A method, system and medium for scoring lane-changing safety level of an autonomous driving vehicle

Abstract

The present invention relates to the technical field of intelligent driving, and discloses a method, system and medium for scoring the safety level of lane change of an autonomous driving vehicle. The method includes: obtaining the acceleration, speed, relative distance and heading angle of target vehicles around the vehicle; calculating the TTC of the target in front of the lane, the target lane and the target vehicle closest to the vehicle in front and behind the adjacent lane; judging whether the target in the adjacent lane will cut into the target lane; scoring the TTC and relative distance of each target vehicle, taking the minimum value of all scores as the final score, and determining whether the lane change is feasible based on the final score and the set score threshold for lane change. The present invention comprehensively considers the target vehicles in the lane, the target lane and the adjacent lane, aiming to improve the safety and personalized differentiation of lane change, and is used to solve the problem that the current safety judgment of lane change does not consider the target vehicle in the adjacent lane, and the safety level classification is too simple to meet higher personalized needs.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent driving functional safety, and specifically relates to a method, system and medium for scoring the lane change safety level of an autonomous driving vehicle. Background Art

[0002] During the autonomous driving process, autonomous vehicles will encounter many situations where automatic lane changing is required. During the lane changing process, it is necessary to consider whether the current lane change is safe. The current mainstream method for judging whether the lane change is safe is to judge whether the TTC (time to collision) and relative distance between the target vehicle in front of the lane and the target vehicles closest to the vehicle in front and behind the target lane meet the safe lane changing threshold.

[0003] In the patent related to lane change safety judgment "A Vehicle Lane Change Warning Method and Lane Change Warning System" (patent application number: 201210543893.5) retrieved from Baiteng.com, whether lane change is feasible is determined by judging whether the relative distance between the target vehicles in front and behind the lane and the target vehicles closest to the vehicle in front and behind the target lane meets the critical safety distance.

[0004] The above patent only considers the safety distance of the target lane, and does not consider the target vehicle in the adjacent lane (if the target lane is the left lane, then the adjacent lane is the left-left lane, otherwise it is the right-right lane). If the vehicle in the adjacent lane and the vehicle change lanes to the target lane at the same time, and the lane change trajectories intersect, there will be a collision risk. Figure 1 This means that the car has only two states: lane changeable and non-lane changeable, which cannot meet the personalized lane change requirements of autonomous driving at L3 and above driving levels. Summary of the invention

[0005] The purpose of the present invention is to provide a scoring method, system and medium for lane change safety judgment, which comprehensively considers the target vehicles in the lane, target lane and adjacent lane for the lane change safety judgment of an autonomous driving vehicle, calculates the TTC and relative distance of each target vehicle and scores them, aiming to improve the safety and personalized differentiation of lane change, and solves the problem that the current safety judgment of lane change does not take into account the target vehicles in the adjacent lane, and the safety level classification is too simple to meet higher personalized needs.

[0006] In order to achieve the above technical objectives, the technical solution adopted by the present invention is as follows:

[0007] One aspect of the present invention provides a method for scoring the lane change safety level of an autonomous driving vehicle, comprising the following steps:

[0008] S1. Obtain the acceleration, speed, relative distance and heading angle of the target vehicles around the vehicle;

[0009] S2, calculate the TTC of the target in front of the own lane, the target lane, and the target vehicles closest to the self-vehicle in front and behind the adjacent lane;

[0010] S3, judging whether the target in the adjacent lane will cut into the target lane;

[0011] S4, scoring the TTC and relative distance of each target vehicle;

[0012] S5, according to the TTC and relative distance scores of each target vehicle obtained in S4, taking the minimum value of all scores as the final score;

[0013] S6. Determine whether lane changing is feasible based on the final score and the set lane changing score threshold.

[0014] As a preferred technical solution, the acceleration, speed, relative distance and heading angle related information of the target vehicles around the vehicle are obtained through the front-view camera, surround-view camera, ultrasonic radar, millimeter-wave radar and lidar.

[0015] As a preferred technical solution, the TTC of the target in front of the own lane, the target lane, and the target vehicle closest to the own vehicle in front and behind the adjacent lane is calculated as follows:

[0016] The time of collision TTC = relative distance between the front and rear vehicles / (speed of the rear vehicle - speed of the front vehicle). When the speed of the rear vehicle is less than or equal to the speed of the front vehicle, TTC is infinite.

[0017] As a preferred technical solution, the determination of whether the target in the adjacent lane will cut into the target lane is specifically as follows:

[0018] Using the lateral speed, acceleration and lane line distance of the target vehicle in the adjacent lane, the uniform acceleration model is used to predict whether the vehicle will cross the lane line within a calibrated time range to determine whether the vehicle will cut into the target lane.

[0019] As a preferred technical solution, the TTC and relative distance of each target vehicle are scored using a table lookup method, specifically:

[0020] If TTC is less than 3, the score is 0, and if TTC is greater than 10, the score is 100. When TTC is between [2, 10], the score is calculated using linear interpolation.

[0021] When it is determined in S3 that the target vehicle in the adjacent lane will not cut into the target lane, the score is 100 points. If the target vehicle cuts into the target lane, the score is the actually calculated score.

[0022] As a preferred technical solution, in step S6, the lane changing score threshold is set according to the driver's driving style while ensuring safety.

[0023] Another aspect of the present invention provides a lane-changing safety level scoring system for an autonomous driving vehicle, which is applied to the above-mentioned lane-changing safety level scoring method for an autonomous driving vehicle, and includes a target vehicle monitoring module, a TTC calculation module, an adjacent lane judgment module, a safety scoring module, and a result output module;

[0024] The target vehicle monitoring module is used to obtain the acceleration, speed, relative distance and heading angle of the target vehicles around the vehicle;

[0025] The TTC calculation module is used to calculate the TTC of the target in front of the own lane, the target lane and the target vehicle closest to the self-vehicle in front and behind the adjacent lane;

[0026] The adjacent lane judgment module is used to judge whether the adjacent lane object will cut into the target lane;

[0027] The safety scoring module is used to score the TTC and relative distance of each target vehicle, and take the minimum value of all scores as the final score;

[0028] The result output module is used to determine whether the lane change is feasible according to the final score and the set lane change score threshold.

[0029] Another aspect of the present invention provides a storage medium storing a program, which, when executed by a processor, implements the above-mentioned method for scoring the lane change safety level of an autonomous driving vehicle.

[0030] The invention adopting the above technical solution has the following advantages:

[0031] Lane changing is a difficult problem that must be overcome for autonomous driving, and safety assessment of lane changing is an extremely important part of it. The present invention takes into account target vehicles in adjacent lanes and characterizes the safety of lane changing in a scoring manner. First, it can avoid the danger caused by vehicles in adjacent lanes cutting into the target lane at the same time as the vehicle itself, and can provide more personalized processing for rear-end lane changing. For example, when driving normally on the main road, the safety score threshold for lane changing can be set higher to ensure safety. If lane changing is required at a certain point, the score threshold can be lowered within a safe range to ensure the success rate of lane changing; or the threshold of the lane changing score can be adjusted according to the style set by the driver; or in a scenario where lane changing can be done to the left or right at the same time and the vehicle must leave the current lane, the lane changing can be done on the side with a higher safety score. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The present invention can be further illustrated by the non-limiting examples given in the accompanying drawings;

[0033] Figure 1 It is a schematic diagram of the overall process of a scoring method for lane change safety judgment according to an embodiment of the present invention;

[0034] Figure 2 This is a schematic diagram of a large target cut-in scenario of a neighboring car according to an embodiment of the present invention;

[0035] Figure 3 is a schematic diagram of obtaining a security level score by using a table lookup method in an embodiment of the present invention;

[0036] Figure 4 is a structural schematic diagram of a scoring system for lane change safety judgment according to an embodiment of the present invention;

[0037] Figure 5 It is a schematic diagram of the structure of the storage medium of an embodiment of the present invention. DETAILED DESCRIPTION

[0038] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that in the drawings or descriptions of the specification, similar or identical parts use the same figure numbers, and the implementation methods not shown or described in the drawings are forms known to ordinary technicians in the relevant technical field. In addition, the directional terms mentioned in the embodiments, such as "upper", "lower", "top", "bottom", "left", "right", "front", "back", etc., are only referenced to the directions of the drawings and are not used to limit the scope of protection of the present invention.

[0039] like Figure 1 As shown, this embodiment provides a scoring method for lane change safety judgment, including the following steps:

[0040] S1. Obtain the acceleration, speed, relative distance and heading angle of the target vehicles around the vehicle;

[0041] As a preferred technical solution, in this embodiment, sensors such as a forward-looking camera, a surround-looking camera, an ultrasonic radar, a millimeter-wave radar, and a lidar are used to obtain relevant information such as the acceleration, speed, relative distance, and heading angle of target vehicles around the vehicle.

[0042] S2. Calculate the TTC (time to collision) of the target in front of the own lane, the target lane, and the target vehicles closest to the own vehicle in front and behind the adjacent lane. That is, the time required for the two vehicles to rear-end each other assuming that the current relative speed is maintained.

[0043] As a preferred technical solution, in this embodiment, TTC is calculated as follows:

[0044] Time to collision TTC = relative distance between front and rear vehicles / (speed of rear vehicle - speed of front vehicle)

[0045] It should be noted that if the TTC of this car and the car in front is calculated, this car is the rear car and the front car is the front car. If the TTC of the rear car and this car is calculated, the rear car is the rear car and this car is the front car. When the speed of the rear car is less than or equal to the speed of the front car, the TTC is infinite.

[0046] S3, judging whether the target in the adjacent lane will cut into the target lane;

[0047] As a preferred technical solution, this embodiment utilizes the lateral speed, acceleration and lane line distance of the target vehicle in the adjacent lane to predict whether the vehicle will cross the lane line within a calibrated time range according to the uniform acceleration model, so as to determine whether the vehicle will cut into the target lane.

[0048] S4, scoring the TTC and relative distance of each target vehicle;

[0049] As a preferred technical solution, in this embodiment, the TTC and relative distance of each target vehicle are scored using a table lookup method, specifically:

[0050] If the calculated TTC is less than 3, the score is 0, and if the calculated TTC is greater than 10, the score is 100. When the TTC is between [2, 10], the score is calculated using linear interpolation. The TTC lookup table is fixed. Assuming that the TTC input in the lookup table is [3, 7, 10], the output score is [0, 40, 100]. The relative distance table input is based on the dynamic changes in the speed of the ego vehicle and the target vehicle, as shown in the following example. Figure 3 shown.

[0051] It should be noted that, when it is determined in S3 that the target vehicle in the adjacent lane will not cut into the target lane, the score is 100 points. If it cuts in, the score is the actually calculated score.

[0052] S5, according to the TTC and relative distance scores of each target vehicle obtained in S4, taking the minimum value of all scores as the final score;

[0053] S6. Determine whether lane changing is feasible based on the final score and the set lane changing score threshold.

[0054] As a preferred technical solution, in step S6 of this embodiment, the lane change score threshold is set according to the driver's driving style while ensuring safety, specifically:

[0055] According to the lane change safety level score, it is very convenient to make lane changes according to different driving styles. For example, if the user wants to change lanes aggressively or has to turn left, turn right, or go up or down a ramp ahead and must change lanes as soon as possible, the lane change score threshold can be set lower while ensuring safety. For conservative or non-essential lane changes, the score threshold can be set higher, and lane changes will be made only when the score is greater than the safety threshold.

[0056] like Figure 4 As shown, in another embodiment of the present application, a lane-changing safety level scoring system for an autonomous driving vehicle is provided, which is applied to a lane-changing safety level scoring method for an autonomous driving vehicle in the above embodiment, and the system includes a target vehicle monitoring module, a TTC calculation module, an adjacent lane judgment module, a safety scoring module, and a result output module;

[0057] The target vehicle monitoring module is used to obtain the acceleration, speed, relative distance and heading angle of the target vehicles around the vehicle;

[0058] The TTC calculation module is used to calculate the TTC of the target in front of the own lane, the target lane and the target vehicle closest to the self-vehicle in front and behind the adjacent lane;

[0059] The adjacent lane judgment module is used to judge whether the adjacent lane object will cut into the target lane;

[0060] The safety scoring module is used to score the TTC and relative distance of each target vehicle, and take the minimum value of all scores as the final score;

[0061] The result output module is used to determine whether the lane change is feasible according to the final score and the set lane change score threshold.

[0062] It should be noted here that the system provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure is divided into different functional modules to complete all or part of the functions described above. The system is a method for scoring the lane change safety level of an autonomous driving vehicle applied to the above embodiment.

[0063] like Figure 5 As shown, in another embodiment of the present application, a storage medium is further provided, storing a program, and when the program is executed by a processor, a method for scoring the lane change safety level of an autonomous driving vehicle in the above embodiment is implemented, specifically:

[0064] S1. Obtain the acceleration, speed, relative distance and heading angle of the target vehicles around the vehicle;

[0065] S2, calculate the TTC of the target in front of the own lane, the target lane, and the target vehicles closest to the self-vehicle in front and behind the adjacent lane;

[0066] S3, judging whether the target in the adjacent lane will cut into the target lane;

[0067] S4, scoring the TTC and relative distance of each target vehicle;

[0068] S5, according to the TTC and relative distance scores of each target vehicle obtained in S4, taking the minimum value of all scores as the final score;

[0069] S6. Determine whether lane changing is feasible based on the final score and the set lane changing score threshold.

[0070] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0071] The above is a detailed introduction to a scoring method, system and medium for lane change safety judgment provided by the present invention. The description of the specific embodiment is only used to help understand the method of the present invention and its core idea. It should be pointed out that for ordinary technicians in this technical field, without departing from the principle of the present invention, several improvements and modifications can be made to the present invention, and these improvements and modifications also fall within the scope of protection of the claims of the present invention.

Claims

1. A method for scoring the lane-changing safety level of an autonomous driving vehicle, characterized in that: The following steps are involved: Obtain the acceleration, speed, relative distance and heading angle of the target vehicles around the vehicle; Calculate the TTC of the target in front of the own lane, the target lane, and the target vehicles closest to the vehicle in front and behind the adjacent lane; Determine whether the target in the adjacent lane will cut into the target lane; Score the TTC and relative distance of each target vehicle, and take the minimum value of all scores as the final score, specifically: If TTC is less than 3, the score is 0, and if TTC is greater than 10, the score is 100. When TTC is between [2, 10], the score is calculated using linear interpolation. If it is judged that the target vehicle in the adjacent lane will not cut into the target lane, the score is 100 points. If it cuts into the target lane, the score is the actual calculated score. Whether the lane change is feasible is determined based on the final score and the set lane change score threshold.

2. The method for scoring the lane change safety level of an autonomous driving vehicle according to claim 1, characterized in that: The acceleration, speed, relative distance and heading angle information of the target vehicles around the vehicle are obtained through the front-view camera, surround-view camera, ultrasonic radar, millimeter-wave radar and lidar.

3. The method for scoring the lane change safety level of an autonomous driving vehicle according to claim 1, characterized in that: The TTC of the target in front of the own lane, the target lane, and the target vehicle closest to the own vehicle in front and behind the adjacent lane is calculated as follows: The time of collision TTC = relative distance between the front and rear vehicles / (speed of the rear vehicle - speed of the front vehicle). When the speed of the rear vehicle is less than or equal to the speed of the front vehicle, TTC is infinite.

4. The method for scoring the lane change safety level of an autonomous driving vehicle according to claim 1, characterized in that: The step of judging whether the target in the adjacent lane will cut into the target lane is as follows: Using the lateral speed, acceleration and lane line distance of the target vehicle in the adjacent lane, the uniform acceleration model is used to predict whether the vehicle will cross the lane line within a calibrated time range to determine whether the vehicle will cut into the target lane.

5. The method for scoring the lane change safety level of an autonomous driving vehicle according to claim 1, characterized in that: The scoring threshold for lane changing is set based on the driver's driving style while ensuring safety.

6. A lane-changing safety level scoring system for an autonomous driving vehicle, characterized in that: A method for scoring the lane change safety level of an autonomous driving vehicle applied to any one of claims 1-5, comprising a target vehicle monitoring module, a TTC calculation module, an adjacent lane judgment module, a safety scoring module and a result output module; The target vehicle monitoring module is used to obtain the acceleration, speed, relative distance and heading angle of the target vehicles around the vehicle; The TTC calculation module is used to calculate the TTC of the target in front of the own lane, the target lane and the target vehicle closest to the self-vehicle in front and behind the adjacent lane; The adjacent lane judgment module is used to judge whether the adjacent lane object will cut into the target lane; The safety scoring module is used to score the TTC and relative distance of each target vehicle, and take the minimum value of all scores as the final score; The result output module is used to determine whether the lane change is feasible according to the final score and the set lane change score threshold.

7. A storage medium storing a program, characterized in that: When the program is executed by a processor, a method for scoring the lane change safety level of an autonomous driving vehicle according to any one of claims 1 to 5 is implemented.

Images