Method and apparatus for determining vehicle control information, vehicle, device, and medium

Abstract

The application provides a vehicle control information determination method and device, a vehicle, equipment and a medium. The method comprises the following steps: obtaining a first chassis signal sequence of a vehicle in a historical time period, and a first expected chassis signal value of the vehicle in a to-be-controlled time period; and mapping the first chassis signal sequence and the first expected chassis signal value into target control information for a target time of the vehicle in the to-be-controlled time period. Compared with a traditional model, the embodiment of the application does not need to additionally set various coefficients and parameters, and does not need to additionally establish a physical model, and can determine the control information of the vehicle based on less information.

Description

Technical Field

[0001] This invention relates to the technical field of vehicle control, and in particular to a method for determining vehicle control information, a device for determining vehicle control information, a vehicle, an electronic device, and a computer-readable storage medium. Background Technology

[0002] The controller that operates the vehicle chassis needs to model the external forces acting on the vehicle and its own dynamic characteristics. For parameters that cannot be directly measured, such as the road adhesion coefficient and the vehicle's center of gravity sideslip angle, a state observer needs to be designed based on the physical model to indirectly obtain estimates of these parameters for use in controlling the vehicle chassis. Furthermore, linear or nonlinear physical models need to be established for the vehicle's own kinematics and dynamics. Based on these models, methods such as PID (Proportional-Integral-Derivative) control, fuzzy control, and model predictive control can be used to control the vehicle chassis. In addition, a balance must be struck between model complexity and fidelity during the modeling process.

[0003] In summary, determining vehicle control information based on conventional models requires the advance preparation and design of a large number of parameters and models. Summary of the Invention

[0004] In view of the above problems, a method for determining vehicle control information, a device for determining vehicle control information, a vehicle, an electronic device, and a computer-readable storage medium are proposed to overcome or at least partially solve the above problems, comprising:

[0005] A method for determining vehicle control information, the method comprising:

[0006] Acquire the first chassis signal sequence of the vehicle within a historical time period, and the first desired chassis signal value of the vehicle within the time period to be controlled;

[0007] The first chassis signal sequence and the first desired chassis signal value are mapped to target control information for the vehicle at a target time within the time period to be controlled.

[0008] Optionally, the vehicle includes multiple chassis execution units, and the step of acquiring a first chassis signal sequence of the vehicle within a historical time period and a first desired chassis signal value of the vehicle within the time period to be controlled includes:

[0009] The first chassis signal sequence of the vehicle within a historical time period is obtained from the plurality of chassis execution units;

[0010] In addition, the system acquires the first desired chassis signal value set for the plurality of chassis execution units during the control period.

[0011] Optionally, a target end-to-end model is deployed in the vehicle, and mapping the first chassis signal sequence and the first desired chassis signal value to target control information for the vehicle within the target time period includes:

[0012] The first chassis signal sequence and the first desired chassis signal value are input into the target end-to-end model to obtain the target control information; the target end-to-end model is used to map the chassis signal sequence and the desired chassis signal value into control information for the vehicle.

[0013] Optionally, the method further includes:

[0014] Receive model training result parameters for the target end-to-end model sent by the cloud server;

[0015] Based on the currently received model training result parameters, the target end-to-end model is deployed locally on the vehicle; or, based on the currently received model training result parameters, the target end-to-end model deployed locally on the vehicle is updated.

[0016] Optionally, the method further includes:

[0017] The first chassis signal sequence and the first desired chassis signal value are used as training data and uploaded to the cloud server; the cloud server is used to generate the model training result parameters based on the training data and send them to the vehicle.

[0018] Optionally, the vehicle includes multiple chassis actuators, and the method further includes:

[0019] Based on the target control information, the multiple chassis actuators of the vehicle are controlled respectively.

[0020] The present invention also provides a vehicle, the vehicle including a chassis domain controller and a plurality of chassis execution units, the chassis domain controller being used to execute the method for determining vehicle control information as described above.

[0021] The present invention also provides a device for determining vehicle control information, the device comprising:

[0022] The acquisition module is used to acquire the first chassis signal sequence of the vehicle within a historical time period, and the first desired chassis signal value of the vehicle within the time period to be controlled.

[0023] The determination module is used to map the first chassis signal sequence and the first desired chassis signal value into target control information for the vehicle at a target time within the time period to be controlled.

[0024] Optionally, the vehicle includes multiple chassis execution units, and the acquisition module is used to acquire a first chassis signal sequence of the vehicle within a historical time period from the multiple chassis execution units; and to acquire a first desired chassis signal value set for the multiple chassis execution units within a controllable time period.

[0025] Optionally, a target end-to-end model is deployed in the vehicle, and the determining module is used to input the first chassis signal sequence and the first desired chassis signal value into the target end-to-end model to obtain the target control information; the target end-to-end model is used to map the chassis signal sequence and the desired chassis signal value into control information for the vehicle.

[0026] Optionally, the device further includes:

[0027] The update deployment module is used to receive model training result parameters for the target end-to-end model sent by the cloud server; deploy the target end-to-end model locally on the vehicle according to the currently received model training result parameters; or update the target end-to-end model deployed locally on the vehicle according to the currently received model training result parameters.

[0028] Optionally, the device further includes:

[0029] The upload module is used to upload the first chassis signal sequence and the first expected chassis signal value as training data to the cloud server; the cloud server is used to generate the model training result parameters based on the training data and send them to the vehicle.

[0030] Optionally, the vehicle includes multiple chassis actuators, and the device further includes:

[0031] The control module is used to control the multiple chassis actuators of the vehicle respectively according to the target control information.

[0032] The present invention also provides an electronic device, including a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the above-described method for determining vehicle control information.

[0033] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the method for determining vehicle control information as described above.

[0034] The present invention has the following advantages:

[0035] In this invention, the first chassis signal sequence of the vehicle within a historical time period and the first desired chassis signal value of the vehicle within the time period to be controlled can be obtained first. The first chassis signal sequence and the first desired chassis signal value are then mapped to target control information for the vehicle at a target time within the time period to be controlled. Compared to traditional models, this embodiment of the invention does not require setting various coefficients and parameters or establishing additional physical models, and can determine the vehicle's control information based on less information. Attached Figure Description

[0036] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description of the present invention will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0037] Figure 1 This is a flowchart illustrating the steps of a method for determining vehicle control information according to an embodiment of the present invention.

[0038] Figure 2 This is a flowchart illustrating the steps of another method for determining vehicle control information according to an embodiment of the present invention.

[0039] Figure 3 This is a schematic diagram of data interaction according to an embodiment of the present invention;

[0040] Figure 4 This is another data interaction diagram according to an embodiment of the present invention;

[0041] Figure 5 This is another data interaction diagram according to an embodiment of the present invention;

[0042] Figure 6 This is a schematic diagram of the structure of a vehicle according to an embodiment of the present invention;

[0043] Figure 7 This is a schematic diagram of the structure of a vehicle control information determination device according to an embodiment of the present invention. Detailed Implementation

[0044] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0045] To determine vehicle control information with less information, this invention provides a method for determining vehicle control information. This method determines vehicle control information based on logic that directly maps input data to target output. Compared to traditional models, this invention does not require setting various coefficients and parameters, nor does it require building additional physical models, thus determining vehicle control information with less information. Specifically, please refer to... Figure 1 , Figure 1 A flowchart illustrating the steps of a method for determining vehicle control information according to an embodiment of the present invention is shown.

[0046] like Figure 1 As shown, the method may include the following steps:

[0047] Step 101: Obtain the first chassis signal sequence of the vehicle within the historical time period, and the first desired chassis signal value of the vehicle within the time period to be controlled.

[0048] During vehicle operation, the first chassis signal sequence of the vehicle within a historical time period can be acquired, as well as the first expected chassis signal value of the state the vehicle is expected to reach within the control period.

[0049] The historical time period can refer to a certain period of time in the past relative to the current time; for example, if the current time is 11:00:00 on October 29, 2024, then the historical time period can be from 10:50:00 on October 29, 2024 to 10:59:59 on October 29, 2024. This embodiment of the invention does not impose any restrictions on this.

[0050] The time period to be controlled can refer to a future period including the current time, or a future period excluding the current time. For this time period, control information needs to be determined in advance to control the vehicle's chassis during this period. For example, the control information may include information for controlling the vehicle's steering, or information for controlling the vehicle's acceleration, speed, etc., and this embodiment of the invention does not impose any limitations on this.

[0051] When acquiring vehicle information within a historical time period, the first chassis signal sequence of the vehicle within that historical time period can be obtained. This first chassis signal sequence can be composed of the actual chassis signal values ​​corresponding to the vehicle at each time point within the historical time period.

[0052] When acquiring vehicle information within the control period, the chassis signal values ​​that the vehicle is expected to reach within the control period can be acquired, and these chassis signal values ​​can be used as the first expected chassis signal values. It should be noted that the first expected chassis signal values ​​may include multiple values.

[0053] The chassis signal values ​​may include vehicle steering angle, vehicle yaw rate, vehicle longitudinal acceleration, vehicle longitudinal speed, vehicle lateral speed, etc., which will not be listed one by one in this embodiment of the invention.

[0054] For example, the chassis signal values ​​in the first chassis signal sequence can be obtained from various chassis execution units of the vehicle, such as braking unit, steering unit, drive unit, etc.; the chassis signal values ​​in the first desired chassis signal values ​​can be obtained from the planning layer of the intelligent driving domain controller or the driver intention recognition module, etc., and the embodiments of the present invention do not limit this.

[0055] Step 102: Map the first chassis signal sequence and the first desired chassis signal value to target control information for the vehicle at the target time within the control period.

[0056] After obtaining the first chassis signal sequence and the first desired chassis signal value, the first chassis signal sequence and the first desired chassis signal value can be mapped to target control information for the vehicle at a target time within the control period; the target time can be a time period within the control period.

[0057] In one embodiment of the present invention, after determining the target control information, the vehicle can be controlled so that the chassis can be in the state corresponding to the first desired chassis signal value during the control period.

[0058] In this embodiment of the invention, the first chassis signal sequence of the vehicle within a historical time period and the first desired chassis signal value of the vehicle within the time period to be controlled can be obtained first. The first chassis signal sequence and the first desired chassis signal value are then mapped to target control information for the vehicle at a target time within the time period to be controlled. Compared to traditional models, this embodiment of the invention does not require setting various coefficients and parameters or establishing additional physical models, and can determine the vehicle's control information based on less information.

[0059] Reference Figure 2 The diagram illustrates a flowchart of another method for determining vehicle control information according to an embodiment of the present invention, which may include the following steps:

[0060] Step 201: The vehicle includes multiple chassis execution units. The first chassis signal sequence of the vehicle within a historical time period is obtained from the multiple chassis execution units.

[0061] In practical applications, a vehicle may include multiple chassis actuators; such as Figure 3 As shown, the multiple chassis actuators may include: a braking unit 31, a steering unit 32, and a drive unit 33. The braking unit 31, steering unit 32, and drive unit 33 may be connected to the chassis domain controller 34 respectively.

[0062] The drive unit 33 is used to control the motor to drive the vehicle. It can receive control commands from the chassis domain controller 34 or other units in the bus, and at the same time feed back its own status and related sensor signals to the chassis domain controller 34 or other units via the communication bus.

[0063] The braking unit 31 is used to control the master cylinder or electromechanical brake caliper to achieve vehicle braking. It can receive control commands from the chassis domain controller 34 or other units in the bus, and at the same time feed back its own status and related sensor signals to the chassis domain controller 34 or other units via the communication bus.

[0064] The steering unit 32 is used to control the motor to achieve front wheel or four-wheel steering of the vehicle. It can receive control commands from the chassis domain controller 34 or other units in the bus, and at the same time feed back its own status and related sensor signals to the chassis domain controller 34 or other units via the communication bus.

[0065] The chassis domain controller 34 can first obtain a first chassis signal sequence of the vehicle within a historical time period from multiple chassis execution units. For example, the chassis domain controller 34 can obtain multiple chassis signal values ​​of the vehicle collected by the braking unit 31 within a historical time period and use these multiple chassis signal values ​​as the first chassis signal sequence. The chassis domain controller 34 can also obtain multiple chassis signal values ​​of the vehicle collected by the drive unit 33 within a historical time period and use these multiple chassis signal values ​​as the first chassis signal sequence. The chassis domain controller 34 can also obtain multiple chassis signal values ​​of the vehicle collected by the steering unit 32 within a historical time period and use these multiple chassis signal values ​​as the first chassis signal sequence.

[0066] Step 202: Obtain the first desired chassis signal value set for multiple chassis execution units during the control period.

[0067] On the other hand, the chassis domain controller 34 can also obtain the first desired chassis signal value set for multiple chassis execution units during the control period. For example, the chassis domain controller 34 can obtain the desired chassis signal value set for each chassis execution unit during the control period from the planning layer of the intelligent driving domain controller or the driver intention recognition module, and use it as the first desired chassis signal value.

[0068] Step 203: A target end-to-end model is deployed in the vehicle. The first chassis signal sequence and the first desired chassis signal value are input into the target end-to-end model to obtain target control information. The target end-to-end model is used to map the chassis signal sequence and the desired chassis signal value into control information for the vehicle.

[0069] Vehicle models based on physics have poor flexibility and cannot adjust their parameters in a timely manner to changes in the external environment and the aging of the vehicle itself. This leads to discrepancies between the vehicle dynamics model and the actual vehicle dynamics performance, resulting in a decrease in the accuracy of the controller in maneuvering the vehicle chassis. Therefore, to ensure the accuracy of vehicle maneuvering by the chassis domain controller 34, this embodiment of the invention can use an end-to-end model to determine the target control information of the vehicle.

[0070] Compared to traditional models, end-to-end models do not require explicit physical models. This allows complex nonlinear relationships and subtle dynamic changes to be captured by the mapped relationships. Furthermore, end-to-end models avoid the complexity and uncertainty of explicitly building complex physical models, thus eliminating the need for parameter tuning. Additionally, end-to-end models can handle complex nonlinear relationships and capture subtle changes that are difficult for physical models to model. Moreover, end-to-end models are data-driven and automatically adjust model parameters, reducing the complexity of human intervention and manual parameter tuning. Furthermore, end-to-end models directly optimize control objectives, avoiding error propagation from intermediate models and improving the accuracy of the chassis domain controller 34.

[0071] Specifically, a pre-trained end-to-end model can be pre-deployed in the vehicle's chassis domain controller 34. This end-to-end model can be used to map chassis signal sequences and desired chassis signal values ​​into control information for the vehicle. In practical applications, the end-to-end model can be trained based on a large number of chassis signal sequences, desired chassis signal values, and corresponding vehicle control information.

[0072] Based on the target end-to-end model deployed in the chassis domain controller 34, the chassis domain controller 34 can first input the first chassis signal sequence and the first desired chassis signal value into the target end-to-end model; the target end-to-end model can determine the actual state of the vehicle in the historical time period based on the first chassis signal sequence, and determine the state that the vehicle is expected to reach in the time period to be controlled based on the first desired chassis signal value.

[0073] Based on the first chassis signal sequence and the first desired chassis signal value, the target end-to-end model can directly map the target control information for the vehicle at the target time within the time period to be controlled.

[0074] Step 204: Control the multiple chassis actuators of the vehicle separately according to the target control information.

[0075] After obtaining the target control information, the chassis domain controller 34 can control multiple chassis execution units of the vehicle respectively based on the target control information at the target time within the controllable time period, so as to control the vehicle to reach the state corresponding to the first desired chassis signal value at the target time within the controllable time period.

[0076] In one embodiment of the present invention, the above method may further include the following steps:

[0077] Receive model training result parameters for the target end-to-end model from the cloud server 36; deploy the target end-to-end model locally on the vehicle based on the currently received model training result parameters; or update the target end-to-end model deployed locally on the vehicle based on the currently received model training result parameters.

[0078] In some feasible embodiments, the chassis domain controller 34 can obtain the model training result parameters of the target end-to-end model from the cloud server 36, so as to update or deploy the target end-to-end model locally. Specifically, such as Figure 3 As shown, the chassis domain controller 34 can communicate with the cloud server 36 via the 5G module 35.

[0079] The chassis domain controller 34 can obtain the model training result parameters for the target end-to-end model issued by the cloud server 36 through the 5G module 35, and deploy the target end-to-end model locally on the vehicle based on the currently obtained model training result parameters.

[0080] Alternatively, if a target end-to-end model has already been deployed locally, when the chassis domain controller 34 obtains the model training result parameters for the target end-to-end model from the cloud server 36 via the 5G module 35, it can update the target end-to-end model in the chassis domain controller 34 based on the latest model training result parameters obtained.

[0081] Among them, the model training result parameters can refer to the model parameters obtained after training on the cloud server 36, which can be used to build or update the model.

[0082] In one embodiment of the present invention, the above method may further include the following steps:

[0083] The first chassis signal sequence and the first expected chassis signal value are used as training data and uploaded to the cloud server 36. The cloud server 36 is used to generate model training result parameters based on the training data and send them to the vehicle.

[0084] In some feasible embodiments, in order to ensure that the target end-to-end model can continuously adapt to the current environment, the chassis domain controller 34 can obtain the first chassis signal sequence and the first expected chassis signal value, and then use the first chassis signal sequence and the first expected chassis signal value as training data and upload them to the cloud server 36, so that the cloud server 36 can retrain the target end-to-end model according to the new training data, so that the target end-to-end model can continuously learn.

[0085] After obtaining the training data, the cloud server 36 can retrain the target end-to-end model deployed in the cloud based on the training data, generate model training result parameters, and send them to the chassis domain controller 34 of the vehicle to update the target end-to-end model in the chassis domain controller 34.

[0086] For example, such as Figure 4 As shown, A, B, C, D, E, and F are the input data of the target end-to-end model, and G and H are the output data of the target end-to-end model. The input and output data required for training the model both originate from message signals collected by the chassis domain controller. I represents the target end-to-end model used for the autonomous learning of vehicle performance proposed in this invention. The input layer of the target end-to-end model receives data from A, B, C, D, E, and F. The output layer outputs G and H data to control the vehicle's steering wheel angle and pedal opening. The hidden layer consists of multiple fully connected layers.

[0087] A can represent multiple chassis signal sequences from the drive unit, B can represent multiple chassis signal sequences from the braking unit, and C can represent multiple chassis signal sequences from the steering unit.

[0088] The data in A, B, and C are in a uniform format. Taking the yaw rate r as an example: the data input into the target end-to-end model is r. t ,r t-Δ ,r t-2Δ ,…,r t-NΔ Where Δ is the sampling interval of the signal. Therefore, the data A, B, and C input into the target end-to-end model are multiple chassis signal values ​​sampled from time t-NΔ to time t.

[0089] D can represent multiple desired chassis signal values ​​for the drive unit.

[0090] E can represent multiple desired chassis signal values ​​for the braking unit.

[0091] F can represent multiple desired chassis signal values ​​for the steering unit.

[0092] The data for D, E, and F are in a unified format. Taking the yaw rate r as an example, the data input into the target end-to-end model is r. t+μ Where μ is the control period. Therefore, the data D, E, and F input into the target end-to-end model are chassis signal values ​​at multiple times t+μ.

[0093] G is the steering wheel angle at time t.

[0094] H represents the pedal opening value at time t. When the pedal opening value is positive, it represents the opening value of the accelerator pedal; when the pedal opening value is negative, its absolute value represents the opening value of the brake pedal.

[0095] like Figure 5 As shown, during vehicle operation, the chassis domain controller 34 acquires chassis signal sequences from the drive unit 33, braking unit 31, and steering unit 32 from time t-NΔ to time t via the communication bus. Simultaneously, it acquires the desired relevant chassis signal values ​​at time t+μ from the planning layer of the intelligent driving domain controller 38 or the driver intent recognition module 39. This data is input into the target end-to-end model 40, which characterizes vehicle performance and is deployed within the chassis domain controller 34. The model outputs the vehicle steering wheel angle and pedal opening values, which are then sent to the drive unit E, braking unit F, and steering unit G to achieve control of the vehicle chassis.

[0096] In this embodiment of the invention, the vehicle includes multiple chassis execution units. A first chassis signal sequence of the vehicle over a historical time period is obtained from these multiple chassis execution units. A first desired chassis signal value is obtained for the multiple chassis execution units during the control period. A target end-to-end model is deployed in the vehicle. The first chassis signal sequence and the first desired chassis signal value are input into the target end-to-end model to obtain target control information. The target end-to-end model is used to map the chassis signal sequence and the desired chassis signal value to control information for the vehicle. Based on the target control information, the multiple chassis execution units of the vehicle are controlled respectively. Through this embodiment of the invention, the accuracy of the chassis domain controller's vehicle manipulation can be guaranteed.

[0097] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0098] Reference Figure 6 The diagram shows a structural schematic of a vehicle according to an embodiment of the present invention, such as... Figure 6 As shown, the vehicle 60 may include a chassis domain controller 34 and a plurality of chassis execution units 37. The chassis domain controller 34 can be used to execute the vehicle control information determination method mentioned in the above embodiments. Specifically, the chassis domain controller 34 can obtain a first chassis signal sequence from the plurality of chassis execution units 37, and control the plurality of chassis execution units 37 based on the determined target control information.

[0099] Reference Figure 7 The diagram shows a structural schematic of a vehicle control information determination device according to an embodiment of the present invention, which may include the following modules:

[0100] The acquisition module 701 is used to acquire the first chassis signal sequence of the vehicle within a historical time period, and the first desired chassis signal value of the vehicle within the time period to be controlled.

[0101] The determination module 702 is used to map the first chassis signal sequence and the first desired chassis signal value into target control information for the vehicle at a target time within the controllable time period.

[0102] In an optional embodiment of the present invention, the vehicle includes a plurality of chassis execution units, and an acquisition module is configured to acquire a first chassis signal sequence of the vehicle within a historical time period from the plurality of chassis execution units; and to acquire a first desired chassis signal value set for the plurality of chassis execution units within a controllable time period.

[0103] In an optional embodiment of the present invention, a target end-to-end model is deployed in the vehicle. A determination module is used to input a first chassis signal sequence and a first desired chassis signal value into the target end-to-end model to obtain target control information. The target end-to-end model is used to map the chassis signal sequence and the desired chassis signal value into control information for the vehicle.

[0104] In an optional embodiment of the present invention, the apparatus further includes:

[0105] The update deployment module is used to receive model training result parameters for the target end-to-end model from the cloud server; deploy the target end-to-end model locally on the vehicle based on the currently received model training result parameters; or update the target end-to-end model deployed locally on the vehicle based on the currently received model training result parameters.

[0106] In an optional embodiment of the present invention, the apparatus further includes:

[0107] The upload module is used to upload the first chassis signal sequence and the first expected chassis signal value as training data to the cloud server; the cloud server is used to generate model training result parameters based on the training data and send them to the vehicle.

[0108] In an optional embodiment of the present invention, the vehicle includes a plurality of chassis actuators, and the device further includes:

[0109] The control module is used to control multiple chassis actuators of the vehicle separately based on the target control information.

[0110] In this embodiment of the invention, the first chassis signal sequence of the vehicle within a historical time period and the first desired chassis signal value of the vehicle within the time period to be controlled can be obtained first. The first chassis signal sequence and the first desired chassis signal value are then mapped to target control information for the vehicle at a target time within the time period to be controlled. Compared to traditional models, this embodiment of the invention does not require setting various coefficients and parameters or establishing additional physical models, and can determine the vehicle's control information based on less information.

[0111] This invention also provides an electronic device, including a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, it implements the above-described method for determining vehicle control information.

[0112] This invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the method for determining the vehicle control information as described above.

[0113] As the apparatus embodiment is basically similar to the method embodiment, it is described in a relatively simple manner. For relevant details, please refer to the description of the method embodiment.

[0114] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0115] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, embodiments of the present invention can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of the present invention can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0116] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0117] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0118] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0119] Although preferred embodiments of the present invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the present invention.

[0120] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0121] The foregoing has provided a detailed description of a method for determining vehicle control information, a device for determining vehicle control information, a vehicle, an electronic device, and a computer-readable storage medium. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for determining vehicle control information, characterized in that, The method includes: Acquire the first chassis signal sequence of the vehicle within a historical time period, and the first desired chassis signal value of the vehicle within the time period to be controlled; The first chassis signal sequence and the first desired chassis signal value are mapped to target control information for the vehicle at a target time within the time period to be controlled.

2. The method according to claim 1, characterized in that, The vehicle includes multiple chassis execution units. Acquiring the first chassis signal sequence of the vehicle within a historical time period, and the first desired chassis signal value of the vehicle within the time period to be controlled, includes: The first chassis signal sequence of the vehicle within a historical time period is obtained from the plurality of chassis execution units; In addition, the system acquires the first desired chassis signal value set for the plurality of chassis execution units during the control period.

3. The method according to any one of claims 1-2, characterized in that, The vehicle is equipped with a target end-to-end model. Mapping the first chassis signal sequence and the first desired chassis signal value to target control information for the vehicle within the target time period includes: The first chassis signal sequence and the first desired chassis signal value are input into the target end-to-end model to obtain the target control information; the target end-to-end model is used to map the chassis signal sequence and the desired chassis signal value into control information for the vehicle.

4. The method according to claim 3, characterized in that, The method further includes: Receive model training result parameters for the target end-to-end model sent by the cloud server; Based on the currently received model training result parameters, the target end-to-end model is deployed locally on the vehicle; or, based on the currently received model training result parameters, the target end-to-end model deployed locally on the vehicle is updated.

5. The method according to claim 4, characterized in that, The method further includes: The first chassis signal sequence and the first desired chassis signal value are used as training data and uploaded to the cloud server; the cloud server is used to generate the model training result parameters based on the training data and send them to the vehicle.

6. The method according to any one of claims 1-5, characterized in that, The vehicle includes multiple chassis actuators, and the method further includes: Based on the target control information, the multiple chassis actuators of the vehicle are controlled respectively.

7. A vehicle, characterized in that, The vehicle includes a chassis domain controller and multiple chassis execution units, wherein the chassis domain controller is used to perform the method for determining vehicle control information as described in any one of claims 1-6.

8. A device for determining vehicle control information, characterized in that, The device includes: The acquisition module is used to acquire the first chassis signal sequence of the vehicle within a historical time period, and the first desired chassis signal value of the vehicle within the time period to be controlled. The determination module is used to map the first chassis signal sequence and the first desired chassis signal value into target control information for the vehicle at a target time within the time period to be controlled.

9. An electronic device, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the method for determining vehicle control information as described in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, which, when executed by a processor, implements the method for determining vehicle control information as described in any one of claims 1 to 6.

Images