Control method and computer program product for intelligent driving vehicle

Abstract

The invention relates to a control method for an intelligent driving vehicle, which comprises the following steps: when the vehicle runs in a first lane of a current road, identifying that an intersection exists within a preset distance in front, the intersection being jointly formed by the current road and a transverse road, a second lane, adjacent to the current road, of the transverse road is provided with a vehicle entering road section driving towards the intersection and a vehicle exiting road section driving away from the intersection; identifying that at least part of the vehicle entering road section of the transverse road is shielded; enabling the vehicle to deflect in a direction away from the vehicle entering road section relative to a first center line of the first lane, so that the vehicle can detect a specific range of the vehicle entering road section at the first position; when the target vehicle is detected in the specific range, the vehicle is decelerated at a preset deceleration until the vehicle is stopped before a second position, which is a predicted collision point of the vehicle and the target vehicle. The invention also relates to a computer program product. Therefore, the vehicle can safely pass through the intersection with the shielded view and effectively avoid dangerous collision accidents.

Description

Technical Field

[0001] This invention relates to the technical field of intelligent driving vehicles, and in particular to a control method for intelligent driving vehicles. The invention also relates to a corresponding computer program product. Background Technology

[0002] In recent years, with the development of technology and the improvement of living standards, people have increasingly higher requirements for the intelligence and safety of vehicles. Intelligent driving vehicles use onboard sensors to detect the vehicle's surrounding environment and control the vehicle's steering and speed based on the detected information, thereby enabling the vehicle to safely travel to the predetermined destination.

[0003] However, due to the complex and ever-changing uncertainty of the environment, especially when vehicles need to pass through intersections, the field of vision is often obstructed by dynamic or static obstacles, resulting in blind spots in the detection range of on-board sensors. Other vehicles may drive out of these blind spots, leaving insufficient time to perform safe avoidance actions and easily leading to safety accidents. Summary of the Invention

[0004] Therefore, the object of this invention is to provide an improved control method for intelligent driving vehicles, which enables vehicles to safely pass through intersections with obstructed visibility and effectively avoid dangerous collisions. A further object of this invention is to provide a corresponding computer program product.

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

[0006] S1: When a vehicle is traveling in the first lane of the current road, an intersection is identified at a preset distance ahead. The intersection is formed by the current road and a transverse road. The second lane of the transverse road, which is adjacent to the current road, has an entry section for vehicles to enter the intersection and an exit section for vehicles to leave the intersection.

[0007] S2: It is identified that the access road section of the transverse road is at least partially obstructed;

[0008] S3: The vehicle is deflected relative to the first centerline of the first lane in a direction away from the approach section, so that the vehicle can detect a specific range of the approach section at the first position;

[0009] S4: When a target vehicle is detected within the specified range, the vehicle is decelerated at a preset deceleration until it stops before a second position, which is the predicted collision point between the vehicle and the target vehicle.

[0010] In the control method for intelligent driving vehicles according to the present invention, when an intersection is detected ahead of the vehicle and the approach section of the second lane of the transverse road adjacent to the current road is obstructed, the vehicle deflects away from the approach section relative to the first center line of the first lane. This adjusts the detection field of the on-board sensors and increases the detectable range of the approach section to detect potential conflicting vehicles earlier. It also keeps the vehicle as far away from the approach section as possible and extends the reaction time and braking distance. When a target vehicle is detected within a specific range of the approach section, the vehicle decelerates at a preset deceleration, thereby stopping the vehicle before the predicted collision point between the vehicle and the target vehicle. This effectively avoids dangerous collisions and ensures the vehicle safely passes through the intersection, thereby reliably improving driving safety.

[0011] For example, in step S3, the speed of the vehicle when it reaches the first position is reduced to below a speed threshold.

[0012] For example, the speed threshold is determined by the first distance from the target vehicle to the second position, the second distance from the first position to the second position, the speed of the target vehicle, and the preset deceleration.

[0013] For example, the speed of the target vehicle is set to the maximum permissible speed in the transverse road; and / or, the preset deceleration is the maximum permissible deceleration of the vehicle.

[0014] For example, the second location is the intersection of the extended portion of the edge line of the first lane away from the entry section and the second center line of the second lane.

[0015] For example, the intersection and / or obstacles blocking the roadway are identified by the vehicle's environmental sensors in conjunction with navigation information.

[0016] For example, the specific range of the approach road is determined based on the detection capability of the vehicle's environmental sensors, wherein the longitudinal extension dimension of the specific range is at least greater than an average vehicle length, which is derived based on empirical data.

[0017] For example, the control method further includes step S5: when no target vehicle is detected in the specific range, the vehicle is accelerated through the intersection.

[0018] For example, the control method is executed when the vehicle needs to turn left or go straight through the intersection according to the navigation route.

[0019] According to a second aspect of the present invention, a computer program product is provided, comprising a computer program, wherein 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. Attached Figure Description

[0020] The invention will now be described in more detail with reference to the accompanying drawings, which will provide a better understanding of its principles, features, and advantages. The drawings include:

[0021] Figure 1 A schematic flowchart of a control method for an intelligent driving vehicle according to an exemplary embodiment of the present invention is shown;

[0022] Figure 2a and Figure 2b A schematic and simplified view of a driving condition according to an exemplary embodiment is shown, in which the control method according to the invention is executed. Detailed Implementation

[0023] To make the technical problems to be solved, the technical solutions, and the beneficial technical effects of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and several exemplary embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of protection of this invention.

[0024] This specification provides the operational steps for the methods described in the embodiments or flowcharts, but based on conventional or non-inventive labor, more or fewer operational steps may be included. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only possible execution order.

[0025] Figure 1 A schematic flowchart of a control method for an intelligent driving vehicle according to an exemplary embodiment of the present invention is shown. Figure 2a and Figure 2b A schematic and simplified view of a driving condition according to an exemplary embodiment is shown, in which the control method according to the invention is executed.

[0026] Within the framework of this invention, "intelligent driving vehicle" should be understood as a vehicle with assisted driving functions, especially highly automated driving functions, which enables the vehicle to assist the driver, especially in navigating complex scenarios in an automated manner.

[0027] like Figure 1 and Figure 2a As shown, the control method for intelligent driving vehicles according to the present invention includes at least the following steps:

[0028] S1: When vehicle 1 is traveling in the first lane W1 of the current road R1, an intersection is identified within a preset distance ahead. This preset distance can be determined based on experimental and / or empirical data. The identified intersection is formed by the current road R1 and a transverse road R2 relative to the current road R1. The intersection can be a T-junction, a crossroads, or other types of multi-way intersections that are considered meaningful by those skilled in the art. Here, the current road R1 may have at least one lane traveling in the same direction as the first lane W1 and / or at least one lane traveling opposite to the first lane W1, while the transverse road R2 has at least one second lane W2 adjacent to the current road R1. The target vehicle 2 traveling in this second lane typically has the highest probability of colliding with vehicle 1 traveling in the current road R1. Furthermore, the transverse road R2 may also have at least one lane traveling in the same direction as the second lane W2 and / or at least one third lane W3 traveling opposite to the second lane W2. Each lane may have a center line and two side edge lines. Here, the second lane W2 has an entry section A1 for vehicles heading towards the intersection and an exit section A2 for vehicles leaving the intersection. The target vehicle 2 in the second lane W2 enters the intersection from the entry section A1 and leaves via the exit section A2. In countries and regions where "left-hand drive and right-hand driving" is permitted, the entry section A1 is usually located on the left side of the current road R1. In countries and regions where "right-hand drive and left-hand driving" is permitted, the entry section A1 is usually located on the right side of the current road R1. The following will describe the case of "left-hand drive and right-hand driving" as shown schematically in Figure 2.

[0029] S2: Identify that the approach road segment A1 of the transverse road R2 is at least partially obscured by obstacle B, so that the environmental sensors of vehicle 1, such as lidar or camera, cannot fully and clearly detect the target vehicle 2 in the approach road segment A1. The obstacle B can be a static obstacle on the side of the current road R1 facing the approach road segment A1, such as a building, billboard, road infrastructure or vegetation, or it can be other vehicles, especially large vehicles or construction barriers, in the current road R1 that are closer to the approach road segment A1 than the first lane W1.

[0030] S3: Vehicle 1 is deflected relative to the first centerline M1 of the first lane W1 in a direction away from the approach segment A1, i.e., deflected to the right, as shown by the dashed outline in Figure 2. By actively deflecting vehicle 1, the detection range of the environmental sensors can be adjusted, thereby allowing it to bypass obstacle B to a certain extent and enabling vehicle 1 to detect a specific range of the approach segment A1 at the first position P1. This specific range is defined by the dashed line originating from vehicle 1 and is significantly larger than the detection range of vehicle 1 in its undeflected state. Furthermore, by deflecting vehicle 1 in a direction away from the approach segment A1, the distance between vehicle 1 and the target vehicle 2 can be increased, thereby extending vehicle 1's reaction time and braking distance.

[0031] S4: When the environmental sensor of vehicle 1 detects the target vehicle 2 in a specific range of the approach section A1 of the second lane W2 of the transverse road R2, vehicle 1 decelerates at a preset deceleration until it stops before the second position P2, which is the predicted collision point between vehicle 1 and the target vehicle 2, thereby ensuring that vehicle 1 stops before the collision and effectively avoids a dangerous collision accident.

[0032] For example, in step S1, the intersection ahead is identified by the vehicle 1's environmental sensors, such as LiDAR or cameras, combined with navigation information provided by the in-vehicle navigation system. The image data detected by the environmental sensors can be input into a trained machine learning algorithm, which then outputs the identification result. Similarly, obstacle B obstructing the entrance to road segment A1 can also be identified by the vehicle 1's environmental sensors combined with navigation information.

[0033] For example, in step S3, while deflecting vehicle 1 away from the approach road segment A1, vehicle 1 is decelerated so that its speed is reduced below a speed threshold when it reaches the first position P1. This advance deceleration before reaching the first position P1 allows vehicle 1 to brake and stop safely and at a preset deceleration acceptable to passengers when traveling from the first position P1 to the second position P2.

[0034] For example, such as Figure 2b As shown, when a target vehicle 2 is detected within a specific range of the approach road segment A1, a first distance L1 exists between the target vehicle 2 and the second position P2, and a second distance L2 exists between the first position P1 and the second position P2. Here, the speed threshold of vehicle 1 at the first position P1 can be determined by the first distance L1 from the target vehicle 2 to the second position P2, the second distance L2 from the first position P1 to the second position P2, the speed of the target vehicle 2, and the preset deceleration of vehicle 1. Specifically, in this case, the predicted collision time t is calculated using the following formula:

[0035] t = L1 / v2

[0036] Where t is the time required for the target vehicle 2 to reach the second position P2, and v2 is the speed of the target vehicle 2, which is specifically set as the maximum permissible speed in the transverse road R2, and the maximum permissible speed can be directly obtained from navigation information;

[0037] By simplifying and assuming that vehicle 1 has a constant deceleration, the driving process of vehicle 1 satisfies the following formula:

[0038]

[0039] Where v1 is the speed threshold of vehicle 1, a is the constant preset deceleration of vehicle 1, and the preset deceleration is in particular the maximum allowable deceleration of vehicle 1, which can be determined based on test data and / or empirical data.

[0040] From the two formulas above, we can derive the following formula:

[0041]

[0042] This allows us to determine the speed threshold of vehicle 1 at the first position P1.

[0043] For example, such as Figure 2a As shown, the second position P2, i.e., the predicted collision point between vehicle 1 and target vehicle 2, is the intersection of the extended portion of the edge line G of the first lane W1 away from the entry segment A1 and the second center line M2 of the second lane W2. This allows vehicle 1 to move as far away from the entry segment A1 as possible without affecting vehicles in other lanes and without touching the curb, thereby increasing the braking distance and further improving safety.

[0044] For example, such as Figure 2a As shown, the specific range of the approach segment A1 of the second lane W2 of the transverse road R2 detected by the environmental sensor of vehicle 1 is determined according to the detection capability of the environmental sensor of vehicle 1, such as effective detection distance, field of view and resolution, wherein the longitudinal extension scale of the specific range is at least greater than an average vehicle length, which can be derived based on empirical data, for example, 5 meters.

[0045] For example, such as Figure 1As shown, the control method according to the present invention further includes step S5: when no target vehicle 2 is detected in a specific range of the approach segment A1 of the second lane W2 of the transverse road R2, the vehicle 1 accelerates through the intersection according to the navigation path S. In particular, when the transverse road R2 also has a third lane W3 opposite to the second lane W2, the vehicle 1 accelerates through the intersection according to the navigation path S only when no target vehicle is detected in the approach segments of both the second lane W2 and the third lane W3 of the transverse road R2. This improves the traffic efficiency of the intersection while ensuring driving safety.

[0046] For example, such as Figure 2a As shown, when vehicle 1 needs to turn left through the intersection according to the preset navigation path S, the control method according to the invention is executed, causing vehicle 1 to veer to the right away from the left-hand approach segment A1, thereby expanding the detection range of the approach segment A1 and extending the braking distance. However, it is also possible to execute the control method according to the invention when vehicle 1 needs to proceed straight through the intersection according to the preset navigation path S. Furthermore, the control method according to the invention is particularly suitable for implementation at intersections without traffic lights.

[0047] The present invention also provides a computer program product comprising a computer program that, when executed by one or more processors, enables the processors to perform the control method according to the present invention. Here, the computer program product is particularly integrated into the electronic control unit of vehicle 1.

[0048] The foregoing description of the embodiments is limited to the framework of the examples given. Of course, the various features of the embodiments can be freely combined with each other without departing from the framework of the invention, as long as it is technically meaningful.

[0049] Other advantages and alternative embodiments of the present invention will be apparent to those skilled in the art. Therefore, the present invention is not, in its broader sense, limited to the specific details, representative structures, and exemplary embodiments shown and described. Rather, those skilled in the art can make various modifications and substitutions without departing from the basic spirit and scope of the invention.

Claims

1. A control method for intelligent driving vehicles, characterized in that, The control method includes at least the following steps: S1: When a vehicle (1) is traveling in the first lane (W1) of the current road (R1), an intersection is identified at a preset distance ahead. The intersection is formed by the current road (R1) and the transverse road (R2). The second lane (W2) of the transverse road (R2) adjacent to the current road (R1) has an approach section (A1) leading to the intersection and an exit section (A2) leading away from the intersection. S2: It is identified that the approach section (A1) of the transverse road (R2) is at least partially obscured; S3: The vehicle (1) is deflected away from the approach road segment (A1) relative to the first center line (M1) of the first lane (W1) so that the vehicle (1) can detect a specific range of the approach road segment (A1) at the first position (P1); S4: When a target vehicle (2) is detected in the specified range, the vehicle (1) is decelerated at a preset deceleration until the vehicle (1) stops before the second position (P2), which is the predicted collision point between the vehicle (1) and the target vehicle (2).

2. The control method according to claim 1, characterized in that, In step S3, the speed of the vehicle (1) when it reaches the first position (P1) is reduced to below a speed threshold.

3. The control method according to claim 2, characterized in that, The speed threshold is determined by the first distance (L1) from the target vehicle (2) to the second position (P2), the second distance (L2) from the first position (P1) to the second position (P2), the speed of the target vehicle (2), and the preset deceleration.

4. The control method according to claim 3, characterized in that, The speed of the target vehicle (2) is set to the maximum permissible speed in the transverse road (R2); and / or The preset deceleration is the maximum permissible deceleration of the vehicle (1).

5. The control method according to any one of the preceding claims, characterized in that, The second position (P2) is the intersection of the extended portion of the edge line (G) of the first lane (W1) away from the approach section (A1) and the second center line (M2) of the second lane (W2).

6. The control method according to any one of the preceding claims, characterized in that, The intersection and / or obstacles (B) that block the roadway (A1) are identified by the vehicle's (1) environmental sensors in conjunction with navigation information.

7. The control method according to any one of the preceding claims, characterized in that, The specific range of the approach section (A1) is determined based on the detection capability of the environmental sensors of the vehicle (1), wherein the longitudinal extension scale of the specific range is at least greater than an average vehicle length, which is derived based on empirical data.

8. The control method according to any one of the preceding claims, characterized in that, The control method further includes step S5: when no target vehicle (2) is detected in the specific range, the vehicle (1) is accelerated through the intersection.

9. The control method according to any one of the preceding claims, characterized in that, The control method is executed when the vehicle (1) needs to turn left or go straight through the intersection according to the navigation path (S).

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 performing the control method according to any one of claims 1 to 9.

Images