Control method and computer program product for autonomous driving vehicle

Abstract

The present invention relates to a control method for an autonomous vehicle, comprising the steps of: detecting an intersection area in front of the autonomous vehicle, the intersection area being jointly formed by a current road and a lateral road, in a case where the autonomous vehicle runs straight along the current road; identifying a target vehicle close to the intersection area on the transverse road, wherein the estimated driving route of the target vehicle intersects with or at least partially coincides with the navigation route of the autonomous vehicle; evaluating a priority passing coefficient, wherein the vehicle with the higher priority passing coefficient has the priority passing right; when the autonomous vehicle does not have the priority right of passing, identifying at least one road user facing one side of the lateral road of the autonomous vehicle, the road user having an estimated trajectory of movement crossing the intersection area in a direction parallel to the current road; and S5, controlling the automatic driving vehicle to continue driving along the navigation route. The invention also relates to a computer program product. The traffic flow is optimized, the passing time is obviously shortened, the traffic jam is avoided, and the riding experience is improved.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a control method for an autonomous driving vehicle. The present invention also relates to a corresponding computer program product. Background Art

[0002] In recent years, with the progress of society and the development of technology, the vehicle's autonomous driving technology has received more and more attention and application. Autonomous driving vehicles can significantly improve the riding experience, reduce traffic accidents caused by human errors or fatigue, and thus improve traffic safety.

[0003] For safety reasons, autonomous vehicles are controlled to drive more cautiously than typical drivers. In particular, when an autonomous vehicle is driving straight ahead and encounters an intersection formed by a current road and a lateral road, if there is a target vehicle on the lateral road that intends to merge into the current lane or cross the current lane, the autonomous vehicle will stop to give way, which may cause the autonomous vehicle to wait for a long time, significantly prolong the driving time, and may cause unexpected traffic congestion, thereby adversely affecting the riding experience. Summary of the invention

[0004] Therefore, the purpose of the present invention is to propose an improved control method for autonomous driving vehicles, by which the autonomous driving vehicle can pass through the intersection area as quickly as possible while ensuring driving safety and legality and compliance, so as to optimize traffic flow and significantly shorten the travel time, thereby avoiding traffic congestion and improving the riding experience.

[0005] According to a first aspect of the present invention, a control method for an autonomous driving vehicle is provided, wherein the control method comprises at least the following steps:

[0006] S1: When the autonomous driving vehicle is traveling straight along a current road, detecting an intersection area in front of the autonomous driving vehicle, where the intersection area is formed by the current road and at least one lateral road;

[0007] S2: Identifying a target vehicle located on the lateral road and close to the intersection area, wherein the estimated driving route of the target vehicle intersects or at least partially overlaps with the navigation route of the autonomous driving vehicle;

[0008] S3: Evaluate the priority coefficients of the autonomous driving vehicle and the target vehicle respectively, and the vehicle with a higher priority coefficient has the right of way;

[0009] S4: when the autonomous driving vehicle does not have the right of way, identifying at least one road user located on a side of the autonomous driving vehicle facing the lateral road, the road user having an estimated movement trajectory crossing the intersection area in a direction parallel to the current road;

[0010] S5: Control the autonomous driving vehicle to continue traveling along the navigation route.

[0011] Compared with the prior art, in the control method for an autonomous driving vehicle according to the present invention, during the straight-moving process of the autonomous driving vehicle, when an intersection area formed by the current road and the lateral road in front is detected, a target vehicle located on the lateral road that may interfere with the autonomous driving vehicle is identified, and then the priority coefficients of the autonomous driving vehicle and the target vehicle are evaluated to determine which vehicle has the right of priority. When the autonomous driving vehicle does not have the right of priority, a road user who is about to cross the intersection area and is located on the side of the autonomous driving vehicle facing the lateral road is identified. In this case, the target vehicle on the lateral road will inevitably stop in order to avoid hitting the road user. The time period when the road user crosses the intersection area is utilized to control the autonomous driving vehicle to drive through the intersection area. Therefore, even if the autonomous driving vehicle does not have the right of priority, it can still drive through the intersection area as quickly as possible while ensuring driving safety. This can significantly shorten the travel time, avoid traffic congestion, and improve the riding experience.

[0012] Exemplarily, the priority coefficient is calculated based on the following factors: road signs, traffic signals, driving speed, distance relative to the intersection area, and vehicle type.

[0013] Exemplarily, when the road sign indicates that a driving direction is a priority direction and there is no traffic light, the priority coefficient of vehicles traveling along the driving direction is higher.

[0014] Exemplarily, the faster the vehicle travels and / or the shorter the distance from the intersection area, the higher the priority coefficient of the vehicle.

[0015] Exemplarily, when the vehicle type of the vehicle is a school bus or an emergency vehicle with warning lights, the priority coefficient of the vehicle is higher.

[0016] Exemplarily, each factor used to calculate the priority coefficient is provided with a weight value, and the weight value is obtained from empirical data and / or experimental data.

[0017] Exemplarily, in step S4, the position of the road user relative to the intersection area is additionally detected, and step S5 is implemented only when the road user has entered a predetermined range of the intersection area; and / or, in step S4, the movement speed of the road user is additionally detected, and when the movement speed decreases to zero, the autonomous driving vehicle is controlled to slow down and give way.

[0018] Exemplarily, the control method additionally comprises the following steps:

[0019] S6: When the autonomous driving vehicle does not have the right of way and does not identify the road user, controlling the autonomous driving vehicle to slow down and yield;

[0020] S7: When the autonomous driving vehicle has the right of way, control the autonomous driving vehicle to continue traveling along the navigation route.

[0021] Exemplarily, in the case where the current road has multiple lanes, the control method is implemented only when the current lane in which the autonomous driving vehicle is located is an edge lane adjacent to the lateral road.

[0022] Exemplarily, the estimated driving route of the target vehicle is determined based on the type of the intersection area, the driving direction of the target vehicle, the type of lane in which the target vehicle is located, and the turn signal information of the target vehicle, wherein the type of the intersection area is a crossroads, a T-junction, or a multi-way intersection, and the lane type is a through lane, a left-turn lane, or a right-turn lane, wherein the estimated driving route of the target vehicle is selected from the following groups: turning to merge into the current road, turning to merge into the opposite road of the current road, and going straight through the current road; and / or, the estimated action trajectory of the road user is calculated by an object tracking algorithm.

[0023] Exemplarily, the intersection area is detected by environmental sensors of the autonomous driving vehicle and / or based on a digital map stored in the autonomous driving vehicle; and / or, the target vehicle and the road user are identified by environmental sensors of the autonomous driving vehicle in combination with an image processing algorithm.

[0024] Exemplarily, the environmental sensors include millimeter-wave radars and / or cameras and / or lidars arranged at the front and sides of the autonomous driving vehicle; and / or the image processing algorithm includes an object classifier and / or a convolutional neural network algorithm; and / or the road user is a pedestrian or a two-wheeler rider.

[0025] According to a second aspect of the present invention, there is provided a computer program product comprising a computer program, when the computer program is executed by one or more processors, the processors are capable of performing the control method according to the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The present invention will be described in more detail below with reference to the accompanying drawings, so that the principles, features and advantages of the present invention can be better understood. The accompanying drawings include:

[0027] Figure 1 A schematic flow chart of a control method for an autonomous driving vehicle according to an exemplary embodiment of the present invention is shown;

[0028] Figure 2a and Figure 2b Driving scenarios of a control method for an autonomous driving vehicle according to different exemplary embodiments of the present invention are respectively shown. DETAILED DESCRIPTION

[0029] In order to make the technical problems, technical solutions and beneficial technical effects to be solved by the present invention more clearly understood, the present invention will be further described in detail below in conjunction with the accompanying drawings and multiple exemplary embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the scope of protection of the present invention.

[0030] It should be understood that, in this document, the expressions "first", "second", etc. are used for descriptive purposes only and should not be understood as indicating or implying relative importance, nor should they be understood as implicitly indicating the number of technical features indicated. Features defined as "first" or "second" may explicitly or implicitly indicate that at least one of the features is included.

[0031] Figure 1 A schematic flow chart of a control method for an autonomous driving vehicle 1 according to an exemplary embodiment of the present invention is shown. Figure 2a and Figure 2b The driving scenarios of the control method for the autonomous driving vehicle 1 according to different exemplary embodiments of the present invention are respectively shown. In the framework of the present invention, an "autonomous driving vehicle" is to be understood as a vehicle that is conditionally automated, i.e., level L3, or highly automated, i.e., level L4, or fully automated, i.e., level L5. Figure 2a The driving situation shown illustrates the control method according to the invention.

[0032] like Figure 1 As shown, the control method for the automatic driving vehicle 1 according to the present invention comprises at least the following steps:

[0033] S1: When the autonomous driving vehicle 1 is traveling straight along the current road 10 according to the navigation route L1, the intersection area 30 in front of the autonomous driving vehicle 1 is detected. The intersection area 30 is formed by the current road 10 and at least one transverse road 20. In the framework of the present invention, the "transverse road" should be understood as a road that is not parallel to the current road 10 and intersects at the intersection area 30, wherein the transverse road 20 can extend perpendicular to the current road 10, i.e., forming a T-shaped intersection, but can also form another angle with the current road 20 that is considered meaningful by those skilled in the art, such as 45° or 60°, i.e., forming a Y-shaped intersection. Here, the navigation route L1 can be predetermined by the navigation unit of the autonomous driving vehicle 1, and the intersection area 30 can be detected by the environmental sensors of the autonomous driving vehicle 1, such as millimeter wave radars and / or cameras and / or laser radars arranged at the front and sides of the autonomous driving vehicle 1. In addition, it is also possible that the intersection area 30 is directly acquired based on a digital map stored in the navigation unit of the autonomous driving vehicle 1, especially a high-precision digital map;

[0034] S2: The target vehicle 2 located on the lateral road 20 and close to the intersection area 30 is identified by the environmental sensor of the autonomous driving vehicle 1. The estimated driving route L2 of the target vehicle 2 intersects or at least partially overlaps with the navigation route L1 of the autonomous driving vehicle 1. In this case, if the autonomous driving vehicle 1 and the target vehicle 2 do not slow down to give way, a collision accident between the two is likely to occur.

[0035] S3: Evaluate the priority coefficients of the autonomous driving vehicle 1 and the target vehicle 2 respectively, wherein the priority coefficient is a quantitative indicator for evaluating the degree of priority of a vehicle under specific circumstances and can be calculated in combination with multiple factors to be used for dynamic priority allocation of traffic scheduling and autonomous driving decision-making, wherein a vehicle with a higher priority coefficient has the right of way;

[0036] S4: When the autonomous driving vehicle 1 does not have the right of way, that is, the priority coefficient of the autonomous driving vehicle 1 in step S3 is lower than the priority coefficient of the target vehicle 2, at least one road user 3 located on the side of the autonomous driving vehicle 1 facing the lateral road 20 is identified through the environmental sensor of the autonomous driving vehicle 1. The road user may be a pedestrian or a two-wheeled vehicle rider, such as a bicycle or a motorcycle rider. The road user 3 has an estimated action trajectory L3 that crosses the intersection area 30 in a direction parallel to the current road 10. The estimated action trajectory L3 just crosses the front of the target vehicle 2, so that the target vehicle 2 has to stop and wait for the road user 3 to pass.

[0037] S5: Using the time when the road user 3 passes through the intersection area 30 , the automatic driving vehicle 1 is controlled to continue driving along the navigation route L1 through the intersection area 30 in a manner parallel to the road user 3 .

[0038] In this case, even if the target vehicle 2 on the lateral road 20 has the right of way, the autonomous driving vehicle 1 can still quickly pass through the intersection area 30 under the cover of the road users 3, which greatly saves unnecessary waiting time, thereby shortening the travel time and avoiding traffic congestion as much as possible, thereby improving the riding experience of the occupants of the autonomous driving vehicle 1.

[0039] Exemplarily, the method according to the present invention may also additionally include the following steps:

[0040] S6: When the autonomous driving vehicle 1 does not have the right of way and does not identify the road user 3 on the side of the autonomous driving vehicle 1 facing the lateral road 20, the autonomous driving vehicle 1 is controlled to slow down and yield, so that the target vehicle 2 with the right of way passes through the intersection area 30 first, thereby avoiding a traffic accident and assuming the responsibility for the accident;

[0041] S7: When the autonomous driving vehicle 1 has the right of way, that is, the priority coefficient of the autonomous driving vehicle 1 in step S3 is higher than the priority coefficient of the target vehicle 2, the target vehicle 2 on the lateral road 20 should slow down and give way, so the autonomous driving vehicle 1 is controlled to continue driving directly along the navigation route L1 through the intersection area 30 without additionally identifying the road user 3 on the side of the autonomous driving vehicle 1 facing the lateral road 20.

[0042] Exemplarily, in step S3, the priority coefficient of each vehicle can be calculated based on the following factors: road sign 4, traffic signal, driving speed, distance from the intersection area 30, and vehicle type. Here, the road sign 4 can be a stop and yield sign or a main road sign, which clarifies the order of vehicles in different ways to improve safety and traffic efficiency. For example, the stop and yield sign has a red octagonal sign and is marked with the words "STOP" or "stop". The vehicle must stop completely before the stop and yield sign and ensure that no other vehicles are coming before passing. In addition, when the traffic signal is green, the vehicle has the right of way, and when the traffic signal is red, the vehicle must stop and yield. In particular, when the road sign 4 indicates that a driving direction is a priority direction and there is no traffic light, the priority coefficient of the vehicle traveling in the driving direction is higher. In addition, the faster the vehicle's driving speed and / or the shorter the distance from the intersection area 30, the faster the vehicle arrives and passes through the intersection area 30, and the higher the priority coefficient of the vehicle. In particular, when the vehicle type is a school bus or an emergency vehicle with warning lights, such as a police car, a fire truck or an ambulance, the priority coefficient of the vehicle is higher. Here, each factor used to calculate the priority coefficient is provided with a weight value, which can be obtained from empirical data and / or experimental data. For example, the weight value for road signs 4 and traffic signals is significantly greater than the weight value for vehicle speed.

[0043] Exemplarily, the target vehicle 2 and the road user 3 are identified by the environmental sensors of the autonomous driving vehicle 1 in combination with an image processing algorithm, wherein the environmental sensors include a millimeter wave radar and / or a camera and / or a laser radar arranged at the front and side of the autonomous driving vehicle 1, and the image processing algorithm includes a trained object classifier and / or a convolutional neural network algorithm. In particular, the estimated action trajectory L3 of the road user 3 can be calculated by the trained object tracking algorithm to estimate the action trajectory and future behavior of the road user 3 in real time.

[0044] Exemplarily, in step S4, the position of the road user 3 relative to the intersection area 30, in particular the sidewalk, is additionally detected. Only when the road user 3 has entered a predetermined range of the intersection area 30, such as an intermediate range of 20% to 80% of the sidewalk, is step S5 implemented to allow the automated driving vehicle 1 to continue traveling along the navigation route L1, thereby ensuring that the target vehicle 2 will stop to allow the road user 3 to pass the sidewalk first.

[0045] Exemplarily, in step S4, the movement speed of the road user 3 is additionally detected. When the movement speed decreases to zero, that is, the road user 3 stops moving in the intersection area 30, this indicates that the road user 3 may be giving way to the target vehicle 2. Therefore, the automatic driving vehicle 1 is controlled to slow down and give way accordingly, thereby reliably improving driving safety.

[0046] For example, Figure 2a and Figure 2b As shown, the estimated driving route L2 of the target vehicle 2 is determined according to the type of the intersection area 30, the driving direction of the target vehicle 2, the type of lane in which the target vehicle 2 is located, and the turn signal information of the target vehicle 2. Here, the type of the intersection area 30 may be a crossroads, a T-junction, or a multi-way intersection; the driving direction of the target vehicle 2 may be determined by the direction of the vehicle head; the type of lane in which the target vehicle 2 is located may be a straight lane, a left-turn lane, or a right-turn lane, and the lane type may be obtained from the signs on the lane or from the digital map stored in the navigation unit of the autonomous driving vehicle 1; and the turn signal information of the target vehicle 2 may be identified by the environmental sensors of the autonomous driving vehicle 1. In particular, the estimated driving route L2 of the target vehicle 2 may be selected from the following groups: turning to merge into the current road 10, turning to merge into the opposite road of the current road 10, and going straight through the current road 10. Figure 2a In FIG. 1 , the estimated driving route L2 of the target vehicle 2 merges into the current road 10 by turning left, and the estimated driving route L2 partially overlaps with the navigation route L1 of the autonomous driving vehicle 1. Figure 2b In the example, the estimated driving route L2 of one target vehicle 2 is to merge into the current road 10 by turning right, while the estimated driving route L2 of another target vehicle 2 is to go straight through the current road 10, and the estimated driving route intersects with the navigation route L1 of the autonomous driving vehicle 1. However, it is also possible that the estimated driving route L2 of the target vehicle 2 is to merge into the opposite road of the current road 10 by turning left, and the estimated driving route also intersects with the navigation route L1 of the autonomous driving vehicle 1.

[0047] For example, Figure 2b As shown, in the case where the current road 10 has multiple lanes, the control method according to the present invention is implemented only when the current lane where the autonomous driving vehicle 1 is located is an edge lane adjacent to the lateral road 20. When the current lane where the autonomous driving vehicle 1 is located is the middle lane of the current road 10, the autonomous driving vehicle 1 can be controlled to directly pass through the intersection area 30 without considering the target vehicle 2 on the lateral road 20.

[0048] The present invention also relates to a computer program product, which includes a computer program, and when the computer program is executed by one or more processors, the processors are capable of executing the control method according to the present invention for the autonomous driving vehicle 1. Here, the computer program product according to the present invention is arranged in a vehicle control unit of the autonomous driving vehicle 1, for example.

[0049] The above explanation of the embodiments only describes the invention within the framework of the examples. Of course, the individual features of the embodiments can be freely combined with one another as long as it makes technical sense, without departing from the framework of the invention.

[0050] Other advantages and alternative embodiments of the present invention are obvious to those skilled in the art. Therefore, the present invention in its broader sense is not limited to the specific details, representative structures and exemplary embodiments shown and described. On the contrary, those skilled in the art can make various modifications and substitutions without departing from the basic spirit and scope of the present invention.

Claims

1. A control method for an autonomous driving vehicle (1), characterized in that: The control method comprises at least the following steps: S1: When the autonomous driving vehicle (1) is traveling straight along a current road (10), detecting an intersection area (30) in front of the autonomous driving vehicle (1), wherein the intersection area (30) is formed by the current road (10) and at least one lateral road (20); S2: Identifying a target vehicle (2) located on the lateral road (20) and close to the intersection area (30), wherein an estimated driving route (L2) of the target vehicle (2) intersects or at least partially overlaps with a navigation route (L1) of the autonomous driving vehicle (1); S3: Evaluate the priority coefficients of the autonomous driving vehicle (1) and the target vehicle (2) respectively, and the vehicle with a higher priority coefficient has the right of way; S4: when the autonomous driving vehicle (1) does not have the right of way, identifying at least one road user (3) located on a side of the autonomous driving vehicle (1) facing the lateral road (20), the road user (3) having an estimated action trajectory (L3) passing through the intersection area (30) in a direction parallel to the current road (10); S5: Control the autonomous driving vehicle (1) to continue traveling along the navigation route (L1).

2. The control method according to claim 1, characterized in that: The priority coefficient is calculated based on the following factors: road signs (4), traffic signals, driving speed, distance relative to the intersection area (30), and vehicle type.

3. The control method according to claim 2, characterized in that: When the road sign (4) indicates that a driving direction is a priority direction and there is no traffic light, the priority coefficient of vehicles traveling in this driving direction is higher; and / or The faster the vehicle is traveling and / or the shorter the distance from the intersection area (30), the higher the priority coefficient of the vehicle; and / or When the vehicle type of the vehicle is a school bus or an emergency vehicle with hazard lights, the vehicle has a higher priority factor; and / or Each factor used to calculate the priority coefficient is provided with a weight value, and the weight value is obtained from empirical data and / or experimental data.

4. A control method according to any one of the preceding claims, characterized in that In step S4, the position of the road user (3) relative to the intersection area (30) is additionally detected, and step S5 is performed only when the road user (3) has entered a predetermined range of the intersection area (30); and / or In step S4, the movement speed of the road user (3) is additionally detected, and when the movement speed decreases to zero, the automatic driving vehicle (1) is controlled to slow down and give way.

5. A control method according to any one of the preceding claims, characterized in that The control method additionally comprises the following steps: S6: When the autonomous driving vehicle (1) does not have the right of way and does not identify the road user (3), controlling the autonomous driving vehicle (1) to slow down and give way; S7: When the autonomous driving vehicle (1) has the right of way, the autonomous driving vehicle (1) is controlled to continue traveling along the navigation route (L1).

6. A control method according to any one of the preceding claims, characterized in that In the case where the current road (10) has multiple lanes, the control method is implemented only when the current lane in which the autonomous driving vehicle (1) is located is an edge lane adjacent to the lateral road (20).

7. A control method according to any one of the preceding claims, characterized in that The estimated driving route (L2) of the target vehicle (2) is determined based on the type of the intersection area (30), the driving direction of the target vehicle (2), the type of lane in which the target vehicle (2) is located, and the turn signal information of the target vehicle (2), wherein the type of the intersection area (30) is a crossroads, a T-junction, or a multi-way intersection, and the lane type is a through lane, a left-turn lane, or a right-turn lane, wherein the estimated driving route (L2) of the target vehicle (2) is selected from the following group: turning to merge into the current road (10), turning to merge into the opposite road of the current road (10), and going straight through the current road (10); and / or The estimated movement trajectory (L3) of the road user (3) is calculated by an object tracking algorithm.

8. A control method according to any one of the preceding claims, characterized in that The intersection area (30) is detected by an environmental sensor of the autonomous driving vehicle (1) and / or based on a digital map stored in the autonomous driving vehicle (1); and / or The target vehicle (2) and the road user (3) are identified by the environmental sensors of the autonomous driving vehicle (1) in combination with an image processing algorithm.

9. The control method according to claim 8, characterized in that: The environmental sensors include millimeter wave radars and / or cameras and / or laser radars arranged at the front and sides of the autonomous driving vehicle (1); and / or The image processing algorithm includes an object classifier and / or a convolutional neural network algorithm; and / or The road user (3) is a pedestrian or a two-wheeled vehicle rider.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by one or more processors, the processors are capable of executing the control method according to any one of claims 1 to 9.

Images