CN111409632A - Vehicle control method and device, computer equipment and storage medium - Google Patents

Abstract

A vehicle control method, a vehicle control apparatus, a computer device, and a computer storage medium, the method of one embodiment comprising: acquiring a real-time position of a vehicle; generating a path planning reference line according to the real-time position; determining a real-time offset value between the real-time position and the path planning reference line; and determining a control quantity according to the real-time deviation value, and determining a steering angle of a steering wheel according to the control quantity. According to the scheme, the vehicle can be kept on the path planning reference line, the vehicle control precision is effectively improved, the problem that the vehicle deviates from a lane is avoided, and the vehicle running safety is improved.

Description

Vehicle control method and device, computer equipment and storage medium

technical field

The present application relates to the technical field of intelligent driving, and in particular, to a vehicle control method, a vehicle control device, a computer device and a computer storage medium.

Background technique

When the unmanned vehicle is driving on the road, the intelligent control modules on the vehicle will perceive the road environment through the on-board sensing system, and plan a driving path that exceeds the safe driving distance based on the real-time road environment for automatic driving of the vehicle. However, in the process of automatic driving of the vehicle, due to factors such as control errors and execution module errors, the vehicle will not completely follow the planned road trajectory, and may deviate from the planned driving lane to a certain extent, especially when the vehicle is running at high speed. The impact will be very obvious, which will bring safety hazards to itself and vehicles driving in other lanes.

SUMMARY OF THE INVENTION

Based on this, it is necessary to provide a vehicle control method, a vehicle control device, a computer device and a computer storage medium.

A vehicle control method, the method comprising:

Get the real-time location of the vehicle;

generating a path planning reference line according to the real-time position;

determining a real-time offset value between the real-time position and the path planning reference line;

A control amount is determined according to the real-time offset value, and a steering wheel steering angle is determined according to the control amount.

A vehicle control device comprising:

The location acquisition module is used to acquire the real-time location of the vehicle;

a reference line planning module, configured to generate a path planning reference line according to the real-time position;

an offset value determination module, configured to determine a real-time offset value between the real-time position and the path planning reference line;

A control amount determination module, configured to determine a control amount according to the real-time offset value, and determine a steering wheel steering angle according to the control amount.

A computer device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the steps of the above method are implemented.

A computer-readable storage medium having a computer program stored thereon, the computer program, when executed by a processor, implements the steps of the method as described above.

The vehicle control method, vehicle control device, computer equipment and computer storage medium in the above-mentioned embodiments, after obtaining the real-time position of the vehicle, generating a path planning reference line based on the real-time position, and determining the real-time position and the path planning reference line The real-time offset value between the two, and the control amount is calculated based on the real-time offset value, and the steering angle of the steering wheel is determined accordingly, so that the steering angle of the steering wheel can be set based on the generated path planning reference line. The control of the vehicle enables the vehicle to remain on the path planning reference line, which effectively improves the accuracy of the vehicle control, avoids the problem of the vehicle deviating from the lane, and improves the safety of the vehicle.

Description of drawings

FIG. 1 is a schematic flowchart of a vehicle control method in one embodiment;

FIG. 2 is a schematic diagram of a state in which a vehicle is traveling in a lane in one embodiment;

3 is a schematic diagram of a state in which a vehicle is traveling in a lane in another embodiment;

4 is a schematic diagram of the principle of determining a lateral control amount in one embodiment;

5 is a schematic diagram of the principle of determining a control amount in one embodiment;

Fig. 6 is the principle schematic diagram of determining the steering wheel steering angle in one embodiment;

7 is a schematic diagram of a module structure of a vehicle control device in one embodiment;

FIG. 8 is a diagram of the internal structure of a computer device in one embodiment.

Detailed ways

In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application will be described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application.

Referring to FIG. 1 , a vehicle control method in one embodiment, the method may be executed by a device for vehicle control, or by a device for providing control parameters for the device under vehicle control, including steps S101 to S104 .

Step S101: Obtain the real-time position of the vehicle.

In one embodiment, the real-time position of the vehicle may be obtained in any possible manner, such as GPS positioning, GPS positioning combined with satellite positioning, and the like.

In one embodiment, after the real-time position of the vehicle is obtained, a body coordinate system may also be established based on the real-time position and the head direction of the vehicle, and a relative map is generated based on the body coordinate system. Among them, when establishing the body coordinate system, the center of the rear axle of the vehicle can be used as the origin of the coordinate system, the front-facing direction of the vehicle is the positive direction of the first coordinate axis, and the direction of the front-facing direction after rotating 90 degrees counterclockwise/clockwise is the first coordinate system. The positive direction of the two coordinate axes. After the relative map is generated, the above-mentioned real-time position is projected onto the relative map, so as to obtain the relative position of the vehicle on the relative map.

Step S102: Generate a path planning reference line according to the real-time position.

In one embodiment, the path planning reference line may be a lane centerline. Accordingly, the path planning reference line can be generated in various possible ways.

For example, in one of the methods, when generating the path planning reference line according to the real-time position, the following methods can be used: acquiring surrounding environment information, and extracting lane line information from the surrounding environment information; and then according to the real-time position and the lane line information to generate the path planning reference line. In one embodiment, the surrounding environment information may include information obtained by shooting with an in-vehicle camera. When the driving environment of the vehicle is located in a road environment where lane lines are drawn, the information obtained by shooting with the in-vehicle camera will include lane line information, thereby The lane line information can be extracted from information (eg, images) captured by the vehicle-mounted camera device. The manner of extracting the lane line from the image may be performed in any possible manner, which is not specifically limited in this embodiment of the present application.

In another way, when generating the path planning reference line according to the real-time position, the following methods may be adopted: obtaining the lane line information of the lane where the real-time position is located from the map data according to the real-time position; The real-time position and the lane line information are used to generate the path planning reference line. At this time, when the map data includes lane line information of each lane, the position information of each lane line information and the real-time position can be combined to determine the lane line information of the lane where the real-time position is located.

In another way, when generating the path planning reference line according to the real-time position, it can be done in the following way: according to the driving path determined based on the departure and destination of the vehicle, determine the lane line, and combine the real-time position and the determined driving path. Lane lines generate route planning guides. At this time, based on the driving path, it is possible to plan which road sections the vehicle needs to travel on, and even which lane of the road section to drive on, so that the lane line can be determined based on the driving path, and then combined with the real-time position and lane line. Generate route planning guides. The path planning reference line may be generated by combining the lane lines corresponding to the travel path of a certain length starting from the real-time position. The specific way of determining the travel path based on the departure place and destination of the vehicle and determining the lane line based on the formal path can be performed in any possible way, which is not specifically limited in this embodiment.

Wherein, when generating the path planning reference line according to the real-time position and the lane line information, any possible manner may be used. In one embodiment, the vehicle may be projected onto the two nearest lane lines (that is, the lane lines determined above), the two lane line projection points may be obtained, and the midpoint of the two lane line projection points may be determined, and then connected. Each midpoint forms the path planning reference line. That is, each point in the path planning reference line is the midpoint of the point on the projection points of the two lane lines, wherein the projection points of the two lane lines are the intersections of the tangent vertical line of the point and the two lane lines, The tangent vertical line is the line perpendicular to the tangent of the point on the path planning reference line.

Wherein, in the above process, when the relative map is generated above, after the lane line information is extracted, the lane line information can also be projected onto the relative map to obtain the relative lane line information of the lane line on the relative map . Subsequent processing such as generating path planning reference lines can be performed on the relative map based on relative lane line information.

In another way, when generating the path planning reference line according to the real-time position, the following methods may be adopted: determining the road segment identifier corresponding to the real-time location based on the real-time location; obtaining the road segment identifier corresponding to the road segment identifier. road segment centerline; generating the route planning reference line based on the real-time position and the road segment centerline. Therefore, in a road segment or area without a lane line drawn, or an unusable area where the lane line is damaged or blocked, the road segment centerline of the road segment in the area can be pre-recorded. During recording, the vehicle can be controlled to drive on the road section in the relevant area, and during the driving process, the vehicle location information can be collected and recorded in real time, and the center line of the road segment can be generated based on the recorded vehicle location information. It can be understood that, in order to improve the accuracy of the recorded road segment centerline, the road segment centerline can be generated by combining the results of multiple recordings, and certain error correction processing can be performed, which will not be repeated here.

Based on the pre-recorded centerline of each road segment, when the vehicle is driving, combined with the real-time position of the vehicle and the geographic location of each road segment, the road segment where the vehicle is located can be determined. The road segment where the vehicle is located is recorded as the center of the corresponding road segment. When a road segment of the line is selected, the road segment centerline corresponding to the road segment identifier of the road segment is obtained, and the path planning reference line is generated based on the real-time position and the road segment centerline. Among them, since the centerline of the road segment can be regarded as the centerline of the lane when it is recorded, when the centerline of the route planning is generated, the centerline of the road segment with a certain length from the real-time position can be used as the path reference. Wire. In one embodiment, after the path planning reference line is generated, two lane lines may be generated based on the generated path planning reference line. The real-time position of the vehicle is in the position area between the two lane lines, and the above-mentioned center line of the road segment is the lane center line of the two lane lines. The manner of generating two lane lines based on the path planning reference line may be performed in any possible manner, which is not specifically limited in this embodiment of the present application.

Wherein, in the above process, when the relative map is generated above, after the centerline of the road segment is obtained, the centerline of the road segment can also be projected onto the relative map to obtain the relative road segment centerline of the centerline of the road segment on the relative map information. Subsequent processing such as generating path planning reference lines, generating lane lines, etc., may be performed on a relative map based on relative road segment centerline information.

After the path planning reference line is generated according to the real-time position, the generated path planning reference line can be further filtered and smoothed, so as to remove the signal distortion caused by the interference of sensors and positioning modules, and ensure the obtained real-time reference line. smoothness. When filtering and smoothing, any smoothing algorithm may be used, such as a five-point cubic smoothing algorithm or a point-by-point filtering algorithm, which is not specifically limited in this embodiment of the present application.

Step S103: Determine a real-time offset value between the real-time position and the path planning reference line.

In one embodiment, when determining the real-time position and the path planning reference line, the following methods may be used.

First, determine the reference point to project the real-time position onto the routing guideline. Specifically, after determining the projection point for projecting the real-time position to the path planning reference line, the point in the path planning reference line that is closest to the projection point is determined as the reference point.

Secondly, the distance between the real-time position and the reference point is determined as the real-time offset value between the real-time position and the path planning reference line.

Step S104: Determine a control amount according to the real-time offset value, and determine a steering wheel steering angle according to the control amount.

Wherein, when the control amount is determined according to the real-time offset value, various possible ways can be adopted. The control amount in the embodiment of the present application may only include the control amount for lateral control (referred to as the lateral control amount in the embodiment of the present application), or may include the control amount determined based on the curvature (referred to as the curvature control in the embodiment of the present application). quantity).

In one embodiment, only lateral control quantities may be included. At this time, when the control amount is determined according to the real-time offset value, the method may include: determining a lateral control amount according to the real-time offset value, where the control amount includes the lateral control amount.

Wherein, in an example, when determining the lateral control amount according to the real-time offset value, the above-obtained real-time offset value may be directly used as the reference deviation value, and then the lateral control amount is determined according to the reference deviation value. In some examples, the reference deviation value may be directly used as the lateral control amount.

In another example, when determining the lateral control amount according to the real-time offset value, it may be after obtaining the offset value corresponding to the previous vehicle control (referred to as the historical offset value in this embodiment of the present application), and then determining the real-time offset value. The difference between the offset value and the historical offset value (referred to as the first difference in the embodiment of this application), that is, the value obtained by subtracting the historical offset value from the real-time offset value, and then based on the above real-time offset value. The shift value and the first difference determine the reference deviation value, and determine the lateral control amount according to the reference deviation value. In some examples, the reference deviation value may be directly used as the lateral control amount. In some embodiments, when the first difference value is less than or equal to 0, it means that the last lateral control can achieve the control effect. Therefore, the above real-time offset value can be directly used as the reference offset value; when the first difference value is greater than 0 , it means that the effect of the last lateral control is not good, so the sum of the real-time offset value and the difference value can be used as the reference offset value.

In another example, when determining the lateral control amount according to the real-time offset value, the above-mentioned real-time offset value may be compared with the error tolerance range, and when the real-time offset value is outside the above-mentioned error tolerance range, the real-time offset value is calculated. The difference between the shift value and the allowable error range (referred to as the second difference in the embodiment of the present application) is used as the reference deviation value, and the lateral control amount is determined according to the reference deviation value. In some examples, the reference deviation value may be directly used as the lateral control amount. In some embodiments, when the second difference is within the allowable range of the error, the lateral control amount may be directly set to 0, or the lateral control amount determined last time may be determined as the lateral control amount currently being controlled. .

In another example, when determining the lateral control amount according to the real-time offset value, it may be after obtaining the offset value corresponding to the previous vehicle control (referred to as the historical offset value in this embodiment of the present application), and then determining the real-time offset value. The difference between the offset value and the historical offset value (referred to as the first difference in the embodiment of this application), that is, the value obtained by subtracting the historical offset value from the real-time offset value, and based on the real-time offset value The value and the first difference determine a pending reference offset value. Then compare the undetermined reference deviation value with the allowable error range, and when the undetermined reference deviation value is outside the allowable error range, calculate the difference between the undetermined reference deviation value and the allowable error range (referred to as the third difference in the embodiment of this application). value), take the third difference value as a reference deviation value, and determine the lateral control amount according to the reference deviation value. In some embodiments, when the first difference value is less than or equal to 0, the real-time offset value is used as the undetermined reference offset value; when the first difference value is greater than 0, the sum of the real-time offset value and the difference value is used. , as the undetermined reference deviation value. In some embodiments, when the undetermined reference deviation value is within the allowable error range, the lateral control amount may be directly set to 0, or the lateral control amount determined last time may be determined as the lateral control amount currently being controlled.

In one embodiment, the above-mentioned control quantities may include lateral control quantities and curvature control quantities. At this time, the embodiment of the present application may further include the steps of: determining a reference point for projecting the real-time position onto the path planning reference line, and determining the curvature of the reference point on the path planning reference line; calculating a curvature control amount according to the curvature. The method of determining the reference point may be the same as the above-mentioned method of determining the reference point, that is, after determining the projection point for projecting the real-time position to the path planning reference line, the point in the path planning reference line with the closest distance to the projection point is determined as the reference point. In some embodiments, when the curvature control amount is calculated according to the curvature, when the curvature is greater than or equal to the curvature threshold, the curvature control amount is calculated according to the curvature threshold, and when the curvature is less than or equal to the curvature threshold, the curvature control amount is directly set to zero. That is, in this case, the control amount may be determined directly based on the lateral control amount.

At this time, when the control amount is determined according to the real-time offset value, the method may include: determining the lateral control amount according to the real-time offset value; and determining the control amount according to the curvature control amount and the lateral control amount.

In some embodiments, when determining the steering wheel steering angle according to the control amount, the following methods may be used, which may specifically include: determining the steering wheel steering angle to be determined according to the control amount; obtaining the current vehicle speed, and determining the steering angle safety range according to the current vehicle speed; The comparative relationship between the steering angle of the steering wheel to be determined and the safe range of the steering angle is used to determine the steering angle of the steering wheel.

Wherein, when determining the steering angle of the steering wheel based on the comparison relationship between the undetermined steering wheel steering angle and the steering angle safety range, it may include: when the undetermined steering wheel steering angle exceeds the steering angle safety range, determining the maximum value of the steering wheel steering angle safety range as Steering wheel steering angle; when the pending steering wheel steering angle is within the steering angle safety range, the pending steering wheel steering angle is determined as the steering wheel steering angle.

In some embodiments, after the path planning reference line and the real-time offset value are determined, the vehicle travel planning path may also be generated according to the real-time offset value and the path planning reference line. Wherein, in some embodiments, the vehicle travel planning path may be a curve line segment of a predetermined length starting from the real-time position on the path planning reference line. On the other hand, during the driving process, the generated planned driving path of the vehicle may also be adjusted according to the above-mentioned control amount.

In some embodiments, it may further include: acquiring surrounding environment information, and extracting obstacle information from the surrounding environment information, where the acquired obstacle information may include: obstacle position, obstacle size, and obstacle moving speed ; and adjust the above-mentioned vehicle driving planning path according to the obstacle information.

Wherein, when adjusting the planned driving path of the vehicle according to the obstacle information, when the obstacle is at the edge of the lane of the lane where the real-time position is located, the position of the planned driving path of the vehicle is adjusted in the lane to ensure that the vehicle is connected to the obstacle. When the obstacle is located in front of the vehicle's planned path, and the distance between the obstacle and the vehicle is less than the distance threshold, shorten the length of the vehicle's planned path to a second length, where the second length is less than the above-mentioned predetermined length, The second length may be the length of the distance from the real-time location to the obstacle.

It can be understood that, in the case of establishing the relative map above, the subsequent processing procedure described above may be performed after the obstacle information is converted into the obstacle coordinate information in the relative map.

Based on the above-mentioned embodiments, the following description is given in conjunction with a specific application example. In some application embodiments, the solutions of the embodiments of the present application may be applied to a vehicle control process of an unmanned vehicle.

In the solution of the embodiment of the present application, in the process of controlling the vehicle, a coordinate system is established based on the real-time body position of the vehicle and a relative map is generated in real time. When the relative map is generated in real time, it can be generated based on the current position of the vehicle and the head direction , among which, the center of the rear axle of the vehicle is the origin of the coordinate system, the front-facing direction of the vehicle is the positive direction of the first coordinate axis (such as the x-axis), and the front-facing direction is the direction after rotating 90 degrees counterclockwise/clockwise, such as the front of the vehicle The left side of the opposite direction is the positive direction of the second coordinate axis (such as the y-axis).

During the implementation of the solutions of the embodiments of the present application, the perception module of the vehicle itself detects and provides information about the surrounding environment of the vehicle in real time. The perception module may include cameras, lidars, etc. The obstacle information, lane line information obtained by the camera device, etc. On the other hand, during the driving process of the vehicle, a path planning reference line (also called a real-time reference line) is generated in real time. Reference for lateral controls. The generated path planning reference line, in addition to the information of the coordinates (x, y) of the path planning reference line, can also include the curvature of the path planning reference line. In the case where a relative map is generated based on the vehicle body position, the curvature can refer to the path The curvature of the planning reference line relative to the body position coordinate system.

When generating the real-time reference line in real time, in some embodiments, after obtaining the lane line information, a real-time reference line may be generated in combination with the lane line information, and the real-time reference line is located in the middle of the lane line. The lane line information of the lane can be extracted from the image captured by the camera device. The camera device needs to collect lane line information that is not less than a predetermined length according to the vehicle position. When generating the real-time reference line based on this, after determining the two lane line projection points for projecting the vehicle on the left and right lane lines, the data point located in the middle of the lane line is calculated according to the coordinate values of the two lane line projection points, And a real-time reference line not less than a predetermined length is sequentially generated according to the data point. The specific value of the predetermined length can be determined in combination with technical requirements, for example, it can be set to 200 meters.

In some embodiments, the lane line information of the lane where the real-time position is located may be extracted from the map data based on the real-time position of the vehicle, and the real-time reference line is located in the middle of the lane line. For example, a real-time reference line is generated by combining the travel path between the origin and destination of the vehicle. Based on the formal path between the departure point and the destination, combined with the real-time position of the vehicle, based on the driving path between the real-time position and the destination, select a driving path, and segment according to the selected driving path, and the generated length is not less than predetermined Live guide for length.

In the case of generating a relative map, a real-time real-time reference line on the relative map and lane lines on the relative map can be generated in combination with the above-mentioned relative map, and the obstacle information obtained by detection can also be converted into relative coordinates on the relative map. location information and display it on a relative map.

In some embodiments, the path planning reference line may also be produced offline, and the path planning reference line that matches the real-time position of the vehicle is used as the path planning reference line generated above. Therefore, in some specific scenarios, such as mining areas, docks, etc., there are generally no obvious lane lines in these scenarios, and the reference line can be recorded by the vehicle driving one or more times in advance. During the specific recording, the vehicle position information output by the vehicle's positioning module can be collected in real time while the vehicle is driving, and a path planning reference line can be generated according to the collected vehicle position information. Corresponding to the identification of the identification area. When the offline recorded reference line is used as the real-time reference line, two lane lines can be generated equidistantly on both sides of the real-time reference line. In this case, there may be some differences between the generated two lane lines and the actual driving lane of the vehicle. , or the actual driving environment of the vehicle does not have lane lines drawn, so it can be preferably applied to the relevant areas where the lane lines are not obvious or where no lane lines are drawn.

After the real-time reference line is generated, the generated real-time reference line can be further filtered to remove signal distortion caused by interference of sensors and positioning modules, and the smoothness of the obtained real-time reference line can be ensured. The specific filtering process can be performed in any possible manner, such as a five-point cubic smoothing algorithm or a point-by-point filtering algorithm.

During vehicle driving, based on the generated path planning reference line, a vehicle driving planning path ahead of a certain distance is generated. The vehicle driving planning path may be a curved line segment of a predetermined length in front of the vehicle starting from the real-time position of the vehicle. The predetermined length may be the same as the length of the above-mentioned path planning reference line, for example, both are 200 meters. In general, when the vehicle is in an ideal state of lane keeping during driving, the planning path of the vehicle is located on the path planning reference line, as shown in Figure 2. At this time, the vehicle is driving in the middle of the lane, which is an ideal state for lane keeping during the vehicle driving process. The real-time offset value between the vehicle and the real-time reference line is 0, and there is no need to adjust the lateral position of the vehicle.

On the other hand, when the surrounding environment information provided by the perception module of the vehicle includes information on obstacles on the lane, such as a moving vehicle, the planned path of the vehicle needs to be adjusted according to the position, size, and speed of the provided obstacles. For example, when the obstacle is on the edge of the lane, adjust the position of the vehicle's planned path in the lane to ensure a safe distance between the vehicle and the obstacle. When the obstacle is located in front of the planned route of the vehicle, and the distance between the obstacle and the vehicle is less than the distance threshold (for example, the above-mentioned predetermined length), the length of the planned route of the vehicle is shortened to a second length, and the second length may be for the vehicle. The length of the distance from the real-time position to the obstacle.

In another embodiment, a schematic diagram of the state of the vehicle running in the lane is shown in Figure 3. At this time, the vehicle has a certain offset value to the left in the figure. At this time, it is necessary to control based on the offset value to avoid Keep the vehicle in the lane.

In the process of vehicle control, after the real-time position of the vehicle is obtained, in the case of generating a relative map, the real-time position is converted to the relative map to obtain the relative position of the vehicle, and then the relative position of the vehicle is projected to the above-mentioned real-time reference line, According to this, the real-time offset value between the vehicle and the real-time reference line is calculated, and based on the real-time offset value, the lateral control amount is calculated to adjust the lateral position of the vehicle, and the vehicle lane keeping function is realized. , the curvature control amount can be calculated and controlled in combination with the curvature at the same time to ensure that the vehicle remains in the lane where the reference line is located at all times, and the lane keeping function is realized.

Referring to FIG. 4 , when determining the lateral control amount in one embodiment, the real-time position of the vehicle is first projected onto the above-mentioned real-time reference line, the reference line data point closest to the projection point is obtained, and the difference between the real-time position and the reference line data point is calculated. The difference between the vehicle and the real-time reference line is used as the real-time offset value between the vehicle and the real-time reference line. Then according to the size of the real-time offset value, the closed-loop PID (proportional proportion, integral integration, differential differentiation) control method or LQR (linear quadratic regulator, linear quadratic regulator) optimal controller algorithm is used to calculate the feedback control amount (this In the application examples, it is called the lateral control amount). The obtained feedback control amount can be mainly used for lane keeping control when the vehicle is traveling in a straight line or a curve with a small curve.

Referring to FIG. 4 , first, considering that there may be a positioning error in the positioning module, a certain value is selected as the allowable range of deviation error. The specific value that deviates from the allowable range of error is set based on the acceptance of the error in practical technical applications.

Considering that the offset value caused by the high-speed driving of the vehicle will exceed the adjustment value when the actual control is executed, it is possible to compare the real-time offset value obtained this time minus the historical offset value corresponding to the previous (or previous control cycle) vehicle control. The difference between the offset values (referred to as the first difference in the embodiment of the present application), if the first difference is less than or equal to 0, it means that the adjustment is effective, and the current real-time offset value can continue to be used as the input. If the first difference is greater than 0, it means that the adjustment has no effect, and the last adjustment cannot offset the offset caused by the car itself, so the first difference needs to be added to the real-time offset. In the embodiment of the present application, for the convenience of description, the real-time offset value when the first difference value is less than or equal to 0, and the sum of the real-time offset value and the first difference value when the first difference value is greater than 0 are referred to as undetermined Reference deviation value.

The pending reference deviation value is then compared to the deviation error tolerance. If the undetermined reference deviation value exceeds the allowable range of deviation error, the difference between the undetermined reference deviation value and the allowable range of deviation error (referred to as the third difference in the embodiment of this application) is used as the reference deviation value, and the lateral control amount is determined accordingly. If the undetermined reference deviation value is within the deviation error range, it will not be adjusted. For example, set the reference deviation value to 0, or keep the last lateral control amount unchanged to avoid excessive adjustment during PID adjustment. Vibration around.

In addition, considering the safety of lateral adjustment when the vehicle is running at high speed, it is necessary to set the maximum adjustment amount of allowable control. If the reference deviation value is greater than the maximum adjustment amount, the maximum adjustment amount is used as the reference deviation value, and the lateral control amount is determined accordingly. In order to avoid excessive adjustment of the output when the vehicle deviates far from the real-time reference line, it will affect the driving safety.

On the other hand, the feedforward control quantity required for lane keeping (referred to as curvature control quantity in the embodiment of the present application) is also calculated according to the curvature of the reference line data points projected by the vehicle onto the real-time reference line. The calculation method of the curvature control quantity can adopt the PID feedforward control algorithm and so on. The curvature control amount is mainly used when the vehicle is making a U-turn or turning, combined with the lateral control amount, to ensure that the vehicle can keep driving in the lane when turning or turning. When determining the curvature control amount, when the curvature of the reference line data point exceeds the set curvature threshold, it can be determined that the vehicle is in a curve or turning around, and the PID feedforward control algorithm is used to calculate the control amount according to the curvature of the reference line data point. The specific method of calculating the control amount and the control method may not be specifically limited. When the curvature of the reference line data point is less than the set curvature threshold, the curvature control amount can be directly set to 0.

Referring to FIG. 5 , after the lateral control amount and the curvature control amount are obtained, the final control amount can be comprehensively determined in combination with the lateral control amount and the curvature control amount. In some embodiments, the final control amount may be the sum of the lateral control amount and the curvature control amount. After the control amount is determined, the above-mentioned vehicle travel planning path may be further adjusted based on the control amount. By combining the lateral control amount and the curvature control amount, the lateral control of the vehicle is ensured on the one hand, and the lane keeping control of the vehicle during turning and U-turn is ensured at the same time.

After the control amount is determined, the steering wheel steering angle can be determined based on the control amount, and the steering wheel steering angle is output to the steering wheel steering actuator to drive the steering wheel to rotate to realize the lateral movement of the vehicle to complete the control execution process.

In some embodiments, the steering wheel steering angle of the vehicle steering mechanism may be directly calculated according to the control amount, and the steering wheel steering angle may be converted into an executable electrical signal to control the rotation of the steering wheel angle. In some embodiments, referring to FIG. 6 , in order to ensure safety, the vehicle speed needs to be fully considered when determining the final steering wheel steering angle. After obtaining the current vehicle speed, the steering angle safety range is determined based on the current vehicle speed, that is, the vehicle speed is too fast. It is necessary to limit the steering angle of the steering wheel to a certain range. If the steering angle of the steering wheel calculated according to the control amount is within the safe range of the steering angle, the steering angle of the steering wheel can be directly output to convert it into an executable electrical signal. If the steering angle of the steering wheel calculated according to the control amount is within the steering angle safety range, then take the maximum value (maximum or minimum value, generally the maximum value) of the steering angle safety range and output, as the final output steering wheel steering The angle is converted into an executable electrical signal, so as to avoid the safety problem caused by the excessively large steering angle of the steering wheel caused by the excessively large executable electrical signal.

Referring to FIG. 7 , a vehicle control apparatus provided in one embodiment includes: a position acquisition module 701 , a reference line planning module 702 , an offset value determination module 703 and a control amount determination module 704 .

The location acquisition module 701 is used to acquire the real-time location of the vehicle.

In one embodiment, the position obtaining module 701 can obtain the real-time position of the vehicle in any possible manner, such as GPS positioning, GPS positioning combined with satellite positioning, and the like.

In one embodiment, the vehicle control device may further include: a relative map generation module for establishing a body coordinate system based on the real-time position and the head direction of the vehicle, and generating a relative map based on the vehicle body coordinate system. Among them, when establishing the body coordinate system, the center of the rear axle of the vehicle can be used as the origin of the coordinate system, the front-facing direction of the vehicle is the positive direction of the first coordinate axis, and the direction of the front-facing direction after rotating 90 degrees counterclockwise/clockwise is the first coordinate system. The positive direction of the two coordinate axes. After the relative map is generated, the above-mentioned real-time position is projected onto the relative map, so as to obtain the relative position of the vehicle on the relative map. After the relative map is generated, all subsequent processing can be converted to the relative map and performed based on the relative map, which will not be described in detail in subsequent embodiments.

A reference line planning module 702, configured to generate a path planning reference line according to the real-time position.

In one embodiment, the reference line planning module 702 extracts lane line information from surrounding environment information; and then generates a path planning reference line according to the real-time position and the lane line information. The surrounding environment information may include information obtained by photographing by a vehicle-mounted camera device.

In one embodiment, the reference line planning module 702 obtains the lane line information of the lane where the real-time position is located from the map data according to the real-time position; and generates a path planning reference line according to the real-time position and the lane line information.

In one embodiment, the reference line planning module 702 determines the lane line according to the travel path determined based on the departure and destination of the vehicle, and generates a path planning reference line in combination with the real-time position and the determined lane line.

In one embodiment, the reference line planning module 702 determines, based on the real-time position, a road segment identifier corresponding to the real-time location; obtains a road segment centerline corresponding to the road segment identifier; based on the real-time location and the road segment center line to generate a path planning reference line.

Wherein, after the reference line planning module 702 generates the path planning reference line, the generated path planning reference line can be further filtered and smoothed, so as to remove the signal distortion caused by the interference of the sensor and the positioning module, etc., and can ensure the obtained real-time The smoothness of the reference line. When filtering and smoothing, any smoothing algorithm may be used, such as a five-point cubic smoothing algorithm or a point-by-point filtering algorithm, which is not specifically limited in this embodiment of the present application.

An offset value determination module 703, configured to determine a real-time offset value between the real-time position and the path planning reference line.

In one embodiment, the offset value determination module 703 determines the distance between the real-time position and the reference point as the distance between the real-time position and the path planning reference line after determining the reference point for projecting the real-time position to the path planning reference line. real-time offset value. Specifically, after the projection point for projecting the real-time position to the path planning reference line is determined, the point in the path planning reference line that is closest to the projection point is determined as the reference point.

A control amount determination module 704, configured to determine a control amount according to the real-time offset value, and determine a steering wheel steering angle according to the control amount.

In one embodiment, the control amount determination module 704 determines the lateral control amount according to the real-time offset value, and the control amount includes the lateral control amount.

In some embodiments, the control amount determination module 704 may directly use the real-time offset value as the lateral control amount.

In some embodiments, the control amount determination module 704 determines the real-time offset value and the historical offset value after acquiring the offset value corresponding to the previous vehicle control (referred to as the historical offset value in this embodiment of the present application). The difference (referred to as the first difference in this embodiment of the present application) determines a reference deviation value based on the real-time offset value and the first difference, and determines a lateral control amount according to the reference deviation value. In some examples, the reference deviation value may be directly used as the lateral control amount. In some embodiments, when the first difference value is less than or equal to 0, it means that the last lateral control can achieve the control effect. Therefore, the above real-time offset value can be directly used as the reference offset value; when the first difference value is greater than 0 , it means that the effect of the last lateral control is not good, so the sum of the real-time offset value and the difference value can be used as the reference offset value.

In some embodiments, the control amount determination module 704 compares the real-time offset value with the error tolerance range, and when the real-time offset value is outside the error tolerance range, calculates the difference between the real-time offset value and the error tolerance range. The difference value (referred to as the second difference value in the embodiment of the present application), the second difference value is used as the reference deviation value, and the lateral control amount is determined according to the reference deviation value.

In some embodiments, the control amount determination module 704 determines the real-time offset value and the historical offset value after acquiring the offset value corresponding to the previous vehicle control (referred to as the historical offset value in this embodiment of the present application). The difference (referred to as the first difference in this embodiment of the present application), that is, the value obtained by subtracting the historical offset from the real-time offset value, and the pending reference is determined based on the real-time offset value and the first difference. Deviation. Then compare the undetermined reference deviation value with the allowable error range, and when the undetermined reference deviation value is outside the allowable error range, calculate the difference between the undetermined reference deviation value and the allowable error range (referred to as the third difference in the embodiment of this application). value), take the third difference value as a reference deviation value, and determine the lateral control amount according to the reference deviation value.

In some embodiments, the above-mentioned control quantities may include lateral control quantities and curvature control quantities.

At this time, the control amount determination module 704 also determines the reference point for projecting the real-time position to the path planning reference line, and determines the curvature of the reference point on the path planning reference line; The control amount and the lateral control amount determine the control amount.

In some embodiments, the control amount determination module 704 calculates the curvature control amount according to the curvature threshold when the curvature is greater than or equal to the curvature threshold, and directly sets the curvature control amount to zero when the curvature is less than or equal to the curvature threshold.

In some embodiments, when the control amount determination module 704 determines the steering wheel steering angle according to the control amount, the pending steering wheel steering angle is determined according to the control amount; the current vehicle speed is obtained, and the steering angle safety range is determined according to the current vehicle speed; The comparative relationship of the steering angle safety range determines the steering angle of the steering wheel. The control amount determination module 704 determines the maximum value of the steering wheel steering angle safety range as the steering wheel steering angle when the undetermined steering wheel steering angle exceeds the steering angle safety range, and determines the undetermined steering wheel steering angle when the undetermined steering wheel steering angle is within the steering angle safety range. The steering wheel steering angle is determined as the steering wheel steering angle.

In some embodiments, the above-mentioned apparatus further includes a path planning module, configured to generate a planned travel path of the vehicle according to the real-time offset value and the path planning reference line. Wherein, in some embodiments, the vehicle travel planning path may be a curve line segment of a predetermined length starting from the real-time position on the path planning reference line. On the other hand, during the driving process, the generated planned driving path of the vehicle may also be adjusted according to the above-mentioned control amount.

In some embodiments, the path planning module further extracts obstacle information from the surrounding environment information sensed by the sensing module, and the obtained obstacle information may include: obstacle position, obstacle size, and obstacle movement speed; The information adjusts the above-mentioned vehicle travel planning path.

Wherein, when adjusting the planned driving path of the vehicle according to the obstacle information, when the obstacle is at the edge of the lane of the lane where the real-time position is located, the position of the planned driving path of the vehicle is adjusted in the lane to ensure that the vehicle is connected to the obstacle. When the obstacle is located in front of the vehicle's planned path, and the distance between the obstacle and the vehicle is less than the distance threshold, shorten the length of the vehicle's planned path to a second length, where the second length is less than the above-mentioned predetermined length, The second length may be the length of the distance from the real-time location to the obstacle.

In one embodiment, a computer device is provided. The computer device can be any device that can be used in a vehicle and can control the vehicle. The computer device can also be configured in the vehicle as a part of a vehicle system. The internal structure diagram of the computer device in one embodiment may be as shown in FIG. 8 . The computer equipment includes a processor and a memory connected through a system bus, and may also include a network interface connected through the system bus, and may also include a display screen and an input device.

Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium, an internal memory. The nonvolatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the execution of the operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. The computer program, when executed by the processor, implements a vehicle control method. The display screen of the computer equipment may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment may be a touch layer covered on the display screen, or a button, a trackball or a touchpad set on the shell of the computer equipment , or an external keyboard, trackpad, or mouse.

Those skilled in the art can understand that the structure shown in FIG. 8 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer equipment to which the solution of the present application is applied. Include more or fewer components than shown in the figures, or combine certain components, or have a different arrangement of components.

Accordingly, in one embodiment, a computer is also provided, comprising a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps of the method in any of the above-described embodiments when the processor executes the computer program.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage In a medium or an embedded system, when the computer program is executed, it may include the processes of the foregoing method embodiments. Wherein, any reference to memory, storage, database or other medium used in the various embodiments provided in this application may include non-volatile and/or volatile memory. Nonvolatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), embedded system devices, or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Road (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

Therefore, in one embodiment, there is also provided a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, implements the steps of the method as described above.

The technical features of the above embodiments can be combined arbitrarily. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features It is considered to be the range described in this specification.

The above-mentioned embodiments only represent several embodiments of the present application, and the descriptions thereof are specific and detailed, but should not be construed as a limitation on the scope of the invention patent. It should be pointed out that for those skilled in the art, without departing from the concept of the present application, several modifications and improvements can be made, which all belong to the protection scope of the present application. Therefore, the scope of protection of the patent of the present application shall be subject to the appended claims.

Claims (10)

1. A vehicle control method, the method comprising:

acquiring a real-time position of a vehicle;

generating a path planning reference line according to the real-time position;

determining a real-time offset value between the real-time position and the path planning reference line;

and determining a control quantity according to the real-time deviation value, and determining a steering angle of a steering wheel according to the control quantity.

2. The method of claim 1, wherein the path planning reference line is a lane centerline, further comprising at least one of:

the first item:

generating a path planning reference line according to the real-time position, comprising:

acquiring surrounding environment information, and extracting lane line information from the surrounding environment information;

generating the path planning reference line according to the real-time position and the lane line information;

the second term is:

generating a path planning reference line according to the real-time position, comprising:

acquiring lane line information of a lane where the real-time position is located from map data according to the real-time position;

generating the path planning reference line according to the real-time position and the lane line information;

the third item:

generating a path planning reference line according to the real-time position, comprising:

determining a road section identification corresponding to the real-time position based on the real-time position;

acquiring a road section central line corresponding to the road section identification;

and generating the path planning reference line based on the real-time position and the road section central line.

3. The method of claim 1, wherein determining a real-time offset value between the real-time location and the path-planning reference line comprises:

determining a reference point for projecting the real-time position to the path planning reference line;

and determining the distance between the real-time position and the reference point as a real-time offset value between the real-time position and the path planning reference line.

4. The method of claim 1, comprising any one of:

the first item:

determining a control quantity according to the real-time offset value, comprising:

determining a horizontal control quantity according to the real-time offset value, wherein the control quantity comprises the horizontal control quantity;

the second term is:

further comprising the steps of: determining a reference point for projecting the real-time position to the path planning reference line, and determining the curvature of the reference point on the path planning reference line; calculating a curvature control amount according to the curvature;

determining a control quantity according to the offset value, comprising: determining a horizontal control quantity according to the real-time deviation value; determining the control amount according to the curvature control amount and the lateral control amount.

5. The method of claim 4, comprising any one of:

the first item:

determining a lateral control quantity according to the real-time offset value, comprising:

taking the real-time deviation value as a reference deviation value, and determining a transverse control quantity according to the reference deviation value;

the second term is:

determining a lateral control quantity according to the real-time offset value, comprising:

acquiring a corresponding historical deviation value during last vehicle control;

determining a first difference between the real-time offset value and the historical offset value;

determining a reference deviation value based on the real-time deviation value and the first difference value;

determining a transverse control quantity according to the reference deviation value;

the third item:

determining a lateral control quantity according to the real-time offset value, comprising:

comparing the real-time offset value to an error tolerance range;

when the real-time offset value is out of the error allowable range, calculating a second difference value between the real-time offset value and the error allowable range, and taking the second difference value as a reference deviation value;

determining a transverse control quantity according to the reference deviation value;

the fourth item:

determining a lateral control quantity according to the real-time offset value, comprising:

acquiring a corresponding historical deviation value during last vehicle control;

determining a first difference between the real-time offset value and the historical offset value;

determining a pending reference deviation value based on the real-time deviation value and the first difference value;

comparing the undetermined reference deviation value with an error allowable range;

and when the undetermined reference deviation value is out of the error allowable range, calculating a third difference value between the undetermined reference deviation value and the error allowable range, taking the third difference value as a reference deviation value, and determining a transverse control quantity according to the reference deviation value.

6. The method of claim 1, wherein determining a steering wheel steering angle from the control amount comprises:

determining a steering angle of the steering wheel to be determined according to the control quantity;

obtaining a current vehicle speed, and determining a steering angle safety range according to the current vehicle speed;

and determining the steering angle of the steering wheel based on the comparison relationship between the steering angle of the steering wheel to be determined and the safety range of the steering angle.

7. The method of claim 1, wherein:

further comprising the steps of: establishing a body coordinate system based on the real-time position and the direction of the head of the vehicle, and generating a relative map based on the body coordinate system, wherein the center of the rear axle of the vehicle is the origin of the coordinate system, the direction opposite to the head is the positive direction of a first coordinate axis, and the direction opposite to the head after rotating 90 degrees anticlockwise/clockwise is the positive direction of a second coordinate axis;

and after the real-time position is projected to the relative map to obtain a vehicle relative position, taking the vehicle relative position as the real-time position, and generating the path planning reference line by combining the relative map.

8. A vehicle control apparatus, the apparatus comprising:

the position acquisition module is used for acquiring the real-time position of the vehicle;

the reference line planning module is used for generating a path planning reference line according to the real-time position;

an offset value determination module for determining a real-time offset value between the real-time position and the path planning reference line;

and the control quantity determining module is used for determining the control quantity according to the real-time deviation value and determining the steering angle of the steering wheel according to the control quantity.

9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.

Images