A lane navigation method and system, computer equipment, and storage medium.

Abstract

This invention relates to a lane navigation method and system, a computer device, and a storage medium, comprising: receiving a forward image captured by an onboard camera within the current period; inputting the forward image into a pre-trained deep learning model for image recognition to obtain the speed (Speed_A) and brake light activation count (Count_A) of vehicle A in the current lane, and the speed (Speed_B) and brake light activation count (Count_B) of vehicle B in the adjacent lane; performing Bayesian statistics on the brake light activation count (Count_A) and brake light activation count (Count_B) to obtain the braking deviation probability of vehicle A or vehicle B at the next moment; determining whether to change lanes to the adjacent lane based on the relationship between the speeds (Speed_A and Speed_B) and the braking deviation probability of vehicle A or vehicle B at the next moment; and outputting corresponding navigation instructions based on the results of the above determination, thereby improving the accuracy of lane navigation.

Description

Technical Field

[0001] This invention relates to the field of vehicle technology, specifically to a lane navigation method and system, computer equipment, and storage medium. Background Technology

[0002] Car navigation systems offer positioning and route planning capabilities, allowing drivers to know their exact location anytime, anywhere while driving and providing driving routes for easy and efficient travel. With the continuous development of car navigation systems, some systems can now provide lane navigation based on lane congestion, guiding drivers to avoid congested lanes. However, current lane navigation systems typically predict congestion in advance based on the vehicle's real-time location and third-party map data. But the real-time lane data collected by third-party maps may not accurately reflect the actual situation, thus the accuracy of this method is still somewhat insufficient. Summary of the Invention

[0003] The purpose of this invention is to propose a lane navigation method and system, computer equipment, and storage medium to combine real-time road conditions collected and identified during vehicle driving for lane navigation, thereby improving the accuracy of lane navigation.

[0004] To achieve the above objectives, embodiments of the present invention provide a lane navigation method, comprising the following steps:

[0005] The system receives images of the vehicle ahead within the current period from the vehicle-mounted camera and inputs these images into a pre-trained deep learning model for image recognition to obtain the speed Speed_A, brake light counts_A, speed Speed_B, and brake light counts_B of the vehicle ahead A in the current lane and the adjacent vehicle B in the current period.

[0006] The probability of braking deviation of the preceding vehicle A or the preceding vehicle B at the next moment is obtained by performing Bayesian statistics on the number of times the brake lights illuminate (Count_A) and the number of times the brake lights illuminate (Count_B).

[0007] Based on the relationship between Speed_A and Speed_B, and the probability of braking deviation of the preceding vehicle A or preceding vehicle B at the next moment, it is determined whether it is necessary to change lanes to the adjacent lane.

[0008] Based on the results of the above judgment, the corresponding navigation instruction information will be output.

[0009] Preferably, the step of determining whether to change lanes to the adjacent lane based on the relationship between the speeds Speed_A and Speed_B, and the probability of braking deviation of the preceding vehicle A or preceding vehicle B at the next moment, includes:

[0010] Based on the braking deviation probability and braking probability distribution Determine the relationship between the values ​​of a and b in the braking probability distribution; where θ is the braking deviation probability of the preceding vehicle A at the next moment, and (1-θ) is the braking deviation probability of the preceding vehicle B.

[0011] The determination of whether to change lanes to the adjacent lane is based on the relationship between the speeds Speed_A and Speed_B, as well as the relationship between the values ​​of a and b.

[0012] Preferably, determining whether to change lanes to the adjacent lane based on the relationship between the speeds Speed_A and Speed_B, and the relationship between the values ​​a and b, includes:

[0013] When the speed Speed_A is greater than the speed Speed_B, it is determined that there is no need to change lanes to the adjacent lane;

[0014] When the speed Speed_A is equal to the speed Speed_B, and the value of a is less than or equal to the value of b, it is determined that there is no need to change lanes to the adjacent lane; otherwise, it is necessary to change lanes to the adjacent lane.

[0015] When the speed Speed_A is less than the speed Speed_B, and the value of a is greater than or equal to the value of b, it is determined that a lane change to the adjacent lane is required; otherwise, a lane change to the adjacent lane is not required.

[0016] Preferably, the step of outputting corresponding navigation instruction information based on the above determination includes:

[0017] If the above judgment result is negative, output navigation prompts to continue driving in the lane where the vehicle is located or do not provide a prompt; if the above judgment result is positive, output navigation prompts to change lanes to the adjacent lane.

[0018] Another embodiment of the present invention provides a lane navigation system, comprising:

[0019] The image recognition unit is used to receive the forward image captured by the vehicle-mounted camera within the current period, and input the forward image into a pre-trained deep learning model to perform image recognition to obtain the speed Speed_A, brake light count_A of the vehicle A in the lane where the vehicle is located, the speed Speed_B and brake light count_B of the vehicle B in the adjacent lane within the current period.

[0020] The statistics unit is used to perform Bayesian statistics on the number of times the brake lights illuminate (Count_A) and the number of times the brake lights illuminate (Count_B) to obtain the braking deviation probability of the preceding vehicle A or the preceding vehicle B at the next moment.

[0021] The lane change decision unit is used to determine whether it is necessary to change lanes to the adjacent lane based on the relationship between the speeds Speed_A and Speed_B, and the braking deviation probability of the preceding vehicle A or the preceding vehicle B at the next moment.

[0022] The navigation instruction unit is used to output corresponding navigation instruction information based on the results of the above judgment.

[0023] Preferably, the lane change decision unit includes:

[0024] The weight calculation unit calculates the braking deviation probability and the braking probability distribution. Determine the relationship between the values ​​of a and b in the braking probability distribution; where θ is the braking deviation probability of the preceding vehicle A at the next moment, and (1-θ) is the braking deviation probability of the preceding vehicle B.

[0025] The judgment unit is used to determine whether it is necessary to change lanes to the adjacent lane based on the relationship between the speeds Speed_A and Speed_B, and the relationship between the values ​​of a and b.

[0026] Preferably, the determining unit is specifically used for:

[0027] When the speed Speed_A is greater than the speed Speed_B, it is determined that there is no need to change lanes to the adjacent lane;

[0028] When the speed Speed_A is equal to the speed Speed_B, and the value of a is less than or equal to the value of b, it is determined that there is no need to change lanes to the adjacent lane; otherwise, it is necessary to change lanes to the adjacent lane.

[0029] When the speed Speed_A is less than the speed Speed_B, and the value of a is greater than or equal to the value of b, it is determined that a lane change to the adjacent lane is required; otherwise, a lane change to the adjacent lane is not required.

[0030] Preferably, the navigation indicator unit is specifically used for:

[0031] When the lane change decision unit determines the outcome, it outputs a navigation prompt to continue driving in the lane where the vehicle is currently located or does not provide a prompt; when the lane change decision unit determines the outcome, it outputs a navigation prompt to change lanes to the adjacent lane.

[0032] Another embodiment of the present invention provides a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the lane navigation method described above.

[0033] Another embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the lane navigation method described above.

[0034] The embodiments of the present invention have at least the following beneficial effects:

[0035] The system uses a deep learning model to acquire information on the brake lights and speeds of vehicles in the lane in front of the vehicle, as well as the brake lights and speeds of vehicles in adjacent lanes (left or right). A Bayesian statistical model is used to obtain the braking status (i.e., braking deviation probability) of vehicles in the lane in front of the vehicle and vehicles in adjacent lanes at the next time step. Combined with the speed information of vehicles in the lane in front of the vehicle and vehicles in adjacent lanes, the system determines the congestion situation in the lane in front of the vehicle and vehicles in adjacent lanes. Based on the congestion situation, the system determines whether a lane change is necessary, thereby guiding drivers to avoid congested lanes and choose more open lanes in advance.

[0036] Other features and advantages of embodiments of the present invention will be set forth in the following description. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 This is a flowchart illustrating a lane navigation method according to an embodiment of the present invention.

[0039] Figure 2 This is a schematic diagram illustrating the braking probability distribution curve in an embodiment of the present invention.

[0040] Figure 3 This is a flowchart illustrating a lane navigation system according to an embodiment of the present invention. Detailed Implementation

[0041] The various exemplary embodiments, features, and aspects of this disclosure will now be described in detail with reference to the accompanying drawings. Furthermore, numerous specific details are set forth in the following detailed embodiments to better illustrate the invention. Those skilled in the art will understand that the invention can be practiced without certain specific details. In some instances, means well known to those skilled in the art have not been described in detail in order to highlight the spirit of the invention.

[0042] See Figure 1 The present invention provides a lane navigation method, comprising the following steps:

[0043] Step S100: Receive the forward image captured by the vehicle-mounted camera within the current period, and input the forward image into a pre-trained deep learning model for image recognition to obtain the speed Speed_A, brake light counts_A, speed Speed_B, and brake light counts_B of the vehicle A in the lane where the vehicle is located within the current period.

[0044] It should be noted that the adjacent lane refers to the left or right adjacent lane, and the time of one cycle is preferably, but not limited to, 1 minute. In this embodiment, the vehicle-mounted camera is a camera installed at the front of the vehicle. Generally, current driver assistance systems are equipped with a front camera to collect images of the front. Furthermore, using a deep learning model to perform image recognition on the images of the front of the vehicle during driving to obtain the speed information of the vehicle in front and the number of times the brake lights illuminate is a mature application of deep learning models in the field of vehicle-assisted driving. For example, its principle can be to identify the target vehicle in the current vehicle's lane and the adjacent lane in the image, and to determine the speed information of the vehicle in front and the number of times the brake lights illuminate based on the images of the previous and next frames. The distance of the vehicle's camera is used to determine the distance the preceding vehicle travels between frames, thus allowing the calculation of the vehicle's speed. This is just one example of a simple principle. Of course, to improve recognition accuracy, the model parameters need to be continuously trained and improved. Recognizing the number of times the brake lights illuminate is even easier to achieve. By identifying the brake light target in the image ahead and judging the pixel changes of the brake light target, it can be determined whether the light is on or off, thus obtaining the number of times the brake lights illuminate. This is just one example of a simple principle. It should be understood that there are many types of deep learning model structures currently in use, and this embodiment is not limited to any one of them.

[0045] Step S200: Perform Bayesian statistics on the number of times the brake lights illuminate (Count_A) and the number of times the brake lights illuminate (Count_B) to obtain the braking deviation probability of the preceding vehicle A or the preceding vehicle B at the next moment;

[0046] Specifically, the number of times the brake lights illuminate (Count_A) and the number of times the brake lights illuminate (Count_B) are input into a preset Bayesian statistical model to perform probability statistics on the braking situation of the vehicle in the current period and the vehicle in the adjacent lane, and output a braking deviation probability. This braking deviation probability can be set as the braking deviation probability of the vehicle in front (A) or the vehicle in front (B) at the next moment, which is predicted by statistically analyzing the braking data of the current period. In this embodiment, the lane change decision only needs to use one of the probabilities.

[0047] Step S300: Based on the relationship between the speeds Speed_A and Speed_B, and the braking deviation probability of the preceding vehicle A or the preceding vehicle B at the next moment, determine whether it is necessary to change lanes to the adjacent lane.

[0048] Specifically, as described above, in step S200, the braking deviation probability of the preceding vehicle A or the preceding vehicle B at the next moment will be obtained. The sum of the braking deviation probabilities of the preceding vehicle A and the preceding vehicle B is 1. Therefore, it is only necessary to output one of the braking deviation probability of the preceding vehicle A or the braking deviation probability of the preceding vehicle B.

[0049] Further, step S300 may include:

[0050] Step S301: Based on the braking deviation probability θ and the braking probability distribution... Determine the relationship between the values ​​of a and b in the braking probability distribution; where θ is the braking deviation probability of the preceding vehicle A at the next moment, and (1-θ) is the braking deviation probability of the preceding vehicle B.

[0051] Specifically, braking probability distribution The three distribution scenarios are as follows: Figure 2 As shown, Figure 2 In the middle Beta(2,8), the braking probability distribution curve is Count_A = 2 and Count_B = 8, and the corresponding braking deviation probability θ is 2 / (8+2). Figure 2 In the middle Beta(5,5), the braking probability distribution curve is Count_A = 5 and Count_B = 5, and the corresponding braking deviation probability θ is 5 / (5+5). Figure 2 In the diagram, Beta(8,2) represents the braking probability distribution curve with Count_A = 8 and Count_B = 2, and the corresponding braking deviation probability θ is 2 / (8+2). It should be understood that the integral result of the braking probability distribution curve is... If the value of θ is given, then the braking deviation probability θ has been statistically predicted using a Bayesian statistical model. Therefore, the braking probability distribution... The function has only two parameters, a and b, and both a and b are values ​​greater than or equal to 0. Therefore, the relationship between the values ​​of a and b can be determined.

[0052] Step S302: Determine whether it is necessary to change lanes to the adjacent lane based on the relationship between the speeds Speed_A and Speed_B, and the relationship between the values ​​of a and b.

[0053] Specifically, the speed of the vehicle in front indicates the smoothness of its movement on the road and reflects lane congestion to some extent. At the same time, the predicted probability of the vehicle in front braking at the next moment also reflects lane congestion to some extent. It is necessary to combine the two pieces of information to make a judgment.

[0054] Further, step S302 includes:

[0055] When the speed Speed_A is greater than the speed Speed_B, it is determined that there is no need to change lanes to the adjacent lane;

[0056] When the speed Speed_A is equal to the speed Speed_B, and the value of a is less than or equal to the value of b, it is determined that there is no need to change lanes to the adjacent lane; otherwise, it is necessary to change lanes to the adjacent lane.

[0057] When the speed Speed_A is less than the speed Speed_B, and the value of a is greater than or equal to the value of b, it is determined that a lane change to the adjacent lane is required; otherwise, a lane change to the adjacent lane is not required.

[0058] Specifically, when Speed_A is greater than Speed_B, it indicates that, considering the speed of the vehicle ahead, the traffic conditions in the lane where this vehicle is located are better than those in the adjacent lane. In this case, lane changing is not considered regardless of whether the value of 'a' is greater than the value of 'b'. When Speed_A is equal to Speed_B, it indicates that, considering the speed of the vehicle ahead, the traffic conditions in the lane where this vehicle is located and the adjacent lane are equal. In this case, it is considered whether the value of 'a' is greater than the value of 'b'. If the value of 'a' is greater than the value of 'b', it means that the probability of the vehicle ahead (A) braking in the next moment is higher than that of the vehicle ahead (B). If the probability that vehicle B in front is likely to brake is higher, then a lane change is necessary. If the value of a is less than or equal to the value of b, it means that the probability that vehicle A in front is likely to brake in the next moment is not greater than the probability that vehicle B in front is likely to brake, so a lane change is not necessary. When the speed Speed_A is less than the speed Speed_B, it means that considering the speed of the vehicle in front, the traffic situation in the lane where this vehicle is located is worse than that in the adjacent lane. In this case, if the value of a is greater than or equal to the value of b, that is, as long as the probability that vehicle A in front is likely to brake in the next moment is not less than the probability that vehicle B in front is likely to brake, a lane change should be made.

[0059] Step S400: Output the corresponding navigation instruction information based on the results of the above judgment.

[0060] Further, step S400 includes:

[0061] If the above judgment result is negative, output navigation prompts to continue driving in the lane where the vehicle is located or do not provide a prompt; if the above judgment result is positive, output navigation prompts to change lanes to the adjacent lane.

[0062] This embodiment uses a deep learning model to acquire brake light and speed information of the vehicle in front in the vehicle's lane and the vehicle in front in the adjacent lane (left or right lane). It uses a Bayesian statistical model to obtain the braking status (i.e., braking deviation probability) of the vehicle in front in the vehicle's lane and the vehicle in front in the adjacent lane at the next moment. It then combines the vehicle speed information of the vehicle in front in the vehicle's lane and the vehicle in front in the adjacent lane to determine the congestion situation in the vehicle's lane and the adjacent lane. Based on the congestion situation, it determines whether a lane change is necessary, thereby guiding the driver to avoid congested lanes and choose a more open lane in advance.

[0063] See Figure 3 Another embodiment of the present invention provides a lane navigation system that can be used to implement the methods of the above embodiments, including:

[0064] Image recognition unit 1 is used to receive the forward image captured by the vehicle-mounted camera in the current period, and input the forward image into a pre-trained deep learning model to perform image recognition to obtain the speed Speed_A, brake light counts_A of the vehicle A in the lane where the vehicle is located, the speed Speed_B and brake light counts_B of the vehicle B in the adjacent lane in the current period;

[0065] Statistical unit 2 is used to perform Bayesian statistics on the number of times the brake lights illuminate (Count_A) and the number of times the brake lights illuminate (Count_B) to obtain the braking deviation probability of the preceding vehicle A or the preceding vehicle B at the next moment.

[0066] Lane change decision unit 3 is used to determine whether it is necessary to change lanes to the adjacent lane based on the relationship between the speeds Speed_A and Speed_B, and the braking deviation probability of the preceding vehicle A or the preceding vehicle B at the next moment.

[0067] The navigation instruction unit 4 is used to output corresponding navigation instruction information based on the results of the above judgment.

[0068] Furthermore, the lane change decision unit 3 includes:

[0069] The weight calculation unit calculates the braking deviation probability θ and the braking probability distribution. Determine the relationship between the values ​​of a and b in the braking probability distribution; where θ is the braking deviation probability of the preceding vehicle A at the next moment, and (1-θ) is the braking deviation probability of the preceding vehicle B.

[0070] The judgment unit is used to determine whether it is necessary to change lanes to the adjacent lane based on the relationship between the speeds Speed_A and Speed_B, and the relationship between the values ​​of a and b.

[0071] Furthermore, the determination unit is specifically used for:

[0072] When the speed Speed_A is greater than the speed Speed_B, it is determined that there is no need to change lanes to the adjacent lane;

[0073] When the speed Speed_A is equal to the speed Speed_B, and the value of a is less than or equal to the value of b, it is determined that there is no need to change lanes to the adjacent lane; otherwise, it is necessary to change lanes to the adjacent lane.

[0074] When the speed Speed_A is less than the speed Speed_B, and the value of a is greater than or equal to the value of b, it is determined that a lane change to the adjacent lane is required; otherwise, a lane change to the adjacent lane is not required.

[0075] Furthermore, the navigation instruction unit 4 is specifically used for:

[0076] When the lane change decision unit determines the outcome, it outputs a navigation prompt to continue driving in the lane where the vehicle is currently located or does not provide a prompt; when the lane change decision unit determines the outcome, it outputs a navigation prompt to change lanes to the adjacent lane.

[0077] The systems described in the embodiments above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of the system solution in the embodiments, depending on actual needs.

[0078] It should be noted that the system in the above embodiments corresponds to the method in the above embodiments. Therefore, the parts of the system in the above embodiments that are not described in detail can be obtained by referring to the content of the method in the above embodiments. That is, the specific steps recorded in the method in the above embodiments can be understood as the functions that the system in the above embodiments can achieve, and will not be described again here.

[0079] Furthermore, if the lane navigation system described above is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0080] Another embodiment of the present invention provides a computer device, comprising: a lane navigation system according to the above embodiments; or, a memory and a processor, wherein the memory stores computer-readable instructions, which, when executed by the processor, cause the processor to perform the steps of the lane navigation method according to the above embodiments.

[0081] Of course, the computer device may also have wired or wireless network interfaces, keyboards, and input / output interfaces for input and output. The computer device may also include other components for implementing device functions, which will not be elaborated here.

[0082] For example, the computer program may be divided into one or more units, which are stored in the memory and executed by the processor to perform the present invention. The one or more units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the computer device.

[0083] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the computer device, connecting all parts of the computer device via various interfaces and lines.

[0084] The memory can be used to store the computer programs and / or units. The processor implements various functions of the computer device by running or executing the computer programs and / or units stored in the memory and by calling data stored in the memory. Furthermore, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disks, RAM, plug-in hard disks, smart media cards (SMC), secure digital cards (SD), flash cards, at least one disk storage device, flash memory device, or other volatile solid-state storage devices.

[0085] Another embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the lane navigation method described in the above embodiments.

[0086] Specifically, the computer-readable storage medium may include any entity or device capable of carrying the computer program instructions, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0087] The various embodiments of the present invention have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or technical improvements to the embodiments in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A lane navigation method characterized by, The method comprises the following steps: receiving a front image collected by a vehicle-mounted camera in a current period, and inputting the front image into a pre-trained deep learning model for image recognition to obtain a speed Speed_A of a front vehicle A in a lane where the vehicle is located, a brake light on count Count_A, a speed Speed_B of a front vehicle B in a neighboring lane, and a brake light on count Count_B; performing Bayesian statistics on the brake light on count Count_A and the brake light on count Count_B to obtain brake deviation probabilities of the front vehicle A or the front vehicle B at a next moment; and the brake deviation probabilities of the front vehicle A and the front vehicle B are 1 in total; judging whether to change lanes to the neighboring lane according to a size relationship between the speed Speed_A and the speed Speed_B and the brake deviation probabilities of the front vehicle A or the front vehicle B at the next moment; outputting corresponding navigation instruction information according to a result of the judgment.

2. The method of claim 1, wherein, The judgment whether to change lanes to the neighboring lane according to the size relationship between the speed Speed_A and the speed Speed_B and the brake deviation probabilities of the front vehicle A or the front vehicle B at the next moment comprises: According to the brake deviation probability and the brake probability distribution Determine the size relationship of a value and b value in the brake probability distribution; wherein, θ is the brake deviation probability of the front vehicle A at the next time, (1-θ) is the brake deviation probability of the front vehicle B; judging whether to change lanes to the neighboring lane according to the size relationship between the speed Speed_A and the speed Speed_B and a size relationship between the a value and the b value.

3. The method of claim 2, wherein, The judgment whether to change lanes to the neighboring lane according to the size relationship between the speed Speed_A and the speed Speed_B and the size relationship between the a value and the b value comprises: when the speed Speed_A is greater than the speed Speed_B, it is determined that the lanes do not need to be changed to the neighboring lane; when the speed Speed_A is equal to the speed Speed_B and the a value is less than or equal to the b value, it is determined that the lanes do not need to be changed to the neighboring lane, otherwise the lanes need to be changed to the neighboring lane; when the speed Speed_A is less than the speed Speed_B and the a value is greater than or equal to the b value, it is determined that the lanes need to be changed to the neighboring lane, otherwise the lanes do not need to be changed to the neighboring lane.

4. The method of claim 1, wherein, The outputting of the corresponding navigation instruction information according to the result of the judgment comprises: when the judgment result is no, navigation prompt information for continuing to drive in the lane where the vehicle is located or no prompt is outputted; and when the judgment result is yes, navigation prompt information for changing lanes to the neighboring lane is outputted.

5. A lane navigation system, characterized by, The method comprises the following steps: an image recognition unit, configured to receive a front image collected by a vehicle-mounted camera in a current period, and input the front image into a pre-trained deep learning model for image recognition to obtain a speed Speed_A of a front vehicle A in a lane where the vehicle is located, a brake light on count Count_A, a speed Speed_B of a front vehicle B in a neighboring lane, and a brake light on count Count_B; a statistics unit, configured to perform Bayesian statistics on the brake light on count Count_A and the brake light on count Count_B to obtain brake deviation probabilities of the front vehicle A or the front vehicle B at a next moment; and the brake deviation probabilities of the front vehicle A and the front vehicle B are 1 in total; and judging whether to change lanes to the neighboring lane according to a size relationship between the speed Speed_A and the speed Speed_B and the brake deviation probabilities of the front vehicle A or the front vehicle B at the next moment. The lane changing decision unit is configured to determine whether to change lanes to the adjacent lane according to the size relationship between the speed Speed_A and the speed Speed_B and the brake deviation probability of the front vehicle A or the front vehicle B at the next time point. The navigation instruction unit is configured to output corresponding navigation instruction information according to the determination result.

6. The system of claim 5, wherein, The lane changing decision unit comprises: a weight calculation unit configured to calculate a weight according to the brake deviation probability and the brake probability distribution determine a size relationship between the a value and the b value in the brake probability distribution; wherein θ is a brake deviation probability of a preceding vehicle A at a next time, and (1-θ) is a brake deviation probability of a preceding vehicle B The determination unit is configured to determine whether to change lanes to the adjacent lane according to the size relationship between the speed Speed_A and the speed Speed_B and the size relationship between the a value and the b value.

7. The system of claim 6, wherein, The determination unit is specifically configured to: when the speed Speed_A is greater than the speed Speed_B, determine not to change lanes to the adjacent lane; when the speed Speed_A is equal to the speed Speed_B and the a value is less than or equal to the b value, determine not to change lanes to the adjacent lane, otherwise, determine to change lanes to the adjacent lane; when the speed Speed_A is less than the speed Speed_B and the a value is greater than or equal to the b value, determine to change lanes to the adjacent lane, otherwise, determine not to change lanes to the adjacent lane.

8. The system of claim 5, wherein, The navigation instruction unit is specifically configured to: when the determination result of the lane changing decision unit is no, output navigation prompt information for continuing to drive along the lane where the vehicle is located or not to perform prompting; and when the determination result of the lane changing decision unit is yes, output navigation prompt information for changing lanes to the adjacent lane.

9. A computer device, comprising: The processor executes the program to implement the steps of the lane navigation method in any one of claims 1-4. 10.A computer readable storage medium, having stored thereon a computer program, the computer program being executed by a processor to implement the steps of the lane navigation method in any one of claims 1-4.

Images