A vehicle lane-changing decision method

Abstract

This invention relates to the field of intelligent driving technology, and more particularly to a lane-changing decision-making method. The method includes: acquiring actual driving data of a target vehicle driver and determining the driver's driving style; acquiring the target vehicle's current following speed in its original lane and determining the target vehicle's safe acceleration based on the driving style; calculating the safe following distance between the target vehicle and the vehicle in front in the same lane using a preset safe following distance model established based on the safe acceleration; and determining whether the current actual distance between the target vehicle and the vehicle in front meets the lane-changing requirements based on the safe following distance. If so, lane changing is permitted; otherwise, lane changing is prohibited. This invention, by considering the driver's driving style, makes the calculation results more consistent with the actual driving situation of the target vehicle, thereby effectively assisting the driver in making lane-changing decisions.

Description

Technical Field

[0001] This invention relates to the field of intelligent driving technology for vehicles, and in particular to a vehicle lane-changing decision-making method. Background Technology

[0002] Actual lane changing can be divided into two scenarios: free lane changing and non-free lane changing. Non-free lane changing usually occurs when the target vehicle is in its original lane, and the vehicle in front is traveling at a relatively low speed, while the target vehicle wants to overtake.

[0003] Lane changing is typically accompanied by a following process and a lane change itself. Existing following models use traditional safety distance models. These models are based on headway distance. Headway distance is the time difference between adjacent vehicles passing the same designated point, and its magnitude is the ratio of the distance between the vehicles to their relative speeds. When vehicles follow at relatively low relative speeds, the distance between the two vehicles has a linear relationship with the speed of the following vehicle. Based on this linear relationship, a safety distance model is established as follows:

[0004] S=υ0t d +d

[0005] Where S is the safety distance; t d The braking hysteresis time can be 1.2 to 2.0 seconds; υ0 is the speed of the following vehicle before braking; d is the distance between the following vehicle and the vehicle in front after the following vehicle stops, which is generally 2-5 meters.

[0006] Safety distance models have wide applications; in most cases, knowing the maximum braking acceleration the driver will apply is sufficient for the model's needs. While these models can yield acceptable results, several issues remain. For example, they only consider situations with low relative speeds between vehicles, offering less consideration for safety at higher relative speeds. This leads to underestimating the safe distances calculated by the model. In actual traffic, due to varying driving styles, the calculated safe following distance may not align with the driver's style, making it difficult to effectively aid in lane-changing decisions. Summary of the Invention

[0007] Based on the above analysis, the present invention aims to provide a vehicle lane-changing decision-making method to solve the technical problem in the prior art that, due to the lack of consideration for the driver's driving style, the following safety distance calculated based on the safety distance model may not match the driver's driving style, thus failing to play a role in assisting in lane-changing decisions.

[0008] The technical solution provided by this invention is:

[0009] This invention provides a vehicle lane-changing decision-making method, including:

[0010] Obtain the actual driving data of the target vehicle driver and determine the driver's driving style;

[0011] Obtain the current following speed of the target vehicle in the original lane, and determine the safe acceleration of the target vehicle based on the driving style;

[0012] Using a preset following safety distance model established based on the aforementioned safety acceleration, the following safety distance between the target vehicle and the vehicle in front in the same lane is calculated;

[0013] Based on the aforementioned following safety distance, determine whether the current actual distance between the target vehicle and the vehicle in front meets the lane-changing requirements. If so, lane changing is allowed; otherwise, a prompt prohibiting lane changing is displayed.

[0014] Preferably, the actual driving data includes: parameter values ​​of three driving characteristic parameters, namely: vehicle steering wheel angle, longitudinal acceleration, and lateral acceleration;

[0015] The acquisition of the actual driving data of the target vehicle driver includes:

[0016] Using the parameter values ​​of every three driving characteristic parameters as a group of sample data, multiple groups of the sample data are sampled within a preset time period;

[0017] Determining the driver's driving style includes:

[0018] In the three-dimensional space formed by the three driving feature parameters, N driving style cluster centers corresponding to the experience driving data of N different driving styles are calculated in advance using a pre-selected clustering algorithm, where N>1.

[0019] Using the clustering algorithm, a cluster center for the sampled data corresponding to multiple sets of sampled data is calculated;

[0020] Within the three-dimensional space, the distance from the cluster center of the sampled data to each driving style cluster center is calculated, and the driving style corresponding to the shortest distance is the driving style to which the driver belongs.

[0021] Preferably, determining the safe acceleration of the target vehicle based on the driving style includes:

[0022] Calculate the first desired speed using a preset driving hazard coefficient corresponding to the driving style and the current following vehicle speed;

[0023] By using the current following vehicle speed and the first desired speed, the maximum acceleration of the target vehicle is corrected to obtain the safe acceleration.

[0024] Preferably, let the maximum acceleration be a.max The first desired speed is υ exp If the current following vehicle speed is υ0, then:

[0025] The safety acceleration

[0026] Preferably, let the driving hazard coefficient be γ, and the current following vehicle speed be υ0, then:

[0027] υ exp =υ0×γ.

[0028] Preferably, the following safety distance model includes Equation 1:

[0029]

[0030] Among them, S f This indicates the car-following safety distance. t r Let t be the driver's reaction time. c To eliminate the coordination time of braking clearance, t i Increase the braking time to increase the braking speed.

[0031] Preferably, the following safety distance model includes Equation 2:

[0032]

[0033] in,

[0034]

[0035] S f This indicates the following safety distance; t r Let t be the driver's reaction time. c To eliminate the coordination time of braking clearance, t i The duration of the increased braking speed; S is the current actual distance; S0 is the time during which the target vehicle accelerates at a speed of α within time t1. f Braking distance; υ f Preset free-flow speed; υ opt (a f ) represents the second expected speed of the target vehicle considering the traffic flow at the current moment; a(t) n (t) represents the acceleration of the target vehicle considering the traffic flow at the current moment; n+1 -t n ) represents a unit of time; [S(t) n+1 )-S(t n [υ(t)] represents the change in the distance traveled by the target vehicle within a unit of time;n+1 )-υ(t n [)] represents the change in speed of the target vehicle within one unit of time. The difference between the second expected speed and the current vehicle speed; [S(t n+2 )-S(t n [υ(t)] represents the change in the distance traveled by the target vehicle within two unit time intervals; n+2 )-υ(t n )] represents the speed change of the target vehicle within two unit time intervals; k1, k2, λ1, and λ2 are preset weighting coefficients.

[0036] Preferably, determining whether the current actual distance between the target vehicle and the vehicle in front meets the lane-changing requirements, in conjunction with the following safety distance, includes:

[0037] If the current actual distance is greater than the following safety distance, then the lane-changing requirement is met; otherwise, the lane-changing requirement is not met.

[0038] Preferably, before determining whether the current actual distance between the target vehicle and the preceding vehicle meets the lane-changing requirements, the method further includes:

[0039] Calculate the lane-changing collision avoidance distance using a preset lane-changing collision avoidance distance model;

[0040] The step of determining whether the current actual distance between the target vehicle and the vehicle in front meets the lane-changing requirements, in conjunction with the following safety distance, includes:

[0041] Compare the following safety distance with the lane-changing collision avoidance distance, and select the larger one;

[0042] If the current actual distance is greater than the larger one, then the lane-changing requirement is met; otherwise, the lane-changing requirement is not met.

[0043] Preferably, the lane-changing collision avoidance distance model includes Equation 3:

[0044] S MLO =S M -S Ld +W sinθ; Equation 3

[0045] Among them, S MLO S is the lane-changing collision avoidance distance; M S represents the distance the target vehicle travels in its original lane during the lane change process; Ld The distance the preceding vehicle travels in the original lane during the lane change process; W is the width of the target vehicle; θ is the angle between the axis of the target vehicle's body direction and the direction of the original lane at the start of the lane change.

[0046] In the technical solution provided by the embodiments of the present invention, the driver's driving style is determined based on the actual driving data of the target vehicle driver, and a following safety distance model is established based on the driving style. When calculating the following safety distance, the driver's driving style is taken into account, so the calculation result is more consistent with the actual driving situation of the target vehicle, thereby effectively helping the driver to make lane-changing decisions.

[0047] Furthermore, the following safety distance model set in the technical solution provided in this embodiment of the invention not only considers the driver's driving style, but also the current traffic flow situation. When using the following safety distance model to perform capacity analysis, its calculation results are more consistent with the actual traffic situation, thereby effectively helping drivers make lane-changing decisions.

[0048] The following safety distance model proposed in this invention, which takes into account driving style, comprehensively considers factors such as the target vehicle's speed, the relative speed between the target vehicle and the vehicle in front, and the expected values ​​of different driving styles. It effectively improves the shortcomings of the traditional safety distance model based on the headway, making the calculated following safety distance more realistic and helping to coordinate the relationship between vehicle safety and the lane-changing needs of different drivers.

[0049] In this invention, the above-described technical solutions can be combined with each other to achieve more preferred combinations. Other features and advantages of this invention will be set forth in the following description, and some advantages may become apparent from the description or be learned by practicing the invention. The objects and other advantages of this invention can be realized and obtained from what is particularly pointed out in the description and drawings. Attached Figure Description

[0050] The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Throughout the drawings, the same reference numerals denote the same parts.

[0051] Figure 1 This is a flowchart of the vehicle lane-changing decision-making method in an embodiment of the present invention;

[0052] Figure 2 This is an embodiment of the present invention. Figure 1 Example diagram of the specific implementation process of step 101 shown;

[0053] Figure 3 This is a flowchart illustrating the specific implementation of step 102 in this embodiment of the invention.

[0054] Figure 4 This is a schematic diagram illustrating the acceleration change of a vehicle during braking in the following phase, as described in this embodiment of the invention.

[0055] Figure 5This is an example diagram of the parameters involved in the lane-changing collision avoidance distance model in this embodiment of the invention;

[0056] Figure 6 This is a schematic diagram illustrating the changes in the vehicle speed and the speed of the vehicle in front during the lane-changing process of the target vehicle in this embodiment of the invention;

[0057] Figure 7 This is a schematic diagram of the expected acceleration change and the actual acceleration change of the target vehicle in an embodiment of the present invention;

[0058] Figure 8 This is a comparison diagram of the driver's expected distance between the target vehicle and the vehicle in front during lane changing in an embodiment of the present invention and the actual distance during lane changing. Detailed Implementation

[0059] Preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, which form part of this application and, together with the embodiments of the present invention, serve to illustrate the principles of the present invention.

[0060] This invention provides a vehicle lane-changing decision-making method, see [link to relevant documentation]. Figure 1 , Figure 1 This is a flowchart of a vehicle lane-changing decision-making method in an embodiment of the present invention. The method may include:

[0061] Step 101: Obtain the actual driving data of the target vehicle driver and determine the driver's driving style.

[0062] Step 102: Obtain the current following speed of the target vehicle in the original lane, and determine the safe acceleration of the target vehicle based on the driving style.

[0063] Step 103: Calculate the safe following distance between the target vehicle and the vehicle in front in the same lane using the preset safe following distance model established based on the safe acceleration.

[0064] Step 104: Based on the following safety distance, determine whether the current actual distance between the target vehicle and the vehicle in front meets the lane-changing requirements. If so, lane changing is allowed; otherwise, a prompt prohibiting lane changing is issued.

[0065] In the technical solution provided by the embodiments of the present invention, the driver's driving style is determined based on the actual driving data of the target vehicle driver, and a following safety distance model is established based on the driving style. When calculating the following safety distance, the driver's driving style is taken into account, so the calculation result is more consistent with the actual driving situation of the target vehicle, thereby effectively helping the driver to make lane-changing decisions.

[0066] Specifically, in this embodiment of the invention, the actual driving data may include the parameter values ​​of three driving characteristic parameters, which may include: vehicle steering wheel angle, longitudinal acceleration, and lateral acceleration.

[0067] See Figure 2 , Figure 2 This is an embodiment of the present invention. Figure 1 The diagram shown illustrates a specific implementation flow for step 101. This flow may include:

[0068] Step 201: Using the parameter values ​​of every three driving feature parameters as a set of sample data, multiple sets of the sample data are sampled within a preset time period.

[0069] In this embodiment of the invention, actual driving data is sampled within a period of time, such as half an hour, after the driver starts driving the vehicle to obtain more real-time driving data. Based on "unsupervised learning", cluster analysis is performed on the collected actual driving data of the driver to lay the foundation for further determination of the driver's driving style.

[0070] Step 202: In the three-dimensional space composed of three driving feature parameters, calculate the N driving style cluster centers corresponding to the experience driving data of N different driving styles in advance using a pre-selected clustering algorithm, where N>1.

[0071] The clustering algorithm selected in this embodiment of the invention is the Fuzzy C-means Clustering (FCM) algorithm. The FCM algorithm has advantages such as simple principle, high accuracy, and fast running efficiency. A sample dataset D = {X1, X2, ..., X...} is used. n Taking} as an example, its objective function can be set as:

[0072]

[0073] Where m is the fuzzy weighting index, which can be 2 in this embodiment of the invention; u ij d represents the membership degree of the j-th sample point to the i-th cluster center; ij Let be the distance from the j-th sample point to the i-th cluster center.

[0074] Criteria for finding the optimal solution to the objective function. At that time, there were:

[0075]

[0076] In the specific implementation of this invention, the inventors conduct data analysis based on the driving data of 300 drivers collected in advance. The analysis shows that the drivers' driving styles can be roughly divided into three categories: aggressive, moderate and conservative. Accordingly, in step 202, C=3 can be taken to represent the three types of driving styles, which correspond to three driving style cluster centers.

[0077] See Table 1, which is an example of cluster centers for three types of driving styles calculated by the inventors based on a large amount of collected experience driving data in an embodiment of the present invention.

[0078]

[0079] Table 1

[0080] As can be seen from the data in Table 1, the difference between the maximum and minimum values ​​in the driving data of aggressive drivers is relatively large, which better reflects their aggressive driving style.

[0081] Step 203: Using the above clustering algorithm, calculate a cluster center for the sampled data corresponding to the multiple sets of sampled data.

[0082] In this embodiment of the invention, since the actual driving data collected comes from the same driver who drives the target vehicle within a certain time period, the number of cluster centers C=1 in the above FCM algorithm can be set, and a cluster center of the sampled data will be calculated accordingly.

[0083] Step 204: In the three-dimensional space, calculate the distance from the cluster center of the sampled data to each driving style cluster center, wherein the driving style corresponding to the shortest distance is the driving style to which the driver belongs.

[0084] This allows us to determine the driving style of the driver of the target vehicle.

[0085] See Figure 3 , Figure 3 This is a flowchart illustrating the specific implementation of step 102 in this embodiment of the invention. The process may include:

[0086] Step 301: Obtain the current following speed of the target vehicle in the original lane.

[0087] Step 302: Calculate the first desired speed using the preset driving hazard coefficient corresponding to the driver's driving style and the current following vehicle speed.

[0088] In this embodiment of the invention, based on some work done in advance by the inventors, a preset driving hazard coefficient corresponding to the driver's driving style can be obtained.

[0089] The clustering results of vehicle driver driving styles show that driving style reflects a driver's reaction ability, danger perception, and degree of driving aggression. Drivers with different driving styles have different levels of driving risk. Therefore, in the specific implementation of this invention, the subjective situational risk assessment scores of drivers under different conditions are obtained in advance, and an evaluation model is established to further study the driving risk of each driving style. The driving risk coefficient γ is used to characterize the driving risk.

[0090]

[0091] SUM j SUM represents the subjective situational risk assessment score for the j-th driver. obj The objective situational risk assessment score is given, where a represents the number of dangerous situations, b represents the number of expert drivers, and C represents the number of dangerous situations. ij This represents the risk assessment score of the j-th driver for the i-th subjective scenario. Dangerous scenarios include: a pedestrian suddenly crossing the road while driving straight, the vehicle in front suddenly braking, and vehicles dangerously changing lanes on the left; the vehicle in front braking on a curved section of road; and a pedestrian crossing the road at an intersection. The scenarios include three types: driving straight, driving on a curve, and driving at an intersection, each with a free-driving phase and a phase incorporating traffic flow (vehicles and pedestrians), totaling 15 scenarios. The subjective scenario risk assessment is the driver's subjective evaluation of the experimental scenario, while the objective scenario risk assessment is the evaluation of relevant experimental scenarios by relevant literature. Experts will evaluate whether the driver slows down and brakes in advance at traffic lights, whether they brake and slow down when changing lanes, whether they start quickly when waiting at a red light, and whether they slow down to a reasonable speed before making a U-turn. The risk assessment score for each scenario reflects the degree of risk in that scenario.

[0092] In this embodiment of the invention, the value of γ is between 0.6 and 0.7 for aggressive drivers; between 0.35 and 0.6 for moderate drivers; and between 0 and 0.35 for conservative drivers.

[0093] Let the current following vehicle speed be υ0, and the first desired speed be υ. exp Then we have:

[0094] υ exp =υ0×γ.

[0095] Step 303: Using the current following vehicle speed and the calculated first desired speed, correct the maximum acceleration of the target vehicle to obtain the safe acceleration.

[0096] In step 303, safety acceleration Among them, the safety acceleration a f Considering the driver's driving style, this can be understood as the expected acceleration.

[0097] In this embodiment of the invention, the following car safety distance model can be represented as shown in Equation 1:

[0098]

[0099] Among them, S f The aforementioned safe following distance can be understood as the expected vehicle distance; See Figure 4, Figure 4 This is a schematic diagram illustrating the acceleration change of a vehicle during braking in the following phase, as described in an embodiment of the present invention. Figure 4 In the middle, t r For driver reaction time, t c To eliminate the coordination time of braking clearance, t i To increase the braking speed over time, t p This represents the braking duration.

[0100] Combination Figure 4 Description of S in the embodiments of the present invention f The derivation process is as follows:

[0101] ① In (t) r +t c In stage ) the corresponding target vehicle travels a distance of S1, we have:

[0102] S1=υ0(t r +t c );

[0103] ②At t i In this stage, the corresponding travel distance of the target vehicle is S2, and we have:

[0104]

[0105] ③ At t p In this stage, the corresponding travel distance of the target vehicle is S3, and we have:

[0106]

[0107] but:

[0108] In specific implementation, the above (t) r +t c The time interval can be taken as 0.8–1.0 s, t i A value of 0.1–0.2 s can be taken. Because t i The value is very small, therefore, If the value is very small and can be ignored, then:

[0109] Therefore, we get:

[0110]

[0111] In this embodiment of the invention, the following car-following safety distance model can be represented as shown in Equation 2:

[0112]

[0113] in,

[0114]

[0115] S f This indicates the following safety distance; t r Let t be the driver's reaction time. c To eliminate the coordination time of braking clearance, t i The duration of the increased braking speed; S is the current actual distance; S0 is the time during which the target vehicle accelerates at a speed of α within time t1. f Braking distance; υ f To preset the free-flow speed, a speed below 60 km / h can be used in urban roads; opt (a f ) represents the second expected speed of the target vehicle considering the traffic flow at the current moment; a(t) n The acceleration of the target vehicle is taken into account in the current traffic flow.

[0116] Let t be... n For the current time, t n+1 t represents the time corresponding to the next unit of time after the current time. n+2 If the time corresponds to two units of time after the current time, then:

[0117] (t n+1 -t n ) represents a unit of time; [S(t) n+1 )-S(t n [υ(t)] represents the change in the distance traveled by the target vehicle within a unit of time; n+1 )-υ(t n [)] represents the change in speed of the target vehicle within one unit of time. The difference between the second expected speed and the current vehicle speed; [S(t n+2 )-S(t n [υ(t)] represents the change in the distance traveled by the target vehicle within two unit time intervals; n+2 )-υ(t n )] represents the speed change of the target vehicle within two unit time intervals; k1, k2, λ1, and λ2 are preset weighting coefficients.

[0118] The above regarding a(t) n In the expression, k1υ opt (a f ) terms and k2[υ opt (a f )-υ(t n The term represents the change in expected speed over a unit of time, taking into account driving style. Item and The item takes into account the speed change per unit time under the influence of traffic flow.

[0119] The duration of a single unit can be within 10 seconds, such as 8 seconds.

[0120] The values ​​of the weighting coefficient k1 mentioned above are as follows:

[0121] For the aggressive type, a value between 0.5 and 0.6 can be used;

[0122] For moderate sizes, a value of around 0.4 is suitable.

[0123] For a conservative approach, a value of around 0.3 is acceptable.

[0124] The values ​​of the weighting coefficient k2 mentioned above are as follows:

[0125] For the aggressive type, a value between 0.3 and 0.4 can be used;

[0126] For moderate sizes, a value of around 0.2 is acceptable.

[0127] For a conservative approach, a value of around 0.15 is suitable.

[0128] In practical applications, k1 > k2.

[0129] The aforementioned weighting coefficients λ1≈λ2 have the following values:

[0130] For the aggressive approach, a value of around 0.1 can be used;

[0131] For moderate sizes, a value of around 0.07 is suitable.

[0132] For a conservative approach, a value of around 0.04 is suitable.

[0133] In a specific implementation of the present invention, step 104 can be implemented in two ways:

[0134] One approach is that if the current actual distance is greater than the following safety distance, then the lane-changing requirement is met; otherwise, the lane-changing requirement is not met.

[0135] Another method is to calculate the lane-changing collision avoidance distance using a preset lane-changing collision avoidance distance model;

[0136] Compare the following safety distance with the lane-changing collision avoidance distance, and select the larger one;

[0137] If the current actual distance is greater than the larger one, then the lane-changing requirement is met; otherwise, the lane-changing requirement is not met.

[0138] In practical applications, the above two scenarios can be set according to specific circumstances. Generally speaking, both can meet the safety requirements for lane changing and help drivers achieve safe lane changing.

[0139] Specifically, the lane-changing collision avoidance distance model can include Equation 3:

[0140] S MLO =S M -S Ld +W sinθ=(υ M -υ LO )t l +W sinθ; Equation 3

[0141] The technical solution provided by this invention mainly addresses the technical problems related to the following phase before lane changes. The aforementioned lane change collision avoidance distance model involves collision avoidance processing at the lane change critical point. See also... Figure 5 , Figure 5 This is an example diagram of the parameters involved in the lane-changing collision avoidance distance model in an embodiment of the present invention. Figure 5 In the diagram, M represents the target vehicle, and S... MLO For lane-changing collision avoidance distance; S M (Not shown) represents the distance the target vehicle travels in its original lane during the lane-changing process (i.e., from following the car to preparing to change lanes); S Ld The distance the preceding vehicle travels in the original lane during the lane change; W is the length of the target vehicle; L0 represents the preceding vehicle; θ is the angle between the target vehicle's directional axis and the original lane direction during the lane change. Additionally, υ M The speed of the target vehicle when it changes lanes; LO t is the speed of the vehicle in front in its original lane; l The time it takes for the target vehicle to travel in its original lane to the point of collision with the preceding vehicle.

[0142] In a specific implementation of the present invention, the inventors selected 300 vehicle trajectory data points from the following phase and performed Matlab simulation verification to determine the correctness of the model construction in the embodiments of the present invention.

[0143] Taking a typical driver as an example, suppose the vehicle in front is traveling at 80 km / h, while the target vehicle is traveling at an initial speed of 70 km / h, and the initial distance between the two vehicles is set to 55m. This yields the traditional following safety distance and the following safety distance based on driving style in this embodiment of the invention. Specifically, see... Figure 6 , Figure 6 This is a schematic diagram illustrating the changes in the vehicle speed and the speed of the vehicle in front during the lane-changing process of the target vehicle in this embodiment of the invention; see also Figure 7 , Figure 7 This is a schematic diagram illustrating the expected acceleration change and the actual acceleration change of the target vehicle in an embodiment of the present invention; see also Figure 8 , Figure 8This is a comparison chart of the driver's expected distance between the target vehicle and the vehicle in front during the lane-changing process in the embodiments of the present invention, and the actual distance during the lane-changing process, thereby verifying the effectiveness of the models constructed in the embodiments of the present invention.

[0144] In summary, the technical solution provided by the embodiments of the present invention determines the driver's driving style based on the actual driving data of the target vehicle driver, and then establishes a following safety distance model based on the driving style. When calculating the following safety distance, the driver's driving style is taken into account, so the calculation result is more consistent with the actual driving situation of the target vehicle, thereby effectively helping the driver to make lane-changing decisions.

[0145] Furthermore, the following safety distance model set in the technical solution provided in this embodiment of the invention not only considers the driver's driving style, but also the current traffic flow situation. When using the following safety distance model to perform capacity analysis, its calculation results are more consistent with the actual traffic situation, thereby effectively helping drivers make lane-changing decisions.

[0146] The following safety distance model proposed in this invention, which takes into account driving style, comprehensively considers factors such as the target vehicle's speed, the relative speed between the target vehicle and the vehicle in front, and the expected values ​​of different driving styles. It effectively improves the shortcomings of the traditional safety distance model based on the headway, making the calculated following safety distance more realistic and helping to coordinate the relationship between vehicle safety and the lane-changing needs of different drivers.

[0147] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware, and the program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0148] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A vehicle lane-changing decision-making method, characterized in that, include: Obtain the actual driving data of the target vehicle driver and determine the driver's driving style; The actual driving data includes the parameter values ​​of three driving characteristic parameters, namely: vehicle steering wheel angle, longitudinal acceleration, and lateral acceleration; The acquisition of the actual driving data of the target vehicle driver includes: taking three driving feature parameters as a group of sample data and sampling multiple groups of the sample data within a preset time period; Determining the driver's driving style includes: in the three-dimensional space composed of the three driving feature parameters, using a pre-selected clustering algorithm, calculating N driving style cluster centers corresponding to N different driving styles of experience driving data, where N>1; using the clustering algorithm, calculating a sample data cluster center corresponding to multiple sets of sample data; in the three-dimensional space, calculating the distance from the sample data cluster center to each driving style cluster center, and determining the driving style corresponding to the shortest distance as the driver's driving style; Obtain the current following speed of the target vehicle in the original lane, and determine the safe acceleration of the target vehicle based on the driving style; The step of determining the safe acceleration of the target vehicle based on the driving style includes: calculating a first desired speed using a preset driving hazard coefficient corresponding to the driving style and the current following speed; correcting the maximum acceleration of the target vehicle using the current following speed and the first desired speed to obtain the safe acceleration; and setting the maximum acceleration as... The first desired speed is The current following vehicle speed is The safety acceleration ; Using a preset following safety distance model established based on the aforementioned safety acceleration, the following safety distance between the target vehicle and the vehicle in front in the same lane is calculated; The following safety distance model includes either Equation 1 or Equation 2: Formula 1 Formula 2 in, ; ； This indicates the following safety distance; The driver's reaction time. To eliminate the coordination time of braking clearance, Increased braking speed duration; This represents the current actual distance; The target vehicle is currently in Acceleration within a time period Braking distance; Preset free-flow speed; The second expected speed of the target vehicle is taken into account in the current traffic flow; To take into account the acceleration of the target vehicle in the traffic flow at the current moment; A unit of time; The change in the travel distance of the target vehicle within a unit of time; The change in speed of the target vehicle within a unit of time; The difference between the second expected speed and the current vehicle speed; This represents the change in the travel distance of the target vehicle within two unit time intervals; The change in speed of the target vehicle over two unit time intervals; Preset weighting coefficients; Based on the aforementioned safe following distance, determine whether the current actual distance between the target vehicle and the vehicle in front meets the lane-changing requirements. If so, lane changing is allowed; otherwise, a prompt prohibiting lane changing is displayed.

2. The vehicle lane-changing decision-making method according to claim 1, characterized in that, Let the driving hazard factor be The current following vehicle speed is Then we have: 。 3. The vehicle lane-changing decision-making method according to any one of claims 1 to 2, characterized in that, The step of determining whether the current actual distance between the target vehicle and the vehicle in front meets the lane-changing requirements, in conjunction with the following safety distance, includes: If the current actual distance is greater than the following safety distance, then the lane-changing requirement is met; otherwise, the lane-changing requirement is not met.

4. The vehicle lane-changing decision-making method according to any one of claims 1 to 2, characterized in that, Before determining whether the current actual distance between the target vehicle and the preceding vehicle meets the lane-changing requirements, the method further includes: Calculate the lane-changing collision avoidance distance using a preset lane-changing collision avoidance distance model; The step of determining whether the current actual distance between the target vehicle and the vehicle in front meets the lane-changing requirements, in conjunction with the following safety distance, includes: Compare the following safety distance with the lane-changing collision avoidance distance, and select the larger one; If the current actual distance is greater than the larger one, then the lane-changing requirement is met; otherwise, the lane-changing requirement is not met.

5. The vehicle lane-changing decision-making method according to claim 4, characterized in that, The lane-changing collision avoidance distance model includes Equation 3: Formula 3 in, The lane-changing collision avoidance distance is mentioned. The distance the target vehicle travels in the original lane during the lane change process; The distance the preceding vehicle traveled in the original lane during the lane change process; The width of the target vehicle; The angle between the target vehicle's body direction axis and the original lane direction at the start of the lane change.

Images