KR20230099753A - Intelligent vehicle control system and error detection method thereof - Google Patents

Abstract

An intelligent vehicle control system according to a preferred embodiment of the present invention includes a communication unit that receives an optimal speed profile, an optimal torque profile, and vehicle information, and a communication unit that learns the vehicle information and uses it to calculate the optimal speed profile and the optimal torque profile. It includes a learning unit that generates a neural network model, and a control unit that controls the vehicle according to the speed suggested by the optimum speed profile and the torque suggested by the optimum torque profile based on the vehicle information.

Description

Intelligent vehicle control system and its error detection method

The present invention relates to an intelligent vehicle control system and an error detection method thereof.

Cruise Control is a driving assistance system that maintains the vehicle's own set speed without the driver stepping on the accelerator pedal.

The most basic cruise control is to maintain constant speed at the speed set by the driver. Recently, an intelligent cruise control system has been developed that can optimize the synergistic effect of fuel economy and fuel economy by utilizing road information or V2X (Vehicle to Everything). It is becoming.

In addition, the intelligent cruise control system is divided into a cloud computing method in which the central server handles all the calculation load and an edge computing method in which the calculation load is allocated to individual vehicles.

The edge-computing intelligent cruise control system predicts wheel torque in individual vehicles through machine learning and creates a speed profile based on dynamic planning using road information and wheel torque predicted in the cloud.

In the case of such an intelligent cruise control system, vehicle driving control is performed using various information through many sensors for optimal control in terms of fuel economy and fuel economy.

In addition, the intelligent cruise control system has a very complex configuration as it uses a large number of information, and even if one sensor malfunctions, there is a risk that the overall control system will become unstable, leading to a major accident in a situation where the vehicle has control. can

However, there is a lack of research on maintenance of driving safety or fail-safe based on the malfunction of such a sensor.

Republic of Korea Patent No. 10-1824394

Accordingly, the present invention has been made in view of the above circumstances, and when an error occurs in vehicle information due to a malfunction of a vehicle sensor, an intelligent vehicle control system that detects a malfunction of a vehicle sensor and safely controls a vehicle, and an error thereof It aims to provide a detection method.

An intelligent vehicle control system according to a preferred embodiment of the present invention for achieving the above object includes a communication unit for receiving an optimal speed profile, an optimal torque profile, and vehicle information; a learning unit configured to learn the vehicle information and generate a neural network model used to calculate the optimum speed profile and the optimum torque profile; and a control unit configured to perform vehicle control according to the optimal speed profile based on the vehicle information, and to detect an error in the vehicle information based on the optimal torque profile and actual driving torque.

The vehicle information may include vehicle torque, vehicle speed, traffic information, and vehicle location information.

The control unit may check the optimum torque profile and the actual driving torque based on the vehicle location information when entering the tracking state of the optimum speed profile before performing the vehicle control.

The control unit may calculate an optimum torque change amount and an actual travel torque change amount by differentiating the optimum torque profile and the actual driving torque, respectively.

The controller may determine whether signs of the optimal torque change amount and the actual driving torque change amount are different from each other.

The control unit may determine that the vehicle location information is in an error condition, warn the cancellation of the estimation of the optimum speed profile, and stop the vehicle control when the signs of the optimal torque change amount and the actual driving torque change amount are different from each other. there is.

The control unit may calculate a difference value between the optimum torque profile and the actual vehicle torque when signs of the optimum torque change amount and the actual driving torque change amount are the same, and compare the calculated torque difference value with a preset reference torque. there is.

The control unit may calculate a moving average value for the torque difference value and compare the moving average value with the reference torque when the torque difference value is greater than or equal to the reference torque during a predetermined reference time period.

When the moving average value is greater than or equal to the reference torque, the control unit may determine that the vehicle location information is in an error state, warn the cancellation of the estimation of the optimum speed profile, and stop the vehicle control.

An error detection method of an intelligent vehicle control system according to a preferred embodiment of the present invention for achieving the above object is to calculate an optimal torque change amount and an actual driving torque change amount by differentiating an optimum torque profile and an actual driving torque, respectively, based on vehicle information. change amount calculation step; and a sign determination step of determining whether signs of the optimal torque change amount and the actual driving torque change amount are opposite to each other.

After the sign determination step, if the signs of the optimal torque change amount and the actual driving torque change amount are opposite to each other, a warning step of determining that the vehicle location information among the vehicle information is an error and warning release of following the optimum speed profile; may further include.

After the warning step, the method may further include a follow-up release step of stopping autonomous driving control of the vehicle by canceling the follow-up of the optimum speed profile.

After the sign-determining step, when signs of the optimal torque change amount and the actual driving torque change amount are the same, a difference value between the optimal torque profile and the actual driving torque is calculated, and the calculated torque difference value and the preset reference torque are calculated. A difference value determination step of comparing the; may further include.

After the difference value determining step, when the torque difference value is greater than or equal to the reference torque, an average value calculating step of calculating a moving average value for the torque difference value; may be further included.

After the average value calculation step, an average value determination step of comparing the moving average value and the reference torque; and a warning step of determining that vehicle location information among the vehicle information is erroneous and warning of releasing the optimum speed profile when the moving average value is greater than or equal to the reference torque after the average value determining step.

a speed following step of following the optimum speed profile and entering a speed following mode before the change amount calculation step; and a torque check step of checking the optimal torque profile and the actual driving torque based on vehicle location information among the vehicle information when entering the speed following mode.

An intelligent vehicle control system and an error detection method thereof according to a preferred embodiment of the present invention have an effect of safely controlling a vehicle by detecting an error in vehicle information through a comparison between an optimal torque profile and an actual vehicle torque.

In addition, there is an effect of detecting a malfunction of the intelligent cruise control using vehicle information of an existing control system without an additional sensor.

In addition, when a malfunction of the vehicle is detected, the cruise control is terminated through a control sequence to prevent unpleasant or dangerous driving to the driver.

1 is a block diagram of an intelligent vehicle control system according to a preferred embodiment of the present invention.
2 is a diagram showing an example of an optimal speed profile and an optimal torque profile.
3 is a diagram showing an example of a speed profile and a torque profile that are distorted due to errors in sensor information.
4 is a flowchart of an error detection method of an intelligent vehicle control system according to a preferred embodiment of the present invention.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. First, in adding reference numerals to components of each drawing, it should be noted that the same components have the same numerals as much as possible even if they are displayed on different drawings. In addition, although preferred embodiments of the present invention will be described below, the technical idea of the present invention is not limited or limited thereto and can be modified and implemented in various ways by those skilled in the art.

1 is a block diagram of an intelligent vehicle control system according to a preferred embodiment of the present invention.

Referring to FIG. 1 , the intelligent vehicle control system 100 according to a preferred embodiment of the present invention performs vehicle control at a speed suggested by an optimal speed profile based on vehicle location information, but errors may occur in vehicle information. In this case, vehicle control is performed at the wrong speed suggested by the optimum speed profile. In order to prevent this, the intelligent vehicle control system 100 is characterized by performing vehicle information error detection and step-by-step vehicle control.

The intelligent vehicle control system 100 according to a preferred embodiment of the present invention includes a communication unit 110, a learning unit 120, and a control unit 130.

The communication unit 110 may receive vehicle driving information and various sensor information. The sensor information may include vehicle location information obtained through a global position sensor (GPS). The communication unit 110 may transmit the neural network model learned by the learning unit 120 to the cloud server 200 . The communication unit 110 may receive an optimal speed profile and an optimal torque profile from the cloud server 200 . Here, the cloud server 200 may collect big data information related to vehicle driving, such as wheel torque, speed, and traffic information. The cloud server 200 may calculate an edge cost of the vehicle using a neural network model. The cloud server 200 may include an optimization unit 210 that calculates an optimal speed profile and an optimal torque profile based on big data information and edge cost.

The learning unit 120 may generate a neural network model by learning road load or wheel torque of the vehicle based on vehicle driving information. The learning unit 120 may transmit the neural network model to the cloud server 200 so that an optimal speed profile and an optimal torque profile can be calculated.

The controller 130 may receive vehicle driving information and sensor information, and perform vehicle control according to a speed suggested by an optimal speed profile based on vehicle location information. The controller 130 may control the vehicle at an incorrect speed when an error occurs in vehicle location information. In order to prevent this, the controller 130 may determine an error in vehicle information through a comparison between an optimal torque profile and an actual vehicle torque. When determining an error in vehicle information, the controller 130 may perform step-by-step vehicle control to prevent an accident while the vehicle is driving. The control unit 130's error determination of vehicle information and step-by-step vehicle control will be described later in detail.

2 is a diagram showing an example of an optimal speed profile and an optimal torque profile. 3 is a diagram showing an example of a speed profile and a torque profile that are distorted due to errors in sensor information.

Referring to FIGS. 1 to 3 , the cloud server 200 may calculate an optimal velocity profile and an optimal torque profile using a dynamic programming method and a neural network model to increase fuel efficiency and fuel economy. The vehicle may drive at the optimum speed by following the optimum speed profile. The optimal torque profile may appear as the optimal torque according to the vehicle position.

The controller 130 may determine the location of the vehicle using the vehicle location information and compare the optimum torque according to the location of the vehicle with the current vehicle driving torque. The controller 130 may detect an error in the vehicle location information according to the comparison result. Hereinafter, an error state of the vehicle position will be described as an example.

In one embodiment, the vehicle may be driving downhill after climbing a hill. In this case, the optimum speed profile may suggest constant speed driving when the vehicle is going uphill, and acceleration driving when the vehicle is going downhill. The optimum torque profile may suggest maximum torque when the vehicle starts climbing and minimum torque at the highest point of the vehicle.

In one embodiment, an error may occur in vehicle location information sensed by a vehicle location sensor in the actual vehicle location S1. The control unit 130 may determine the erroneous estimated location S2 due to an error in location information, not the actual vehicle location S1, as the current location of the vehicle. The control unit 130 uses the second speed V2 proposed by the optimal torque profile based on the error-estimated position S2 instead of the first speed V1 suggested by the optimal torque profile based on the actual vehicle position S1. We want to control the speed of the vehicle using In addition, the control unit 130 outputs the second torque T1 distorted due to the position error instead of the first torque T1 suggested by the optimum torque profile based on the actual vehicle position S1. The vehicle rapidly accelerates to follow the second speed V2 and the second torque T2 while climbing a hill at a constant speed. At this time, the driver of the vehicle may feel fear in a state in which there is no right to control the driving of the vehicle.

The controller 130 may calculate an optimal torque change amount and an actual driving torque change amount by performing differentiation on each of the optimum torque profile and the actual driving torque in order to detect an error in the positional information. The controller 130 may determine that the vehicle location information is erroneous based on a situation in which signs of the optimal torque change amount and the actual driving torque change amount are opposite.

Specifically, the control unit 130 checks whether the directions (negative or positive directions) of the optimal torque change amount and the actual driving torque change amount are different from each other in the same vehicle position through differentiation between the optimum torque profile and the actual driving torque.

When a situation occurs in which the direction of the optimal torque change and the actual driving torque change occur, the control unit 130 determines that the vehicle position sensor is in error, warns the release of the optimum speed profile, and stops autonomous driving control of the vehicle. can

Also, when the directions of the optimum torque change amount and the actual driving torque change amount are the same, the controller 130 calculates a difference value between the optimum torque profile and the actual vehicle torque and compares the torque difference value with a preset reference torque. When the torque difference value as a result of the comparison is equal to or greater than the reference torque, the control unit 130 may check whether this situation continues for a predetermined reference time or longer. When the controller 130 checks the case where the torque difference value is equal to or greater than the reference torque for a reference period of time or more, it may be determined that the vehicle position sensor is in an error state. The control unit 130 may calculate a moving average value for the torque difference value from the time point when the torque difference value exceeds the reference torque.

Calculation of the moving average value may be expressed as in Equation 1 below.

<Equation 1>

In Equation 1, P represents the torque difference between the optimal torque profile and the actual driving torque, M represents the number of times the moving average value is calculated, and n represents a second unit.

When the moving average value is equal to or greater than the reference torque, the control unit 130 may determine that the vehicle position sensor is in an error state, cancel the follow-up of the optimum speed profile, and stop autonomous driving control of the vehicle. Through this, accidents of autonomous vehicles due to incorrect information can be prevented.

4 is a flowchart of an error detection method of an intelligent vehicle control system according to a preferred embodiment of the present invention.

Referring to FIG. 4 , an error detection method of an intelligent vehicle control system according to a preferred embodiment of the present invention detects an error in vehicle location information during vehicle driving control according to an optimal speed profile and performs step-by-step vehicle control according to the detection result. characterized by carrying out

An error detection method of an intelligent vehicle control system according to a preferred embodiment of the present invention includes a speed tracking step (S410), a torque check step (S420), a change amount calculation step (S430), a code determination step (S440), and a difference value determination step. (S450), an average value calculation step (460), an average value determination step (S470), a warning step (S480), and a follow-up release step (S490) may be included.

In the speed following step (S410), the control unit 130 follows the optimum speed profile and enters the following mode. An optimal speed profile may be calculated by the cloud server 200 .

In the torque checking step (S420), the control unit 130 checks the current vehicle location information, and checks the optimal torque profile and actual driving torque at the current vehicle location. An optimal torque profile may be calculated by the cloud server 200 . Actual driving torque may be obtained from a vehicle torque sensor.

In the variation calculation step ( S430 ), the control unit 130 calculates the variation of each of the optimal torque profile and the actual driving torque. That is, the control unit 130 may calculate the optimum torque change amount and the actual travel torque change amount by performing differentiation on each of the optimum torque profile and the actual driving torque.

In the sign determination step S440, the control unit 130 determines whether signs of the optimal torque change amount and the actual driving torque change amount are opposite to each other.

In the step of determining the difference value (S450), the control unit 130 calculates the difference between the optimum torque profile and the actual driving torque when the signs of the optimal torque change and the actual driving torque change are the same, and calculates the difference between the calculated torque difference and the Compare the set reference torque. The reference torque may be approximately 10% of the optimal torque profile.

In the average value calculation step 460, the control unit 130 may determine whether this situation lasts longer than a predetermined reference time when the torque difference value as a result of the comparison is greater than or equal to the reference torque. The reference time may be appropriately set according to the needs of the user. When the controller 130 confirms that the torque difference value is equal to or greater than the reference torque for a predetermined reference time or longer, the controller 130 may calculate a moving average value for the torque difference value from the time point when the torque difference value exceeds the reference torque.

In the average value determination step (S470), the controller 130 may compare the moving average value with the reference torque.

In the warning step (S480), the control unit 130 may determine that the vehicle location information is in an error state when signs of the optimal torque change amount and the actual driving torque change amount are different from each other. In addition, the controller 130 may determine that the vehicle position sensor is in an error state when the moving average value is greater than or equal to the reference torque. If it is determined that the vehicle position sensor is in an error state, the control unit 130 may warn the user of canceling the follow-up of the optimum speed profile through a separate output device (eg, audio, instrument panel, etc.). Through this, the user may check in advance a situation in which autonomous driving of the vehicle is stopped.

In the following releasing step (S490), the control unit 130 cancels the following of the optimum speed profile and stops the control of the autonomous driving (cruise function) of the vehicle. Through this, autonomous driving of a vehicle that provides a user with an unpleasant and dangerous situation may be prevented.

The above description is merely an example of the technical idea of the present invention, and those skilled in the art can make various modifications, changes, and substitutions without departing from the essential characteristics of the present invention. will be. Therefore, the embodiments disclosed in the present invention and the accompanying drawings are not intended to limit the technical idea of the present invention, but to explain, and the scope of the technical idea of the present invention is not limited by these embodiments and the accompanying drawings. .

Steps and/or actions in accordance with the present invention may occur concurrently in different embodiments, in different orders, or in parallel, or for different epochs, etc., as would be understood by one skilled in the art. can

In some embodiments, some or all of the steps and/or actions may include instructions, programs, interactive data structures, clients and/or servers stored on one or more non-transitory computer-readable media. At least some of them may be implemented or performed using one or more processors that do. The one or more non-transitory computer-readable media may illustratively be software, firmware, hardware, and/or any combination thereof. Additionally, the functions of a “module” discussed herein may be implemented in software, firmware, hardware, and/or any combination thereof.

100: intelligent vehicle control system
110: communication department
120: learning unit
130: control unit

Claims (16)

a communication unit that receives an optimal speed profile, an optimal torque profile, and vehicle information;
a learning unit configured to learn the vehicle information and generate a neural network model used to calculate the optimum speed profile and the optimum torque profile; and
a controller configured to perform vehicle control according to the optimum speed profile based on the vehicle information, and to detect an error in the vehicle information based on the optimum torque profile and actual driving torque;
Intelligent vehicle control system comprising a. According to claim 1,
The vehicle information,
An intelligent vehicle control system comprising vehicle torque, vehicle speed, traffic information, and vehicle location information. According to claim 2,
The control unit,
The intelligent vehicle control system, characterized in that for checking the optimum torque profile and the actual driving torque based on the vehicle location information when entering the following state of the optimum speed profile before performing the vehicle control. According to claim 3,
The control unit,
The intelligent vehicle control system according to claim 1 , wherein an optimum torque change amount and an actual travel torque change amount are calculated by differentiating the optimum torque profile and the actual driving torque, respectively. According to claim 4,
The control unit,
The intelligent vehicle control system, characterized in that for determining whether the sign of the optimal torque change amount and the actual driving torque change amount are different from each other. According to claim 5,
The control unit,
Intelligent characterized in that when the signs of the optimal torque change amount and the actual driving torque change amount are different from each other, it is determined that the vehicle location information is in an error situation, the estimation cancellation of the optimum speed profile is warned, and the vehicle control is stopped. vehicle control system. According to claim 5,
The control unit,
When the signs of the optimal torque change amount and the actual driving torque change amount are the same, a difference value between the optimum torque profile and the actual vehicle torque is calculated, and the calculated torque difference value is compared with a preset reference torque. Characterized in that Intelligent vehicle control system. According to claim 7,
The control unit,
When the torque difference value is greater than or equal to the reference torque during a predetermined reference time, a moving average value for the torque difference value is calculated, and the moving average value is compared with the reference torque. According to claim 8,
The control unit,
When the moving average value is equal to or greater than the reference torque, it is determined that the vehicle location information is in an error state, the estimation release of the optimum speed profile is warned, and the vehicle control is stopped. a variation calculation step of calculating an optimum torque variation and an actual driving torque variation by differentiating the optimum torque profile and the actual driving torque based on the vehicle information; and
a sign determination step of determining whether signs of the optimal torque change amount and the actual driving torque change amount are opposite to each other;
Error detection method of an intelligent vehicle control system comprising a. According to claim 10,
After the sign determination step, if the signs of the optimal torque change amount and the actual driving torque change amount are opposite to each other, a warning step of determining that the vehicle location information among the vehicle information is an error and warning release of following the optimum speed profile;
Error detection method of the intelligent vehicle control system, characterized in that it further comprises. According to claim 11,
After the warning step, a follow-up release step of stopping autonomous driving control of the vehicle by releasing the follow-up of the optimum speed profile;
Error detection method of the intelligent vehicle control system, characterized in that it further comprises. According to claim 10,
After the sign determination step, when signs of the optimal torque change amount and the actual driving torque change amount are the same, a difference value between the optimal torque profile and the actual driving torque is calculated, and the calculated torque difference value and the preset reference torque are calculated. Difference value determination step of comparing ;
Error detection method of the intelligent vehicle control system, characterized in that it further comprises. According to claim 13,
an average value calculation step of calculating a moving average value for the torque difference value when the torque difference value is greater than or equal to the reference torque after the difference value determining step;
Error detection method of the intelligent vehicle control system, characterized in that it further comprises. 15. The method of claim 14,
After the average value calculation step, an average value determination step of comparing the moving average value and the reference torque; and a warning step of determining that the vehicle location information among the vehicle information is an error and warning release of following of the optimum speed profile when the moving average value is greater than or equal to the reference torque after the average value determination step.
Error detection method of the intelligent vehicle control system, characterized in that it further comprises. According to claim 10,
a speed following step of following the optimum speed profile and entering a speed following mode before the change amount calculation step; and
a torque checking step of checking the optimal torque profile and the actual driving torque based on vehicle location information among the vehicle information when entering the speed following mode;
Error detection method of the intelligent vehicle control system, characterized in that it further comprises.

Images