Intelligent driving method and device
By obtaining the vehicle's driving path and obstacle avoidance information uploaded by other vehicles, and combining the obstacle information identified by the vehicle itself, obstacle avoidance is avoided, the problem of insufficient obstacle avoidance ability of intelligent driving vehicles is solved, the accuracy of obstacle identification and obstacle avoidance ability is improved, and driving safety is ensured.
Patent Information
- Application Number
- CN202411508044.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-28
- Publication Date
- 2025-03-14
AI Technical Summary
The obstacle avoidance ability of intelligent driving vehicles is limited by sensors. For example, the camera is greatly affected by light and weather, the radar detection range is small and the cost is high, resulting in insufficient obstacle avoidance ability.
By obtaining the vehicle's driving path, determining the fixed monitoring device and obtaining information such as the detour start point, end point and trajectory from the obstacle avoidance information uploaded by other vehicles, and combining the obstacle information identified by the vehicle itself, obstacle avoidance is avoided.
The obstacle avoidance information stored in the fixed monitoring device is used to supplement obstacle information, which improves the accuracy of obstacle identification, enhances the obstacle avoidance ability of intelligent driving vehicles, reduces the incidence of accidents, and ensures driving safety.
Smart Images
Figure CN119620747A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field related to intelligent driving, and more specifically, to an intelligent driving method and device. Background Art
[0002] Smart driving vehicles use their own cameras, radars and other sensors to sense obstacles around the vehicle and provide support for vehicle obstacle avoidance. However, various sensors have their own defects. For example, cameras are greatly affected by light and weather, and radars have defects such as small detection range and high cost. In other words, the obstacle avoidance ability of smart driving vehicles still has room for improvement. Therefore, it is necessary to design a technical solution that can overcome the above defects. Summary of the invention
[0003] An object of the present invention is to provide an intelligent driving method and device, which can improve the obstacle avoidance capability of an intelligent driving vehicle and ensure driving safety.
[0004] In order to achieve these objectives and other advantages of the present invention, according to one aspect of the present invention, the present invention provides an intelligent driving method, including: S1: obtaining a vehicle driving path; S2: determining a fixed monitoring device located on the vehicle driving path, and obtaining obstacle avoidance information from the fixed monitoring device, wherein the obstacle avoidance information is uploaded by other vehicles; S3: performing obstacle avoidance on obstacles using the obstacle avoidance information and obstacle information identified by the vehicle itself.
[0005] Furthermore, the obstacle avoidance information includes a detour starting point, a detour end point, and a detour trajectory; the obstacle information includes a position, a shape, and a size; the obstacle information is corrected according to the obstacle avoidance information, and obstacle avoidance is performed on the obstacle using the corrected obstacle information.
[0006] Furthermore, obstacle prediction information is estimated based on the obstacle avoidance information; an error between the obstacle prediction information and the obstacle information is compared, and if the error is greater than a first predetermined value, the obstacle prediction information is used to correct the obstacle information.
[0007] Furthermore, in S3, it also includes: calculating the confidence of the obstacle avoidance information, and selecting the obstacle avoidance information whose confidence is greater than a second predetermined value.
[0008] Furthermore, the confidence level is the sum of a first confidence level and a second confidence level; the first confidence level is a weighted average of uploaded behavior parameters of the vehicle corresponding to the obstacle avoidance information; and the second confidence level is a weighted average of the trusted data corresponding to the obstacle avoidance information.
[0009] According to another aspect of the present invention, an intelligent driving device is also provided, including: a first acquisition module, used to obtain a vehicle driving path; a second acquisition module, used to determine a fixed monitoring device located on the vehicle driving path, and obtain obstacle avoidance information from the fixed monitoring device, wherein the obstacle avoidance information is uploaded by other vehicles; and an obstacle avoidance module, used to perform obstacle avoidance on obstacles using the obstacle avoidance information and obstacle information identified by the vehicle itself.
[0010] Furthermore, the obstacle avoidance information includes a detour starting point, a detour end point, and a detour trajectory; the obstacle information includes a position, a shape, and a size; the obstacle avoidance module corrects the obstacle information according to the obstacle avoidance information, and uses the corrected obstacle information to perform obstacle avoidance on the obstacle.
[0011] Furthermore, the obstacle avoidance module estimates obstacle prediction information according to the obstacle avoidance information, and compares an error between the obstacle prediction information and the obstacle information, and if the error is greater than a first predetermined value, uses the obstacle prediction information to correct the obstacle information.
[0012] Furthermore, the obstacle avoidance module calculates the confidence of the obstacle avoidance information, and selects the obstacle avoidance information whose confidence is greater than a second predetermined value.
[0013] Furthermore, the confidence level is the sum of a first confidence level and a second confidence level; the first confidence level is a weighted average of uploaded behavior parameters of the vehicle corresponding to the obstacle avoidance information; and the second confidence level is a weighted average of the trusted data corresponding to the obstacle avoidance information.
[0014] The present invention has at least the following beneficial effects: The present invention obtains a vehicle driving path, determines a fixed monitoring device located on the vehicle driving path, obtains obstacle avoidance information from the fixed monitoring device, and performs obstacle avoidance on the obstacle using the obstacle avoidance information and obstacle information identified by the vehicle itself; the present invention supplements the obstacle information with the obstacle avoidance information stored in the fixed monitoring device, thereby improving the accuracy of obstacle identification, thereby improving the obstacle avoidance capability of the intelligent driving vehicle, reducing the accident rate, and ensuring driving safety.
[0015] Other advantages, objectives and features of the present invention will be embodied in part through the following description, and in part will be understood by those skilled in the art through study and practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] Figure 1 This is a flow chart of an embodiment of the present application. DETAILED DESCRIPTION
[0017] The present invention is further described in detail below in conjunction with the accompanying drawings so that those skilled in the art can implement the invention with reference to the description.
[0018] It should be understood that the terms such as "having", "including" and "comprising" used in the embodiments of the present application do not exclude the existence or addition of one or more other elements or their combinations. All directional indications (such as up, down, left, right, front, back...) in the embodiments of the present application are only used to explain the relative position relationship, movement, etc. between the components in a certain specific posture. If the specific posture changes, the directional indication will also change accordingly. When an element is referred to as "fixed on" or "set on" another element, it can be directly on the other element or there may be a centering element at the same time. When an element is referred to as "connecting" another element, it can be directly connected to another element or it can be indirectly connected to another element through a centering element. The description of "first", "second", etc. in the embodiments of the present application is only for descriptive purposes, and cannot be understood as indicating or implying its relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" can explicitly or implicitly include at least one of the features.
[0019] It should be noted that the technical solutions between the various embodiments of the present application can be combined with each other, but it must be based on the fact that ordinary technicians in the field can implement it. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.
[0020] like Figure 1 As shown, an embodiment of the present application provides an intelligent driving method, including: S1: Obtain vehicle driving path; Exemplarily, the driving path is determined by a navigation route of the vehicle; For example, if there is no navigation route, the possible driving path of the vehicle can be estimated based on the driving direction of the vehicle and the map; S2: determining a fixed monitoring device located on the driving path of the vehicle, and obtaining obstacle avoidance information from the fixed monitoring device, wherein the obstacle avoidance information is uploaded by other vehicles; Exemplarily, the fixed monitoring devices are arranged on facilities such as street lamps, bridge piers, and overpasses near the road, and are distributed around the road at intervals. Each fixed monitoring device pre-sets a certain monitoring range and stores obstacle avoidance information within the monitoring range. Exemplarily, the fixed monitoring device has a processing unit, a storage unit and a communication unit. The storage unit is used to store obstacle avoidance information. The communication unit uses short-distance communication methods such as WIFI and Bluetooth to communicate with the vehicle. When the vehicle approaches the fixed monitoring device, the obstacle avoidance information uploaded by the vehicle is received or the obstacle avoidance information is sent to the vehicle. The processing unit performs logical control. Exemplarily, the obstacle avoidance information includes the driving behavior of the vehicle deviating from the driving path; S3: using the obstacle avoidance information and the obstacle information identified by the vehicle itself, performing obstacle avoidance on the obstacle; For example, the vehicle itself has sensors such as cameras and radars, which can realize obstacle modeling; In this step, due to the inherent defects of cameras and radars, the obstacle model may not be accurate enough. For example, the camera is affected by light and there are large errors in the estimation of the position and size of the obstacle. The obstacle avoidance information obtained from the fixed monitoring device is used to supplement and correct the obstacle model to obtain a new obstacle model with higher accuracy. The new obstacle model is used to perform obstacle avoidance. It can be seen that this embodiment uses the obstacle avoidance information stored in the fixed monitoring device to supplement the obstacle information, overcomes the defects of the vehicle's own sensors, improves the accuracy of obstacle recognition, and further improves the obstacle avoidance capability of the intelligent driving vehicle, reduces the accident rate, and ensures driving safety; the obstacle avoidance information comes from other intelligent driving vehicles, so that multiple intelligent driving vehicles can share information, combine the sensor detection capabilities of multiple intelligent driving vehicles, improve the obstacle avoidance capability, and further improve the utilization rate of sensors on a single intelligent driving vehicle.
[0021] In another embodiment, the obstacle avoidance information includes a detour starting point, a detour end point, and a detour trajectory; the obstacle information includes a position, a shape, and a size; the obstacle information is corrected according to the obstacle avoidance information, and obstacle avoidance is performed on the obstacle using the corrected obstacle information; Exemplarily, the obstacle avoidance information is determined according to the difference between the actual driving route and the theoretical driving route within the monitoring range, and may include the position information of the detour starting point, the position information of the detour end point, and the position information of the sites included in the detour trajectory; Exemplarily, the obstacle information is determined based on the image data or point cloud data collected by the sensor, and the obstacle model establishment method in the prior art may be referred to, which at least includes the position, shape and size of the obstacle, so that the intelligent driving vehicle can make obstacle avoidance decisions; Exemplarily, obstacle prediction information is estimated based on the obstacle avoidance information; errors between the obstacle prediction information and the obstacle information are compared; if the error is greater than a first predetermined value, the obstacle information is corrected using the obstacle prediction information; the first predetermined value can be determined based on experience or statistical data, as long as it can ensure that the corrected obstacle information has sufficient accuracy; the correction method can be to directly replace the obstacle information with the obstacle prediction information, or to re-process the data collected by the sensor based on the difference between the two and re-establish the obstacle model.
[0022] Exemplarily, a convolutional neural network model is established using historical data training, and the location information of the detour starting point, the location information of the detour end point, and the location information of the sites included in the detour trajectory are combined into a matrix and input into the convolutional neural network model. The location, shape, and size of the obstacle are output to obtain obstacle prediction information.
[0023] In another embodiment, in S3, it further includes: calculating the confidence of the obstacle avoidance information, and selecting the obstacle avoidance information whose confidence is greater than a second predetermined value; This embodiment screens the obstacle avoidance information stored in the fixed monitoring device, selects obstacle avoidance information with high confidence to correct the obstacle information, and reduces the interference of invalid obstacle avoidance information on the obstacle avoidance strategy; Exemplarily, the confidence level is the sum of the first confidence level and the second confidence level; the first confidence level is the weighted average value of the uploaded behavior parameters of the vehicle corresponding to the obstacle avoidance information; the second confidence level is the weighted average value of the trusted data corresponding to the obstacle avoidance information; the uploaded behavior parameters express the credit behavior of the vehicle itself, and the trusted data expresses the credibility of the obstacle avoidance information itself; Exemplarily, the upload behavior parameters include the vehicle's historical upload times and historical acceptance times. The acceptance times refer to the total number of times the obstacle avoidance information uploaded by the vehicle is accepted by other vehicles for obstacle information correction. The weights of the two are determined by expert scoring method or hierarchical analysis method.
[0024] Exemplarily, the accepted data include upload time, weather parameters at the time of upload, acceptance time, and number of acceptances. The weight of each parameter is determined by expert scoring method or hierarchical analysis method. The weather parameters at the time of upload mainly include parameters that affect sensors, such as rain, snow, and fog. The closer the weather is to the time when the obstacle avoidance information is obtained, the higher the weight. Generally speaking, the upload time and acceptance time are the time when the obstacle avoidance information is uploaded and the time when it was last accepted, respectively. The closer to the time when the vehicle obtains the obstacle avoidance information, the higher the weight.
[0025] The embodiment of the present application further provides an intelligent driving device, comprising: a first acquisition module, used to acquire a vehicle driving path; a second acquisition module, used to determine a fixed monitoring device located on the vehicle driving path, and acquire obstacle avoidance information from the fixed monitoring device, wherein the obstacle avoidance information is uploaded by other vehicles; an obstacle avoidance module, used to perform obstacle avoidance on obstacles using the obstacle avoidance information and obstacle information identified by the vehicle itself; This embodiment uses a computer program to construct a first acquisition module, a second acquisition module and an obstacle avoidance module. The first acquisition module is used to obtain a driving path from a vehicle, and the second acquisition module is used to obtain obstacle avoidance information from a fixed monitoring device to supplement and correct the obstacle model to obtain a new obstacle model. The new obstacle model has higher accuracy, and the obstacle avoidance module uses the new obstacle model to perform obstacle avoidance.
[0026] In another embodiment, the obstacle avoidance information includes a detour start point, a detour end point, and a detour trajectory; the obstacle information includes a position, a shape, and a size; the obstacle avoidance module corrects the obstacle information according to the obstacle avoidance information, and uses the corrected obstacle information to perform obstacle avoidance on the obstacle; the obstacle avoidance module estimates obstacle prediction information according to the obstacle avoidance information, and compares an error between the obstacle prediction information and the obstacle information, and if the error is greater than a first predetermined value, uses the obstacle prediction information to correct the obstacle information; In this embodiment, the obstacle avoidance information is determined based on the difference between the actual driving route and the theoretical driving route within the monitoring range, and may include the position information of the detour starting point, the position information of the detour end point, and the position information of the sites included in the detour trajectory; illustratively, the obstacle avoidance module uses historical data training to establish a convolutional neural network model, combines the position information of the detour starting point, the position information of the detour end point, and the position information of the sites included in the detour trajectory into a matrix, inputs the convolutional neural network model, outputs the position, shape and size of the obstacle, and obtains the obstacle prediction information. When the obstacle prediction information is significantly different from the obstacle information, it is necessary to correct the obstacle information based on the obstacle prediction information.
[0027] In another embodiment, the obstacle avoidance module calculates the confidence of the obstacle avoidance information, and selects the obstacle avoidance information whose confidence is greater than a second predetermined value; the confidence is the sum of the first confidence and the second confidence; the first confidence is the weighted average of the uploaded behavior parameters of the vehicle corresponding to the obstacle avoidance information; the second confidence is the weighted average of the trusted data corresponding to the obstacle avoidance information; In this embodiment, the upload behavior parameter expresses the credit behavior of the vehicle itself, and the accepted data expresses the credibility of the obstacle avoidance information itself; illustratively, the upload behavior parameter includes the vehicle's historical upload times and historical acceptance times, the acceptance times refer to the total number of times the obstacle avoidance information uploaded by the vehicle is accepted by other vehicles for obstacle information correction, and the weights of the two are determined by expert scoring method or hierarchical analysis method; illustratively, the accepted data includes upload time, weather parameters at the time of upload, acceptance time, and acceptance times, and the weights of each parameter are determined by expert scoring method or hierarchical analysis method. The weather parameters at the time of upload mainly include parameters that affect the sensor, such as rain, snow, and fog. The closer to the weather when the obstacle avoidance information is obtained, the higher the weight. Generally speaking, the upload time and acceptance time are the time when the obstacle avoidance information is uploaded and the time when it was last accepted, respectively. The closer to the time when the vehicle obtains the obstacle avoidance information, the higher the weight.
[0028] Although the embodiments of the present invention have been disclosed as above, they are not limited to the applications listed in the specification and the implementation modes, and they can be fully applied to various fields suitable for the present invention. For those familiar with the art, additional modifications can be easily implemented. Therefore, without departing from the general concept defined by the claims and the scope of equivalents, the present invention is not limited to the specific details and the illustrations shown and described herein.
Claims
1. An intelligent driving method, characterized in that: include: S1: Obtain vehicle driving path; S2: determining a fixed monitoring device located on the driving path of the vehicle, and obtaining obstacle avoidance information from the fixed monitoring device, wherein the obstacle avoidance information is uploaded by other vehicles; S3: Utilizing the obstacle avoidance information and the obstacle information identified by the vehicle itself, the obstacle avoidance is performed.
2. The intelligent driving method according to claim 1, characterized in that: The obstacle avoidance information includes a detour starting point, a detour end point, and a detour trajectory; The obstacle information includes position, shape and size; The obstacle information is corrected according to the obstacle avoidance information, and obstacle avoidance is performed on the obstacle using the corrected obstacle information.
3. The intelligent driving method according to claim 2, characterized in that: estimating obstacle prediction information based on the obstacle avoidance information; The obstacle prediction information and the obstacle information have an error compared, and if the error is greater than a first predetermined value, the obstacle prediction information is used to correct the obstacle information.
4. The intelligent driving method according to claim 1, characterized in that: In the S3, it also includes: Calculate the confidence of the obstacle avoidance information, and select the obstacle avoidance information whose confidence is greater than a second predetermined value.
5. The intelligent driving method according to claim 4, characterized in that: The confidence level is the sum of the first confidence level and the second confidence level; The first confidence level is a weighted average of the uploaded behavior parameters of the vehicle corresponding to the obstacle avoidance information; The second confidence level is a weighted average of the trusted data corresponding to the obstacle avoidance information.
6. An intelligent driving device, characterized in that: include: A first acquisition module is used to acquire a vehicle driving path; A second acquisition module is used to determine a fixed monitoring device located on the driving path of the vehicle and obtain obstacle avoidance information from the fixed monitoring device, wherein the obstacle avoidance information is uploaded by other vehicles; The obstacle avoidance module is used to avoid obstacles by using the obstacle avoidance information and obstacle information identified by the vehicle itself.
7. The intelligent driving device according to claim 6, characterized in that: The obstacle avoidance information includes a detour starting point, a detour end point, and a detour trajectory; The obstacle information includes position, shape and size; The obstacle avoidance module corrects the obstacle information according to the obstacle avoidance information, and uses the corrected obstacle information to perform obstacle avoidance on the obstacle.
8. The intelligent driving device according to claim 7, characterized in that: The obstacle avoidance module estimates obstacle prediction information according to the obstacle avoidance information, and compares an error between the obstacle prediction information and the obstacle information, and if the error is greater than a first predetermined value, uses the obstacle prediction information to correct the obstacle information.
9. The intelligent driving device according to claim 6, characterized in that: The obstacle avoidance module calculates the confidence of the obstacle avoidance information and selects the obstacle avoidance information whose confidence is greater than a second predetermined value.
10. The intelligent driving device according to claim 9, characterized in that: The confidence level is the sum of the first confidence level and the second confidence level; the first confidence level is the weighted average of the uploaded behavior parameters of the vehicle corresponding to the obstacle avoidance information; the second confidence level is the weighted average of the trusted data corresponding to the obstacle avoidance information.