Method, device and electronic device for training autonomous driving model

Abstract

The present disclosure provides a method, device, and electronic device for training an autonomous driving model, in the field of computer technology, and in particular, in the field of autonomous driving and artificial intelligence technology. The implementation scheme is as follows: deploying an autonomous driving model with current parameters on a vehicle; obtaining first predicted driving decision information output by the autonomous driving model with current parameters in response to perception information of the vehicle in a real environment; recording first route environmental data of the vehicle traveling in the real environment in response to the first predicted driving decision information; using a teacher model to annotate the first route environmental data to obtain first target driving decision information corresponding to the first route environmental data; and training the autonomous driving model by adjusting the current parameters of the autonomous driving model according to the first target driving decision information, wherein the current parameters are adjusted to reduce the difference between the first predicted driving decision information and the first target driving decision information.

Description

Technical Field

[0001] The present disclosure relates to the fields of computer technology, in particular to the fields of autonomous driving and artificial intelligence technology, and specifically to a method, device, electronic device, computer-readable storage medium, computer program product, and autonomous driving vehicle for training an autonomous driving model. Background Art

[0002] Artificial intelligence (AI) is the study of how computers can simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, specialized AI chips, cloud computing, distributed storage, and big data processing. AI software technologies primarily encompass computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graphs.

[0003] During the training process of the autonomous driving model, the parameters of the autonomous driving model are adjusted through labeled training data to improve the driving ability of the autonomous driving model.

[0004] The approaches described in this section are not necessarily approaches that have been previously conceived or employed. Unless otherwise indicated, it should not be assumed that any approach described in this section is prior art simply by virtue of its inclusion in this section. Similarly, unless otherwise indicated, the issues raised in this section should not be considered as having been recognized in any prior art. Summary of the Invention

[0005] The present disclosure provides a method, apparatus, electronic device, computer-readable storage medium, computer program product, and autonomous driving vehicle for training an autonomous driving model.

[0006] According to one aspect of the present disclosure, a method for training an autonomous driving model is provided, comprising: deploying the autonomous driving model with current parameters on a vehicle; obtaining first predicted driving decision information output by the autonomous driving model with the current parameters in response to perception information of the vehicle in a real environment; recording first route environment data of the vehicle traveling in the real environment in response to the first predicted driving decision information; labeling the first route environment data using a teacher model to obtain first target driving decision information corresponding to the first route environment data; and training the autonomous driving model by adjusting the current parameters of the autonomous driving model according to the first target driving decision information, wherein the current parameters are adjusted to reduce the difference between the first predicted driving decision information and the first target driving decision information.

[0007] According to another aspect of the present disclosure, a device for training an autonomous driving model is provided, comprising: a deployment unit configured to deploy the autonomous driving model with current parameters on a vehicle; a prediction unit configured to obtain first predicted driving decision information output by the autonomous driving model with the current parameters in response to perception information of the vehicle in a real environment; a data recording unit configured to record first route environment data of the vehicle traveling in the real environment in response to the first predicted driving decision information; a labeling unit configured to label the first route environment data using a teacher model to obtain first target driving decision information corresponding to the first route environment data; and a training unit configured to train the autonomous driving model by adjusting the current parameters of the autonomous driving model according to the first target driving decision information, wherein the current parameters are adjusted to reduce the difference between the first predicted driving decision information and the first target driving decision information.

[0008] According to another aspect of the present disclosure, an electronic device is also provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method provided according to an embodiment of the present disclosure.

[0009] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is further provided, wherein the computer instructions are used to enable the computer to execute the method provided according to the embodiment of the present disclosure.

[0010] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the method provided according to the embodiment of the present disclosure is implemented.

[0011] According to another aspect of the present disclosure, an autonomous driving vehicle is provided, on which a trained autonomous driving model is deployed, wherein the autonomous driving model is trained using a method provided according to an embodiment of the present disclosure.

[0012] According to one or more embodiments of the present disclosure, the cost of collecting training data can be reduced and the training efficiency of the autonomous driving model can be improved.

[0013] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The accompanying drawings illustrate exemplary embodiments and constitute a part of the specification. Together with the description of the specification, they serve to explain exemplary implementation of the embodiments. The illustrated embodiments are for illustrative purposes only and do not limit the scope of the claims. Throughout the drawings, the same reference numerals designate similar, but not necessarily identical, elements.

[0015] Figure 1 A schematic diagram illustrating an exemplary system in which the various methods described herein may be implemented according to an embodiment of the present disclosure;

[0016] Figure 2 An exemplary flowchart of training an autonomous driving model according to an embodiment of the present disclosure is shown;

[0017] Figure 3 An exemplary process of a training process according to an embodiment of the present disclosure is shown;

[0018] Figure 4 An exemplary block diagram of an apparatus for training an autonomous driving model according to an embodiment of the present disclosure is shown;

[0019] Figure 5 A structural block diagram of an exemplary electronic device that can be used to implement the embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0020] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be appreciated by those skilled in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0021] In this disclosure, unless otherwise specified, the use of terms such as "first" and "second" to describe various elements is not intended to limit the positional relationship, temporal relationship, or importance relationship of these elements. Such terms are only used to distinguish one element from another. In some examples, the first element and the second element may refer to the same instance of the element, while in some cases, based on the context of the description, they may also refer to different instances.

[0022] The terms used in the descriptions of the various examples described in this disclosure are for the purpose of describing specific examples only and are not intended to be limiting. Unless the context clearly indicates otherwise, if the number of elements is not specifically limited, the element may be one or more. In addition, the term "and / or" used in this disclosure encompasses any one and all possible combinations of the listed items.

[0023] The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0024] Figure 1 FIG2 is a schematic diagram of an exemplary system 100 in which the various methods and apparatuses described herein may be implemented according to an embodiment of the present disclosure. Figure 1 , the system 100 includes a motor vehicle 110 , a server 120 , and one or more communication networks 130 coupling the motor vehicle 110 to the server 120 .

[0025] In an embodiment of the present disclosure, the motor vehicle 110 may include a computing device according to an embodiment of the present disclosure and / or be configured to perform a method according to an embodiment of the present disclosure.

[0026] The server 120 may run one or more services or software applications that enable methods for training the autonomous driving model. In some embodiments, the server 120 may also provide other services or software applications that may include non-virtual environments and virtual environments. Figure 1 In the configuration shown, the server 120 may include one or more components that implement the functions performed by the server 120. These components may include software components, hardware components, or a combination thereof that can be executed by one or more processors. The user of the motor vehicle 110 may, in turn, utilize one or more client applications to interact with the server 120 to utilize the services provided by these components. It should be understood that a variety of different system configurations are possible, which may differ from the system 100. Therefore, Figure 1 is one example of a system for implementing the various methods described herein and is not intended to be limiting.

[0027] Server 120 may include one or more general-purpose computers, specialized server computers (e.g., PC (personal computer) servers, UNIX servers, mid-range servers), blade servers, mainframe computers, server clusters, or any other suitable arrangement and / or combination. Server 120 may include one or more virtual machines running virtual operating systems, or other computing architectures involving virtualization (e.g., one or more flexible pools of logical storage devices that may be virtualized to maintain a server's virtual storage device). In various embodiments, server 120 may run one or more services or software applications that provide the functionality described below.

[0028] The computing units in the server 120 may run one or more operating systems including any of the operating systems described above as well as any commercially available server operating systems. The server 120 may also run any of a variety of additional server applications and / or middle-tier applications, including HTTP servers, FTP servers, CGI servers, JAVA servers, database servers, and the like.

[0029] In some embodiments, server 120 may include one or more applications to analyze and consolidate data feeds and / or event updates received from motor vehicle 110. Server 120 may also include one or more applications to display data feeds and / or real-time events via one or more display devices of motor vehicle 110.

[0030] The network 130 may be any type of network known to those skilled in the art that can support data communications using any of a variety of available protocols, including but not limited to TCP / IP, SNA, IPX, etc. By way of example only, the one or more networks 130 may be a satellite communication network, a local area network (LAN), an Ethernet-based network, a token ring, a wide area network (WAN), the Internet, a virtual network, a virtual private network (VPN), an intranet, an extranet, a blockchain network, a public switched telephone network (PSTN), an infrared network, a wireless network (including, for example, Bluetooth, WiFi), and / or any combination of these and other networks.

[0031] The system 100 may also include one or more databases 150. In some embodiments, these databases can be used to store data and other information. For example, one or more of the databases 150 can be used to store information such as audio files and video files. The data repository 150 can reside in a variety of locations. For example, the data repository used by the server 120 can be local to the server 120, or can be remote from the server 120 and can communicate with the server 120 via a network-based or dedicated connection. The data repository 150 can be of different types. In some embodiments, the data repository used by the server 120 can be a database, such as a relational database. One or more of these databases can store, update, and retrieve data to and from the database in response to commands.

[0032] In some embodiments, one or more of the databases 150 may also be used by applications to store application data. The databases used by the applications may be different types of databases, such as a key-value store, an object store, or a conventional store backed by a file system.

[0033] Motor vehicle 110 may include sensors 111 for sensing its surroundings. Sensors 111 may include one or more of the following: visual cameras, infrared cameras, ultrasonic sensors, millimeter-wave radar, and laser radar (LiDAR). Different sensors offer different detection accuracy and range. Cameras may be mounted on the front, rear, or other locations of the vehicle. Visual cameras can capture real-time information about the vehicle's interior and exterior and present it to the driver and / or passengers. Furthermore, by analyzing the images captured by the visual cameras, information such as traffic light indications, intersection conditions, and the operating status of other vehicles can be obtained. Infrared cameras can detect objects in night vision conditions. Ultrasonic sensors can be mounted on all sides of the vehicle, utilizing the strong directionality of ultrasonic waves to measure the distance of external objects from the vehicle. Millimeter-wave radars can be mounted on the front, rear, or other locations of the vehicle, utilizing the properties of electromagnetic waves to measure the distance of external objects from the vehicle. LiDARs can be mounted on the front, rear, or other locations of the vehicle, detecting object edges and shapes for object recognition and tracking. Due to the Doppler effect, radar devices can also measure changes in the speed of the vehicle and moving objects.

[0034] The motor vehicle 110 may also include a communication device 112. The communication device 112 may include a satellite positioning module that can receive satellite positioning signals (e.g., Beidou, GPS, GLONASS, and GALILEO) from satellites 141 and generate coordinates based on these signals. The communication device 112 may also include a module for communicating with a mobile communication base station 142. The mobile communication network may implement any suitable communication technology, such as GSM / GPRS, CDMA, LTE, and other current or evolving wireless communication technologies (e.g., 5G technology). The communication device 112 may also have a vehicle-to-everything (V2X) module that is configured to implement vehicle-to-vehicle (V2V) communication with other vehicles 143 and vehicle-to-infrastructure (V2I) communication with infrastructure 144, for example. In addition, the communication device 112 may also include a module configured to communicate with a user terminal 145 (including but not limited to a smartphone, tablet computer, or wearable device such as a watch) via a wireless local area network or Bluetooth using the IEEE 802.11 standard, for example. Using the communication device 112, the motor vehicle 110 may also access the server 120 via the network 130.

[0035] The motor vehicle 110 may also include a control device 113. The control device 113 may include a processor that communicates with various types of computer-readable storage devices or media, such as a central processing unit (CPU) or a graphics processing unit (GPU), or other dedicated processors. The control device 113 may include an autonomous driving system for automatically controlling various actuators in the vehicle. The autonomous driving system is configured to control the powertrain, steering system, and braking system of the motor vehicle 110 (not shown) via multiple actuators in response to input from multiple sensors 111 or other input devices to control acceleration, steering, and braking, respectively, without human intervention or limited human intervention. Some processing functions of the control device 113 may be implemented through cloud computing. For example, some processing may be performed using an on-board processor, while other processing may be performed using computing resources in the cloud. The control device 113 may be configured to execute the method according to the present disclosure. In addition, the control device 113 may be implemented as an example of a computing device on the motor vehicle side (client) according to the present disclosure.

[0036] Figure 1 The system 100 may be configured and operated in various ways to enable the application of various methods and apparatuses described in accordance with the present disclosure.

[0037] After being deployed on a real vehicle and interacting with a real-world environment, autonomous driving systems often fail to fully capture the diverse environments, triggering manual intervention. Therefore, rapidly improving autonomous driving systems' capabilities in real-world environments has long been a challenging problem.

[0038] To address the issue of insufficient driving capabilities of autonomous driving systems in real-world environments, related technologies employ the following two approaches to address these issues:

[0039] The first type is a rule-based modular system, which uses artificially set rules to specifically address the system's insufficient driving capabilities in specific scenarios.

[0040] The second type: a learning-based modeling system, which collects targeted data manually to improve training data for scenarios where capabilities are insufficient, and then trains the model to improve driving capabilities in the corresponding scenarios.

[0041] However, rule-based modular systems have two significant drawbacks when solving specific driving scenario problems: First, due to the limitations of manual rule setting, the system's generalizability is insufficient. Similar scenario problems usually require a large number of manually written rules to gradually cover them, and the ability to respond to emerging problems is insufficient. Second, as the number and complexity of rule settings increase, the overall complexity of the system also increases rapidly, and maintenance costs are very high.

[0042] Learning-based modeling systems have better generalization than rule-based modular systems. Models can achieve a certain degree of generalization by learning from target scenario data. As long as the scenarios are similar, they can have a certain ability to deal with new problems that may arise. However, learning-based modeling systems also have the following disadvantages: First, the data collection cost is high. First, it is necessary to build or select target scenarios that meet the requirements (such as left and right turns / traffic lights / obstacles). Second, a large amount of manual driving data needs to be collected in the target scenarios. Finally, as the model performance improves and the target scenarios become more complex, the cost of manually collecting unit training data increases significantly. Second, the model's optimization efficiency on such data is low. Manual driving behavior produces general driving data, which cannot directly provide targeted guidance on the model's driving behavior in failure scenarios.

[0043] In order to solve the above-mentioned problems in the related art, the present disclosure provides a new method for training an autonomous driving model.

[0044] Figure 2 An exemplary flowchart for training an autonomous driving model according to an embodiment of the present disclosure is shown.

[0045] In step S202, the autonomous driving model with current parameters is deployed on the vehicle.

[0046] In step S204, first predicted driving decision information output by the autonomous driving model with current parameters in response to perception information of the vehicle in the real environment is obtained.

[0047] In step S206 , first route environment data of the vehicle traveling in a real environment in response to the first predicted driving decision information is recorded.

[0048] In step S208 , the first route environment data is labeled using the teacher model to obtain first target driving decision information corresponding to the first route environment data.

[0049] In step S210 , the autonomous driving model is trained by adjusting current parameters of the autonomous driving model according to the first target driving decision information, wherein the current parameters are adjusted to reduce the difference between the first predicted driving decision information and the first target driving decision information.

[0050] The above-mentioned training method provided by the embodiments of the present disclosure can reduce the cost of collecting training data and improve the training efficiency of the autonomous driving model.

[0051] The principles of the present disclosure will be described in detail below.

[0052] In step S202, the autonomous driving model with the current parameters can be deployed on the vehicle. The specific form of the autonomous driving model is not limited in the embodiments of the present disclosure. The autonomous driving model of the embodiments of the present disclosure can be implemented using various models that can be used for autonomous driving, such as an autonomous driving model based on a convolutional neural network model (CNN) or a Transformer-based autonomous driving model. These autonomous driving models can perceive environmental data surrounding the vehicle and make decisions about future vehicle driving behavior based at least on the perceived environmental data, the vehicle's current state, and its historical state.

[0053] In step S204, first predicted driving decision information output by the autonomous driving model with current parameters in response to the vehicle's perception information in the real environment is obtained. The driving decision information may include decision information for controlling the vehicle's speed and direction, such as control information for controlling the throttle level and steering wheel direction.

[0054] Various sensors deployed on the vehicle can be used to acquire perception information about the environment. This perception information can be in the form of images, text, video, or a fusion of multiple videos, such as observation information from one or more cameras, one or more lidars, and one or more millimeter-wave radars. The perception information input into the autonomous driving model can be sensor input collected by sensors at the current moment or sensor input collected by at least one sensor at a previous moment.

[0055] In step S206, environmental data of a first route traveled by the vehicle in a real environment in response to the first predicted driving decision information may be recorded. The vehicle's perception information is processed using an autonomous driving model deployed on the vehicle, and the vehicle may move forward in response to the driving decision information output by the autonomous driving model. Driving data collected during the vehicle's travel may be used as the first route environmental data.

[0056] In some embodiments, the first route environment data includes multiple locations along the route traveled by the vehicle in response to the first predicted driving decision information, and surrounding environment perception information associated with each location. This method can collect information about the interaction between the vehicle and the real environment and record the vehicle's driving performance in the real environment.

[0057] In step S208 , the teacher model may be used to label the first route environment data to obtain first target driving decision information corresponding to the first route environment data.

[0058] In some embodiments, step S208 may include: for each of the plurality of locations, processing the surrounding environment perception information corresponding to the location using the teacher model to obtain target driving decision information at the location, and processing the surrounding environment perception information corresponding to the location using the autonomous driving model to obtain predicted driving decision information at the location. Using the above-described annotation method, data obtained from vehicle driving can be efficiently annotated.

[0059] Among them, the teacher model may have the ability to process the driving route in the scene belonging to the real environment in which the vehicle is located when driving in steps S202-S206. The teacher model can be obtained by training data of the corresponding scene. For example, the teacher model can be obtained by learning the training data corresponding to the scene in the form of supervised learning and / or reinforcement learning. The teacher model obtained in this way has the ability to process the driving route of the specific scene. The ability of the teacher model to process sample environmental data means that the teacher model can output the driving route in the scene where the driving behavior is successfully completed. Among them, the successful completion of the route means that the proportion of the length of the road section traveled through while meeting the safety requirements to the length of the corresponding route is greater than a predetermined threshold, such as 95%. In addition, by only training the teacher model to process training data in a specific scene, the training difficulty of the teacher model can be reduced and the training efficiency of the teacher model can be improved.

[0060] The specific form of the teacher model is not limited in the embodiments of the present disclosure. The teacher model can have the same model structure as the trained autonomous driving model, or it can be an autonomous driving model optimized for a specific scenario.

[0061] By using a teacher model to annotate route data obtained from vehicles equipped with an autonomous driving model, the data used to train the autonomous driving model can be efficiently annotated. Furthermore, because route data obtained from autonomous driving models directly reflects the model's current performance, using this data to annotate and adjust the model's parameters can help address any existing issues.

[0062] In step S210 , the autonomous driving model is trained by adjusting current parameters of the autonomous driving model according to the first target driving decision information, wherein the current parameters are adjusted to reduce the difference between the first predicted driving decision information and the first target driving decision information.

[0063] In some embodiments, for each of a plurality of location points, parameters of the autonomous driving model are adjusted to reduce the difference between the target driving decision information at the location point and the predicted driving decision information at the location point.

[0064] Using this method, the autonomous driving model is trained using data annotated by the teacher model. This provides simulation targets for scenarios encountered by the autonomous driving model during driving, and trains the autonomous driving model to output driving decision information in a manner closer to that of the teacher model. Because the teacher model has been trained to perform well in specific scenarios, training the autonomous driving model with this annotated data can improve its performance in the current scenario.

[0065] After adjusting the parameters of the autonomous driving model in step S210, the autonomous driving model can be redeployed on the vehicle, and the vehicle can be controlled to drive again in the real environment and collect data. Then the above steps can be repeated to further adjust the parameters of the autonomous driving model.

[0066] In some embodiments, method 200 may further include: determining updated parameters of the autonomous driving model after adjusting current parameters using target driving decision information corresponding to the first route environment data; deploying the autonomous driving model with updated parameters on a vehicle; obtaining second predicted driving decision information output by the autonomous driving model with updated parameters in response to perception information of the vehicle in a real environment; recording second route environment data of the vehicle traveling in a real environment in response to the second predicted driving decision information; processing the second route environment data using a teacher model to obtain second target driving decision information; and further training the autonomous driving model by adjusting the updated parameters of the autonomous driving model, wherein the updated parameters are adjusted to reduce the difference between the second predicted driving decision information and the second target driving decision information.

[0067] Using this method, we can obtain the interaction results between the updated autonomous driving model and the real environment, and further train the updated autonomous driving model on real roads, thereby further improving the autonomous driving model's driving capabilities. This training process can be repeated until the autonomous driving model's performance on the current road section meets expectations.

[0068] Figure 3 An exemplary process of a training process according to an embodiment of the present disclosure is shown.

[0069] At block 301, the parameters of the autonomous driving model at time T are obtained. At block 302, the autonomous driving model at time T is deployed on a real vehicle to interact with the real environment, thereby obtaining driving data during the driving process. At block 303, the driving data can be annotated using the teacher model to obtain annotated data. At block 304, the annotated data can be used to train the autonomous driving model at time T to obtain an autonomous driving model at time T+1. It will be understood that the time T and time T+1 mentioned here do not refer to real time, but to the number of current training iterations, and T can be a positive integer.

[0070] By repetition Figure 3 The process shown in can obtain the interaction data between the model and the real environment in a closed-loop manner, and perform targeted training on the model based on the real interaction data.

[0071] Figure 4 An exemplary block diagram of an apparatus for training an autonomous driving model according to an embodiment of the present disclosure is shown.

[0072] like Figure 4 As shown, the apparatus 400 may include a deployment unit 410 , a prediction unit 420 , a data recording unit 430 , a labeling unit 440 , and a training unit 450 .

[0073] The deployment unit 410 can be configured to deploy the autonomous driving model with current parameters on a vehicle. The prediction unit 420 can be configured to obtain first predicted driving decision information output by the autonomous driving model with current parameters in response to perception information of the vehicle in a real environment. The data recording unit 430 can be configured to record first route environment data of the vehicle traveling in a real environment in response to the first predicted driving decision information. The annotation unit 440 can be configured to annotate the first route environment data using a teacher model to obtain first target driving decision information corresponding to the first route environment data. The training 450 can be configured to train the autonomous driving model by adjusting the current parameters of the autonomous driving model according to the first target driving decision information, wherein the current parameters are adjusted to reduce the difference between the first predicted driving decision information and the first target driving decision information.

[0074] The above-mentioned training device provided by the embodiments of the present disclosure can reduce the cost of collecting training data and improve the training efficiency of the autonomous driving model.

[0075] In some embodiments, the first route environment data includes a plurality of location points passed by the vehicle on the route traveled by the vehicle in response to the first predicted driving decision information and surrounding environment perception information associated with each location point.

[0076] In some embodiments, using a teacher model to label the first route environment data to obtain first target driving decision information corresponding to the first route environment data includes: for each of a plurality of location points, using the teacher model to process the surrounding environment perception information corresponding to the location point to obtain the target driving decision information at the location point, and using the automatic driving model to process the surrounding environment perception information corresponding to the location point to obtain the predicted driving decision information at the location point.

[0077] In some embodiments, training the autonomous driving model by adjusting the current parameters of the autonomous driving model according to the first target driving decision information includes: adjusting the parameters of the autonomous driving model for each of a plurality of location points to reduce the difference between the target driving decision information at the location point and the predicted driving decision information at the location point.

[0078] In some embodiments, the device 400 may further include an updating unit, which is configured to: determine the updated parameters of the autonomous driving model after adjusting the current parameters using the target driving decision information corresponding to the first route environment data; deploy the autonomous driving model with the updated parameters on the vehicle; obtain the second predicted driving decision information output by the autonomous driving model with the updated parameters in response to the perception information of the vehicle in the real environment; record the second route environment data of the vehicle traveling in the real environment in response to the second predicted driving decision information; use the teacher model to process the second route environment data to obtain the second target driving decision information; and further train the autonomous driving model by adjusting the updated parameters of the autonomous driving model to reduce the difference between the second predicted driving decision information and the second target driving decision information.

[0079] In some embodiments, the teacher model has the ability to process driving routes in real-world scenarios.

[0080] It should be understood that Figure 4 The modules or units of the apparatus 400 shown in FIG. 4 can be used in conjunction with the reference Figure 2 The steps in the method 200 described above correspond to each other. Therefore, the operations, features and advantages described above for the method 200 are also applicable to the apparatus 400 and the modules and units included therein. For the sake of brevity, some operations, features and advantages are not repeated here.

[0081] Although specific functionality is discussed above with reference to specific modules, it should be noted that the functionality of the various units discussed herein may be separated into multiple units, and / or at least some functionality of multiple units may be combined into a single unit.

[0082] It should also be understood that various techniques may be described herein in the general context of software hardware elements or program modules. Figure 4The various units described can be implemented in hardware or in hardware in combination with software and / or firmware. For example, these units can be implemented as computer program code / instructions, which are configured to be executed in one or more processors and stored in a computer-readable storage medium. Alternatively, these units can be implemented as hardware logic / circuits. For example, in some embodiments, one or more of units 410 to 450 can be implemented together in a system on chip (SoC). SoC can include an integrated circuit chip (which includes a processor (e.g., a central processing unit (CPU), a microcontroller, a microprocessor, a digital signal processor (DSP), etc.), a memory, one or more communication interfaces, and / or one or more components in other circuits), and can optionally execute the received program code and / or include embedded firmware to perform functions.

[0083] In the technical solutions disclosed herein, the acquisition, storage, and application of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0084] According to an embodiment of the present disclosure, an electronic device, a readable storage medium, a computer program product and an autonomous driving vehicle are also provided.

[0085] According to an embodiment of the present disclosure, an electronic device is also provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method provided according to an embodiment of the present disclosure.

[0086] According to an embodiment of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is further provided, wherein the computer instructions are used to enable the computer to execute the method provided according to the embodiment of the present disclosure.

[0087] According to an embodiment of the present disclosure, a computer program product is further provided, including a computer program, wherein the computer program implements the method provided according to the embodiment of the present disclosure when executed by a processor.

[0088] According to an embodiment of the present disclosure, an autonomous driving vehicle is also provided, on which a trained autonomous driving model is deployed, wherein the autonomous driving model is trained using a method provided according to an embodiment of the present disclosure.

[0089] refer to Figure 5, a block diagram of an electronic device 500 that can serve as a server or client of the present disclosure will now be described, which is an example of a hardware device that can be applied to various aspects of the present disclosure. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0090] like Figure 5 As shown, the electronic device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. Various programs and data required for the operation of the electronic device 500 can also be stored in the RAM 503. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0091] Multiple components within electronic device 500 are connected to I / O interface 505, including an input unit 506, an output unit 507, a storage unit 508, and a communication unit 509. Input unit 506 can be any type of device capable of inputting information into electronic device 500. Input unit 506 can receive input numeric or character information and generate key signal input related to user settings and / or function control of the electronic device. It may include, but is not limited to, a mouse, keyboard, touch screen, trackpad, trackball, joystick, microphone, and / or remote control. Output unit 507 can be any type of device capable of presenting information, and may include, but is not limited to, a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. Storage unit 508 may include, but is not limited to, a magnetic disk or an optical disk. Communication unit 509 allows electronic device 500 to exchange information / data with other devices via computer networks such as the Internet and / or various telecommunication networks. It may include, but is not limited to, a modem, a network card, an infrared communication device, a wireless communication transceiver and / or chipset, such as a Bluetooth™ device, an 802.11 device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0092] The computing unit 501 can be a variety of general-purpose and / or specialized processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 501 performs the various methods and processes described above, such as method 200. For example, in some embodiments, method 200 can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as a storage unit 508. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 500 via ROM 502 and / or communication unit 509. When the computer program is loaded into RAM 503 and executed by the computing unit 501, one or more steps of the method 200 described above can be performed. Alternatively, in other embodiments, the computing unit 501 can be configured to perform method 200 in any other appropriate manner (e.g., by means of firmware).

[0093] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0094] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0095] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0096] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0097] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), the Internet, and a blockchain network.

[0098] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises through computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0099] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not limited herein.

[0100] Although the embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it should be understood that the above-mentioned methods, systems and devices are merely exemplary embodiments or examples, and the scope of the present invention is not limited by these embodiments or examples, but is only limited by the claims after authorization and their equivalents. Various elements in the embodiments or examples may be omitted or replaced by their equivalents. In addition, the steps may be performed in an order different from that described in this disclosure. Further, the various elements in the embodiments or examples may be combined in various ways. It is important that as technology evolves, many of the elements described herein may be replaced by equivalent elements that appear after this disclosure.

Claims

1. A method for training an autonomous driving model, comprising: Deploying the autonomous driving model with current parameters on a vehicle; Obtaining first predicted driving decision information output by the autonomous driving model with the current parameters in response to perception information of the vehicle in a real environment; recording first route environment data of the vehicle traveling in the real environment in response to the first predicted driving decision information; annotating the first route environment data using a teacher model to obtain first target driving decision information corresponding to the first route environment data, wherein, for each location point among a plurality of location points passed by the vehicle on the route traveled by the vehicle in response to the first predicted driving decision information, processing surrounding environment perception information corresponding to the location point using the teacher model to obtain target driving decision information at the location point, and processing the surrounding environment perception information corresponding to the location point using the autonomous driving model to obtain predicted driving decision information at the location point; The autonomous driving model is trained by adjusting the current parameters of the autonomous driving model according to the first target driving decision information, wherein the current parameters are adjusted to reduce the difference between the first predicted driving decision information and the first target driving decision information, wherein, for each of the multiple location points, the parameters of the autonomous driving model are adjusted to reduce the difference between the target driving decision information at the location point and the predicted driving decision information at the location point.

2. The method according to claim 1, wherein The first route environment data includes the plurality of location points and surrounding environment perception information associated with each location point.

3. The method according to any one of claims 1 to 2, further comprising: After adjusting the current parameters using the target driving decision information corresponding to the first route environment data, determining updated parameters of the autonomous driving model; deploying the autonomous driving model with the updated parameters on a vehicle; Obtaining second predicted driving decision information output by the autonomous driving model with the updated parameters in response to perception information of the vehicle in a real environment; recording second route environment data of the vehicle traveling in the real environment in response to the second predicted driving decision information; labeling the second route environment data using the teacher model to obtain second target driving decision information corresponding to the second route environment data; The autonomous driving model is further trained by adjusting the update parameters of the autonomous driving model, wherein the update parameters are adjusted to reduce the difference between the second predicted driving decision information and the second target driving decision information.

4. The method according to any one of claims 1 to 2, wherein The teacher model has the ability to process the driving route in the scene to which the real environment belongs.

5. A device for training an autonomous driving model, comprising: a deployment unit configured to deploy the autonomous driving model with current parameters on a vehicle; a prediction unit configured to obtain first predicted driving decision information output by the autonomous driving model having the current parameters in response to perception information of the vehicle in a real environment; a data recording unit configured to record first route environment data of the vehicle traveling in the real environment in response to the first predicted driving decision information; a labeling unit configured to label the first route environment data using a teacher model to obtain first target driving decision information corresponding to the first route environment data, wherein, for each location point among a plurality of location points passed by the vehicle on the route traveled by the vehicle in response to the first predicted driving decision information, the teacher model is used to process the surrounding environment perception information corresponding to the location point to obtain the target driving decision information at the location point, and the autonomous driving model is used to process the surrounding environment perception information corresponding to the location point to obtain the predicted driving decision information at the location point; A training unit is configured to train the autonomous driving model by adjusting the current parameters of the autonomous driving model according to the first target driving decision information, wherein the current parameters are adjusted to reduce the difference between the first predicted driving decision information and the first target driving decision information, wherein, for each of the multiple location points, the parameters of the autonomous driving model are adjusted to reduce the difference between the target driving decision information at the location point and the predicted driving decision information at the location point.

6. The device according to claim 5, wherein The first route environment data includes the plurality of location points and surrounding environment perception information associated with each location point.

7. The apparatus according to any one of claims 5 to 6, further comprising an updating unit, wherein the updating unit is configured to: After adjusting the current parameters using the target driving decision information corresponding to the first route environment data, determining updated parameters of the autonomous driving model; deploying the autonomous driving model with the updated parameters on a vehicle; Obtaining second predicted driving decision information output by the autonomous driving model with the updated parameters in response to perception information of the vehicle in a real environment; recording second route environment data of the vehicle traveling in the real environment in response to the second predicted driving decision information; processing the second route environment data using the teacher model to obtain second target driving decision information; The autonomous driving model is further trained by adjusting the update parameters of the autonomous driving model to reduce the difference between the second predicted driving decision information and the second target driving decision information.

8. The device according to any one of claims 5 to 6, wherein: The teacher model has the ability to process the driving route in the scene to which the real environment belongs.

9. An electronic device comprising: at least one processor; as well as a memory communicatively coupled to the at least one processor; in The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 4.

10. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-4.

11. A computer program product comprising a computer program, wherein When the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

12. An autonomous driving vehicle having a trained autonomous driving model deployed thereon, wherein the autonomous driving model is trained by the method according to any one of claims 1-4.

Images