A vehicle control method, apparatus, device, and medium

Abstract

This application discloses a vehicle control method, device, equipment, and medium, relating to the field of autonomous driving technology. The method includes: determining whether a vehicle needs to turn based on target information; if a turn is needed, detecting whether there is a corresponding waiting-turn lane line in the current lane where the vehicle is located; if not, generating a virtual waiting-turn lane line for the current lane based on a preset strategy, and controlling the vehicle to turn based on the virtual waiting-turn lane line; if a turn is needed, controlling the vehicle to turn based on the waiting-turn lane line. This application can generate a virtual waiting-turn lane line according to a preset strategy when the vehicle needs to turn and there is no corresponding waiting-turn lane line in the current lane, allowing the vehicle to perform turning control, thereby improving the comfort of intelligent driving and enhancing the driver's experience.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, and in particular to a vehicle control method, device, equipment, and medium. Background Technology

[0002] When driving on city roads, some vehicles typically need to turn at intersections. Assuming a vehicle is in the left lane, when the green light comes on, vehicles with driver assistance features can automatically enter the left-turn waiting area based on the lane markings or directly make a left turn. However, in many cases, left-turn guide lines are not drawn or are unclear, such as... Figure 1 As shown in the diagram. If a vehicle is driving in the second left-turn lane, which is the second lane from the left without a left-turn guide line, when the green light comes on, the vehicle cannot automatically enter the left-turn waiting area or automatically control the left turn because there is no clear guide line. This will result in an uncomfortable intelligent driving experience for the driver.

[0003] In summary, how to control vehicle turning in the waiting area to improve the comfort of intelligent driving and enhance the driver's driving experience is a problem that needs to be solved. Summary of the Invention

[0004] In view of this, the purpose of this invention is to provide a vehicle control method, device, equipment, and medium capable of controlling a vehicle to turn in a waiting area, thereby improving the comfort of intelligent driving and enhancing the driver's experience. The specific solution is as follows:

[0005] In a first aspect, this application discloses a vehicle control method, comprising:

[0006] Determine whether the vehicle needs to turn based on the target information;

[0007] If a turn is required, the system checks whether there is a corresponding lane line for the waiting area in the current lane where the vehicle is located.

[0008] If not, then a virtual lane line for the turning zone of the current lane is generated based on a preset strategy, and the vehicle is turned based on the virtual lane line for the turning zone.

[0009] If so, the vehicle is controlled to turn based on the lane lines of the waiting area.

[0010] Optionally, determining whether the vehicle needs to turn based on the target information includes:

[0011] The turning probability of the vehicle is determined based on the target information; the target information includes the lateral displacement of the preceding vehicle relative to the vehicle, the turn signal status of the preceding vehicle, the road sign information, and the turn signal status of the vehicle.

[0012] Determine whether the turning probability is not less than a preset threshold;

[0013] If so, then it is determined that the vehicle needs to turn.

[0014] Optionally, determining the turning probability of the vehicle based on the target information includes:

[0015] Obtain the lateral displacement of the vehicle in front relative to the vehicle itself, and determine the turning probability of the vehicle in front based on the lateral displacement;

[0016] The probability of the turn signal of the vehicle in front is determined based on the status of the turn signal of the vehicle in front, the probability of the ground road sign is determined based on the information of the ground road sign, and the probability of the turn signal of the vehicle itself is determined based on the status of the turn signal of the vehicle itself.

[0017] The turning probability of the preceding vehicle, the turn signal probability of the preceding vehicle, the probability of the road sign, and the turn signal probability of the vehicle itself are calculated using preset weighting coefficients, and the weighted result is used as the turning probability of the vehicle itself.

[0018] Optionally, generating the virtual lane lines for the turning zone of the current lane based on a preset strategy includes:

[0019] Determine the current position of the vehicle; the current position includes the position of the lead vehicle and the positions of other vehicles.

[0020] If the vehicle is in the lead vehicle position, then the virtual lane line of the current lane is generated based on the adjacent lane lines and lane width of the waiting area on the side of the turning direction.

[0021] If the vehicle is not in the lead vehicle position, a virtual lane line for the waiting area of ​​the current lane is generated based on the waiting traffic flow and lane width on the side of the waiting direction.

[0022] Optionally, the step of controlling the vehicle to turn based on the virtual lane lines in the waiting-to-turn area includes:

[0023] If the vehicle is in the position of the lead vehicle, then determine the traffic light status on the side of the current turning direction;

[0024] If the traffic light is green, the longitudinal speed of the vehicle is determined based on the average longitudinal speed of the adjacent turning traffic and the corresponding first weighting coefficient, and the average speed of the adjacent straight traffic and the corresponding second weighting coefficient. The vehicle is then controlled to turn using the longitudinal speed and a pre-set first safe distance between the vehicle and the virtual lane line of the waiting area. The first weighting coefficient is greater than the second weighting coefficient.

[0025] If the traffic light is red, the vehicle is controlled to enter the corresponding turning waiting area based on the virtual lane lines of the turning waiting area. After the traffic light turns green, the process jumps to the step of determining the vehicle's longitudinal speed based on the longitudinal average speed of adjacent turning traffic and the corresponding first weighting coefficient, and the longitudinal average speed of adjacent straight traffic and the corresponding second weighting coefficient, and controlling the vehicle to turn using the longitudinal speed and the pre-set first safe distance between the vehicle and the virtual lane lines of the turning waiting area.

[0026] Optionally, the step of controlling the vehicle to turn based on the virtual lane lines in the waiting-to-turn area includes:

[0027] If the vehicle is in the non-leading vehicle position, the vehicle's speed is determined based on the speed of the preceding vehicle. When the traffic light is green, the vehicle is controlled to turn using the vehicle's speed and a pre-set first safe distance between the vehicle and the virtual lane line of the waiting area.

[0028] Optionally, after determining whether the vehicle needs to turn based on the target information, the method further includes:

[0029] If turning is not required, the current position of the vehicle is determined; wherein, the current position includes the position of the lead vehicle and the positions of non-lead vehicles;

[0030] If the vehicle is in the lead vehicle position, the vehicle's speed is determined based on the longitudinal average speed of the adjacent turning traffic flow and the corresponding first weighting coefficient, as well as the average speed of the adjacent straight traffic flow and the corresponding second weighting coefficient. A vehicle boundary trajectory line is generated based on the driving information of the adjacent straight traffic flow, so as to control the vehicle's straight-line driving by using the driving speed and a pre-set second safety interval distance between the vehicle and the vehicle boundary trajectory line; wherein, the second weighting coefficient is greater than the first weighting coefficient.

[0031] If the vehicle is not in the lead vehicle position, the vehicle's speed is determined based on the speed of the preceding vehicle, and a vehicle boundary trajectory line is generated based on the driving information of adjacent straight traffic flow, so as to control the vehicle's straight-line driving by using the driving speed and the pre-set second safety interval distance between the vehicle and the vehicle boundary trajectory line.

[0032] Secondly, this application discloses a vehicle control device, characterized in that it includes:

[0033] The turning detection module is used to determine whether the vehicle needs to turn based on target information;

[0034] The lane line detection module is used to detect whether there is a corresponding lane line for the waiting area in the current lane where the vehicle is located if a turn is required.

[0035] The lane line generation module is used to generate virtual lane lines for the turning area of ​​the current lane based on a preset strategy if no.

[0036] The first turning control module is used to control the vehicle to turn based on the virtual lane lines of the waiting area;

[0037] If the second turning control module is present, it controls the vehicle to turn based on the lane lines of the turning area.

[0038] Thirdly, this application discloses an electronic device, including:

[0039] Memory, used to store computer programs;

[0040] A processor is used to execute the computer program to implement the steps of the aforementioned disclosed vehicle control method.

[0041] Fourthly, this application discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the steps of the aforementioned disclosed vehicle control method.

[0042] As can be seen, this application determines whether the vehicle needs to turn based on target information; if a turn is needed, it checks whether there is a corresponding waiting-turn lane line in the current lane where the vehicle is located; if not, it generates a virtual waiting-turn lane line for the current lane based on a preset strategy, and controls the vehicle to turn based on the virtual waiting-turn lane line; if a turn is needed, it controls the vehicle to turn based on the waiting-turn lane line. Thus, this application first determines whether the vehicle needs to turn based on target information. If a turn is determined, it then checks whether there is a corresponding waiting-turn lane line in the current lane where the vehicle is located. If a corresponding waiting-turn lane line exists, it directly controls the vehicle to turn based on the waiting-turn lane line. If no corresponding waiting-turn lane line exists, it generates a virtual waiting-turn lane line for the current lane based on a preset strategy, and then controls the vehicle to turn based on the generated virtual waiting-turn lane line. In this way, when there is no corresponding waiting-turn lane line in the current lane where the vehicle is located, this application can generate a virtual lane line through a preset strategy for the vehicle to turn, thereby improving the comfort of intelligent driving and enhancing the driver's experience. Attached Figure Description

[0043] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0044] Figure 1 This is a schematic diagram of a current dual left-turn lane disclosed in this application;

[0045] Figure 2 This is a flowchart of a vehicle control method disclosed in this application;

[0046] Figure 3 This is a flowchart of a specific vehicle control method disclosed in this application;

[0047] Figure 4 This is a schematic diagram of virtual lane line generation when the vehicle is in the lead vehicle position, as disclosed in this application.

[0048] Figure 5 This is a schematic diagram of virtual lane line generation when a vehicle is in a non-leading vehicle position, as disclosed in this application.

[0049] Figure 6 This is a schematic diagram of turning control when the vehicle is in the lead vehicle position, as disclosed in this application;

[0050] Figure 7 This is a schematic diagram of turning control when the vehicle is in a non-leading position, as disclosed in this application;

[0051] Figure 8 This is a flowchart of another specific vehicle control method disclosed in this application;

[0052] Figure 9 This is a schematic diagram of straight-moving control when the vehicle is in the lead vehicle position, as disclosed in this application.

[0053] Figure 10 This is a schematic diagram of straight-moving control when the vehicle is not in the lead vehicle position, as disclosed in this application.

[0054] Figure 11 This is a schematic diagram of the structure of a vehicle control device disclosed in this application;

[0055] Figure 12 This is a structural diagram of an electronic device disclosed in this application. Detailed Implementation

[0056] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0057] Currently, in many cases, only the lane lines of the leftmost left-turn waiting area are drawn, while the left-turn guide lines for the second lane are not. If a vehicle is driving in the second left-turn lane (the second lane from the left without left-turn guide lines), when the green light turns on, because there are no clear guide lines, the vehicle cannot automatically enter the left-turn waiting area or automatically control its left turn, thus providing an uncomfortable intelligent driving experience for the driver. Therefore, this application discloses a vehicle control method, device, equipment, and medium that can control vehicle turning in the waiting area to improve the comfort of intelligent driving and enhance the driver's experience.

[0058] See Figure 2 As shown in the figure, this application discloses a vehicle control method, which includes:

[0059] Step S11: Determine whether the vehicle needs to turn based on the target information.

[0060] In this embodiment, it is possible to determine whether the vehicle needs to turn based on the currently collected target information. Specifically, determining whether the vehicle needs to turn based on target information includes: determining the vehicle's turning probability based on the target information; the target information includes the lateral displacement of the preceding vehicle relative to the vehicle, the preceding vehicle's turn signal status, ground road sign information, and the vehicle's turn signal status; determining whether the turning probability is not less than a preset threshold; if so, it is determined that the vehicle needs to turn. That is, this application calculates the vehicle's current turning probability by comprehensively considering the preceding vehicle's lateral displacement relative to the vehicle, the preceding vehicle's turn signal status, ground road sign information, and the vehicle's turn signal status. If the turning probability is not less than a preset threshold, it can be determined that the vehicle needs to turn. In this embodiment, the preset threshold can be set to 0.3. If the turning probability is greater than or equal to 0.3, it can be considered that the vehicle has a turning tendency.

[0061] In a specific implementation, determining the turning probability of the vehicle based on target information includes: acquiring the lateral displacement of the preceding vehicle relative to the vehicle, and determining the turning probability of the preceding vehicle based on the lateral displacement; determining the corresponding turning probability of the preceding vehicle based on the turn signal status of the preceding vehicle, determining the corresponding ground road sign probability based on ground road sign information, and determining the corresponding turning probability of the vehicle based on the turn signal status of the vehicle itself; and using preset weighting coefficients to perform a weighted calculation on the turning probability of the preceding vehicle, the turning probability of the preceding vehicle, the ground road sign probability, and the turning probability of the vehicle itself, and using the weighted result as the turning probability of the vehicle itself. That is, this application first needs to determine the corresponding probability values ​​based on the lateral displacement of the preceding vehicle relative to the vehicle, the turn signal status of the preceding vehicle, the ground road sign information, and the turn signal status of the vehicle itself, and then perform a weighted calculation on each probability value to obtain the total turning probability. Since left-turn waiting areas are more common in real-world scenarios, the following embodiments use left turns as an example to describe the technical solution of this application in detail.

[0062] Specifically, after obtaining the lateral displacement of the vehicle in front relative to the vehicle itself, if the value of the lateral displacement of the vehicle in front is positive and increasing, the probability of the vehicle in front turning is also greater. Taking a left turn as an example, taking the left side of the vehicle itself as the positive direction, the further to the left the vehicle in front is relative to the vehicle, and the greater the distance, the higher the probability that the vehicle in front will turn left. The specific calculation formula is as follows:

[0063]

[0064] Where, p lat The probability of the vehicle in front turning is given by lat, the lateral displacement of the vehicle in front relative to the vehicle itself is given by w, and the width of the vehicle is given by w, which can be 1.7 in meters.

[0065] Regarding the turn signal status of the vehicle in front, if the vehicle in front has its left turn signal on, then the probability p of the corresponding vehicle's turn signal will be changed. frn_sta Set it to 1; if no one is detected or if it is detected as closed, then set p. frn_sta Set to 0;

[0066] Regarding ground road sign information, if a left-turn indicator is detected, the corresponding ground road sign probability p is set. sig Set p to 1; if no p is detected, then p is set to 1. sig Set to 0;

[0067] Regarding the vehicle's turn signal status, if the vehicle's left turn signal is on, then the corresponding vehicle turn signal probability p will be... ego_sta Set it to 1; if it is turned off, then p will be... ego_sta Set to 0;

[0068] Finally, using preset weighting coefficients, the turning probability of the vehicle in front, the turn signal probability of the vehicle in front, the probability of road signs, and the turn signal probability of the vehicle itself are weighted and calculated. The resulting weighted sum is then used as the turning probability of the vehicle itself. The formula for calculating the turning probability P is:

[0069] P = w lat p lat +w frn_sta p frn_sta +w sig p sig +w ego_sta p ego_sta ;

[0070] Where, p lat Let p be the probability that the vehicle in front is turning. frn_sta Let p be the probability of the vehicle in front activating its turn signal. sig Let p be the probability of a ground landmark. ego_sta w represents the probability of a vehicle's turn signal. lat w frn_sta w sig and w ego_sta These are all weighting coefficients. In one specific implementation, the four weighting coefficients can be set to 0.25, 0.25, 0.2, and 0.3, respectively. If the weighted result P is not less than 0.3, then the vehicle can be considered to have a tendency to turn left.

[0071] Step S12: If a turn is required, check whether there is a corresponding lane line for the waiting area in the current lane where the vehicle is located.

[0072] In this embodiment, if a turn is required based on the turning probability, the system detects whether there is a corresponding waiting lane line in the vehicle's current lane. It is understood that for double-turn lanes, such as double left-turn lanes, typically the lane line for the leftmost left-turn waiting area is drawn, while only the left-turn lane line for the second lane from the left is not drawn. Therefore, the application scenario of this application mainly focuses on the second lane from the left. In a specific implementation, the presence of a corresponding waiting lane line can be determined based on which lane the vehicle is currently in, and the presence of a corresponding waiting lane line on the road ahead can be detected using an image sensor.

[0073] Step S13: If not, generate a virtual lane line for the turning area of ​​the current lane based on a preset strategy, and perform turning control on the vehicle based on the virtual lane line for the turning area.

[0074] In this embodiment, if there is no corresponding waiting lane line in the current lane, a virtual waiting lane line for the current lane is generated based on a preset strategy, so that the vehicle can be controlled to turn based on the generated virtual waiting lane line. In this way, when there is no corresponding waiting lane line in the current lane where the vehicle is located, this application can generate a virtual lane line through a preset strategy for the vehicle to control turning, thereby improving the comfort of intelligent driving and enhancing the driver's driving experience.

[0075] Step S14: If so, then control the vehicle to turn based on the lane lines of the waiting area.

[0076] In this embodiment, if there is a corresponding waiting lane line in the current lane, the vehicle can be controlled to turn based on the existing waiting lane line.

[0077] As can be seen, this application determines whether the vehicle needs to turn based on target information; if a turn is needed, it checks whether there is a corresponding waiting-turn lane line in the current lane where the vehicle is located; if not, it generates a virtual waiting-turn lane line for the current lane based on a preset strategy, and controls the vehicle to turn based on the virtual waiting-turn lane line; if a turn is needed, it controls the vehicle to turn based on the waiting-turn lane line. Thus, this application first determines whether the vehicle needs to turn based on target information. If a turn is determined, it then checks whether there is a corresponding waiting-turn lane line in the current lane where the vehicle is located. If a corresponding waiting-turn lane line exists, it directly controls the vehicle to turn based on the waiting-turn lane line. If no corresponding waiting-turn lane line exists, it generates a virtual waiting-turn lane line for the current lane based on a preset strategy, and then controls the vehicle to turn based on the generated virtual waiting-turn lane line. In this way, when there is no corresponding waiting-turn lane line in the current lane where the vehicle is located, this application can generate a virtual lane line through a preset strategy for the vehicle to turn, thereby improving the comfort of intelligent driving and enhancing the driver's experience.

[0078] See Figure 3 As shown, this application discloses a specific vehicle control method. Compared to the previous embodiment, this embodiment further explains and optimizes the technical solution. Specifically, it includes:

[0079] Step S21: Determine whether the vehicle needs to turn based on the target information.

[0080] Step S22: If a turn is required, check whether there is a corresponding lane line for the waiting area in the current lane where the vehicle is located.

[0081] Step S23: If not, determine the current position of the vehicle; the current position includes the position of the lead vehicle and the positions of non-lead vehicles.

[0082] In this embodiment, if there is no corresponding waiting lane line in the current lane, it means that the vehicle is traveling in the second left-turn lane. Then, the current position of the vehicle is further determined, that is, whether the vehicle is in the lead vehicle position or not.

[0083] Step S24: If the vehicle is in the lead vehicle position, then generate the virtual lane line of the current lane based on the adjacent waiting area lane line and lane width on the side of the turning direction; if the vehicle is not in the lead vehicle position, then generate the virtual lane line of the current lane based on the waiting traffic flow and lane width on the side of the turning direction.

[0084] In this embodiment, taking a dual left-turn lane as an example, in one specific implementation, such as... Figure 4 As shown, if the vehicle is traveling in the second left-turn lane and is in the lead vehicle position, a virtual lane line for the current lane is generated based on the adjacent left-turn lane lines detected by the vehicle's sensors and the lane width. In other words, the vehicle can generate a virtual lane line by fitting the detected left lane line curve characteristics and the lane width to its own lane.

[0085] Specifically, lane markings can be expressed using a spiral curve equation. If the vehicle detects the left lane marking, the spiral curve equation would be:

[0086] y = c3x 3 +c2x 2 +c1x+c0;

[0087] Where c3 is the rate of change of curvature, c2 is the curvature, c1 is the heading angle, and c0 is the lateral displacement.

[0088] According to national standards, the width of a lane is generally 3.5 meters (which can be specified). Therefore, the spiral curve equation of the right lane line of the virtual lane in the waiting area generated from the left lane line can be expressed as:

[0089] y = c3x 3 +(c² / 1+3.5c²)x 2 +c1x+(c0-3.5).

[0090] That is, the detected left lane line and the generated right lane line together constitute the virtual lane line of the turning area.

[0091] In one specific implementation, such as Figure 5As shown, if the vehicle is traveling in the second left-turn lane and is not in the lead vehicle position, its sensors can only detect a limited area because it is behind the traffic flow. Furthermore, the lane lines are obscured by vehicles ahead, preventing the vehicle from clearly detecting the left lane lines. In this case, the vehicle can generate a virtual lane line for its current lane based on the detected adjacent left-turn lane lines and the lane width. That is, if the vehicle can detect the traffic flow on the left, it can also fit and generate a virtual lane line for its lane based on the left traffic flow. Additionally, if the left lane lines are obscured, a virtual lane line for the current lane can also be generated based on the left traffic flow.

[0092] First, based on the right edge of the bounding boxes of each vehicle in the left-hand traffic flow, a spiral curve equation is fitted: y = c3x 3 +c2x 2 Given +c1x+c0, and assuming the left-hand vehicle is 1.7 meters wide and traveling in the middle of its lane (typically the lane width is 3.5 meters), the spiral curve equation of the left lane line of the virtual lane in the waiting area generated based on the left-hand traffic flow can be expressed as:

[0093]

[0094] The equation of the spiral curve of the right lane line of the virtual lane in the waiting area can be expressed as:

[0095]

[0096] Step S25: Perform turning control on the vehicle based on the virtual lane lines of the waiting area.

[0097] In this embodiment, in one specific implementation, the above-mentioned turning control of the vehicle based on the virtual lane line of the waiting-to-turn area specifically includes: if the vehicle is in the position of the lead vehicle, determining the traffic light status on the side of the current turning direction; if the traffic light status is green, determining the longitudinal speed of the vehicle based on the longitudinal average speed of adjacent turning traffic and the corresponding first weighting coefficient, and the longitudinal average speed of adjacent straight traffic and the corresponding second weighting coefficient, and using the longitudinal speed and a pre-set first safety interval distance between the vehicle and the virtual lane line of the waiting-to-turn area to control the vehicle's turning. The process involves driving; wherein the first weighting coefficient is greater than the second weighting coefficient; if the traffic light is red, the vehicle is controlled to enter the corresponding turning waiting area based on the virtual lane line of the turning waiting area; after the traffic light turns green, the process jumps to the step of determining the vehicle's longitudinal speed based on the longitudinal average speed of adjacent turning traffic and the corresponding first weighting coefficient, and the average speed of adjacent straight traffic and the corresponding second weighting coefficient, and controlling the vehicle to turn using the longitudinal speed and the first safe interval distance between the vehicle and the virtual lane line of the turning waiting area.

[0098] It is understandable that, such as Figure 6 As shown, when the vehicle is in the lead vehicle position, the traffic light status on the side of the vehicle waiting to turn is determined. If the straight traffic light is green and the left turn traffic light is green, it means that a left turn can be performed directly. From the above, we know that the curve equations of the left and right lanes of the virtual lane in the waiting area are as follows:

[0099] y = c3x 3 +c2x 2 +c1x+c0;

[0100] y = c3x 3 +(c² / 1+3.5c²)x 2 +c1x+(c0-3.5);

[0101] The system then uses the generated virtual lane lines to control the vehicle's lateral and longitudinal movements when turning. Specifically, in terms of lateral control, the vehicle needs to be kept within the virtual lane lines, constantly monitoring the lateral distance to the traffic flow on the left and the left edge of the virtual lane. First, it must ensure the vehicle does not cross the virtual lane lines; that is, a pre-set first safety distance must be maintained between the vehicle and the virtual lane lines, and a distance of at least 1.5 meters must be maintained from adjacent vehicles.

[0102] In terms of longitudinal control, the longitudinal speed of the vehicle needs to be determined based on the average longitudinal speed v1 of the left-turning traffic flow and its corresponding first weighting coefficient w1, and the average longitudinal speed v2 of the right-going straight traffic flow and its corresponding second weighting coefficient w2. In the case of a left turn, the perception weight w1 of the left-turning vehicle speed needs to be increased, while the perception weight w2 of the right-turning vehicle speed needs to be decreased. That is, the first weighting coefficient w1 must be greater than the second weighting coefficient w2 for the vehicle's longitudinal speed v1 to be determined. ego The calculation formula is as follows:

[0103] v ego =w1*v1+w2*v2;

[0104] The first weighting coefficient w1 can be calculated by interpolation based on the probability value of the vehicle turning left:

[0105]

[0106] The second weighting coefficient w2 = 1 - w1.

[0107] Additionally, if the straight traffic light changes from red to green, and the left-turn traffic light is red, it means that you need to first control your vehicle to enter the corresponding turning waiting area according to the generated virtual lane lines of the waiting area, and stop within the stop line of the waiting area. Then, when the traffic light changes to green, you can then perform the steps corresponding to the left-turn operation described above.

[0108] In another specific embodiment, the above-mentioned turning control of the vehicle based on the virtual lane line of the waiting area specifically includes: if the vehicle is in the non-leading vehicle position, the driving speed of the vehicle is determined based on the driving speed of the preceding vehicle, and when the traffic light is green, the vehicle is controlled to turn by using the driving speed and the first safe interval distance between the vehicle and the virtual lane line of the waiting area.

[0109] It is understandable that, such as Figure 7 As shown, when the vehicle is not in the lead vehicle position, as can be seen from the above, the curve equations of the left and right lanes of the virtual lane in the turning area are as follows:

[0110]

[0111]

[0112] When the left-turn traffic light turns green and the vehicle in front moves forward, the system performs lateral and longitudinal control of the vehicle during the turn based on the generated virtual lane lines. Specifically, in terms of longitudinal control, it adjusts the lateral and longitudinal control based on the speed v of the vehicle in front. ego front The determined speed v of the vehicle egoControl your vehicle's speed and maintain a safe distance from the vehicle in front. At this time, the influence of lateral speeds is irrelevant: v ego =v ego front .

[0113] In terms of lateral control, the virtual lane line of the waiting area is formed based on the driving information of the traffic flow on the left, and combined with the movement trajectory of the vehicle in front, as the basis for lateral control. The final vehicle trajectory reference line needs to ensure that a first safe distance is maintained between the vehicle and the virtual lane line of the waiting area. In this embodiment, the distance is more than 1.5 meters from the traffic flow on the left.

[0114] Step S26: If there is a corresponding lane line for the waiting area, then control the vehicle to turn based on the lane line for the waiting area.

[0115] For more detailed processing procedures of steps S21, S22 and S26, please refer to the corresponding content disclosed in the foregoing embodiments, which will not be repeated here.

[0116] As can be seen, in this embodiment, if the vehicle is in the lead vehicle position, a virtual lane line for the waiting area of ​​the current lane is generated based on the detected left-turn lane line and the lane width. If the vehicle is not in the lead vehicle position, a virtual lane line for the waiting area of ​​the current lane is generated based on the detected left-turn waiting traffic flow and the lane width. That is, the vehicle can generate its own virtual lane line for the waiting area based on the detected left-turn lane line or left-turn waiting traffic flow, and then perform lateral and longitudinal control of the vehicle based on the virtual lane line. This improves the comfort of intelligent driving and enhances the driver's driving experience.

[0117] See Figure 8 As shown, this application discloses a specific vehicle control method. Compared to the previous embodiment, this embodiment further explains and optimizes the technical solution. Specifically, it includes:

[0118] Step S31: Determine whether the vehicle needs to turn based on the target information.

[0119] Step S32: If turning is not required, determine the current position of the vehicle; wherein the current position includes the position of the lead vehicle and the positions of non-lead vehicles.

[0120] In this embodiment, if the vehicle does not need to turn, it is further determined whether the current position of the vehicle is the lead vehicle position or a non-lead vehicle position.

[0121] Step S33: If the vehicle is in the lead vehicle position, the driving speed of the vehicle is determined based on the longitudinal average speed of the adjacent turning traffic flow and the corresponding first weighting coefficient, and the average speed of the adjacent straight traffic flow and the corresponding second weighting coefficient. The vehicle boundary trajectory line is generated according to the driving information of the adjacent straight traffic flow, so as to control the straight driving of the vehicle by using the driving speed and the pre-set second safety interval distance between the vehicle and the vehicle boundary trajectory line; wherein, the second weighting coefficient is greater than the first weighting coefficient.

[0122] In this embodiment, as Figure 9 As shown, if the vehicle is in the lead position, regardless of whether the traffic light for the left-turn lane is red or green, the vehicle is currently judged to be traveling straight, and there is no need to generate a virtual lane line for the waiting area. When the straight-ahead traffic light is green, the vehicle's speed is determined based on the longitudinal average speed v1 of the left-turning traffic flow and the corresponding first weight coefficient w1, and the average speed v2 of the right-hand straight-ahead traffic flow and the corresponding second weight coefficient w2. Because there is no virtual lane line for straight-ahead traffic at the intersection, the vehicle needs to increase the perception weight w2 for the right-hand vehicle's trajectory and speed v2, and decrease the perception weight w1 for the left-hand lane line and the left-hand vehicle's speed v1. The vehicle's speed v ego The calculation formula is as follows:

[0123] v ego =w1*v1+w2*v2.

[0124] Then, the vehicle speed is controlled using this speed to achieve longitudinal control. A vehicle boundary trajectory line is generated based on the driving information of adjacent straight-moving traffic. This allows for lateral control by using a pre-set second safety interval between the vehicle and the trajectory line to control the vehicle's straight-line movement. Specifically, a distance of more than 1.5 meters needs to be maintained between the vehicle and the trajectory line during movement.

[0125] Step S34: If the vehicle is not in the lead vehicle position, the vehicle's speed is determined based on the speed of the preceding vehicle, and a vehicle boundary trajectory line is generated according to the driving information of adjacent straight traffic flow, so as to control the vehicle's straight-line driving by using the driving speed and the pre-set second safety interval distance between the vehicle and the vehicle boundary trajectory line.

[0126] In this embodiment, as Figure 10 As shown, if the vehicle is not in the lead vehicle position, regardless of whether the traffic light for the left-turn lane is red or green, the vehicle is currently judged to be traveling straight, and there is no need to generate a virtual lane line for the waiting area. When the straight-ahead traffic light is green, the speed of the vehicle in front is used as the basis for the lane line. ego front Determine the vehicle's speed v egoIt generates vehicle boundary trajectory lines based on the driving information of adjacent straight-ahead traffic, so as to utilize the calculated driving speed v ego Control the vehicle's speed while maintaining a safe distance from the vehicle in front to achieve longitudinal control. At this point, the influence of lateral speeds does not need to be considered: v ego =v ego front .

[0127] Furthermore, the vehicle's straight-line movement is controlled based on a pre-set second safety interval distance between itself and the vehicle boundary trajectory line, thereby achieving lateral control. Specifically, based on the vehicle boundary trajectory line and the trajectory of the vehicle in front, the final vehicle trajectory reference line is determined, which must maintain a distance of at least 1.5 meters from the traffic flow on the right.

[0128] Furthermore, it should be noted that in all the aforementioned situations where the vehicle is not in the lead car position, because it is not in the lead car position, it is impossible to detect the stop line information ahead. Therefore, it is necessary to consider the traffic light countdown to avoid accidentally running a red light. If the countdown is less than 10 seconds and the vehicle in front shows a tendency to decelerate, the vehicle needs to take appropriate deceleration measures:

[0129] Detect the acceleration a and speed v of the vehicle in front. ego front Let y be the distance to the vehicle in front. If the differential of the acceleration of the vehicle in front, da / dt, is less than 0, it indicates that the vehicle in front is decelerating. Therefore, the vehicle needs to take braking measures to ensure that it has a similar acceleration to the vehicle in front. By controlling the accelerator and brakes, the vehicle can maintain a similar speed, v, to the vehicle in front. ego ≈v ego front And the safe distance between the two workshops, dy>2 meters.

[0130] For a more detailed description of the process of step S31, please refer to the relevant content disclosed in the foregoing embodiments, which will not be repeated here.

[0131] As can be seen, in this embodiment of the application, if it is determined based on the target information that the vehicle does not need to turn but travels straight, the conditions for straight-line control also need to be determined according to the current position of the vehicle. When in the lead vehicle position, its driving speed needs to take into account the longitudinal average speed of the left-turning traffic flow and the average speed of the right-going straight traffic flow. When not in the lead vehicle position, only the speed of the vehicle in front needs to be considered, and the influence of left and right vehicle speeds does not need to be considered.

[0132] See Figure 11 As shown in the figure, this application discloses a vehicle control device, which includes:

[0133] The turning judgment module 11 is used to determine whether the vehicle needs to turn based on the target information.

[0134] The lane line detection module 12 is used to detect whether there is a corresponding lane line for the waiting area in the current lane where the vehicle is located if a turn is required.

[0135] Lane line generation module 13 is used to generate virtual lane lines for the turning area of ​​the current lane based on a preset strategy if no.

[0136] The first turning control module 14 is used to control the vehicle to turn based on the virtual lane lines of the waiting area;

[0137] If the second turning control module 15 is used, then the vehicle is turned based on the lane lines of the waiting-to-turn area.

[0138] As can be seen, this application determines whether the vehicle needs to turn based on target information; if a turn is needed, it checks whether there is a corresponding waiting-turn lane line in the current lane where the vehicle is located; if not, it generates a virtual waiting-turn lane line for the current lane based on a preset strategy, and controls the vehicle to turn based on the virtual waiting-turn lane line; if a turn is needed, it controls the vehicle to turn based on the waiting-turn lane line. Thus, this application first determines whether the vehicle needs to turn based on target information. If a turn is determined, it then checks whether there is a corresponding waiting-turn lane line in the current lane where the vehicle is located. If a corresponding waiting-turn lane line exists, it directly controls the vehicle to turn based on the waiting-turn lane line. If no corresponding waiting-turn lane line exists, it generates a virtual waiting-turn lane line for the current lane based on a preset strategy, and then controls the vehicle to turn based on the generated virtual waiting-turn lane line. In this way, when there is no corresponding waiting-turn lane line in the current lane where the vehicle is located, this application can generate a virtual lane line through a preset strategy for the vehicle to turn, thereby improving the comfort of intelligent driving and enhancing the driver's experience.

[0139] Figure 12 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Specifically, it may include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 stores a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the vehicle control method performed by the electronic device disclosed in any of the foregoing embodiments.

[0140] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and is not specifically limited here; the input / output interface 25 is used to acquire external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs, and is not specifically limited here.

[0141] The processor 21 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 21 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 21 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 21 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, the processor 21 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0142] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk or optical disk, etc. The resources stored thereon include operating system 221, computer program 222 and data 223, etc., and the storage method can be temporary storage or permanent storage.

[0143] The operating system 221 manages and controls the various hardware devices and computer programs 222 on the electronic device 20 to enable the processor 21 to perform calculations and processing on the massive amounts of data 223 in the memory 22. The operating system 221 can be Windows, Unix, Linux, etc. The computer program 222, in addition to including a computer program capable of performing the vehicle control method executed by the electronic device 20 as disclosed in any of the foregoing embodiments, may further include computer programs capable of performing other specific tasks. The data 223 may include data received by the electronic device from external devices, as well as data collected by its own input / output interface 25.

[0144] Furthermore, embodiments of this application also disclose a computer-readable storage medium storing a computer program. When the computer program is loaded and executed by a processor, it implements the method steps executed during vehicle control as disclosed in any of the foregoing embodiments.

[0145] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0146] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0147] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0148] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0149] The present invention provides a detailed description of a vehicle control method, apparatus, device, and storage medium. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A vehicle control method, characterized in that, include: Determine whether the vehicle needs to turn based on the target information; If a turn is required, the system checks whether there is a corresponding lane line for the waiting area in the current lane where the vehicle is located. If not, then a virtual lane line for the turning zone of the current lane is generated based on a preset strategy, and the vehicle is turned based on the virtual lane line for the turning zone. If so, then the vehicle is controlled to turn based on the lane lines of the waiting-to-turn area; The step of generating the virtual lane lines for the turning zone of the current lane based on a preset strategy includes: Determine the current position of the vehicle; the current position includes the position of the lead vehicle and the positions of other vehicles. If the vehicle is in the lead vehicle position, then the virtual lane line of the current lane is generated based on the adjacent lane lines and lane width of the waiting area on the side of the turning direction. If the vehicle is not in the lead vehicle position, a virtual lane line for the waiting area of ​​the current lane is generated based on the waiting traffic flow and lane width on the side of the waiting direction. The method of controlling the vehicle to turn based on the virtual lane lines in the waiting area includes: If the vehicle is in the position of the lead vehicle, then determine the traffic light status on the side of the current turning direction; If the traffic light is green, the longitudinal speed of the vehicle is determined based on the average longitudinal speed of the adjacent turning traffic and the corresponding first weighting coefficient, and the average speed of the adjacent straight traffic and the corresponding second weighting coefficient. The vehicle is then controlled to turn using the longitudinal speed and a pre-set first safe distance between the vehicle and the virtual lane line of the waiting area. The first weighting coefficient is greater than the second weighting coefficient. If the traffic light is red, the vehicle is controlled to enter the corresponding turning waiting area based on the virtual lane lines of the turning waiting area. After the traffic light turns green, the process jumps to the step of determining the vehicle's longitudinal speed based on the longitudinal average speed of adjacent turning traffic and the corresponding first weighting coefficient, and the longitudinal average speed of adjacent straight traffic and the corresponding second weighting coefficient, and controlling the vehicle to turn using the longitudinal speed and the pre-set first safe distance between the vehicle and the virtual lane lines of the turning waiting area.

2. The vehicle control method according to claim 1, characterized in that, The process of determining whether the vehicle needs to turn based on target information includes: The turning probability of the vehicle is determined based on the target information; the target information includes the lateral displacement of the preceding vehicle relative to the vehicle, the turn signal status of the preceding vehicle, the road sign information, and the turn signal status of the vehicle. Determine whether the turning probability is not less than a preset threshold; If so, then it is determined that the vehicle needs to turn.

3. The vehicle control method according to claim 2, characterized in that, The determination of the vehicle's turning probability based on target information includes: Obtain the lateral displacement of the vehicle in front relative to the vehicle itself, and determine the turning probability of the vehicle in front based on the lateral displacement; The probability of the turn signal of the vehicle in front is determined based on the status of the turn signal of the vehicle in front, the probability of the ground road sign is determined based on the information of the ground road sign, and the probability of the turn signal of the vehicle itself is determined based on the status of the turn signal of the vehicle itself. The turning probability of the preceding vehicle, the turn signal probability of the preceding vehicle, the probability of the road sign, and the turn signal probability of the vehicle itself are calculated using preset weighting coefficients, and the weighted result is used as the turning probability of the vehicle itself.

4. The vehicle control method according to claim 1, characterized in that, The method of controlling the vehicle to turn based on the virtual lane lines in the waiting area includes: If the vehicle is in the non-leading vehicle position, the vehicle's speed is determined based on the speed of the preceding vehicle. When the traffic light is green, the vehicle is controlled to turn using the vehicle's speed and a pre-set first safe distance between the vehicle and the virtual lane line of the waiting area.

5. The vehicle control method according to any one of claims 1 to 4, characterized in that, After determining whether the vehicle needs to turn based on the target information, the process also includes: If turning is not required, the current position of the vehicle is determined; wherein, the current position includes the position of the lead vehicle and the positions of non-lead vehicles; If the vehicle is in the lead vehicle position, the vehicle's speed is determined based on the longitudinal average speed of the adjacent turning traffic flow and the corresponding first weighting coefficient, as well as the average speed of the adjacent straight traffic flow and the corresponding second weighting coefficient. A vehicle boundary trajectory line is generated based on the driving information of the adjacent straight traffic flow, so as to control the vehicle's straight-line driving by using the driving speed and a pre-set second safety interval distance between the vehicle and the vehicle boundary trajectory line; wherein, the second weighting coefficient is greater than the first weighting coefficient. If the vehicle is not in the lead vehicle position, the vehicle's speed is determined based on the speed of the preceding vehicle, and a vehicle boundary trajectory line is generated based on the driving information of adjacent straight traffic flow, so as to control the vehicle's straight-line driving by using the driving speed and the pre-set second safety interval distance between the vehicle and the vehicle boundary trajectory line.

6. A vehicle control device, characterized in that, include: The turning detection module is used to determine whether the vehicle needs to turn based on target information; The lane line detection module is used to detect whether there is a corresponding lane line for the waiting area in the current lane where the vehicle is located if a turn is required. The lane line generation module is used to generate virtual lane lines for the turning area of ​​the current lane based on a preset strategy if no. The first turning control module is used to control the vehicle to turn based on the virtual lane lines of the waiting area; If so, the second turning control module performs turning control on the vehicle based on the lane lines of the waiting-to-turn area; Specifically, the lane line generation module is used to determine the current position of the vehicle; the current position includes the position of the lead vehicle and the position of non-lead vehicles; if the vehicle is in the position of the lead vehicle, the virtual lane line of the waiting area of ​​the current lane is generated based on the adjacent waiting area lane lines and lane width on the side of the turning direction; if the vehicle is in the position of non-lead vehicles, the virtual lane line of the waiting area of ​​the current lane is generated based on the waiting traffic flow and lane width on the side of the turning direction. The first turning control module is specifically used to: if the vehicle is in the position of the lead vehicle, determine the traffic light status on the side of the current turning direction; if the traffic light status is green, determine the vehicle's longitudinal speed based on the average longitudinal speed of adjacent turning traffic and the corresponding first weighting coefficient, and the average speed of adjacent straight traffic and the corresponding second weighting coefficient, and control the vehicle to turn using the longitudinal speed and a pre-set first safety interval distance between the vehicle and the virtual lane line of the turning area; wherein, the first weighting coefficient is greater than the second weighting coefficient; if the traffic light status is red, control the vehicle to enter the corresponding turning waiting area based on the virtual lane line of the turning area, and after the traffic light status changes to green, jump to the step of determining the vehicle's longitudinal speed based on the average longitudinal speed of adjacent turning traffic and the corresponding first weighting coefficient, and the average speed of adjacent straight traffic and the corresponding second weighting coefficient, and controlling the vehicle to turn using the longitudinal speed and the pre-set first safety interval distance between the vehicle and the virtual lane line of the turning area.

7. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the steps of the vehicle control method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, Used to store a computer program; wherein, when executed by a processor, the computer program implements the steps of the vehicle control method as described in any one of claims 1 to 5.

Images