Vehicle-mounted millimeter wave radar multi-mode adaptive switching method, system and platform based on dynamic vehicle speed threshold and tunnel identification

Abstract

The invention discloses a vehicle-mounted millimeter wave radar multi-mode adaptive switching method, system and platform based on a dynamic vehicle speed threshold and tunnel identification. The method comprises the following steps: respectively generating and acquiring first data and second data corresponding to a vehicle loaded with a millimeter wave radar through the method; respectively creating third data, fourth data and fifth data corresponding to the vehicle loaded with the millimeter wave radar; based on the first data and the second data, in combination with the third data or the fourth data and the fifth data, adaptively switching and processing the speed mode of the vehicle loaded with the millimeter wave radar; wherein the speed modes comprise a low-speed mode and a high-speed mode, and the applicability and robustness of radar mode switching are effectively improved through the system and the platform corresponding to the method; meanwhile, a tunnel mode is added, and the applicability is wider than that of a simple high-speed / low-speed mode.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent driving processing technology, and specifically relates to a multi-mode adaptive switching method, system and platform for vehicle-mounted millimeter-wave radar based on dynamic vehicle speed thresholds and tunnel recognition. Background Art

[0002] In autonomous driving systems, on-board millimeter-wave radar is a key sensor responsible for detection, perception, and target location. Compared to other sensors like cameras and lidar, it offers advantages such as low cost, long range, all-weather operation, and the ability to directly measure Doppler velocity.

[0003] In recent years, with the gradual implementation of a series of supporting policies and the orderly progress of pilot projects across various regions, unmanned / intelligent / autonomous driving has become one of the most cutting-edge technologies in the automotive industry and a major application scenario for artificial intelligence. Currently, 4D millimeter-wave radar, in addition to traditional radar's range, speed, and azimuth (3D) measurements, can also measure pitch, adding a 1D measurement dimension. Millimeter-wave radar can accurately sense and identify various traffic participants, including vehicles, pedestrians, bicycles, and motorcycles, thereby improving traffic safety and efficiency, reducing traffic accidents and congestion, lowering energy consumption and emissions, and enhancing travel comfort and convenience. Millimeter-wave radar can also be combined with technologies such as the Internet of Vehicles, cloud computing, and big data to enable real-time collection, analysis, and sharing of traffic information, providing strong support for the planning, management, and services of intelligent transportation and smart cities. Furthermore, millimeter-wave radar can be applied in other fields, such as security, healthcare, industry, and agriculture, demonstrating broad market prospects and social value.

[0004] Like many things, radar system parameters cannot be optimized simultaneously given limited resources: designing one system metric high often means designing another low. To maximize radar performance, different operating modes can be assigned to the radar. For example, the most common near- and far-range modes are: Near-range mode is used in congested urban environments and emphasizes higher point cloud density. Waveforms with higher range resolution and accuracy can be designed for this mode, at the expense of maximum range and speed measurement. Long-range mode is used in open areas such as highways and emphasizes longer range. Waveforms with longer detection range and speed measurement range can be designed for this mode, at the expense of range resolution and accuracy.

[0005] In addition, vehicles often drive into tunnels, where multipath and clutter increase significantly. This requires corresponding algorithmic strategy modifications, such as increasing the CFAR threshold and adding multipath filtering.

[0006] Traditional automotive radar mode switching schemes include: antenna-based switching: The radar is designed with two antennas: a high-gain narrow-beam antenna and a low-gain wide-beam antenna. The transmit and receive channels corresponding to these two antennas correspond to long-range and short-range modes, respectively. Switching is performed frame by frame based on the radar's transmission sequence: the radar transmits a long-range waveform in the first frame, a short-range waveform in the second frame, a long-range waveform in the third frame, and so on, repeating the cycle. The same mode data is captured every other frame. Speed-based switching: The radar switches modes based on vehicle speed, operating in long-range mode when the vehicle speed is greater than or equal to X km / h (usually on highways) and in short-range mode when the speed is less than X km / h (usually on congested urban roads).

[0007] In other words, traditional mode switching schemes have their drawbacks: Switching based on different antennas: Designing two antenna modes on the same radar requires separate transmit and receive channel resources, which reduces radar angular resolution. High-gain antennas are too large and their narrow beams run counter to the current trend of miniaturization and wide beams in automotive millimeter-wave radars. Switching based on the radar's transmission sequence: The radar transmits different modes frame by frame, which affects continuous target tracking. For example, a typical automotive radar frame cycle is 50ms, refreshing the target tracking point every 50ms. If the long-range and short-range waveforms are transmitted frame by frame, for long-range targets, the target refresh rate is equivalent to 100ms, effectively increasing the frame cycle to 100ms. This contradicts the "real-time and fast response" emphasis of automotive millimeter-wave radars. Switching based on vehicle speed: The radar switches modes based on vehicle speed. Typically, low speeds in urban areas require short-range mode, while high speeds on highways require long-range mode. Traditionally, the switching threshold is set based on a fixed vehicle speed. This can cause the radar to frequently switch modes when the vehicle speed fluctuates near the threshold. Radar mode switching is not instantaneous, and excessive switching can cause numerous problems.

[0008] Therefore, in response to the above technical problems and defects such as frequent switching when the vehicle speed fluctuates near the threshold, doubling of the frame period, and dual-antenna design increasing hardware costs and reducing angular resolution, it is urgent to design and develop a multi-mode adaptive switching method, system and platform for vehicle-mounted millimeter-wave radar based on dynamic vehicle speed threshold and tunnel recognition. Summary of the Invention

[0009] To overcome the shortcomings and difficulties of the above-mentioned existing technologies, the purpose of the present invention is to propose a multi-mode adaptive switching method, system and platform for on-board millimeter-wave radar based on dynamic vehicle speed thresholds and tunnel recognition. This method effectively overcomes the problems caused by the fixed threshold of traditional vehicle speed switching modes and adds a tunnel mode, thus having wider applicability.

[0010] The first object of the present invention is to provide a multi-mode adaptive switching method of a vehicle-mounted millimeter-wave radar based on dynamic vehicle speed thresholds and tunnel recognition; the second object of the present invention is to provide a multi-mode adaptive switching system of a vehicle-mounted millimeter-wave radar based on dynamic vehicle speed thresholds and tunnel recognition; the third object of the present invention is to provide a multi-mode adaptive switching platform of a vehicle-mounted millimeter-wave radar based on dynamic vehicle speed thresholds and tunnel recognition.

[0011] The first object of the present invention is achieved in that the method comprises the steps of:

[0012] Generate and obtain first data and second data corresponding to the vehicle equipped with millimeter-wave radar, respectively; wherein the first data is the real-time vehicle speed state data; the second data is the real-time vehicle environment characteristic parameter data;

[0013] Creating third data, fourth data, and fifth data corresponding to the vehicle equipped with the millimeter-wave radar, respectively; wherein the third data and the fourth data are both dynamic vehicle speed threshold data, and the value of the third data is greater than the value of the fourth data; and the fifth data is vehicle speed maintenance time data;

[0014] Based on the first data and the second data, and in combination with the third data or the fourth data, and the fifth data, the speed mode of the vehicle carrying the millimeter-wave radar is adaptively switched; wherein the speed mode includes a low-speed mode and a high-speed mode.

[0015] Furthermore, the adaptive switching processing of the speed mode of the vehicle equipped with the millimeter-wave radar based on the first data and the second data, in combination with the third data or the fourth data, and the fifth data, further includes:

[0016] Generate and obtain sixth data and seventh data corresponding to the vehicle equipped with the millimeter wave radar; wherein the sixth data is the real-time speed mode of the vehicle; and the seventh data is the speed mode switching control data;

[0017] When the on-board radar is in a low-speed mode and the vehicle speed is continuously greater than or equal to the third data for a time greater than or equal to the fifth data, and based on the seventh data, switching the vehicle speed to a high-speed mode;

[0018] When the on-board radar is in low-speed mode and the vehicle speed is continuously less than or equal to the fourth data for a time greater than or equal to the fifth data, and based on the seventh data, the vehicle speed is switched to low-speed mode.

[0019] Furthermore, the adaptive switching processing of the speed mode of the vehicle equipped with the millimeter-wave radar based on the first data and the second data, in combination with the third data or the fourth data, and the fifth data, further includes:

[0020] Creating and generating eighth data corresponding to the vehicle equipped with the millimeter-wave radar; wherein the eighth data is tunnel mode score threshold data;

[0021] Calculating and generating ninth data corresponding to a vehicle equipped with a millimeter-wave radar and in a tunnel mode; wherein the ninth data is tunnel mode score data;

[0022] Based on the second data and the ninth data, and in combination with the eighth data, the speed mode of the vehicle equipped with the millimeter-wave radar is adaptively switched.

[0023] Furthermore, the adaptive switching processing of the speed mode of the vehicle equipped with the millimeter-wave radar based on the first data and the second data, in combination with the third data or the fourth data, and the fifth data, further includes:

[0024] Generating tenth data corresponding to the tunnel; wherein the tenth data is a multi-dimensional tunnel characteristic parameter number; including AB wave invalid target data, CANDI target data, tunnel target data within the guardrail, stationary target data in the own lane, vehicle speed, and turning radius data;

[0025] weight processing the tenth data and generating corresponding eleventh data in combination with a linear filter; wherein the eleventh data is tunnel comprehensive score data;

[0026] Based on the eleventh data, the scene state corresponding to the tunnel is determined in real time.

[0027] Furthermore, the weight processing of the tenth data and generating corresponding eleventh data in combination with a linear filter further includes:

[0028] Generate and obtain twelfth data corresponding to the tunnel mode; wherein the twelfth data is tunnel mode score determination condition data, including that the number of tunnel targets at the original point is less than 5 and the current mode is tunnel; the vehicle body yaw angular velocity is greater than 3° / s; and the vehicle speed is less than 5 m / s;

[0029] Based on the twelfth data, the score data of the tunnel mode is halved.

[0030] The second object of the present invention is achieved as follows: the system is used to implement the multi-mode adaptive switching method of the vehicle-mounted millimeter-wave radar based on dynamic vehicle speed threshold and tunnel identification, and the system includes:

[0031] A first data generating unit is configured to generate and obtain first data and second data corresponding to a vehicle equipped with a millimeter-wave radar, wherein the first data is real-time vehicle speed status data; and the second data is real-time vehicle environment characteristic parameter data;

[0032] a second data generating unit, configured to respectively create third data, fourth data, and fifth data corresponding to the vehicle equipped with the millimeter-wave radar; wherein the third data and the fourth data are both dynamic vehicle speed threshold data, and the value of the third data is greater than the value of the fourth data; and the fifth data is vehicle speed maintenance time data;

[0033] A mode switching processing unit is used to adaptively switch and process the speed mode of a vehicle equipped with a millimeter-wave radar based on the first data and the second data, in combination with the third data or the fourth data, and the fifth data; wherein the speed mode includes a low-speed mode and a high-speed mode.

[0034] Furthermore, the mode switching processing unit further includes:

[0035] A first generating module is configured to generate and obtain sixth data and seventh data corresponding to a vehicle equipped with a millimeter-wave radar; wherein the sixth data is a real-time speed mode of the vehicle; and the seventh data is speed mode switching control data;

[0036] a first determining module, configured to switch the vehicle speed to a high speed mode based on the seventh data when the vehicle-mounted radar is in a low speed mode and the vehicle speed is continuously greater than or equal to the third data for a time greater than or equal to the fifth data;

[0037] a second determination module, configured to switch the vehicle speed to the low speed mode based on the seventh data when the vehicle-mounted radar is in the low speed mode and the vehicle speed is continuously less than or equal to the fourth data for a time greater than or equal to the fifth data;

[0038] A second generating module is configured to create and generate eighth data corresponding to the vehicle equipped with the millimeter-wave radar; wherein the eighth data is tunnel mode score threshold data;

[0039] A third generating module is configured to calculate and generate ninth data corresponding to a vehicle equipped with a millimeter-wave radar and in a tunnel mode; wherein the ninth data is tunnel mode score data;

[0040] a first processing module, configured to adaptively switch and process a speed mode of a vehicle equipped with a millimeter-wave radar based on the second data and the ninth data in combination with the eighth data;

[0041] A fourth generation module is configured to generate tenth data corresponding to the tunnel; wherein the tenth data is a multi-dimensional tunnel characteristic parameter number, including AB wave invalid target data, CANDI target data, tunnel target data within the guardrail, stationary target data in the own lane, vehicle speed, and turning radius data;

[0042] A second processing module is configured to perform weighted processing on the tenth data and generate corresponding eleventh data in combination with a linear filter; wherein the eleventh data is tunnel comprehensive score data;

[0043] The third determination module is configured to determine the scene state corresponding to the tunnel in real time based on the eleventh data.

[0044] Furthermore, the second processing module further includes:

[0045] a fifth generating module, configured to generate and obtain twelfth data corresponding to the tunnel mode; wherein the twelfth data is tunnel mode score determination condition data, including: the number of tunnel targets at the original point is less than 5 and the current mode is tunnel; the vehicle body yaw angular velocity is greater than 3° / s; and the vehicle speed is less than 5 m / s;

[0046] The third processing module is configured to halve the score data of the tunnel mode based on the twelfth data.

[0047] The third object of the present invention is achieved as follows: it includes a processor, a memory, and a vehicle-mounted millimeter-wave radar multi-mode adaptive switching platform control program based on dynamic vehicle speed threshold and tunnel recognition; wherein the vehicle-mounted millimeter-wave radar multi-mode adaptive switching platform control program based on dynamic vehicle speed threshold and tunnel recognition is executed by the processor, the vehicle-mounted millimeter-wave radar multi-mode adaptive switching platform control program based on dynamic vehicle speed threshold and tunnel recognition is stored in the memory, and the vehicle-mounted millimeter-wave radar multi-mode adaptive switching platform control program based on dynamic vehicle speed threshold and tunnel recognition implements the vehicle-mounted millimeter-wave radar multi-mode adaptive switching method based on dynamic vehicle speed threshold and tunnel recognition.

[0048] The present invention generates and acquires first and second data corresponding to a vehicle equipped with a millimeter-wave radar. The first data is the vehicle's real-time speed status data, and the second data is the vehicle's real-time environmental characteristic parameter data. Third, fourth, and fifth data are generated corresponding to the vehicle equipped with the millimeter-wave radar. The third and fourth data are dynamic speed threshold data, and the third data value is greater than the fourth data value. The fifth data value is the vehicle speed maintenance time data. Based on the first and second data, and in combination with the third or fourth data, and the fifth data, the speed mode of the vehicle equipped with the millimeter-wave radar is adaptively switched. The speed modes include low-speed mode and high-speed mode. The system and platform corresponding to the method effectively overcome the problem of conventional fixed speed switching mode thresholds, where the radar frequently switches transmission modes if the vehicle speed fluctuates near the threshold, causing unstable radar operation. The method effectively improves the applicability and robustness of radar mode switching. Furthermore, the addition of a tunnel mode extends its applicability beyond the simple high / low speed mode. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0050] Figure 1 This is a schematic diagram of the process steps of a multi-mode adaptive switching method of a vehicle-mounted millimeter-wave radar based on dynamic vehicle speed threshold and tunnel recognition according to the present invention;

[0051] Figure 2 This is a schematic diagram of the traditional radar mode switching process based on vehicle speed;

[0052] Figure 3 This is a schematic diagram of the radar mode switching process structure of an embodiment of a multi-mode adaptive switching method for a vehicle-mounted millimeter-wave radar based on a dynamic vehicle speed threshold and tunnel recognition according to the present invention;

[0053] Figure 4 This is a schematic diagram of the detailed flow structure of tunnel mode determination in an embodiment of a multi-mode adaptive switching method for a vehicle-mounted millimeter-wave radar based on a dynamic vehicle speed threshold and tunnel identification according to the present invention;

[0054] Figure 5 This is a schematic diagram of the architecture of a multi-mode adaptive switching system for a vehicle-mounted millimeter-wave radar based on dynamic vehicle speed threshold and tunnel recognition according to the present invention;

[0055] Figure 6This is a schematic diagram of the architecture of a multi-mode adaptive switching platform for vehicle-mounted millimeter-wave radar based on dynamic vehicle speed threshold and tunnel recognition in the present invention. DETAILED DESCRIPTION

[0056] In order to better understand the purpose, technical solutions and advantages of the present invention, the present invention is further described below with reference to the accompanying drawings and specific embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification.

[0057] The present invention may also be implemented or applied through other different specific examples, and the details in this specification may also be modified and changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention.

[0058] It should be noted that if the embodiments of the present invention involve directional indications (such as up, down, left, right, front, back, etc.), the directional indications are only used to explain the relative position relationship, movement status, etc. between the various components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indications will also change accordingly.

[0059] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of such features. Secondly, the technical solutions between the various embodiments can be combined with each other, but this must be based on the fact that ordinary technicians in this field can implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0060] Preferably, the multi-mode adaptive switching method for a vehicle-mounted millimeter-wave radar based on dynamic vehicle speed thresholds and tunnel identification is applied to one or more terminals or servers. The terminal is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to a microprocessor, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a digital signal processor (DSP), an embedded device, etc.

[0061] The terminal can be a computing device such as a desktop computer, notebook, PDA, cloud server, etc. The terminal can interact with the client through a keyboard, mouse, remote control, touchpad, or voice control device.

[0062] The present invention provides a method, system and platform for realizing multi-mode adaptive switching of vehicle-mounted millimeter-wave radar based on dynamic vehicle speed threshold and tunnel recognition.

[0063] like Figure 1 、 Figure 3-Figure 4 , which is a flow chart of a multi-mode adaptive switching method of a vehicle-mounted millimeter-wave radar based on dynamic vehicle speed threshold and tunnel recognition provided by an embodiment of the present invention.

[0064] In this embodiment, the multi-mode adaptive switching method of the vehicle-mounted millimeter-wave radar based on dynamic vehicle speed threshold and tunnel recognition can be applied to a terminal with a display function or a fixed terminal. The terminal is not limited to a personal computer, a smart phone, a tablet computer, a desktop computer or an all-in-one computer equipped with a camera, etc.

[0065] The multi-mode adaptive switching method for an on-board millimeter-wave radar based on dynamic speed thresholds and tunnel identification can also be applied to a hardware environment consisting of a terminal and a server connected to the terminal via a network. The network includes, but is not limited to, a wide area network, a metropolitan area network, or a local area network. The multi-mode adaptive switching method for an on-board millimeter-wave radar based on dynamic speed thresholds and tunnel identification in this embodiment of the present invention can be executed by a server, a terminal, or both.

[0066] For example, for a terminal that needs to perform multi-mode adaptive switching of an on-board millimeter-wave radar based on dynamic vehicle speed thresholds and tunnel identification, the multi-mode adaptive switching function of the on-board millimeter-wave radar based on dynamic vehicle speed thresholds and tunnel identification provided by the method of the present invention can be directly integrated on the terminal, or a client for implementing the method of the present invention can be installed. For another example, the method provided by the present invention can also be run on a server or other device in the form of a software development kit (SDK), and an interface for the multi-mode adaptive switching function of the on-board millimeter-wave radar based on dynamic vehicle speed thresholds and tunnel identification is provided in the form of an SDK. The terminal or other device can implement the multi-mode adaptive switching function of the on-board millimeter-wave radar based on dynamic vehicle speed thresholds and tunnel identification through the provided interface. The present invention is further explained below in conjunction with the accompanying drawings.

[0067] like Figure 1 As shown, the present invention provides a multi-mode adaptive switching method for a vehicle-mounted millimeter-wave radar based on a dynamic vehicle speed threshold and tunnel recognition, the method comprising the following steps:

[0068] S1. Generate and obtain first data and second data corresponding to a vehicle equipped with a millimeter-wave radar, respectively; wherein the first data is the vehicle's real-time speed status data; and the second data is the vehicle's real-time environmental characteristic parameter data;

[0069] S2. Creating third data, fourth data, and fifth data corresponding to the vehicle equipped with the millimeter-wave radar, respectively; wherein the third data and the fourth data are both dynamic vehicle speed threshold data, and the value of the third data is greater than the value of the fourth data; and the fifth data is vehicle speed maintenance time data;

[0070] S3. Based on the first data and the second data, and in combination with the third data or the fourth data, and the fifth data, adaptively switch and process the speed mode of the vehicle equipped with the millimeter-wave radar; wherein the speed mode includes a low-speed mode and a high-speed mode.

[0071] The method of adaptively switching and processing the speed mode of the vehicle equipped with the millimeter-wave radar based on the first data and the second data, in combination with the third data or the fourth data, and the fifth data, further includes:

[0072] S31, generating and acquiring sixth data and seventh data corresponding to the vehicle equipped with the millimeter-wave radar; wherein the sixth data is the real-time speed mode of the vehicle; and the seventh data is the speed mode switching control data;

[0073] S32, when the on-board radar is in the low-speed mode and the vehicle speed is continuously greater than or equal to the third data for a time greater than or equal to the fifth data, and based on the seventh data, switching the vehicle speed to the high-speed mode;

[0074] S33. When the on-board radar is in low-speed mode and the vehicle speed is continuously less than or equal to the fourth data for a time greater than or equal to the fifth data, and based on the seventh data, the vehicle speed is switched to low-speed mode.

[0075] The method of adaptively switching and processing the speed mode of the vehicle equipped with the millimeter-wave radar based on the first data and the second data, in combination with the third data or the fourth data, and the fifth data, further includes:

[0076] S34: Create and generate eighth data corresponding to the vehicle equipped with the millimeter-wave radar; wherein the eighth data is tunnel mode score threshold data;

[0077] S35. Calculate and generate ninth data corresponding to the vehicle carrying the millimeter-wave radar and being in tunnel mode; wherein the ninth data is tunnel mode score data;

[0078] S36. Based on the second data and the ninth data, and in combination with the eighth data, adaptively switch and process the speed mode of the vehicle equipped with the millimeter-wave radar.

[0079] The method of adaptively switching and processing the speed mode of the vehicle equipped with the millimeter-wave radar based on the first data and the second data, in combination with the third data or the fourth data, and the fifth data, further includes:

[0080] S37. Generate tenth data corresponding to the tunnel; wherein the tenth data is a multi-dimensional tunnel characteristic parameter number, including AB wave invalid target data, CANDI target data, tunnel target data within the guardrail, stationary target data in the own lane, vehicle speed, and turning radius data;

[0081] S38. Weight-process the tenth data and generate corresponding eleventh data in combination with a linear filter; wherein the eleventh data is tunnel comprehensive score data;

[0082] S39. Based on the eleventh data, determine the scene state corresponding to the tunnel in real time.

[0083] The weight processing of the tenth data and generating corresponding eleventh data in combination with a linear filter further includes:

[0084] S391: Generate and obtain twelfth data corresponding to the tunnel mode; wherein the twelfth data is tunnel mode score determination condition data, including: the number of tunnel targets at the original point is less than 5 and the current mode is tunnel; the vehicle body yaw angular velocity is greater than 3° / s; and the vehicle speed is less than 5 m / s.

[0085] S392: Based on the twelfth data, halve the score data of the tunnel mode.

[0086] Specifically, in an embodiment of the present invention, a multi-mode adaptive switching method of a vehicle-mounted millimeter-wave radar based on dynamic vehicle speed thresholds and tunnel recognition is provided, comprising the following steps: setting a first vehicle speed threshold X for switching from low-speed mode to high-speed mode, a second vehicle speed threshold Y for switching from high-speed mode to low-speed mode, and a minimum maintenance time Z, where X>Y; the radar is started in low-speed mode by default and monitors vehicle speed information in real time; when the radar is in low-speed mode and the vehicle speed continues for ≥X for ≥Z, it switches to high-speed mode; when the radar is in high-speed mode and the vehicle speed continues for ≤Y for ≥Z, it switches back to low-speed mode; in high-speed or low-speed mode, environmental characteristic parameters are collected in real time and a tunnel mode score is calculated. If the score exceeds the set threshold, it switches to tunnel mode and adjusts the radar algorithm parameters.

[0087] The tunnel mode determination includes: collecting multi-dimensional tunnel characteristic parameters, including: the number of invalid AB wave targets, the number of CANDI targets, the number of tunnel targets within the guardrail, the number of stationary targets in the lane, the vehicle speed, and the turning radius; weighting and scoring each characteristic parameter, and calculating the comprehensive score through a linear filter; if the filtered score is greater than 70, it is determined to be a tunnel scenario, triggering an algorithm parameter update.

[0088] The difference between X and Y is ≥ 20 km / h, and Z is ≥ 10 seconds, so as to avoid frequent mode switching caused by vehicle speed fluctuations near the threshold.

[0089] The high-speed mode adopts waveform parameters with low distance resolution and high ranging range, the low-speed mode adopts waveform parameters with high distance resolution and low ranging range, and the tunnel mode increases the CFAR threshold and enables the multipath filtering algorithm.

[0090] If any of the following conditions is met, the tunnel mode score is halved: the number of tunnel targets at the original point is less than 5 and the current mode is tunnel; the vehicle's yaw rate is greater than 3° / s; the vehicle's speed is less than 5m / s.

[0091] That is, the improved radar mode switching based on vehicle speed introduced in the present invention is as follows:

[0092] A. Low speed mode---->High speed mode; the radar default power-on working mode is low speed mode.

[0093] When the radar is operating in low-speed mode and the vehicle is at a speed greater than Xkm / h for a duration greater than ZS, the radar will switch the waveform from the low-speed mode to the high-speed mode.

[0094] B. High speed mode ----> low speed mode: When the radar is operating in high speed mode and the vehicle is at a speed less than Y km / h for a duration greater than ZS, the radar will switch the waveform from high speed to low speed.

[0095] C. High-speed / low-speed mode---->Tunnel mode: When the radar operates in high-speed / low-speed mode, it will perform tunnel mode judgment statistics, perform numerical filtering on the statistical results, and use the filtering score to determine whether it is tunnel mode. If so, the algorithm module parameters in the DSP core are updated. Otherwise, the high-speed / low-speed mode waveform is normally generated.

[0096] The process of this solution is as follows: Vehicle speed information reception: The vehicle speed v information output by the on-board inertial navigation module is transmitted to the vehicle speed information receiving module in the radar MCU core via CAN / on-board Ethernet; the radar MCU combines the current waveform pattern and the vehicle speed information v to make the following branch judgments.

[0097] Currently in low-speed mode: If the vehicle speed v meets the condition of "greater than 80 km / h and maintained for more than 15 seconds", the system enters mode switching state 5, then enters state 7 to update the radar RF front-end configuration parameters. After completion, it enters state 8 to synchronize the parameters to the DSP core. The algorithm module in the DSP core is updated accordingly based on the changes in the RF front-end configuration parameters. Finally, the RF front-end is triggered to transmit the waveform to complete the waveform mode update.

[0098] If the vehicle speed v does not meet the condition of "greater than 80 km / h and maintained for more than 15 seconds", it enters state 6 and maintains the current mode, that is, the RF front end maintains the current transmission mode;

[0099] Currently in high-speed mode: If the vehicle speed v meets the condition of "less than 60 km / h and maintained for more than 15 seconds", the system enters mode switching state 5, then enters state 7 to update the radar RF front-end configuration parameters. After completion, it enters state 8 to synchronize the parameters to the DSP core. The algorithm module in the DSP core is updated accordingly based on the changes in the RF front-end configuration parameters. Finally, the RF front-end is triggered to transmit the waveform to complete the waveform mode update.

[0100] If the vehicle speed v does not meet the condition of "less than 60 km / h and maintained for more than 15 seconds", it enters state 6 and maintains the current mode, that is, the RF front end maintains the current transmission mode.

[0101] Thresholds such as "80 km / h, 60 km / h, 15 seconds" can be adjusted based on actual conditions. However, the following must be adhered to: Threshold X for switching from low-speed mode to high-speed mode ≥ Threshold Y for switching from high-speed mode to low-speed mode. This avoids the back-and-forth switching problem caused by traditional fixed thresholds for speed-based switching modes. Otherwise, the radar will become chaotic in mode switching. Assuming that Threshold X for switching from low-speed mode to high-speed mode is less than Threshold Y for switching from high-speed mode to low-speed mode, "greater than 60 km / h for more than 15 seconds" is the low-speed to high-speed condition, and "less than 80 km / h for more than 15 seconds" is the high-speed to low-speed condition. Initially, the default setting is low-speed mode. If the vehicle speed increases to 70 km / h and remains there for 15 seconds, this state meets both the "greater than 60 km / h for more than 15 seconds" low-speed to high-speed condition and the "less than 80 km / h for more than 15 seconds" high-speed to low-speed condition, causing the radar to switch back and forth in a chaotic manner.

[0102] When the high-speed or low-speed mode is currently maintained, the tunnel mode judgment statistics will be performed, the statistical results will be numerically filtered, and the filtering score will be used to determine whether it is the tunnel mode. If so, the algorithm module parameters in the DSP core will be updated. Otherwise, the high-speed / low-speed mode waveform will be sent normally. The detailed process of tunnel mode judgment is as follows Figure 3 shown.

[0103] The main evidences for judgment include: (1) the number of invalid targets in AB waves (point cloud targets); (2) the number of CANDI point targets (tracks); (3) the number of CANDI targets in the tunnels inside the left and right guardrails; (4) the product of the number of tunnel targets on the left and right sides (original point targets); (5) the number of tunnel targets in the left and right guardrails (original point targets); (6) the number of absolutely stationary targets in the lane (original point targets); (7) the ratio of the number of absolutely stationary targets in the guardrail to the number of absolutely stationary targets (original point targets); (8) the speed of the vehicle; and (9) the turning radius of the vehicle.

[0104] The relevant filters are all linear filters: LP_FILTER(pre,coef,meas)((pre)*(coef)+(1.f-(coef))*(meas)), coef is 0.75, pre is the last filter value, and meas is the current frame statistic.

[0105] The scoring thresholds and score details are as follows:

[0106]

[0107]

[0108] Special evidence: (Total score = total score / 2 if any of the following conditions are met); (1) The number of original tunnel targets is less than 5 and the vehicle is in tunnel mode; (2) The vehicle body yawrate is greater than 3 degrees per second; (3) The vehicle speed is less than 5 meters per second; Final score filtering: The filter is also a linear filter, where pre is the filter score value of the previous frame, coef is 0.9, and meas is the total score value of the current frame (after special evidence).

[0109] Tunnel judgment: If the final filtered score value is greater than 70, it indicates that the current scene is a tunnel; otherwise, it is a non-tunnel scene.

[0110] To address the shortcomings of traditional automotive radar mode switching schemes, the present invention proposes a novel radar mode switching scheme: two vehicle speed thresholds, X and Y, and a minimum maintenance time, Z, are set. The threshold X for switching from low-speed mode to high-speed mode is ≥ the threshold Y for switching from high-speed mode to low-speed mode. Furthermore, when the radar is operating in low-speed mode and a vehicle maintains a speed greater than X km / h for a duration greater than ZS, the radar switches between high-speed and low-speed waveforms, switching from the low-speed waveform to the high-speed waveform. When the radar is operating in high-speed mode and a vehicle maintains a speed less than Y km / h for a duration greater than ZS, the radar switches between high-speed and low-speed waveforms, switching from the high-speed waveform to the low-speed waveform. Furthermore, when the radar operates in high-speed / low-speed mode, it performs tunnel mode statistical analysis, numerically filters the statistical results, and uses the filter score to determine whether tunnel mode is in effect. If so, the algorithm module parameters within the DSP core are updated; otherwise, the high-speed / low-speed mode waveform is generated normally.

[0111] To achieve the above objectives, the present invention also provides a multi-mode adaptive switching system for vehicle-mounted millimeter-wave radar based on dynamic vehicle speed threshold and tunnel recognition, such as Figure 5 As shown, the system is used to implement the multi-mode adaptive switching method of the vehicle-mounted millimeter-wave radar based on dynamic vehicle speed threshold and tunnel recognition, and the system includes:

[0112] A first data generating unit is configured to generate and obtain first data and second data corresponding to a vehicle equipped with a millimeter-wave radar, wherein the first data is real-time vehicle speed status data; and the second data is real-time vehicle environment characteristic parameter data;

[0113] a second data generating unit, configured to respectively create third data, fourth data, and fifth data corresponding to the vehicle equipped with the millimeter-wave radar; wherein the third data and the fourth data are both dynamic vehicle speed threshold data, and the value of the third data is greater than the value of the fourth data; and the fifth data is vehicle speed maintenance time data;

[0114] A mode switching processing unit is used to adaptively switch and process the speed mode of a vehicle equipped with a millimeter-wave radar based on the first data and the second data, in combination with the third data or the fourth data, and the fifth data; wherein the speed mode includes a low-speed mode and a high-speed mode.

[0115] The mode switching processing unit further includes:

[0116] A first generating module is configured to generate and obtain sixth data and seventh data corresponding to a vehicle equipped with a millimeter-wave radar; wherein the sixth data is a real-time speed mode of the vehicle; and the seventh data is speed mode switching control data;

[0117] a first determining module, configured to switch the vehicle speed to a high speed mode based on the seventh data when the vehicle-mounted radar is in a low speed mode and the vehicle speed is continuously greater than or equal to the third data for a time greater than or equal to the fifth data;

[0118] a second determination module, configured to switch the vehicle speed to the low speed mode based on the seventh data when the vehicle-mounted radar is in the low speed mode and the vehicle speed is continuously less than or equal to the fourth data for a time greater than or equal to the fifth data;

[0119] A second generating module is configured to create and generate eighth data corresponding to the vehicle equipped with the millimeter-wave radar; wherein the eighth data is tunnel mode score threshold data;

[0120] A third generating module is configured to calculate and generate ninth data corresponding to a vehicle equipped with a millimeter-wave radar and in a tunnel mode; wherein the ninth data is tunnel mode score data;

[0121] a first processing module, configured to adaptively switch and process a speed mode of a vehicle equipped with a millimeter-wave radar based on the second data and the ninth data in combination with the eighth data;

[0122] A fourth generation module is configured to generate tenth data corresponding to the tunnel; wherein the tenth data is a multi-dimensional tunnel characteristic parameter number, including AB wave invalid target data, CANDI target data, tunnel target data within the guardrail, stationary target data in the own lane, vehicle speed, and turning radius data;

[0123] A second processing module is configured to perform weighted processing on the tenth data and generate corresponding eleventh data in combination with a linear filter; wherein the eleventh data is tunnel comprehensive score data;

[0124] The third determination module is configured to determine the scene state corresponding to the tunnel in real time based on the eleventh data.

[0125] The second processing module further includes:

[0126] a fifth generating module, configured to generate and obtain twelfth data corresponding to the tunnel mode; wherein the twelfth data is tunnel mode score determination condition data, including: the number of tunnel targets at the original point is less than 5 and the current mode is tunnel; the vehicle body yaw angular velocity is greater than 3° / s; and the vehicle speed is less than 5 m / s;

[0127] The third processing module is configured to halve the score data of the tunnel mode based on the twelfth data.

[0128] In the system solution embodiment of the present invention, the method steps involved in the multi-mode adaptive switching of the vehicle-mounted millimeter-wave radar based on dynamic vehicle speed threshold and tunnel recognition have been described above in detail. That is, the functional components in the system are used to implement the steps or sub-steps in the above method embodiment, which will not be repeated here.

[0129] To achieve the above objectives, the present invention also provides a multi-mode adaptive switching platform for vehicle-mounted millimeter-wave radar based on dynamic vehicle speed threshold and tunnel recognition, such as Figure 6 As shown, it includes a processor, a memory, and a vehicle-mounted millimeter-wave radar multi-mode adaptive switching platform control program based on dynamic vehicle speed threshold and tunnel identification; wherein, the processor executes the vehicle-mounted millimeter-wave radar multi-mode adaptive switching platform control program based on dynamic vehicle speed threshold and tunnel identification, the vehicle-mounted millimeter-wave radar multi-mode adaptive switching platform control program based on dynamic vehicle speed threshold and tunnel identification is stored in the memory, and the vehicle-mounted millimeter-wave radar multi-mode adaptive switching platform control program based on dynamic vehicle speed threshold and tunnel identification implements the vehicle-mounted millimeter-wave radar multi-mode adaptive switching method steps based on dynamic vehicle speed threshold and tunnel identification. For example:

[0130] S1. Generate and obtain first data and second data corresponding to a vehicle equipped with a millimeter-wave radar, respectively; wherein the first data is the vehicle's real-time speed status data; and the second data is the vehicle's real-time environmental characteristic parameter data;

[0131] S2. Creating third data, fourth data, and fifth data corresponding to the vehicle equipped with the millimeter-wave radar, respectively; wherein the third data and the fourth data are both dynamic vehicle speed threshold data, and the value of the third data is greater than the value of the fourth data; and the fifth data is vehicle speed maintenance time data;

[0132] S3. Based on the first data and the second data, and in combination with the third data or the fourth data, and the fifth data, adaptively switch and process the speed mode of the vehicle equipped with the millimeter-wave radar; wherein the speed mode includes a low-speed mode and a high-speed mode.

[0133] The specific details of the steps have been explained above and will not be repeated here.

[0134] In an embodiment of the present invention, the built-in processor of the multi-mode adaptive switching platform for on-board millimeter-wave radar based on dynamic vehicle speed thresholds and tunnel recognition can be composed of an integrated circuit, such as a single packaged integrated circuit or a plurality of packaged integrated circuits with the same or different functions, including a combination of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor utilizes various interfaces and circuits to connect various components, executes or runs programs or units stored in memory, and calls data stored in memory to perform various functions and process data for the multi-mode adaptive switching of on-board millimeter-wave radar based on dynamic vehicle speed thresholds and tunnel recognition.

[0135] The memory is used to store program codes and various data. It is installed in the multi-mode adaptive switching platform of the vehicle-mounted millimeter-wave radar based on dynamic vehicle speed thresholds and tunnel recognition, and realizes high-speed and automatic access to programs or data during operation.

[0136] The memory includes read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electronically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0137] The present invention generates and acquires first and second data corresponding to a vehicle equipped with a millimeter-wave radar. The first data is the vehicle's real-time speed status data, and the second data is the vehicle's real-time environmental characteristic parameter data. Third, fourth, and fifth data are generated corresponding to the vehicle equipped with the millimeter-wave radar. The third and fourth data are dynamic speed threshold data, and the third data value is greater than the fourth data value. The fifth data value is the vehicle speed maintenance time data. Based on the first and second data, and in combination with the third or fourth data, and the fifth data, the speed mode of the vehicle equipped with the millimeter-wave radar is adaptively switched. The speed modes include low-speed mode and high-speed mode. The system and platform corresponding to the method effectively overcome the problem of conventional fixed speed switching mode thresholds, where the radar frequently switches transmission modes if the vehicle speed fluctuates near the threshold, causing unstable radar operation. The method effectively improves the applicability and robustness of radar mode switching. Furthermore, the addition of a tunnel mode extends its applicability beyond the simple high / low speed mode.

[0138] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

Claims

1. A multi-mode adaptive switching method for vehicle-mounted millimeter-wave radar based on dynamic vehicle speed threshold and tunnel recognition, characterized in that: The method comprises the steps of: Generate and obtain first data and second data corresponding to the vehicle equipped with millimeter-wave radar, respectively; wherein the first data is the real-time vehicle speed state data; the second data is the real-time vehicle environment characteristic parameter data; Creating third data, fourth data, and fifth data corresponding to the vehicle equipped with the millimeter-wave radar, respectively; wherein the third data and the fourth data are both dynamic vehicle speed threshold data, and the value of the third data is greater than the value of the fourth data; and the fifth data is vehicle speed maintenance time data; Based on the first data and the second data, and in combination with the third data or the fourth data, and the fifth data, the speed mode of the vehicle carrying the millimeter-wave radar is adaptively switched; wherein the speed mode includes a low-speed mode and a high-speed mode.

2. The multi-mode adaptive switching method of vehicle-mounted millimeter-wave radar based on dynamic vehicle speed threshold and tunnel recognition according to claim 1 is characterized in that: The method of adaptively switching and processing the speed mode of the vehicle equipped with the millimeter-wave radar based on the first data and the second data, in combination with the third data or the fourth data, and the fifth data, further includes: Generate and obtain sixth data and seventh data corresponding to the vehicle equipped with the millimeter wave radar; wherein the sixth data is the real-time speed mode of the vehicle; and the seventh data is the speed mode switching control data; When the on-board radar is in a low-speed mode and the vehicle speed is continuously greater than or equal to the third data for a time greater than or equal to the fifth data, and based on the seventh data, switching the vehicle speed to a high-speed mode; When the on-board radar is in low-speed mode and the vehicle speed is continuously less than or equal to the fourth data for a time greater than or equal to the fifth data, and based on the seventh data, the vehicle speed is switched to low-speed mode.

3. The multi-mode adaptive switching method of a vehicle-mounted millimeter-wave radar based on dynamic vehicle speed threshold and tunnel recognition according to claim 1 or 2, characterized in that: The method of adaptively switching and processing the speed mode of the vehicle equipped with the millimeter-wave radar based on the first data and the second data, in combination with the third data or the fourth data, and the fifth data, further includes: Creating and generating eighth data corresponding to the vehicle equipped with the millimeter-wave radar; wherein the eighth data is tunnel mode score threshold data; Calculating and generating ninth data corresponding to a vehicle equipped with a millimeter-wave radar and in a tunnel mode; wherein the ninth data is tunnel mode score data; Based on the second data and the ninth data, and in combination with the eighth data, the speed mode of the vehicle equipped with the millimeter-wave radar is adaptively switched.

4. The multi-mode adaptive switching method of vehicle-mounted millimeter-wave radar based on dynamic vehicle speed threshold and tunnel recognition according to claim 3 is characterized in that: The method of adaptively switching and processing the speed mode of the vehicle equipped with the millimeter-wave radar based on the first data and the second data, in combination with the third data or the fourth data, and the fifth data, further includes: Generating tenth data corresponding to the tunnel; wherein the tenth data is a multi-dimensional tunnel characteristic parameter number; including AB wave invalid target data, CANDI target data, tunnel target data within the guardrail, stationary target data in the own lane, vehicle speed, and turning radius data; weight processing the tenth data and generating corresponding eleventh data in combination with a linear filter; wherein the eleventh data is tunnel comprehensive score data; Based on the eleventh data, the scene state corresponding to the tunnel is determined in real time.

5. The multi-mode adaptive switching method of vehicle-mounted millimeter-wave radar based on dynamic vehicle speed threshold and tunnel recognition according to claim 4 is characterized in that: The weight processing of the tenth data and generating corresponding eleventh data in combination with a linear filter further includes: Generate and obtain twelfth data corresponding to the tunnel mode; wherein the twelfth data is tunnel mode score determination condition data, including that the number of tunnel targets at the original point is less than 5 and the current mode is tunnel; the vehicle body yaw angular velocity is greater than 3° / s; and the vehicle speed is less than 5 m / s; Based on the twelfth data, the score data of the tunnel mode is halved.

6. A multi-mode adaptive switching system for vehicle-mounted millimeter-wave radar based on dynamic vehicle speed threshold and tunnel recognition, characterized in that: The system is used to implement the multi-mode adaptive switching method of a vehicle-mounted millimeter-wave radar based on dynamic vehicle speed threshold and tunnel recognition as described in any one of claims 1 to 5, and the system includes: A first data generating unit is configured to generate and obtain first data and second data corresponding to a vehicle equipped with a millimeter-wave radar, wherein the first data is real-time vehicle speed status data; and the second data is real-time vehicle environment characteristic parameter data; a second data generating unit, configured to respectively create third data, fourth data, and fifth data corresponding to the vehicle equipped with the millimeter-wave radar; wherein the third data and the fourth data are both dynamic vehicle speed threshold data, and the value of the third data is greater than the value of the fourth data; and the fifth data is vehicle speed maintenance time data; A mode switching processing unit is used to adaptively switch and process the speed mode of a vehicle equipped with a millimeter-wave radar based on the first data and the second data, in combination with the third data or the fourth data, and the fifth data; wherein the speed mode includes a low-speed mode and a high-speed mode.

7. The multi-mode adaptive switching system for vehicle-mounted millimeter-wave radar based on dynamic vehicle speed threshold and tunnel recognition according to claim 6, characterized in that: The mode switching processing unit further includes: A first generating module is configured to generate and obtain sixth data and seventh data corresponding to a vehicle equipped with a millimeter-wave radar; wherein the sixth data is a real-time speed mode of the vehicle; and the seventh data is speed mode switching control data; a first determining module, configured to switch the vehicle speed to a high speed mode based on the seventh data when the vehicle-mounted radar is in a low speed mode and the vehicle speed is continuously greater than or equal to the third data for a time greater than or equal to the fifth data; a second determination module, configured to switch the vehicle speed to the low speed mode based on the seventh data when the vehicle-mounted radar is in the low speed mode and the vehicle speed is continuously less than or equal to the fourth data for a time greater than or equal to the fifth data; A second generating module is configured to create and generate eighth data corresponding to the vehicle equipped with the millimeter-wave radar; wherein the eighth data is tunnel mode score threshold data; A third generating module is configured to calculate and generate ninth data corresponding to a vehicle equipped with a millimeter-wave radar and in a tunnel mode; wherein the ninth data is tunnel mode score data; a first processing module, configured to adaptively switch and process a speed mode of a vehicle equipped with a millimeter-wave radar based on the second data and the ninth data in combination with the eighth data; A fourth generation module is configured to generate tenth data corresponding to the tunnel; wherein the tenth data is a multi-dimensional tunnel characteristic parameter number, including AB wave invalid target data, CANDI target data, tunnel target data within the guardrail, stationary target data in the own lane, vehicle speed, and turning radius data; A second processing module is configured to perform weighted processing on the tenth data and generate corresponding eleventh data in combination with a linear filter; wherein the eleventh data is tunnel comprehensive score data; The third determination module is configured to determine the scene state corresponding to the tunnel in real time based on the eleventh data.

8. The multi-mode adaptive switching system for vehicle-mounted millimeter-wave radar based on dynamic vehicle speed threshold and tunnel recognition according to claim 7, characterized in that: The second processing module further includes: a fifth generating module, configured to generate and obtain twelfth data corresponding to the tunnel mode; wherein the twelfth data is tunnel mode score determination condition data, including: the number of tunnel targets at the original point is less than 5 and the current mode is tunnel; the vehicle body yaw angular velocity is greater than 3° / s; and the vehicle speed is less than 5 m / s; The third processing module is configured to halve the score data of the tunnel mode based on the twelfth data.

9. A multi-mode adaptive switching platform for vehicle-mounted millimeter-wave radar based on dynamic vehicle speed threshold and tunnel recognition, characterized in that: The invention comprises a processor, a memory and a vehicle-mounted millimeter-wave radar multi-mode adaptive switching platform control program based on dynamic vehicle speed threshold and tunnel recognition; wherein, the vehicle-mounted millimeter-wave radar multi-mode adaptive switching platform control program based on dynamic vehicle speed threshold and tunnel recognition is executed by the processor, the vehicle-mounted millimeter-wave radar multi-mode adaptive switching platform control program based on dynamic vehicle speed threshold and tunnel recognition is stored in the memory, and the vehicle-mounted millimeter-wave radar multi-mode adaptive switching platform control program based on dynamic vehicle speed threshold and tunnel recognition implements the vehicle-mounted millimeter-wave radar multi-mode adaptive switching method based on dynamic vehicle speed threshold and tunnel recognition as described in any one of claims 1 to 5.

Images