example, in one embodiment of the present application, the fuzzy vehicle speed information and the fuzzy distance information are used to infer the obstacle avoidance rules, and the corresponding obstacle avoidance fuzzy control instructions are inferred by the minimum-maximum synthesis method. The generated obstacle avoidance fuzzy control instructions are used to control the transport vehicle to avoid obstacles.

[0049] Step S220, determining a target trend fuzzy control instruction according to the fuzzy angle information and the target trend rule; For example, in one embodiment of the present application, the fuzzy angle information and the target direction rule are used for reasoning, and the corresponding direction fuzzy control instruction is inferred by the minimum-maximum synthesis method. The direction fuzzy control instruction is used to instruct the transport vehicle to adjust the heading to avoid the transport vehicle from deviating too much from the target heading due to obstacle avoidance.

[0050] Step S230: Determine a target fuzzy control instruction according to the obstacle avoidance fuzzy control instruction and the target approach fuzzy control instruction.

[0051] After the obstacle avoidance fuzzy control instruction is determined through step S210 and the target tendency fuzzy control instruction is determined through step S220, the two fuzzy instructions need to be further integrated. In order to ensure that the final output can comprehensively reflect the requirements of all input instructions and be presented in a clear and executable form, the obstacle avoidance fuzzy control instruction and the target tendency fuzzy control instruction are integrated.

[0052] Exemplarily, in one embodiment of the present application, the obstacle avoidance fuzzy control instruction and the target approach fuzzy control instruction are integrated by setting corresponding coefficients, and the two fuzzy instructions are integrated by setting the coefficients for controlling steering in the obstacle avoidance fuzzy control instruction and the coefficients for controlling steering in the target approach fuzzy control instruction at different distances to obtain the target fuzzy control instruction.

[0053] After the target fuzzy control instruction is obtained, the target fuzzy control instruction can be defuzzified to control the transport vehicle. In the present application, defuzzification is performed in step S140, which is achieved by pre-training the conversion control model.

[0054] Step S140: input the target fuzzy control instruction, vehicle speed information, obstacle distance information and heading information into the pre-trained conversion control model to obtain the target precise control instruction.

[0055] It should be noted that in the embodiment of the present application, the target fuzzy control instruction is defuzzified through a pre-trained conversion control model to determine the target precise control instruction based on the target fuzzy control instruction, vehicle speed information, obstacle distance information and heading information.

[0056] Please refer to Figure 3 , is a schematic diagram of the training steps of a pre-trained conversion control model provided in an embodiment of the present application, such as Figure 3 As shown, the present application is an embodiment, and the pre-trained conversion control model is trained through steps S310 to S330 to obtain: Step S310: Acquire a fuzzy data training set, where the fuzzy data training set includes a plurality of training fuzzy control instructions and training speed information, training distance information, and training heading information corresponding to the training fuzzy control instructions.

[0057] It can be understood that in an embodiment of the present application, after the fuzzy data training set is obtained in step S310, the data can be preprocessed, and the training fuzzy control instructions in the fuzzy data training set and the training speed information, training distance information and training heading information corresponding to the training fuzzy control instructions can be cleaned.

[0058] Step S320: construct an initial conversion control model, input the fuzzy data training set into the initial conversion control model, and obtain training control instructions.

[0059] Through the constructed initial conversion control model, the fuzzy data training set is input into the initial conversion control model to obtain training control instructions for controlling the transport vehicle under the training fuzzy control instructions and the training speed information, training distance information and training heading information corresponding to the training fuzzy control instructions. The training control instructions correspond to the training fuzzy control instructions, and the obtained training control instructions are used to determine the loss function to adjust the initial conversion control model.

[0060] Step S330, determine the loss function according to the training control instruction, and judge whether the loss function is less than the preset loss threshold. If so, use the current initial conversion control model as the pre-trained conversion control model; otherwise, adjust the initial conversion control model according to the loss function, and continue to train the initial conversion control model based on the fuzzy data training set.

[0061] In an embodiment of the present application, the model is updated through a back-propagation algorithm. Therefore, when the initial conversion control model obtains the training control instruction, a loss function is determined to adjust the initial conversion control model, and the loss function is compared with a preset loss threshold to determine whether the initial conversion control model meets the requirements.

[0062] In one embodiment of the present application, adjusting the initial conversion control model according to the loss function may include but is not limited to steps S410 to S420: Step S410, back-propagating the loss function in the initial conversion control model to determine the update gradient; Step S420: Update the initial conversion control model according to the update gradient.

[0063] Exemplarily, in one embodiment of the present application, the mean square error is used to calculate the loss function, and the determined loss function is back-propagated in the initial control model. It can be understood that the initial conversion control model includes multiple layers, and the loss function is back-propagated from the output layer to determine the update gradient in each layer; after the update gradient is determined, the initial conversion control model is updated according to the update gradient.

[0064] Through step S410 to step S420, the initial conversion control model can be updated. When the updated initial conversion control model can obtain a loss function that is less than the preset loss function value, the current initial conversion control model is used as a pre-trained conversion control model.

[0065] By pre-training the conversion control model, it is possible to obtain a target precise control instruction based on the target fuzzy control instruction, vehicle speed information, obstacle distance information and heading information, which is used to control the vehicle to avoid obstacles, that is, execute step S150.

[0066] Step S150: Control the vehicle to avoid obstacles according to the target precise control instruction.

[0067] In the embodiment of the present application, the vehicle obstacle avoidance control method provided is applied to a transport vehicle including a visual module, by obtaining vehicle speed information and heading information and obstacle distance information through the visual module, the obstacle distance information indicates the precise distance of the vehicle from the obstacle, and the heading information indicates the precise information of the deviation between the vehicle and the target direction; according to the vehicle speed information, obstacle distance information and heading information, a fuzzy input set is determined; according to the fuzzy input set and the preset fuzzy rule base, a target fuzzy control instruction is determined; the target fuzzy control instruction, vehicle speed information, obstacle distance information and heading information are input into a pre-trained conversion control model to obtain a target precise control instruction; the vehicle is controlled to avoid obstacles according to the target precise control instruction. The target fuzzy control instruction can be determined by using a fuzzy algorithm, and the target precise control instruction can be determined according to the target fuzzy control instruction, and the transport vehicle can be controlled by the target precise control instruction, so as to improve the autonomous navigation and automatic obstacle avoidance capabilities of the transport vehicle's self-learning and adaptive control.

[0068] It should be noted that in the embodiment of the present application, the vehicle obstacle avoidance control method also includes: Get vehicle power information; When the vehicle power information indicates that the power is low, the vehicle is controlled to search for a charging station.

[0069] By obtaining vehicle power information, it is ensured that the vehicle maintains sufficient power during the mission.

[0070] Reference Figure 4 The embodiment of the present application further provides a vehicle obstacle avoidance control device 400, and the vehicle obstacle avoidance control device 400 includes: The information acquisition module 410 is used to acquire vehicle speed information, obstacle distance information, and heading information, wherein the obstacle distance information is acquired through the visual module, the obstacle distance information indicates the precise distance between the vehicle and the obstacle, and the heading information indicates the precise information of the deviation between the vehicle and the target direction; A set determination module 420, for determining a fuzzy input set according to vehicle speed information, obstacle distance information and angle information; A fuzzy instruction determination module 430 is used to determine a target fuzzy control instruction according to a fuzzy input set and a preset fuzzy rule base; The precise instruction determination module 440 is used to input the target fuzzy control instruction, vehicle speed information, obstacle distance information and heading information into the pre-trained conversion control model to obtain the target precise control instruction; The control module 450 is used to control the vehicle to avoid obstacles according to the target precise control instruction.

[0071] It should be noted that since the vehicle obstacle avoidance control device 400 of this embodiment can implement the vehicle obstacle avoidance control method of the previous embodiment, the vehicle obstacle avoidance control device 400 of this embodiment and the vehicle obstacle avoidance control method of the previous embodiment have the same technical principles and the same beneficial effects, and in order to avoid repetition of content, they will not be repeated here.

[0072] Reference Figure 5 The embodiment of the present application further discloses an electronic device, the electronic device 1100 comprising: at least one processor 1101; At least one memory 1102, used to store at least one program; When at least one program is executed by at least one processor 1101, the vehicle obstacle avoidance control method as described above is implemented.

[0073] An embodiment of the present application also discloses a computer-readable storage medium, which stores a computer program executable by a processor. When the computer program executable by the processor is executed by the processor, it is used to implement the vehicle obstacle avoidance control method as described above.

[0074] An embodiment of the present application also discloses a computer program product, including a computer program or computer instructions, wherein the computer program or computer instructions are stored in a computer-readable storage medium, a processor of an electronic device reads the computer program or computer instructions from the computer-readable storage medium, and the processor executes the computer program or computer instructions, so that the electronic device executes the vehicle obstacle avoidance control method as described above.

[0075] The terms "first", "second", "third", "fourth", etc. (if any) in the specification 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 sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein, for example. 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 that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0076] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0077] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0078] In the embodiments of the present application, the term "module" or "unit" refers to a computer program or a part of a computer program that has a predetermined function and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as processing circuits or memories), or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be part of an overall module or unit that includes the function of the module or unit.

[0079] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0080] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0081] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store program codes.

[0082] The step numbers in the above method embodiment are only provided for the convenience of explanation and description, and no limitation is imposed on the order of the steps. The execution order of each step in the embodiment can be adaptively adjusted according to the understanding of those skilled in the art.

Claims

1. A vehicle obstacle avoidance control method, applied to a transport vehicle, the transport vehicle comprising a vision module, the method comprising: Acquire vehicle speed information, obstacle distance information, and heading information, wherein the obstacle distance information is acquired through a visual module, the obstacle distance information indicates the precise distance between the vehicle and the obstacle, and the heading information indicates the precise information of the deviation between the vehicle and the target direction; Determining a fuzzy input set according to the vehicle speed information, the obstacle distance information, and the heading information; Determining a target fuzzy control instruction according to the fuzzy input set and a preset fuzzy rule base; Inputting the target fuzzy control instruction, the vehicle speed information, the obstacle distance information and the heading information into a pre-trained conversion control model to obtain a target precise control instruction; The vehicle is controlled to avoid obstacles according to the target precise control instruction.

2. The vehicle obstacle avoidance control method according to claim 1, characterized in that: The preset fuzzy rule library includes obstacle avoidance rules and target approach rules; wherein the obstacle avoidance rules are rules that instruct the vehicle to avoid obstacles; and the target approach rules are rules that instruct the vehicle to control the heading.

3. The vehicle obstacle avoidance control method according to claim 2, characterized in that: The fuzzy input set includes: fuzzy vehicle speed information, fuzzy distance information and fuzzy angle information. The target fuzzy control instruction is determined according to the fuzzy input set and a preset fuzzy rule base, including: Determining an obstacle avoidance fuzzy control instruction according to the fuzzy vehicle speed information, the fuzzy distance information and the obstacle avoidance rule; Determining a target trend fuzzy control instruction according to the fuzzy angle information and the target trend rule; The target fuzzy control instruction is determined according to the obstacle avoidance fuzzy control instruction and the target approach fuzzy control instruction.

4. The vehicle obstacle avoidance control method according to claim 3, characterized in that: Before determining the target fuzzy control instruction according to the fuzzy input set and the preset fuzzy rule base, the method further includes: A target location and target work information are obtained, and the preset fuzzy rule base is adjusted according to the target location and the target work information.

5. The vehicle obstacle avoidance control method according to claim 1, characterized in that: The pre-trained conversion control model is trained by the following steps: Acquire a fuzzy data training set, wherein the fuzzy data training set includes a plurality of training fuzzy control instructions and training speed information, training distance information, and training heading information corresponding to the training fuzzy control instructions; Constructing an initial conversion control model, inputting the fuzzy data training set into the initial conversion control model, and obtaining training control instructions; Determine the loss function according to the training control instruction, and judge whether the loss function is less than a preset loss threshold. If so, use the current initial conversion control model as a pre-trained conversion control model; otherwise, adjust the initial conversion control model according to the loss function, and continue to train the initial conversion control model based on the fuzzy data training set.

6. The vehicle obstacle avoidance control method according to claim 4, characterized in that: The adjusting the initial conversion control model according to the loss function comprises: Back-propagating the loss function in the initial conversion control model to determine an update gradient; The initial conversion control model is updated according to the update gradient.

7. The vehicle obstacle avoidance control method according to claim 1, characterized in that: The method further comprises: Get vehicle power information; When the vehicle power information indicates that the power is low, the vehicle is controlled to search for a charging station.

8. A vehicle obstacle avoidance control device, characterized in that: The device comprises: An information acquisition module, used to acquire vehicle speed information, obstacle distance information, and heading information, wherein the obstacle distance information is acquired through a visual module, the obstacle distance information indicates the precise distance between the vehicle and the obstacle, and the heading information indicates the precise information of the deviation between the vehicle and the target direction; A set determination module, used to determine a fuzzy input set according to the vehicle speed information, the obstacle distance information and the angle information; A fuzzy instruction determination module, used for determining a target fuzzy control instruction according to the fuzzy input set and a preset fuzzy rule base; A precise instruction determination module, used for inputting the target fuzzy control instruction, the vehicle speed information, the obstacle distance information and the heading information into a pre-trained conversion control model to obtain a target precise control instruction; A control module is used to control the vehicle to avoid obstacles according to the target precise control instruction.

9. An electronic device, characterized in that: include: at least one processor; at least one memory for storing at least one program; When at least one of the programs is executed by at least one of the processors, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: A computer program executable by a processor is stored therein, and when the computer program executable by the processor is executed by the processor, it is used to implement the method according to any one of claims 1 to 7.

Images