Intersection meeting control method and device, vehicle control equipment and storage medium

Abstract

The application discloses a kind of intersection meeting control method, device, vehicle control equipment and storage medium, comprising: in the process of main car driving, whether there is intersection in the side of main car lane away from opposite lane, front of main car;If yes, when detecting opposite lane has opposite car, first prediction trajectory of opposite car straight goes and second prediction trajectory of opposite car turns into intersection;The first similarity of the driving trajectory of opposite car and first prediction trajectory, and the second similarity of driving trajectory and second prediction trajectory are calculated, the driving intention of opposite car is determined according to first similarity and second similarity, and main car is controlled according to driving intention.It solves the problem that automatic driving vehicle cannot predict opposite car turns into intersection, leading to sudden braking collision risk, can slow down and avoid when predicting the driving intention of opposite car is turning into intersection, avoid sudden braking collision, improve the safety and the comfort of automatic driving vehicle in intersection meeting.

Description

Technical Field

[0001] The present invention relates to the technical field of autonomous driving vehicles, and in particular to a method and apparatus for controlling vehicles passing at an intersection, a vehicle control device, and a storage medium. Background Art

[0002] As more and more self-driving vehicles are driving on the road, it is inevitable that they will meet other vehicles at intersections.

[0003] like Figure 1 As shown, the main vehicle A (autonomous driving vehicle) and the oncoming vehicle B are traveling in opposite directions, and there is an intersection R3 to the right of the lane R1 where the main vehicle A is located. The main vehicle A cannot accurately identify whether the oncoming vehicle B intends to go straight along the lane R2 or turn left from the lane R2 to enter the intersection R3. If the main vehicle A cannot identify that the oncoming vehicle B is turning left to enter the intersection, the main vehicle A will not be able to avoid the oncoming vehicle turning left to enter the intersection R3 in advance, causing the main vehicle A to brake suddenly before driving to the intersection R3, and there is a risk of collision with the oncoming vehicle B. Summary of the Invention

[0004] The present invention provides a method, device, vehicle control equipment and storage medium for controlling intersection meeting, so as to solve the problem in the prior art that when an autonomous driving vehicle reaches an intersection, it is impossible to predict when an oncoming vehicle will turn to enter the intersection, resulting in a collision risk caused by the autonomous driving vehicle's sudden braking.

[0005] In a first aspect, the present invention provides a method for controlling a vehicle passing at an intersection, comprising:

[0006] During the driving process of the main vehicle, detecting whether the main vehicle lane is away from the opposite lane and whether there is an intersection in front of the main vehicle;

[0007] If yes, when an oncoming vehicle that has not passed the intersection is detected in the oncoming lane, a first predicted trajectory of the oncoming vehicle going straight and a second predicted trajectory of the oncoming vehicle turning to enter the intersection are generated;

[0008] Obtaining the driving trajectory of the oncoming vehicle,

[0009] calculating a first similarity between the driving trajectory and the first predicted trajectory, and calculating a second similarity between the driving trajectory and the second predicted trajectory;

[0010] The driving intention of the oncoming vehicle is determined according to the first similarity and the second similarity, and the host vehicle is controlled according to the driving intention.

[0011] In a second aspect, the present invention provides a road intersection meeting control device, comprising:

[0012] An intersection detection module is used to detect whether there is an intersection in front of the main vehicle when the main vehicle lane is away from the opposite lane during the main vehicle's driving process;

[0013] an oncoming vehicle trajectory prediction module, configured to, upon detecting an oncoming vehicle in the oncoming lane that has not yet passed the intersection, generate a first predicted trajectory of the oncoming vehicle traveling straight ahead and a second predicted trajectory of the oncoming vehicle turning to enter the intersection;

[0014] The oncoming vehicle driving trajectory acquisition module is used to obtain the driving trajectory of the oncoming vehicle.

[0015] a similarity calculation module, configured to calculate a first similarity between the driving trajectory and the first predicted trajectory, and to calculate a second similarity between the driving trajectory and the second predicted trajectory;

[0016] The host vehicle meeting control module is configured to determine the driving intention of the oncoming vehicle based on the first similarity and the second similarity, and control the host vehicle based on the driving intention.

[0017] In a third aspect, the present invention provides a vehicle control device, the vehicle control device comprising:

[0018] at least one processor; and

[0019] a memory communicatively connected to the at least one processor; wherein,

[0020] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the intersection meeting control method described in the first aspect of the present invention.

[0021] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a processor to implement the intersection meeting control method described in the first aspect of the present invention when executed.

[0022] In an embodiment of the present invention, when the main vehicle detects that the main vehicle lane is away from the opposite lane and there is an intersection in front of the main vehicle, a first predicted trajectory of the opposite vehicle going straight and a second predicted trajectory of the opposite vehicle turning to enter the intersection are generated, and the similarity between the actual driving trajectory of the main vehicle and the first predicted trajectory and the second predicted trajectory is calculated respectively, so as to determine whether the main vehicle's driving intention is to go straight or turn to enter the intersection based on the similarity, and control the main vehicle according to the driving intention, thereby realizing the automatic driving vehicle to accurately predict the driving intention of the opposite vehicle, and solving the problem that the automatic driving vehicle cannot predict the opposite vehicle turning to enter the intersection, resulting in the risk of collision due to sudden braking of the automatic driving vehicle. When the automatic driving vehicle predicts that the driving intention of the opposite vehicle is to turn to enter the intersection, the automatic driving vehicle slows down and avoids it in advance, avoiding collision due to sudden braking, thereby improving the safety of the automatic driving vehicle when meeting at intersections and the driving comfort.

[0023] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 Schematic diagram of a meeting scene at an intersection according to an embodiment of the present invention;

[0026] Figure 2 This is a flow chart of a method for controlling vehicles passing at an intersection provided by the first embodiment of the present invention;

[0027] Figure 3A This is a flow chart of a method for controlling vehicles passing at an intersection provided by the second embodiment of the present invention;

[0028] Figure 3B Schematic diagram of intersection detection;

[0029] Figure 3C Schematic diagram of calculating the similarity between the driving trajectory and the predicted trajectory in an embodiment of the present invention;

[0030] Figure 4 This is a schematic structural diagram of a vehicle intersection control device provided by the third embodiment of the present invention;

[0031] Figure 5 It is a structural diagram of a vehicle control device provided in Example 4 of the present invention. DETAILED DESCRIPTION

[0032] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0033] Example 1

[0034] Figure 2 This is a flow chart of a method for controlling a vehicle passing at an intersection provided by the first embodiment of the present invention. This embodiment is applicable to controlling a self-driving vehicle passing an oncoming vehicle at an intersection. The method can be executed by a vehicle passing control device at an intersection. The vehicle passing control device at an intersection can be implemented in the form of hardware and / or software. The vehicle passing control device at an intersection can be configured in a vehicle control device. The vehicle control device can be a driving computer of the self-driving vehicle or a remote server communicating with the self-driving vehicle. Figure 2 As shown, the intersection meeting control method includes:

[0035] S201: During the driving of the main vehicle, detect whether there is an intersection in front of the main vehicle and the side of the main vehicle lane away from the opposite lane.

[0036] In this embodiment, the main vehicle is an autonomous driving vehicle. The main vehicle lane is the lane in which the main vehicle is traveling. The opposite lane is a lane adjacent to the main vehicle lane and has a driving direction opposite to that of the main vehicle lane. For the keep right driving rule, the side of the main vehicle lane away from the opposite lane is the right side of the main vehicle lane. For the keep left driving rule, the side of the main vehicle lane away from the opposite lane is the left side of the main vehicle lane. This embodiment takes the keep right driving rule as an example.

[0037] like Figure 1 As shown in FIG, the main vehicle A is driving in the main vehicle lane R1, and the oncoming vehicle B is driving in the oncoming lane R2. During the driving process, the main vehicle A can detect whether there is an intersection in front of the main vehicle or on the right side of the main vehicle lane R1. Figure 1 As shown, it is possible to detect whether there is an intersection R3 in front of the host vehicle A.

[0038] In an optional embodiment, the distance from the center line of the main vehicle lane in front of the main vehicle A to the curb can be calculated. If the distance is greater than a preset distance threshold, it means that an intersection is detected. In another optional embodiment, the current position of the main vehicle A can be mapped to the semantic map to obtain the position of the main vehicle A in the semantic map, and based on the position, it is searched whether there is an intersection on the right side of the main vehicle lane within a preset range in front of the driving direction of the main vehicle A. In another optional embodiment, the environment in front of the main vehicle can be sensed by the sensor on the main vehicle A to obtain environmental data such as images and point clouds, and the environmental data such as images and point clouds can be input into a pre-trained intersection recognition model to identify the intersection. Of course, those skilled in the art can also identify whether there is an intersection by other means. The embodiment of the present invention does not limit the method of detecting the intersection.

[0039] like Figure 1 As shown, when the host vehicle A detects the host vehicle lane R1 and the right intersection R3 in front of the host vehicle A, S202 is executed. If no intersection is detected, the intersection meeting control process of this embodiment is terminated and the host vehicle is controlled to continue driving according to the original trajectory.

[0040] S202: When an oncoming vehicle that has not yet crossed the intersection is detected in the oncoming lane, a first predicted trajectory of the oncoming vehicle going straight and a second predicted trajectory of the oncoming vehicle turning to enter the intersection are generated.

[0041] An oncoming vehicle is a vehicle traveling in the opposite lane and opposite to the host vehicle. It can be either an autonomous vehicle or a human-driven vehicle. The host vehicle uses sensors to sense the environment and obtain environmental data. Based on this environmental data, the host vehicle identifies whether there is a vehicle in the opposite lane. If an oncoming vehicle is present in the opposite lane, the host vehicle obtains data such as its position, speed, acceleration, and vehicle heading to determine whether it has already passed through the detected intersection. If an oncoming vehicle is detected and has not yet passed through the intersection, the host vehicle generates a first predicted trajectory for the oncoming vehicle traveling straight ahead and a second predicted trajectory for the oncoming vehicle turning into the intersection.

[0042] Optionally, the main vehicle can use environmental data to determine the position of the oncoming vehicle after it goes straight through the intersection as the end point of the first predicted trajectory for straight travel, and the position of the oncoming vehicle after it turns and enters the intersection as the end point of the second predicted trajectory for turning travel. Then, after obtaining the status data of the oncoming vehicle, the first predicted trajectory and the second predicted trajectory are planned by combining the environmental data with trajectory planning algorithms such as search algorithms and quadratic optimization algorithms.

[0043] like Figure 1 As shown, the first predicted trajectory of the oncoming vehicle B going straight through the intersection is L1, and the second predicted trajectory of turning to enter the intersection R3 is L2. It should be noted that the first predicted trajectory L1 and the second predicted trajectory L2 can be updated according to the status data of the oncoming vehicle B according to a preset period.

[0044] S203: Obtain the driving trajectory of the oncoming vehicle.

[0045] The driving trajectory of the oncoming vehicle is the actual driving trajectory of the oncoming vehicle within a preset time period. The preset time period can be equal to the update period of the first predicted trajectory and the second predicted trajectory. The host vehicle can collect data such as the position, speed, acceleration, and head direction of the oncoming vehicle at multiple times through sensors to generate a driving trajectory.

[0046] S204 : Calculating a first similarity between the driving trajectory and the first predicted trajectory, and calculating a second similarity between the driving trajectory and the second predicted trajectory.

[0047] The driving trajectory is the actual driving trajectory of the oncoming vehicle within a preset time period. The driving trajectory has a start time and an end time. The trajectory from the start time to the end time can be intercepted from the first predicted trajectory, and the distance between the intercepted trajectory and the trajectory point of the driving trajectory at the same time, such as the position, speed, acceleration, and vehicle head direction, is calculated as the similarity of the two trajectory points. The sum of the similarities of multiple trajectory points is calculated as the first similarity between the driving trajectory and the first predicted trajectory. Similarly, the second similarity between the driving trajectory and the second predicted trajectory is calculated.

[0048] S205 : Determine the driving intention of the oncoming vehicle based on the first similarity and the second similarity, and control the host vehicle based on the driving intention.

[0049] The first similarity indicates the probability that the oncoming vehicle will travel along the first predicted trajectory, that is, the probability that the oncoming vehicle will go straight through the intersection. The second similarity indicates the probability that the oncoming vehicle will travel along the second predicted trajectory, that is, the probability that the oncoming vehicle will turn and enter the intersection. It is possible to determine whether the first similarity and the second similarity are greater than a preset threshold value, respectively. When the first similarity is greater than the preset threshold value, it indicates that the oncoming vehicle's driving intention is to go straight, and the main vehicle can be controlled to travel along the original trajectory, which is the trajectory of the main vehicle going straight through the intersection when the main vehicle does not detect the oncoming vehicle. When the second similarity is greater than the preset threshold value, it indicates that the oncoming vehicle's driving intention is to turn and enter the intersection. There may be an overlapping area between the main vehicle's driving trajectory and the trajectory of the oncoming vehicle turning and entering the intersection. The main vehicle can be controlled to reduce the time it takes to give way to the oncoming vehicle in advance, to avoid the risk of collision due to sudden braking when the main vehicle meets the oncoming vehicle.

[0050] In an embodiment of the present invention, when the main vehicle detects that the main vehicle lane is away from the opposite lane and there is an intersection in front of the main vehicle, a first predicted trajectory of the opposite vehicle going straight and a second predicted trajectory of the opposite vehicle turning to enter the intersection are generated, and the similarity between the actual driving trajectory of the main vehicle and the first predicted trajectory and the second predicted trajectory is calculated respectively to determine whether the main vehicle's driving intention is to go straight or turn to enter the intersection, and the main vehicle is controlled according to the driving intention, thereby enabling the autonomous driving vehicle to accurately predict the driving intention of the opposite vehicle, and solving the problem that the autonomous driving vehicle cannot predict the opposite vehicle turning to enter the intersection, resulting in the risk of collision when the autonomous driving vehicle brakes suddenly. When the autonomous driving vehicle predicts that the opposite vehicle's driving intention is to turn to enter the intersection, the autonomous driving vehicle can slow down and avoid it in advance, avoiding collision due to sudden braking, thereby improving the safety and driving comfort of the autonomous driving vehicle when meeting at intersections.

[0051] Example 2

[0052] Figure 3A This is a flow chart of a method for controlling vehicles passing at an intersection provided by the second embodiment of the present invention. The embodiment of the present invention is optimized based on the above-mentioned first embodiment. Figure 3A As shown, the intersection meeting control method includes:

[0053] S301: During the driving of the main vehicle, detect whether there is an intersection in front of the main vehicle and the side of the main vehicle lane away from the opposite lane.

[0054] In an optional embodiment of the present invention, the lane centerline of the main vehicle lane located within a preset range in front of the main vehicle and the curb of the main vehicle lane away from the opposite lane can be obtained, the lane centerline is sampled to obtain multiple sampling points, and the distance from each sampling point to the curb is calculated. When the distance is greater than a preset distance threshold, it is determined that the main vehicle lane is away from the opposite lane and there is an intersection in front of the main vehicle.

[0055] like Figure 3B As shown, the centerline X1 of the main vehicle lane R1 and the curb X3 of the main vehicle lane R1 can be obtained from the road network map, and the distance d from the point on the centerline X1 of the lane in front of the main vehicle A to the curb X3 is calculated. When d is greater than the set value, it means that the intersection R3 is detected. The intersection is detected by calculating the distance from the lane centerline to the curb, which is suitable for roads with relatively complete roads and curbs.

[0056] In another optional embodiment, the lane centerline of the main vehicle lane can be searched in a preset semantic map, and the current position and driving direction of the main vehicle can be mapped to the semantic map to determine whether there are other lane centerlines that are away from the opposite lane and connected to the lane centerline within a preset range in the driving direction of the current position; if so, it is determined that the main vehicle lane is away from the opposite lane and there is an intersection in front of the main vehicle, and the intersection is identified through the information on the semantic map, with a small amount of data and high accuracy and efficiency.

[0057] like Figure 3B As shown, a lane centerline X2 is connected to the lane centerline X1 of the main vehicle lane R1 in front of the main vehicle A. The lane centerline X2 is used to turn into the intersection, so it can be determined that the intersection is detected.

[0058] In another optional embodiment, the environmental data can be sensed by the sensor on the main vehicle and then input into the intersection recognition model to identify the intersection. Those skilled in the art can also identify the intersection in other ways, and the embodiment of the present invention does not limit this.

[0059] S302. When an oncoming vehicle that has not yet passed the intersection is detected in the opposite lane, a first target position and a second target position are determined. The first target position is the position of the oncoming vehicle after passing the intersection straight ahead, and the second target position is the position of the oncoming vehicle after turning and entering the intersection.

[0060] like Figure 1 As shown, when an oncoming vehicle B is detected in the opposite lane R2 that has not passed the intersection R3, the first target position P1 after the oncoming vehicle B goes straight through the intersection and the second target position P2 after the oncoming vehicle B turns and enters the intersection R3 can be determined based on the obstacle data, other vehicle data, lane line data and other data perceived by the main vehicle A.

[0061] S303. Using the current position of the oncoming vehicle as the starting position, the first target position and the second target position as the end positions, and the current state of the oncoming vehicle as the input of the path planning algorithm, a first predicted trajectory for the oncoming vehicle to go straight and a second predicted trajectory for the oncoming vehicle to turn and enter the intersection are generated.

[0062] like Figure 1 As shown, the current position of the oncoming vehicle B is P0, the first target position is P1, and the second target position is P2. A first predicted trajectory L1 for the oncoming vehicle B traveling straight ahead can be generated with the current position P0 as the starting position and the first target position P1 as the end position. A second predicted trajectory L2 for the oncoming vehicle B turning and entering intersection R3 can be generated with the current position P0 as the starting position and the second target position P2 as the end position. In one example, the first predicted trajectory L1 and the second predicted trajectory L2 can be generated using a path planning algorithm such as a search algorithm or a quadratic optimization algorithm, using data such as the current position, speed, and acceleration of the oncoming vehicle B as state data, and using constraints such as the dimensions of the oncoming vehicle B and obstacles perceived by the host vehicle.

[0063] It should be noted that the first predicted trajectory L1 and the second predicted trajectory L2 can be updated according to the status data of the oncoming vehicle B at a preset period.

[0064] S304: Obtain the driving trajectory of the oncoming vehicle.

[0065] The driving trajectory of the oncoming vehicle is the actual driving trajectory of the oncoming vehicle within a preset time period. The preset time period can be equal to the update period of the first predicted trajectory and the second predicted trajectory. The host vehicle can collect data such as the position, speed, acceleration, and head direction of the oncoming vehicle at multiple times through sensors to generate a driving trajectory.

[0066] S305: Obtain the start time and end time of the driving trajectory.

[0067] In this embodiment, the driving trajectory of the oncoming vehicle is the actual driving trajectory within a preset time period, and the driving trajectory has a start time and an end time, such as Figure 3C Shown is a schematic diagram of a first predicted trajectory L1, a second predicted trajectory L2, and a driving trajectory L3, where the starting time of the driving trajectory L3 is t1 and the ending time is t2.

[0068] S306 , intercepting the trajectory between the start time and the end time from the first predicted trajectory and the second predicted trajectory respectively to obtain a first sub-trajectory and a second sub-trajectory.

[0069] like Figure 3C As shown, the first sub-trajectory L is obtained by intercepting the trajectory between the start time t1 and the end time t2 from the first predicted trajectory L1. 1-2 , intercept the trajectory L between the start time t1 and the end time t2 from the second predicted trajectory L2 2-1 .

[0070] S307 : Calculate the similarity between the driving trajectory and the first sub-trajectory to obtain a first similarity, and calculate the similarity between the driving trajectory and the second sub-trajectory to obtain a second similarity.

[0071] Optionally, when calculating the similarity between the driving trajectory and the first sub-trajectory to obtain the first similarity, the driving trajectory L3 and the first sub-trajectory L can be respectively calculated at a preset time interval. 1-2 Sampling is performed to obtain multiple driving trajectory points on the driving trajectory and sub-trajectory points on the first sub-trajectory, each driving trajectory point and sub-trajectory point including at least one item of status data, a distance between the status data of the driving trajectory point and the sub-trajectory point at the same sampling moment is calculated to obtain a similarity between the driving trajectory point and the sub-trajectory point at the same sampling moment, a sum of the similarities of the driving trajectory points and the sub-trajectory points at multiple sampling moments is calculated to obtain a similarity between the driving trajectory and the first sub-trajectory to obtain a first similarity.

[0072] Assume that the driving trajectory point on the driving trajectory L3 is P1i(a 1i , v 1i , s 1i , x 1i ,y 1i , R 1i ), the first sub-trajectory L1-2 The sub-trajectory point on is P2i(a 2i ,v2i,s 2i , x 2i ,y 2i , R 2i ), where a is acceleration, v is velocity, s is displacement, x and y are two-dimensional coordinates, and R is the vehicle head direction. The Manhattan distance (L1 distance) or Euclidean distance (L2 distance) between the driving trajectory point P1i and the sub-trajectory point P2i can be calculated as the similarity between the driving trajectory point and the sub-trajectory point at the same sampling time i. Then, the similarity of the trajectory points at all sampling times is summed to obtain the driving trajectory L3 and the first sub-trajectory L 1-2 The first similarity of the driving trajectory L3 and the second sub-trajectory L can be calculated in the same way. 2-2 The second similarity.

[0073] This embodiment calculates trajectory similarity using multiple dimensions of state data, including acceleration, speed, displacement, coordinates, and vehicle heading. This allows the oncoming vehicle's driving intention to be reflected from these multiple dimensions. For example, when the speed decreases significantly, the vehicle heading changes significantly, or the acceleration increases, the probability of the oncoming vehicle turning into the intersection is higher, and the similarity between the driving trajectory and the second sub-trajectory is also higher. This allows the similarity to accurately reflect the oncoming vehicle's driving intention, improving the accuracy of the host vehicle's prediction of the oncoming vehicle's driving intention.

[0074] Of course, in another example, the driving trajectory L3 and the first sub-trajectory L 1-2 After the graph is generated, the similarity of the image is calculated as the driving trajectory L3 and the first sub-trajectory L 1-2 Alternatively, the driving trajectory point P1i and the sub-trajectory point P2i are input into the similarity prediction model to obtain the driving trajectory L3 and the first sub-trajectory L 1-2 The first similarity is calculated based on the first similarity. This embodiment does not limit the method for calculating the similarity.

[0075] S308: Determine whether the first similarity and the second similarity are greater than a similarity threshold.

[0076] Specifically, it is possible to determine whether the first similarity and the second similarity are greater than a similarity threshold, respectively. In this embodiment, the oncoming vehicle's driving intention is to go straight or turn, that is, the oncoming vehicle ultimately drives along one of the first predicted trajectory L1 and the second predicted trajectory L2. When one of the first similarity and the second similarity is larger, the other is smaller, that is, when one of the first similarity and the second similarity is greater than the similarity threshold, the other is less than the similarity threshold. When the first similarity is greater than the similarity threshold, S309 and S310 are executed, and when the second similarity is greater than the similarity threshold, S311 and S312 are executed. When both the first similarity and the second similarity are less than the similarity threshold, the driving intention of the oncoming vehicle cannot be determined, and the main vehicle can be controlled to slow down and wait until the driving intention of the oncoming vehicle is determined.

[0077] S309: When the first similarity is greater than the similarity threshold, determine that the driving intention of the oncoming vehicle is to go straight in the oncoming lane.

[0078] If the first similarity is greater than the similarity threshold, the acceleration, speed, displacement, coordinates, vehicle head orientation and other data of the oncoming vehicle are closer to the acceleration, speed, displacement, coordinates and vehicle head orientation of the corresponding trajectory points in the first predicted straight trajectory, indicating that the actual driving trajectory of the oncoming vehicle is more similar to the first predicted straight trajectory, and it can be determined that the oncoming vehicle's driving intention is to go straight in the opposite lane.

[0079] S310: Control the host vehicle to travel along the original trajectory, where the original trajectory is the trajectory of the host vehicle when it does not detect the oncoming vehicle.

[0080] Since the oncoming vehicle intends to go straight, there is no intersection between the oncoming vehicle and the host vehicle in the host vehicle lane, and the host vehicle can be controlled to drive according to the original trajectory, which is the driving trajectory of the host vehicle when the oncoming vehicle is detected.

[0081] S311: When the second similarity is greater than the similarity threshold, determine that the driving intention of the oncoming vehicle is to turn from the oncoming lane to enter the intersection.

[0082] If the second similarity is greater than the similarity threshold, the acceleration, speed, displacement, coordinates, vehicle head orientation and other data of the oncoming vehicle are closer to the acceleration, speed, displacement, coordinates, and vehicle head orientation of the corresponding trajectory points in the second predicted trajectory for turning into the intersection, indicating that the actual driving trajectory of the oncoming vehicle is more similar to the second predicted trajectory for turning into the intersection, and it can be determined that the oncoming vehicle's driving intention is to turn from the opposite lane into the intersection.

[0083] S312: Control the host vehicle to travel according to the second predicted trajectory control and the original trajectory.

[0084] Because the oncoming vehicle turns from the opposing lane into the intersection on the side of the host vehicle's lane, the oncoming vehicle's second predicted trajectory may intersect with the host vehicle's original trajectory. In one example, if the second predicted trajectory and the original trajectory determine that the host vehicle and the oncoming vehicle's driving areas overlap in time and space, the host vehicle is controlled to yield to the oncoming vehicle. For example, the host vehicle is controlled to reduce the amount of time it takes to yield to the oncoming vehicle before entering the intersection, and then the host vehicle is controlled to continue driving. Alternatively, the host vehicle is controlled to drive to the opposing lane to avoid the oncoming vehicle and return to the host vehicle's lane after passing the intersection. Of course, the host vehicle can also determine the avoidance cost of the oncoming vehicle and the host vehicle based on the overlapping driving area, the status data of the oncoming vehicle, and the status data of the host vehicle, with the party with the lower avoidance cost being the one to yield.

[0085] When an intersection is detected and there is an oncoming vehicle in the opposite lane that has not yet crossed the intersection, this embodiment generates a first predicted trajectory of the oncoming vehicle going straight and a second predicted trajectory of turning to enter the intersection, and obtains the start time and end time of the oncoming vehicle's driving trajectory within a preset time period. After respectively intercepting the trajectory from the start time to the end time from the first predicted trajectory and the second predicted trajectory to obtain the first sub-trajectory and the second sub-trajectory, the similarity between the driving trajectory and the first sub-trajectory is calculated to obtain a first similarity, and the similarity between the driving trajectory and the second sub-trajectory is calculated to obtain a second similarity. When the first similarity is greater than a similarity threshold, it is determined that the oncoming vehicle's driving intention is to go straight in the opposite lane. The system controls the main vehicle to go straight along the original trajectory, and when the second similarity is greater than the similarity threshold, determines that the oncoming vehicle's driving intention is to turn from the oncoming lane to enter the intersection, and controls the main vehicle to avoid the oncoming vehicle according to the second predicted trajectory control and the original trajectory, thereby realizing the automatic driving vehicle to accurately predict the driving intention of the oncoming vehicle, and solving the problem that the automatic driving vehicle cannot predict that the oncoming vehicle will turn to enter the intersection, resulting in the risk of collision when the automatic driving vehicle brakes suddenly. When the automatic driving vehicle predicts that the oncoming vehicle's driving intention is to turn to enter the intersection, the automatic driving vehicle can slow down and avoid it in advance, avoiding collision caused by sudden braking, thereby improving the safety of the automatic driving vehicle at intersections and the driving comfort.

[0086] Example 4

[0087] Figure 4 This is a schematic diagram of the structure of a vehicle intersection control device provided by the fourth embodiment of the present invention. Figure 4 As shown, the intersection meeting control device includes:

[0088] The intersection detection module 401 is used to detect whether there is an intersection in front of the main vehicle when the main vehicle lane is away from the opposite lane during the main vehicle's driving process;

[0089] an oncoming vehicle trajectory prediction module 402 for generating, upon detecting an oncoming vehicle in the oncoming lane that has not yet passed the intersection, a first predicted trajectory of the oncoming vehicle traveling straight ahead and a second predicted trajectory of the oncoming vehicle turning to enter the intersection;

[0090] The oncoming vehicle driving track acquisition module 403 is used to acquire the driving track of the oncoming vehicle.

[0091] a similarity calculation module 404, configured to calculate a first similarity between the driving trajectory and the first predicted trajectory, and to calculate a second similarity between the driving trajectory and the second predicted trajectory;

[0092] The host vehicle meeting control module 405 is configured to determine the driving intention of the oncoming vehicle according to the first similarity and the second similarity, and control the host vehicle according to the driving intention.

[0093] Optionally, the intersection detection module 401 includes:

[0094] a host vehicle lane data acquisition unit, configured to acquire a lane centerline of the host vehicle lane located within a preset range in front of the host vehicle, and acquire a curb of the host vehicle lane away from an oncoming lane;

[0095] A lane centerline sampling unit, configured to sample the lane centerline to obtain a plurality of sampling points;

[0096] a distance calculation unit, configured to calculate the distance from each sampling point to the roadside;

[0097] The first intersection determination unit is configured to determine that the host vehicle lane is away from the opposite lane and there is an intersection in front of the host vehicle when the distance is greater than a preset distance threshold.

[0098] Optionally, the intersection detection module 401 includes:

[0099] a semantic map processing unit, configured to search for a lane centerline of the host vehicle lane in a pre-set semantic map, and map the current position and driving direction of the host vehicle into the semantic map;

[0100] An intersection determination unit is configured to determine whether there is another lane centerline connected to the lane centerline and away from the opposite lane within a preset range in the driving direction of the lane centerline at the current position;

[0101] The second intersection determining unit is configured to determine that the host vehicle lane is away from the opposite lane and there is an intersection in front of the host vehicle.

[0102] Optionally, the oncoming vehicle trajectory prediction module 402 includes:

[0103] a target position determining unit, configured to determine a first target position and a second target position, wherein the first target position is the position of the oncoming vehicle after it passes the intersection straight ahead, and the second target position is the position of the oncoming vehicle after it turns and enters the intersection;

[0104] The trajectory prediction unit is used to use the current position of the oncoming vehicle as the starting position, the first target position and the second target position as the end positions, and the current state of the oncoming vehicle as the input of the path planning algorithm to generate a first predicted trajectory for the oncoming vehicle to go straight and a second predicted trajectory for the oncoming vehicle to turn and enter the intersection.

[0105] Optionally, the driving trajectory is a trajectory acquired according to a preset period, and the similarity calculation module 404 includes:

[0106] A time acquisition unit, used to obtain the start time and end time of the driving trajectory;

[0107] a sub-trajectory interception unit, configured to intercept the trajectory between the start time and the end time from the first predicted trajectory and the second predicted trajectory respectively, to obtain a first sub-trajectory and a second sub-trajectory;

[0108] The similarity calculation unit is configured to calculate the similarity between the driving trajectory and the first sub-trajectory to obtain a first similarity, and to calculate the similarity between the driving trajectory and the second sub-trajectory to obtain a second similarity.

[0109] Optionally, the similarity calculation unit includes:

[0110] a trajectory point sampling unit, configured to sample the driving trajectory and the first sub-trajectory at preset time intervals, respectively, to obtain a plurality of driving trajectory points on the driving trajectory and sub-trajectory points on the first sub-trajectory, each driving trajectory point and sub-trajectory point comprising at least one item of status data; each driving trajectory point and sub-trajectory point comprising at least one item of status data;

[0111] a trajectory point similarity calculation unit, configured to calculate the distance between the state data of the driving trajectory point and the sub-trajectory point at the same sampling moment to obtain the similarity between the driving trajectory point and the sub-trajectory point at the same sampling moment;

[0112] The summing unit is configured to calculate the sum of similarities between the driving trajectory points and the sub-trajectory points at multiple sampling moments, and obtain the similarity between the driving trajectory and the first sub-trajectory to obtain a first similarity.

[0113] Optionally, the host vehicle meeting control module 405 includes:

[0114] a similarity determination unit, configured to determine whether the first similarity and the second similarity are greater than a similarity threshold;

[0115] a first driving intention determining unit, configured to determine, when the first similarity is greater than the similarity threshold, that the driving intention of the oncoming vehicle is to go straight in the oncoming lane;

[0116] a first control unit, configured to control the host vehicle to travel according to an original trajectory, wherein the original trajectory is the trajectory of the host vehicle when the host vehicle does not detect the oncoming vehicle;

[0117] a second driving intention determining unit, configured to determine, when the second similarity is greater than the similarity threshold, that the driving intention of the oncoming vehicle is to turn from the oncoming lane into the intersection;

[0118] A second control unit is used to control the main vehicle to travel according to the second predicted trajectory and the original trajectory.

[0119] Optionally, the second control unit includes:

[0120] A yield control unit is configured to control the host vehicle to yield to the oncoming vehicle when it is determined that there is an overlapping driving area between the host vehicle and the oncoming vehicle based on the second predicted trajectory and the original trajectory.

[0121] The intersection meeting control device provided in the embodiment of the present invention can execute the intersection meeting control method provided in the first and second embodiments of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0122] Example 4

[0123] Figure 5 A schematic diagram of a vehicle control device 50 that can be used to implement the present invention is shown. The vehicle control device is intended to represent devices including various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers.

[0124] like Figure 5As shown, the vehicle control device includes at least one processor 51 and a memory, such as a read-only memory (ROM) 52, a random access memory (RAM) 53, etc., which is communicatively connected to the at least one processor 51. The memory stores a computer program that can be executed by the at least one processor, and the processor 51 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 52 or the computer program loaded from the storage unit 58 into the random access memory (RAM) 53. Various programs and data required for the operation of the vehicle control device 50 can also be stored in the RAM 53. The processor 51, ROM 52, and RAM 53 are connected to each other via a bus 54. An input / output (I / O) interface 55 is also connected to the bus 54.

[0125] Multiple components in the vehicle control device 50 are connected to the I / O interface 55, including an input unit 56, such as a keyboard, a mouse, a camera for acquiring depth images, etc.; an output unit 57, such as various types of displays, speakers, etc.; a storage unit 58, such as a magnetic disk, an optical disk, etc.; and a communication unit 59, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 59 allows the vehicle control device 50 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0126] The processor 51 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 51 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 51 executes the various methods and processes described above, such as the intersection meeting control method.

[0127] In some embodiments, the intersection meeting control method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 58. In some embodiments, part or all of the computer program can be loaded and / or installed on the vehicle control device 50 via the ROM 52 and / or the communication unit 59. When the computer program is loaded into the RAM 53 and executed by the processor 51, the intersection meeting control method described above and / or one or more steps of the detection method can be performed. Alternatively, in other embodiments, the processor 41 can be configured to execute the intersection meeting control method by any other appropriate means (e.g., by means of firmware).

[0128] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0129] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0130] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0131] To provide interaction with a user, the systems and techniques described herein can be implemented on a vehicle control device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the vehicle control device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and the input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0132] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0133] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0134] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0135] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for controlling vehicles meeting at an intersection, characterized in that: include: During the driving process of the main vehicle, detecting whether the main vehicle lane is away from the opposite lane and whether there is an intersection in front of the main vehicle; If yes, when an oncoming vehicle that has not passed the intersection is detected in the oncoming lane, a first predicted trajectory of the oncoming vehicle going straight and a second predicted trajectory of the oncoming vehicle turning to enter the intersection are generated; Obtaining the driving trajectory of the oncoming vehicle, calculating a first similarity between the driving trajectory and the first predicted trajectory, and calculating a second similarity between the driving trajectory and the second predicted trajectory; determining a driving intention of the oncoming vehicle based on the first similarity and the second similarity, and controlling the host vehicle based on the driving intention; The driving trajectory is a trajectory acquired according to a preset period, and the calculating of a first similarity between the driving trajectory and the first predicted trajectory, and the calculating of a second similarity between the driving trajectory and the second predicted trajectory, include: Obtain the start time and end time of the driving trajectory; intercepting the trajectory between the start time and the end time from the first predicted trajectory and the second predicted trajectory respectively to obtain a first sub-trajectory and a second sub-trajectory; Calculating the similarity between the driving trajectory and the first sub-trajectory to obtain a first similarity, and calculating the similarity between the driving trajectory and the second sub-trajectory to obtain a second similarity; Calculating the similarity between the driving trajectory and the first sub-trajectory to obtain a first similarity includes: Sampling the driving trajectory and the first sub-trajectory at preset time intervals to obtain a plurality of driving trajectory points on the driving trajectory and sub-trajectory points on the first sub-trajectory, each driving trajectory point and sub-trajectory point containing at least one item of status data; Calculating the distance between the state data of the driving trajectory point and the state data of the sub-trajectory point at the same sampling moment to obtain the similarity between the driving trajectory point and the sub-trajectory point at the same sampling moment; The sum of similarities between the driving trajectory points and the sub-trajectory points at multiple sampling moments is calculated to obtain a first similarity between the driving trajectory and the first sub-trajectory.

2. The method according to claim 1, wherein The detecting, during the driving process of the main vehicle, that the lane of the main vehicle is away from the opposite lane and whether there is an intersection in front of the main vehicle includes: Obtaining a lane centerline of the host vehicle lane located within a preset range in front of the host vehicle, and obtaining a curb of the host vehicle lane away from an oncoming lane; Sampling the lane centerline to obtain a plurality of sampling points; Calculating the distance from each sampling point to the roadside; When the distance is greater than a preset distance threshold, it is determined that the host vehicle lane is away from the opposite lane and there is an intersection in front of the host vehicle.

3. The method according to claim 1, wherein The detecting, during the driving process of the main vehicle, that the lane of the main vehicle is away from the opposite lane and whether there is an intersection in front of the main vehicle includes: Searching for a lane centerline of the host vehicle lane in a pre-set semantic map, and mapping the current position and driving direction of the host vehicle into the semantic map; Determining whether there is another lane centerline connected to the lane centerline, which is away from the opposite lane and within a preset range in the driving direction of the current position; If so, it is determined that the host vehicle lane is away from the opposite lane and there is an intersection in front of the host vehicle.

4. The method according to claim 1, wherein When an oncoming vehicle that has not yet passed the intersection is detected in the oncoming lane, a first predicted trajectory of the oncoming vehicle going straight and a second predicted trajectory of the oncoming vehicle turning to enter the intersection are generated, including: Determine a first target position and a second target position, wherein the first target position is the position of the oncoming vehicle after it passes the intersection straight ahead, and the second target position is the position of the oncoming vehicle after it turns and enters the intersection; Taking the current position of the oncoming vehicle as the starting position, the first target position and the second target position as the end positions respectively, and the current state of the oncoming vehicle as the input of the trajectory planning algorithm, a first predicted trajectory of the oncoming vehicle going straight and a second predicted trajectory of the oncoming vehicle turning to enter the intersection are generated.

5. The method according to claim 1, wherein The determining the driving intention of the oncoming vehicle according to the first similarity and the second similarity, and controlling the host vehicle according to the driving intention, includes: Determining whether the first similarity and the second similarity are greater than a similarity threshold; When the first similarity is greater than the similarity threshold, determining that the driving intention of the oncoming vehicle is to go straight in the oncoming lane; Controlling the host vehicle to travel along an original trajectory, where the original trajectory is the trajectory of the host vehicle when the host vehicle does not detect the oncoming vehicle; When the second similarity is greater than the similarity threshold, determining that the driving intention of the oncoming vehicle is to turn from the oncoming lane into the intersection; The host vehicle is controlled to travel according to the second predicted trajectory and the original trajectory.

6. The method according to claim 5, wherein The controlling the host vehicle to travel according to the second predicted trajectory and the original trajectory includes: When it is determined that the host vehicle and the oncoming vehicle have an overlapping driving area according to the second predicted trajectory and the original trajectory, the host vehicle is controlled to give way to the oncoming vehicle.

7. A road intersection control device, characterized in that: include: An intersection detection module is used to detect whether there is an intersection in front of the main vehicle when the main vehicle lane is away from the opposite lane during the main vehicle's driving process; an oncoming vehicle trajectory prediction module, configured to, upon detecting an oncoming vehicle in the oncoming lane that has not yet passed the intersection, generate a first predicted trajectory of the oncoming vehicle traveling straight ahead and a second predicted trajectory of the oncoming vehicle turning to enter the intersection; The oncoming vehicle driving trajectory acquisition module is used to obtain the driving trajectory of the oncoming vehicle. a similarity calculation module, configured to calculate a first similarity between the driving trajectory and the first predicted trajectory, and to calculate a second similarity between the driving trajectory and the second predicted trajectory; a host vehicle meeting control module, configured to determine a driving intention of the oncoming vehicle based on the first similarity and the second similarity, and control the host vehicle based on the driving intention; The driving trajectory is a trajectory obtained according to a preset period, and the similarity calculation module includes: A time acquisition unit, used to obtain the start time and end time of the driving trajectory; a sub-trajectory interception unit, configured to intercept the trajectory between the start time and the end time from the first predicted trajectory and the second predicted trajectory respectively, to obtain a first sub-trajectory and a second sub-trajectory; a similarity calculation unit, configured to calculate a similarity between the driving trajectory and the first sub-trajectory to obtain a first similarity, and to calculate a similarity between the driving trajectory and the second sub-trajectory to obtain a second similarity; The similarity calculation unit includes: a trajectory point sampling unit, configured to sample the driving trajectory and the first sub-trajectory at preset time intervals, respectively, to obtain a plurality of driving trajectory points on the driving trajectory and sub-trajectory points on the first sub-trajectory, each driving trajectory point and sub-trajectory point comprising at least one item of status data; a trajectory point similarity calculation unit, configured to calculate the distance between the state data of the driving trajectory point and the sub-trajectory point at the same sampling moment to obtain the similarity between the driving trajectory point and the sub-trajectory point at the same sampling moment; The summing unit is configured to calculate the sum of similarities between the driving trajectory points and the sub-trajectory points at multiple sampling moments, and obtain the similarity between the driving trajectory and the first sub-trajectory to obtain a first similarity.

8. A vehicle control device, characterized in that: The vehicle control device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the intersection meeting control method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the intersection meeting control method according to any one of claims 1 to 6 when executed.

Images