Control method and system for remotely driving vehicle

Abstract

The invention discloses a control method and system for a remote driving vehicle, and relates to the technical field of vehicle control. The method comprises the following steps: acquiring real-time state data of a vehicle; predicting the real-time state data by using a state prediction model to obtain predicted state data of the vehicle after a set time; generating a vehicle control instruction according to the predicted state data; and delay data of the wireless network are obtained in real time, and when the delay data reach a preset delay threshold value, the vehicle control instruction is executed. The state prediction model is used for predicting the state of the vehicle after a period of time in the future, the corresponding vehicle control instructions are generated, when the delay of the wireless network is too large, the vehicle control instructions are executed, and when the delay of the wireless network is reduced to the normal value, the remote driver continues to control the vehicle; it is ensured that the vehicle can safely and stably run under the extreme network condition, safety is high, and the application range is wide.

Description

Technical Field

[0001] The present application relates to the field of vehicle control technology, and in particular to a control method and system for a remotely driven vehicle. Background Art

[0002] Remote driving is a driving method based on wireless networks. The driver obtains the vehicle's status information in the remote control room. After the driver makes operations such as acceleration, deceleration, and steering based on the status information, the control instructions generated by the remote control room are transmitted to the vehicle through the wireless network to complete the real-time control of the vehicle. This driving method does not require the driver to be in the vehicle, so it has a good protective effect on the driver.

[0003] It can be seen from the working process of remote driving that remote driving is highly dependent on wireless networks. Only low-latency and high-bandwidth networks can make remote driving possible. Fortunately, the 5G network happens to have the advantages of low latency and high bandwidth, and after a period of development, the cost of using the 5G network has also been reduced. Applying the 5G network in remote driving can ensure the stability and safety of the vehicle. However, even if the 5G network is adopted, delays and packet loss are inevitable. When the delay of the 5G network increases due to base station failures, vehicles entering tunnels, etc., the remote driver cannot know the vehicle status in real time, and therefore cannot make correct driving operations in time. In order to solve this problem, the prior art proposes a variety of driving control methods. For example, CN118092406A proposes a remote driving method and remote control device based on an automatic driving system. The vehicle of this patent has a dual mode of remote driving and automatic driving, and will automatically switch to the automatic driving mode when the network connection status is abnormal. Although this patent solves the problem of vehicle control under high-latency networks to a certain extent, the cost of automatic driving technology is high, and there are still major safety issues at this stage. CN117908551A proposes a remote driving control method for a container truck, a remote control terminal, a container truck system and a medium. The patent triggers the early braking action by judging the time when the container truck drives to the preset working position. The early braking action executed in the patent is not related to the state of network delay. Automatic braking will be executed in any network delay state, and the applicable scenarios are limited. Summary of the invention

[0004] The embodiments of the present application provide a control method and system for a remotely driven vehicle to solve the problems in the prior art.

[0005] On the one hand, an embodiment of the present application provides a control method for a remotely driven vehicle, comprising: Get real-time status data of the vehicle; Use the state prediction model to predict the real-time state data and obtain the predicted state data of the vehicle after a set time; Analyze the predicted state data, generate corresponding vehicle control instructions according to driving requirements, and transmit the vehicle control instructions to the vehicle; The delay data of the wireless network is obtained in real time. When the delay data reaches the preset delay threshold, the vehicle executes the vehicle control command after the set time.

[0006] On the other hand, an embodiment of the present application further provides a control system for a remotely driven vehicle, comprising: A data acquisition module, used to acquire real-time status data of the vehicle; The state prediction module is used to predict the real-time state data using the state prediction model to obtain the predicted state data of the vehicle after a set time; An instruction generation module is used to analyze the predicted state data, generate corresponding vehicle control instructions according to driving requirements, and transmit the vehicle control instructions to the vehicle; The vehicle control module is used to obtain the delay data of the wireless network in real time. When the delay data reaches a preset delay threshold, the vehicle executes the vehicle control command after a set time.

[0007] A remote control method and system for a vehicle in the present application has the following advantages: The state prediction model is used to predict the state of the vehicle in the future and generate corresponding vehicle control instructions. When the delay of the wireless network is too large, these vehicle control instructions will be executed. When the delay of the wireless network is reduced to a normal value, the remote driver will continue to control the vehicle, ensuring that the vehicle can travel safely and stably even in extreme network conditions. It has high safety and a wide range of applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0009] Figure 1 A flowchart of a remote driving vehicle control method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0010] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0011] Figure 1 A flowchart of a remote driving vehicle control method provided in an embodiment of the present application. The present application embodiment provides a remote driving vehicle control method, the method comprising the following steps: S100, obtaining real-time status data of the vehicle.

[0012] Exemplarily, the vehicle in the embodiment of the present application can be any type of vehicle, including passenger cars, freight vehicles, etc., and there is no restriction on the driving form of the vehicle, and it can be driven by an internal combustion engine or an electric motor. Regardless of the type and driving form of the vehicle, it is necessary to set a plurality of sensors for collecting real-time status data on the vehicle. The above-mentioned real-time status data includes position, speed, acceleration and direction, etc., and these real-time status data are respectively collected by a positioning unit, a speed sensor, an acceleration sensor and an angle sensor, etc.

[0013] It should be understood that a communication unit also needs to be installed on the vehicle, which preferably uses a 5G communication unit. After each sensor collects real-time status data, the real-time status data will be transmitted through the communication unit.

[0014] S110, using the state prediction model to predict the real-time state data, to obtain the predicted state data of the vehicle after a set time.

[0015] For example, the state prediction model can be simply expressed as:

[0016] in, t Indicates the time, express t +1 moment prediction status data, f represents the state prediction function, express t Real-time status data at all times, express t The control input at the moment, express t The prediction error at time.

[0017] Specifically, the embodiment of the present application adopts Kalman filtering technology to predict real-time state data. After adopting Kalman filtering technology, the state prediction model is expressed as:

[0018] in, A represents the state transfer matrix, B represents the control matrix, prediction error Usually, Gaussian white noise with zero mean is used.

[0019] After establishing the above state prediction model, the Kalman gain is also used to correct the prediction error in the state prediction model. Specifically, the formula for error correction using the Kalman gain is expressed as:

[0020] in, Indicates the corrected t The prediction error at time express t Moment and t The covariance of the forecast error at time -1, H Represents the observation matrix, the superscript T represents transpose, R represents the observation noise covariance.

[0021] It should be understood that the above-mentioned predicted state data is a general term for state data obtained after predicting multiple real-time state data, which can be specifically expressed as state data after predicting one of the real-time state data such as position, speed, acceleration and direction.

[0022] After the prediction, the predicted state data of the vehicle after a set time, such as 5s or 10s, can be obtained based on the current real-time state data. It should be understood that the prediction of the vehicle state is continuous, and the frequency of predicting the real-time state data is determined according to the delay data. The prediction frequency is proportional to the delay data, that is, the higher the data transmission delay obtained by the communication unit, the higher the prediction frequency. When the delay data is 60ms or less, the state data is predicted at a frequency of once per second. When the delay data is between 60ms and 90ms, the prediction frequency is twice per second. When the delay data is between 90ms and 120ms, the prediction frequency is 4 times per second.

[0023] After the predicted state data is obtained, each predicted state data corresponds to time, so after multiple consecutive predictions, a time series of predicted state data arranged in chronological order is formed, and each state data will form a time series.

[0024] S120, analyzing the predicted state data, generating corresponding vehicle control instructions according to driving requirements, and transmitting the vehicle control instructions to the vehicle.

[0025] For example, after the predicted state data is obtained, it is necessary to analyze the predicted state data at each moment in the time series to determine which control method to adopt according to the actual situation of the predicted state data.

[0026] In the embodiment of the present application, the vehicle control command is determined based on the historical driving data. Specifically, the vehicle will generate a large amount of driving data under similar circumstances under the control of the remote driver, and these driving data are collectively referred to as historical driving data. These historical driving data not only include data such as the accelerator (electric throttle) pedal depression depth, brake pedal depression depth, gear position, steering angle, etc. generated by the remote driver through the remote cab, but also include the vehicle state data at the moment before the remote cab generates these data.

[0027] After the database established by the historical driving data is formed, once the predicted state data containing multiple data are obtained, the similarity between the predicted state data and the vehicle state data in the database will be calculated, and then the historical driving data corresponding to the vehicle state data with the highest similarity to the predicted state data in the database will be used as the predicted driving data. Specifically, the predicted state data and the vehicle state data are both data groups, and the number and type of state data contained therein are the same. When calculating the similarity, the difference between the corresponding state data in the data groups of the predicted state data and the vehicle state data can be calculated respectively, and the sum of the difference values ​​of multiple state data can be used as the basis for evaluating the similarity. The smaller the sum of the difference values, the higher the similarity.

[0028] After obtaining the predicted driving data, it is also necessary to compare it with the vehicle's current driving data to determine the values ​​for adjusting the vehicle's driving state, namely the depth of accelerator (electric accelerator) pedal adjustment, brake pedal adjustment depth, gear target value, steering angle adjustment amount, etc. Based on these adjustment data, corresponding vehicle control instructions can be generated.

[0029] S130, acquiring the delay data of the wireless network in real time, and when the delay data reaches a preset delay threshold, the vehicle executes the vehicle control instruction after a set time.

[0030] Exemplarily, the generated vehicle control instructions will be immediately transmitted to the vehicle, and the vehicle will save these vehicle control instructions in chronological order, and determine in real time whether the execution time of these vehicle control instructions has been reached. If it has been reached, it will determine whether the delay data of the wireless network has reached the preset delay threshold. If it has been reached, the vehicle control instructions will be executed according to the execution time set by the vehicle control instructions to ensure the safety and stability of the vehicle. If the current time has not reached the execution time, continue to wait until the current time reaches the execution time. If the delay data of the wireless network has not reached the preset delay threshold, the vehicle control instruction is deleted and the processing of the vehicle control instruction at the next moment continues.

[0031] In an embodiment of the present application, the preset delay threshold is set to 120ms or above. When the delay data of the wireless network reaches 120ms or above, it means that the delay of the wireless network is too large. At this time, it can be considered that the wireless network is already in an unavailable state, so the vehicle control instruction will be executed.

[0032] Furthermore, when the vehicle executes the vehicle control instruction, the vehicle control instruction is first decomposed into an execution signal for each actuator, and then the corresponding actuator is controlled according to the execution signal. The vehicle control instruction includes the adjustment amount for each driving data of the vehicle. Before executing the vehicle control instruction, it is necessary to generate an execution signal for the corresponding actuator according to the adjustment amount of each driving data, and then send the execution signal corresponding to each actuator to the corresponding actuator, so that the actuator makes adjustments under the control of the corresponding execution signal, so as to achieve the purpose of the vehicle being in the predicted driving state and predicted state data.

[0033] The present application also provides a remote control system for a vehicle, which includes the following functional modules: A data acquisition module, used to acquire real-time status data of the vehicle; The state prediction module is used to predict the real-time state data using the state prediction model to obtain the predicted state data of the vehicle after a set time; An instruction generation module is used to analyze the predicted state data, generate corresponding vehicle control instructions according to driving requirements, and transmit the vehicle control instructions to the vehicle; The vehicle control module is used to obtain the delay data of the wireless network in real time. When the delay data reaches a preset delay threshold, the vehicle executes the vehicle control command after a set time.

[0034] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0035] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A remote-controlled vehicle control method, characterized in that: The method comprises: Get real-time status data of the vehicle; Using a state prediction model to predict the real-time state data, to obtain predicted state data of the vehicle after a set time; Analyzing the predicted state data, generating corresponding vehicle control instructions according to driving requirements, and transmitting the vehicle control instructions to the vehicle; The delay data of the wireless network is acquired in real time, and when the delay data reaches a preset delay threshold, the vehicle executes the vehicle control instruction after the set time.

2. A remote-controlled vehicle control method according to claim 1, characterized in that: The state prediction model is established based on the Kalman filter model, and the state prediction model is expressed as: in, t Indicates the time, express t The predicted state data at time +1, A represents the state transfer matrix, express t The real-time status data at the moment, B represents the control matrix, express t The control input at the moment, express t The prediction error at time.

3. A remote-controlled vehicle control method according to claim 2, characterized in that: After the state prediction model is established, the Kalman gain is used to correct the prediction error in the state prediction model.

4. A remote-controlled vehicle control method according to claim 3, characterized in that: The error correction formula is expressed as: in, Indicates the corrected t The prediction error at time t, express t Moment and t The covariance of the prediction error at time -1, H Represents the observation matrix, the superscript T represents transpose, R represents the observation noise covariance.

5. A remote-controlled vehicle control method according to claim 1, characterized in that: The frequency of predicting the real-time status data is determined according to the delay data, and the prediction frequency is proportional to the delay data.

6. A remote-controlled vehicle control method according to claim 1, characterized in that: When the vehicle executes the vehicle control instruction, the vehicle control instruction is firstly decomposed into an execution signal for each actuator, and then the corresponding actuator is controlled according to the execution signal.

7. A system using a remote-controlled vehicle control method according to any one of claims 1 to 6, characterized in that: The system comprises: A data acquisition module, used to acquire real-time status data of the vehicle; A state prediction module, used to predict the real-time state data using a state prediction model to obtain predicted state data of the vehicle after a set time; An instruction generation module, used for analyzing the predicted state data, generating corresponding vehicle control instructions according to driving requirements, and transmitting the vehicle control instructions to the vehicle; The vehicle control module is used to obtain the delay data of the wireless network in real time. When the delay data reaches a preset delay threshold, the vehicle executes the vehicle control instruction after the set time.

Images