Vehicle auxiliary driving system based on millimeter wave radar

Abstract

The invention relates to the technical field of auxiliary driving, and particularly discloses a vehicle auxiliary driving system based on a millimeter wave radar, and the system comprises an acquisition module which determines a target vehicle, obtains the distance between a user vehicle and the target vehicle, and calculates the target distance; the analysis module is used for generating coordinate points based on the target distance, fitting the coordinate points to obtain a fitting curve, and determining a monitored vehicle based on the fitting curve; target curves are determined, the target curves are grouped, and abnormal groups are determined according to the average distance of the monitored vehicles in the groups; and the judgment module is used for calculating the judgment distance of the monitored vehicle in the abnormal group, and sending prompt information to the user vehicle when the judgment distance is smaller than the safe distance. According to the invention, the problem of frequent alarm in peak hours can be effectively reduced.

Description

Technical Field

[0001] The present invention relates to the field of assisted driving technology, and in particular to a vehicle assisted driving system based on millimeter wave radar. Background Art

[0002] Millimeter-wave radar is a radar that works in the millimeter-wave band. In the field of vehicle driving, millimeter-wave radar is widely used in advanced driver assistance systems (ADAS). Millimeter-wave radar monitors the environment in front of the vehicle in real time, provides accurate road information, and helps drivers make safer driving decisions.

[0003] Millimeter-wave radar measures the distance between vehicles by emitting high-frequency electromagnetic waves and receiving signals reflected from target objects. When the distance between vehicles is detected to be less than the preset safety threshold, the system will trigger an alarm to remind the driver to take corresponding measures, including but not limited to slowing down, speeding up and moving away, etc. However, during peak traffic hours, the distance between vehicles in congested sections is always relatively close, which may frequently trigger alarms and cause greater interference to drivers. Summary of the invention

[0004] The purpose of the present invention is to provide a vehicle assisted driving system based on millimeter wave radar to solve the following technical problems:

[0005] During peak traffic hours, the distance between vehicles in congested sections is always relatively close, which may trigger alarms frequently and cause great interference to drivers.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] A vehicle assisted driving system based on millimeter wave radar, comprising:

[0008] Acquisition module: determine the lane A where the user vehicle is located, mark the vehicle adjacent to the user vehicle on the lane A as the target vehicle, obtain the distance d between the user vehicle and the target vehicle based on the millimeter wave radar, and calculate the target distance D = d*Syh / Smb, where Syh and Smb represent the volume of the user vehicle and the target vehicle respectively;

[0009] Analysis module: periodically obtain the target distance within a preset monitoring period T, generate coordinate points (a, Da), Da represents the target distance obtained for the ath time, fit the coordinate points to obtain a fitting curve f(t), t represents time and t∈[0, T], and determine the monitoring vehicle among the target vehicles based on the fitting curve;

[0010] The fitting curve corresponding to the monitoring vehicle is used as the target curve, and the target curve is grouped. The similarity between any two target curves in the group is greater than a preset similarity threshold, and the distance between any two monitoring vehicles in the same group is obtained, and the average distance F is calculated. When the average distance F is greater than or equal to the preset average distance threshold, the corresponding group is regarded as an abnormal group;

[0011] Judgment module: Calculates the judgment distance of a single monitoring vehicle in the abnormal grouping g(t) represents the fitting curve corresponding to the monitored vehicle in the abnormal group. When the judgment distance L≤Lys, a prompt message is sent to the corresponding user vehicle, indicating that there is an abnormality in the distance between the monitored vehicle and the user vehicle. Lys represents the preset safety distance.

[0012] As a further solution of the present invention: in the step analysis module, determining the process of monitoring the vehicle specifically includes:

[0013] The target vehicles are marked as the first target vehicle and the second target vehicle respectively, and the road traffic direction of lane A is from the first target vehicle to the second target vehicle. Calculate the judgment value Where fahe(t) and frea(t) represent the fitting curves corresponding to the first target vehicle and the second target vehicle respectively;

[0014] When the judgment value is greater than a preset judgment value threshold Pys, the second target vehicle is used as a monitoring vehicle;

[0015] When the judgment value is less than the judgment value threshold Pys, the first target vehicle is used as a monitoring vehicle;

[0016] When the judgment value P∈[-Pys, Pys], the first target vehicle and the second target vehicle are both used as monitoring vehicles.

[0017] As a further solution of the present invention: the analysis module further comprises the following steps:

[0018] Determine the tangent slope K of the coordinate point on the fitting curve. When the ratio C of the number of tangent slopes less than 0 to the total number of coordinate points is greater than or equal to 0.7, do not execute subsequent steps, and send a prompt message to the corresponding user vehicle, indicating that there is an abnormality in the distance between the target vehicle and the user vehicle.

[0019] As a further solution of the present invention: in the analysis module, during the process of periodically acquiring the target distance, when ΔDa=Da-Da-1 / (T / n)≤-0.6, the subsequent steps are not executed, and a prompt message is sent to the corresponding user vehicle, indicating that there is an abnormality in the distance between the target vehicle and the user vehicle, and n represents the total number of times the target distance is acquired during the monitoring period.

[0020] As a further solution of the present invention: in the analysis module, the similarity of the target curve is determined based on a dynamic time warping algorithm.

[0021] As a further solution of the present invention: in the analysis module, when the fitting curve decreases monotonically, the corresponding target vehicle is not used as a monitoring vehicle.

[0022] Beneficial effects of the present invention: In this solution, the target distance is calculated based on the distance measured by the millimeter-wave radar. The calculation of the target distance takes into account the volume of the user vehicle and the target vehicle. The volume of the target vehicle is larger than that of the user vehicle, and the target distance should be closer, so as to facilitate the subsequent issuance of prompts to stay away from large vehicles; after that, the target distance data is periodically collected, and these data are fitted into a curve to identify the dynamic behavior of the target vehicle. The curve obtained by fitting can further analyze the relative motion trajectory of the target vehicle and the user vehicle, thereby avoiding simple single distance judgment, reducing the situation where the instantaneous distance is small and misjudged as dangerous, and determining the monitoring vehicle according to the fitting curve. In this step , if the behavior of the second target vehicle is quite different from that of the first target vehicle, the system can intelligently select which vehicle is more likely to affect the user vehicle. In addition, it allows two vehicles to be monitored simultaneously when the behavior is similar, further improving the system's adaptability to complex traffic scenarios; then, by grouping the fitting curves of the target vehicles, the scheme can identify a group of vehicles with similar behavior patterns, and calculate the average distance between them, and filter abnormal groups based on the average distance, thereby excluding short distances caused by traffic congestion rather than real dangers; in the abnormal group, by calculating the judgment distance of a single monitored vehicle, it is determined whether there is an abnormality, and when there is an abnormality, a prompt message is sent to the user vehicle. The present invention can effectively reduce the problem of frequent alarms during peak hours. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The present invention will be further described below in conjunction with the accompanying drawings.

[0024] Figure 1 It is a flow chart of a vehicle assisted driving system based on millimeter wave radar of the present invention. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] See also Figure 1 As shown, the present invention is a vehicle assisted driving system based on millimeter wave radar, comprising:

[0027] Acquisition module: determine the lane A where the user vehicle is located, mark the vehicle adjacent to the user vehicle on the lane A as the target vehicle, obtain the distance d between the user vehicle and the target vehicle based on the millimeter wave radar, and calculate the target distance D = d*Syh / Smb, where Syh and Smb represent the volume of the user vehicle and the target vehicle respectively;

[0028] Analysis module: periodically obtain the target distance within a preset monitoring period T, generate coordinate points (a, Da), Da represents the target distance obtained for the ath time, fit the coordinate points to obtain a fitting curve f(t), t represents time and t∈[0, T], and determine the monitoring vehicle among the target vehicles based on the fitting curve;

[0029] The fitting curve corresponding to the monitoring vehicle is used as the target curve, and the target curve is grouped. The similarity between any two target curves in the group is greater than a preset similarity threshold, and the distance between any two monitoring vehicles in the same group is obtained, and the average distance F is calculated. When the average distance F is greater than or equal to the preset average distance threshold, the corresponding group is regarded as an abnormal group;

[0030] Judgment module: Calculates the judgment distance of a single monitoring vehicle in the abnormal grouping g(t) represents the fitting curve corresponding to the monitored vehicle in the abnormal group. When the judgment distance L≤Lys, a prompt message is sent to the corresponding user vehicle, indicating that there is an abnormality in the distance between the monitored vehicle and the user vehicle. Lys represents the preset safety distance.

[0031] It should be noted that the target distance is calculated based on the distance measured by the millimeter-wave radar. The calculation of the target distance takes into account the volume of the user vehicle and the target vehicle. The volume of the target vehicle is larger than that of the user vehicle, and the target distance should be closer, so as to facilitate the subsequent prompts to stay away from large vehicles. After that, the target distance data is collected periodically and fitted into a curve to identify the dynamic behavior of the target vehicle. The fitted curve can further analyze the relative motion trajectory of the target vehicle and the user vehicle, thereby avoiding simple single distance judgment, reducing the situation where the instantaneous distance is small and misjudged as dangerous, and determining the monitoring vehicle based on the fitting curve. In this step, if the first The behavior of the second target vehicle is quite different from that of the first target vehicle. The system can intelligently select which vehicle is more likely to affect the user vehicle. In addition, it allows two vehicles to be monitored simultaneously when the behaviors are similar, further improving the system's adaptability to complex traffic scenarios. Then, by grouping the fitting curves of the target vehicles, the scheme can identify a group of vehicles with similar behavior patterns, calculate the average distance between them, and filter out abnormal groups based on the average distance, thereby eliminating short distances caused by traffic congestion rather than real dangers. In the abnormal group, by calculating the judgment distance of a single monitored vehicle, it is determined whether there is an abnormality, and when there is an abnormality, a prompt message is sent to the user vehicle.

[0032] In another preferred embodiment of the present invention, in the step analysis module, determining the process of monitoring the vehicle specifically includes:

[0033] The target vehicles are marked as the first target vehicle and the second target vehicle respectively, and the road traffic direction of lane A is from the first target vehicle to the second target vehicle. Calculate the judgment value Where fahe(t) and frea(t) represent the fitting curves corresponding to the first target vehicle and the second target vehicle respectively;

[0034] When the judgment value is greater than a preset judgment value threshold Pys, the second target vehicle is used as a monitoring vehicle;

[0035] When the judgment value is less than the judgment value threshold Pys, the first target vehicle is used as a monitoring vehicle;

[0036] When the judgment value P∈[-Pys, Pys], the first target vehicle and the second target vehicle are both used as monitoring vehicles.

[0037] It is worth noting that in this step, if the behavior of the second target vehicle is significantly different from that of the first target vehicle, the system can intelligently select which vehicle is more likely to affect the user vehicle. In addition, it allows two vehicles to be monitored simultaneously when the behavior is similar, further improving the system's adaptability to complex traffic scenarios.

[0038] In another preferred embodiment of the present invention, the analysis module further comprises the following steps:

[0039] Determine the tangent slope K of the coordinate point on the fitting curve. When the ratio C of the number of tangent slopes less than 0 to the total number of coordinate points is greater than or equal to 0.7, do not execute subsequent steps, and send a prompt message to the corresponding user vehicle, indicating that there is an abnormality in the distance between the target vehicle and the user vehicle.

[0040] It can be understood that by checking the time proportion of the target vehicle and the user's vehicle being relatively close, when the target vehicle is approaching the user's vehicle for most of the time, the system can quickly identify potential dangers without having to wait for subsequent complex calculations and analysis steps; by analyzing the tangent slope of the target vehicle's fitting curve, it can be determined whether the target vehicle continues to approach the user's vehicle. If the approach trend of the target vehicle is obvious and continuous, the system will directly issue a warning to avoid misjudgment and improve the system's response speed. This method effectively improves the real-time and accuracy of the system, especially for situations with large or complex traffic flows.

[0041] In another preferred embodiment of the present invention, in the analysis module, during the process of periodically acquiring the target distance, when ΔDa=Da-Da-1 / (T / n)≤-0.6, the subsequent steps are not executed, and a prompt message is sent to the corresponding user vehicle, indicating that there is an abnormality in the distance between the target vehicle and the user vehicle, and n represents the total number of times the target distance is acquired during the monitoring period.

[0042] It should be noted that when the target vehicle approaches rapidly, the system can promptly issue a warning to the user's vehicle to avoid safety hazards caused by delayed judgment or low-speed approach.

[0043] In another preferred embodiment of the present invention, in the analysis module, the similarity of the target curve is determined based on a dynamic time warping algorithm.

[0044] It should be noted that the Dynamic Time Warping (DTW) algorithm is an algorithm for calculating the similarity of two time series. It is often used to compare sequences with different time scales or nonlinear speed changes. Compared with the traditional Euclidean distance, DTW can tolerate changes in time series. It is especially effective in vehicle trajectory analysis because the movement speeds and starting times of different vehicles may be different. Since the dynamic time warping algorithm is relatively mature, it will not be described in detail here.

[0045] In another preferred embodiment of the present invention, in the analysis module, when the fitting curve decreases monotonically, the corresponding target vehicle is not used as a monitoring vehicle.

[0046] It can be understood that the monotonically decreasing fitting curve means that the distance between the target vehicle and the user vehicle increases over time, and this growth trend remains consistent. That is, the target vehicle continues to move away from the user vehicle during the monitoring period. At this time, the potential threat of the target vehicle to the user vehicle is relatively small, so it is not necessary to include the corresponding target vehicle in the monitoring range.

[0047] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A vehicle assisted driving system based on millimeter wave radar, characterized in that: include: Acquisition module: determine the lane A where the user vehicle is located, mark the vehicle adjacent to the user vehicle on the lane A as the target vehicle, obtain the distance d between the user vehicle and the target vehicle based on the millimeter wave radar, and calculate the target distance D = d*Syh / Smb, where Syh and Smb represent the volume of the user vehicle and the target vehicle respectively; Analysis module: periodically obtain the target distance within a preset monitoring period T, generate coordinate points (a, Da), Da represents the target distance obtained for the ath time, fit the coordinate points to obtain a fitting curve f(t), t represents time and t∈[0, T], and determine the monitoring vehicle among the target vehicles based on the fitting curve; The fitting curve corresponding to the monitoring vehicle is used as the target curve, and the target curve is grouped. The similarity between any two target curves in the group is greater than a preset similarity threshold, and the distance between any two monitoring vehicles in the same group is obtained, and the average distance F is calculated. When the average distance F is greater than or equal to the preset average distance threshold, the corresponding group is regarded as an abnormal group; Judgment module: Calculates the judgment distance of a single monitoring vehicle in the abnormal grouping g(t) represents the fitting curve corresponding to the monitored vehicle in the abnormal group. When the judgment distance L≤Lys, a prompt message is sent to the corresponding user vehicle, indicating that there is an abnormality in the distance between the monitored vehicle and the user vehicle. Lys represents the preset safety distance.

2. The vehicle assisted driving system based on millimeter wave radar according to claim 1, characterized in that: In the step analysis module, the process of determining the monitored vehicle specifically includes: The target vehicles are marked as the first target vehicle and the second target vehicle respectively, and the road traffic direction of lane A is from the first target vehicle to the second target vehicle. Calculate the judgment value Where fahe(t) and frea(t) represent the fitting curves corresponding to the first target vehicle and the second target vehicle respectively; When the judgment value is greater than a preset judgment value threshold Pys, the second target vehicle is used as a monitoring vehicle; When the judgment value is less than the judgment value threshold Pys, the first target vehicle is used as a monitoring vehicle; When the judgment value P∈[-Pys, Pys], the first target vehicle and the second target vehicle are both used as monitoring vehicles.

3. The vehicle assisted driving system based on millimeter wave radar according to claim 1, characterized in that: The analysis module further comprises the following steps: Determine the tangent slope K of the coordinate point on the fitting curve. When the ratio C of the number of tangent slopes less than 0 to the total number of coordinate points is greater than or equal to 0.7, do not execute subsequent steps, and send a prompt message to the corresponding user vehicle, indicating that there is an abnormality in the distance between the target vehicle and the user vehicle.

4. The vehicle assisted driving system based on millimeter wave radar according to claim 1, characterized in that: In the analysis module, during the process of periodically acquiring the target distance, when ΔDa=Da-Da-1 / (T / n)≤-0.6, the subsequent steps are not executed, and a prompt message is sent to the corresponding user vehicle, indicating that there is an abnormality in the distance between the target vehicle and the user vehicle, and n represents the total number of times the target distance is acquired during the monitoring period.

5. The vehicle assisted driving system based on millimeter wave radar according to claim 1, characterized in that: In the analysis module, the similarity of the target curve is determined based on a dynamic time warping algorithm.

6. The vehicle assisted driving system based on millimeter wave radar according to claim 1, characterized in that: In the analysis module, when the fitting curve decreases monotonically, the corresponding target vehicle is not used as a monitoring vehicle.

Images