A method for improving the function of millimeter-wave radar in a cooperative adaptive cruise control system

Abstract

The present disclosure provides a method for improving the functionality of a millimeter-wave radar in a cooperative adaptive cruise control system, including: using data association-based anomaly detection to determine the signal status of all targets currently detected by the millimeter-wave radar for the cooperative adaptive cruise control system. Signal status includes three conditions: target loss, false target, and normal target. Target loss and false target are defined as signal anomalies. If the current signal status is determined to be target loss or false target, it indicates that the millimeter-wave radar is functionally deficient or misused, and a risk reduction method is initiated to reduce the risk of the millimeter-wave radar in the cooperative adaptive cruise control system. The risk reduction method first initiates a signal correction scheme and then determines whether to take one or more measures: abnormality alarm, takeover request, and downgrade processing. The disclosed method can ensure the safe and stable operation of the platoon.

Description

Technical Field

[0001] The present disclosure relates to the field of cooperative adaptive cruise control systems for intelligent connected vehicles, and in particular to a method for improving the functionality of a millimeter-wave radar in a cooperative adaptive cruise control system. Background Art

[0002] Cooperative Adaptive Cruise Control (CACC) is a key technology for intelligent connected vehicles. Compared to adaptive cruise control, CACC can better ensure the safety and comfort of vehicle following, enabling platooning with shorter following distances. Current research suggests that even if all risks arising from electronic and electrical system failures are addressed through functional safety activities, CACC can still lead to serious consequences due to inadequate design or performance defects in the intended functionality. The key to achieving an acceptable safety level for CACC is to avoid risks in the intended functionality and its implementation, a concept known as Safety of the Intend Functionality (SOTIF). The safe operation of CACC relies on the perception capabilities of millimeter-wave radar. False targets and missed targets in various clutter and interference conditions can lead to unstable platooning or even vehicle collisions. Therefore, addressing the performance limitations of CACC millimeter-wave radars and researching methods to improve the intended functional safety functionality and reduce known and unknown residual risks to an acceptable level are key issues to be addressed. Summary of the Invention

[0003] To ensure the safety of intended functions (SOTIF) of cooperative adaptive cruise control millimeter-wave radar, this paper focuses on proposing a functional improvement method for cooperative adaptive cruise control millimeter-wave radar. Its purpose is to identify whether there are false targets or target loss in the millimeter-wave radar target recognition results, and to adopt corresponding risk reduction methods to ensure the safe and stable operation of the queue in the case of false targets and target loss.

[0004] In order to achieve the above objectives, the present disclosure adopts the following technical solutions:

[0005] The present disclosure provides a method for improving the function of a millimeter-wave radar in a cooperative adaptive cruise control system, comprising:

[0006] In the current cycle, data association-based anomaly detection is used to determine the signal status of all targets currently detected by the millimeter-wave radar for the cooperative adaptive cruise control system. The signal status includes three conditions: target lost, false target, and target normal. Target lost and false target are defined as signal anomalies. If the current signal status is determined to be target lost or false target, it indicates that the millimeter-wave radar has insufficient functionality or is misusing its functionality. Risk reduction processing is used to reduce the risk of the millimeter-wave radar of the cooperative adaptive cruise control system. If the current signal status is determined to be target normal, the next cycle is waited for and the signal status of all targets detected by the millimeter-wave radar in the next cycle is continued.

[0007] The risk reduction method first initiates a signal correction plan and then decides to take one or more measures among abnormal alarm, takeover request and degradation processing.

[0008] In some embodiments, the data association-based anomaly detection is to predict the state of each target in the current cycle based on the measurement data of all targets detected by the millimeter-wave radar in the previous cycle, and perform data association on the predicted state of each target with the measurement data of the corresponding target detected by the millimeter-wave radar in the current cycle. For any target detected by the millimeter-wave radar, if the any target is successfully associated and the number of successful associations is greater than a set threshold, the signal state of the any target is determined to be a normal target; if the any target is successfully associated and the number of successful associations is less than or equal to the set threshold, the signal state of the any target is determined to be a false target; if the any target is not successfully associated, the signal state of the any target is determined to be a lost target.

[0009] Furthermore, for target i, let its time tT in the previous cycle s The measured state and the predicted state at the corresponding time t in the current cycle are and θ i (tT s ),v i (tT s )] T , x i (tT s ),y i (tT s ),θ i (tT s ) and v i (tT s ) are the target i detected by the millimeter wave radar at the last cycle time tT s The longitudinal position, lateral position, heading angle and speed of xi (t) pre ,y i (t) pre ,θ i (t) pre and v i (t) pre are respectively the predicted longitudinal position, lateral position, heading angle and speed of target i at the current cycle time t;

[0010] When the predicted state of target i is associated with the measurement data of target i detected by the millimeter-wave radar in the current period, the associated area Th of target i is set. i , the associated region Th i Status information of all targets in The following conditions are met:

[0011]

[0012]

[0013]

[0014] v th =a max T s

[0015] Where x, y, θ, and v are longitudinal position, lateral position, heading angle, and velocity, respectively; x th ,y th ,θ th ,v th are the longitudinal distance threshold, lateral distance threshold, angle threshold and speed threshold of the associated area respectively; a max is the maximum acceleration of the target;

[0016] If the associated region Th i If there is a target in the memory, select the associated area Th i The target with the smallest inner feature distance S is taken as the associated target, and the target i is determined to be successfully associated, and the number of times the target i is successfully associated is recorded As i (t), As i (t)=As i (tT s )+1,As i (tT s ) is the number of times target i was successfully associated in the previous cycle; if the associated area Th i If there is no target in the target, it is determined that target i is not successfully associated, and the number of times target i is successfully associated As is recorded. i (t)=As i (tT s); the characteristic distance S is calculated according to the following formula:

[0017]

[0018] In some embodiments, the risk reduction process includes: first, starting a signal correction scheme and a secondary alarm to remind the driver to pay attention and monitor the duration of the signal abnormality; if the duration of the signal abnormality exceeds a first time threshold T2, then starting a first alarm, requesting the driver to take over the vehicle and continue to monitor the duration of the signal abnormality, otherwise continuing to use the second alarm to remind the driver to pay attention until the duration of the signal abnormality exceeds the first time threshold T2; if the duration of the signal abnormality exceeds a second time threshold T3 and the driver does not take over the vehicle, then starting a downgrade scheme, the vehicle exits the cooperative adaptive cruise control system, and adjusts to a fixed speed cruise state, otherwise continuing to use the first alarm and requesting the driver to take over the vehicle until the driver takes over the vehicle or starts a downgrade scheme.

[0019] Furthermore, the time interval from when the millimeter wave radar has a malfunction or malfunction to when the malfunction or malfunction is detected by the data association-based malfunction detection is defined as the malfunction detection time ΔT. DTI , the abnormality detection time ΔT DTI , the first time threshold T2 and the second time threshold T3 are set according to the following formulas:

[0020] ΔT DTI <ΔT HTTI -ΔT ART

[0021] T2=ΔT ART -T B -T MG

[0022] T3=ΔT ART -T B

[0023] Where, ΔT HTTI ΔT is the hazard tolerance time interval, which refers to the maximum time interval allowed for insufficient or misused functions of the millimeter-wave radar in the vehicle before a hazard event occurs; ART T is the abnormal response time, which refers to the time interval from when the millimeter-wave radar function deficiency or function misuse is detected by the abnormal detection based on data association to when the vehicle enters a safe state; B The time required for the downgrade strategy to take effect; T MG is the margin time.

[0024] Furthermore, considering the target lost signal, the vehicle is considered to have a maximum acceleration a max Accelerate, the front car has the maximum acceleration a maxThe deceleration condition is the extreme condition. To avoid collision between the vehicle and the preceding vehicle, the hazard tolerance time interval ΔT is set according to the following formula: HTTI,l :

[0025]

[0026] Where, v s is the speed of the vehicle when the signal anomaly is detected based on data association, v f is the speed of the preceding vehicle when the signal anomaly is detected based on data association, d f2s The distance between the vehicle and the preceding vehicle when a signal anomaly is detected for data association-based anomaly detection.

[0027] Furthermore, for the signal of the false target, consider the vehicle with the maximum acceleration a max Decelerate, the following car accelerates at maximum speed a max The acceleration condition is the extreme condition. To avoid collision between the vehicle and the following vehicle, the hazard tolerance time interval ΔT is set according to the following formula: HTTI,f :

[0028]

[0029] Where, v s is the speed of the vehicle when the signal anomaly is detected based on data association, v b The speed of the following vehicle when the signal anomaly is detected based on data association anomaly detection, d s2b The distance between the vehicle and the following vehicle when a signal anomaly is detected for data association-based anomaly detection.

[0030] Furthermore, for the signal of the false target, the signal correction solution adopted is to ignore the false target and reselect the target to follow.

[0031] Furthermore, for target lost signals, a signal correction scheme is adopted to compensate for the lost target motion information using the predicted target motion information.

[0032] Furthermore, the using the predicted target motion information to compensate for the lost target motion information includes:

[0033] Based on the ARIMA model, the historical acceleration sequence of the target is learned, the acceleration sequence characteristics of the target are extracted, and the parameters of the ARIMA model are continuously modified until the predicted target acceleration and the target acceleration change rate meet the requirements. An acceleration prediction model is obtained, and the acceleration prediction model is used to predict the acceleration sequence of the target in the future time. The predicted target acceleration sequence is substituted into the CA model to replace the constant acceleration in the original CA model, and the predicted target position and velocity sequence are calculated, so as to use the predicted target motion information to compensate for the lost target motion information.

[0034] Furthermore, the parameters of the ARIMA model that need to be corrected include the difference order, the autoregressive order, the moving average order, the autoregressive coefficient and the moving average coefficient.

[0035] Furthermore, the KPSS test is used to perform a stationarity test on the historical acceleration series of the target with lost signal to determine the difference order; the grid search method based on Akaike Information Criterion and Bayesian Information Criterion is used to determine the autoregressive order and the moving average order; the maximum likelihood method is used to determine the autoregressive coefficient and the moving average coefficient.

[0036] The features and beneficial effects of the present disclosure are:

[0037] The disclosed embodiments propose a method for improving the functionality of a millimeter-wave radar in a collaborative adaptive cruise control system. The method uses an anomaly detection method to track and predict all targets currently detected by the millimeter-wave radar. The current measurement data is compared with the state prediction information to determine whether the target is lost or a false target has appeared. For different modes of insufficient functionality and duration of anomalies, corresponding secondary alarms, primary alarms, signal corrections, and downgrades to a cruise control scheme are performed. For signal correction in the event of target loss, false targets are ignored and a new target is selected to follow. For signal correction in the event of target loss, the predicted target motion information is used to compensate for the lost target motion information, ultimately ensuring the safe and stable operation of the queue. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The drawings are only for the purpose of illustrating specific embodiments and are not to be considered limiting of the present application.

[0039] Figure 1 It is an overall flow chart of the function improvement method provided by the embodiment of the first aspect of the present disclosure.

[0040] Figure 2 This is a flowchart of the risk identification method provided by the embodiment of the first aspect of the present disclosure.

[0041] Figure 3 It is an overall flow chart of the risk reduction method provided in the embodiment of the first aspect of the present disclosure.

[0042] Figure 4 This is a schematic diagram of the start-up time of the risk reduction method provided in the embodiment of the first aspect of the present disclosure.

[0043] Figure 5 It is a structural diagram of an electronic device provided by three embodiments of the present disclosure. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solutions and advantages of this application more clearly understood, this application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0045] On the contrary, this application covers any alternatives, modifications, equivalents, and solutions made within the spirit and scope of this application as defined by the claims. Furthermore, to facilitate a better understanding of this application, certain specific details are described in detail below in the detailed description of this application. Those skilled in the art will be able to fully understand this application without these details.

[0046] The first embodiment of the present disclosure provides a method for improving the function of a millimeter-wave radar in a cooperative adaptive cruise control system. The overall process is as follows: Figure 1 As shown, the disclosed method is continuously performed while the vehicle is moving until the vehicle stops. The disclosed method includes the following steps:

[0047] 1) CACC millimeter-wave radar risk identification

[0048] In the current cycle, a data association-based anomaly detection method is used to determine whether the signal status of all targets currently detected by the CACC-oriented millimeter-wave radar is abnormal. The signal status includes three situations: target loss, false target, and normal target. Target loss and false target are defined as signal anomalies. If the current signal status is determined to be target loss or false target, it indicates that the CACC millimeter-wave radar has insufficient functions or misused functions, and step 2 is executed. If the current signal status is determined to be normal, wait for the next cycle to arrive and continue to determine the signal status of all targets detected by the millimeter-wave radar in the next cycle.

[0049] 2) CACC millimeter-wave radar risk reduction

[0050] Safety decisions are initiated based on the identified abnormal signals. Specifically, the abnormal signals are first corrected, and then one or more measures including abnormal alarm, takeover request and degradation processing are taken to reduce the risks of CACC millimeter-wave radar.

[0051] In some embodiments, the anomaly detection method based on data association is to track and predict all targets detected by the millimeter-wave radar in the previous cycle, compare the current measurement data with the state prediction information, and determine whether the target is lost or a false target appears. Figure 2The anomaly detection method based on data association is to predict the state of each target in the current cycle based on the measurement data of all targets detected by the millimeter-wave radar in the previous cycle, and perform data association on the predicted state of each target with the measurement data of the corresponding target detected by the millimeter-wave radar in the current cycle. For any target detected by the millimeter-wave radar, if the target is successfully associated and the number of successful associations is greater than the set threshold As0 (generally As0=2), the signal state of the target is determined to be normal; if the target is successfully associated and the number of successful associations is less than or equal to the set threshold As0, the signal state of the target is determined to be a false target; if the target is not successfully associated, the signal state of the target is determined to be lost.

[0052] Furthermore, the Constant Turn Rate and Acceleration (CTRA) model is used to predict the state of each target in the current cycle based on the measurement data of all targets detected by the millimeter-wave radar in the previous cycle. The prediction results are then correlated with the measurement data of the current cycle. Specifically,

[0053] For target i, let its time tT in the previous cycle s The measurement status is y i (tT s ),θ i (tT s ),v i (tT s )] T , x i (tT s ),y i (tT s ),θ i (tT s ) and v i (t-Ts ) They are respectively the target i detected by the millimeter wave radar at time tT in the previous cycle s The longitudinal position, lateral position, heading angle and speed of target i are predicted using the CTRA model at time t in the current cycle. The predicted state of target i is x i (t) pre ,y i (t) pre ,θ i (t) pre and v i (t) preare respectively the predicted longitudinal position, lateral position, heading angle and speed of target i at time t in the current cycle;

[0054] When the predicted state of target i is associated with the measurement data of target i detected by the millimeter-wave radar in the current period, the associated area Th is set. i , the associated region Th i Status information of all targets in The following conditions are met:

[0055]

[0056]

[0057]

[0058] v th =a max T s (4) In the formula, x, y, θ, and v are the longitudinal position, lateral position, heading angle, and velocity, respectively; x th ,y th ,θ th ,v th are the longitudinal distance threshold, lateral distance threshold, angle threshold and speed threshold of the associated area respectively; considering that the steering angle of a general vehicle is between 0.52rad and 0.70rad, θ is set th =1.40rad; a max is the maximum acceleration of the target (the vehicle);

[0059] If the associated region Th i If there is a target in the memory, select the associated area Th i The target with the smallest inner feature distance S is the associated target. It is determined that target i is successfully associated, and the number of times target i is successfully associated is recorded As i (t), As i (t)=As i (tT s )+1,As i (tT s ) is the number of times target i was successfully associated in the previous cycle; if the associated area Th i If there is no target in the target, it is determined that target i is not successfully associated, and the number of times target i is successfully associated As is recorded. i (t)=As i (tT s ); wherein, the characteristic distance S is calculated according to the following formula:

[0060]

[0061] In some embodiments, see Figure 1 、 Figure 3 and Figure 4 The risk reduction method includes: first, starting the signal correction plan and the second-level alarm to remind the driver to pay attention and monitor the duration of the signal abnormality; if the duration of the signal abnormality exceeds the first time threshold T2, then starting the first-level alarm, requesting the driver to take over the vehicle and continuing to monitor the duration of the signal abnormality, otherwise continuing to use the second-level alarm to remind the driver to pay attention until the duration of the signal abnormality exceeds the first time threshold T2; if the duration of the signal abnormality exceeds the second time threshold T3 and the driver does not take over the vehicle, then starting the demotion plan, the vehicle exits the cooperative adaptive cruise control system and adjusts to the fixed speed cruise state, otherwise continuing to use the first-level alarm and requesting the driver to take over the vehicle until the driver takes over the vehicle or the demotion plan is started.

[0062] Furthermore, the safety decision is made based on the function deficiency mode calculated and identified by the anomaly detection method based on data association using the current vehicle (including the own vehicle, the preceding vehicle, and the following vehicle) operating status to calculate the activation time of the signal correction, the second level alarm, the first level alarm, and the degradation processing scheme, such as Figure 4 As shown, where:

[0063] Define the hazard tolerance time interval ΔT HTTI The maximum time interval allowed for the vehicle to detect insufficient CACC millimeter-wave radar functionality or driver misuse of the function before a hazardous event occurs; define the abnormal detection time ΔT DTI The abnormal response time ΔT is defined as the time interval from the occurrence of insufficient or misused CACC millimeter-wave radar function to the detection and sending of the abnormal code by the data association-based abnormality detection method; ART The time interval from when the CACC millimeter-wave radar's insufficient or misused function is detected by the data association-based anomaly detection method to when the vehicle enters a safe state. The functional improvement strategy for expected functional safety is to enable the vehicle to enter a safe state within the hazard tolerance interval. Therefore, the following relationship must be satisfied before the three aforementioned times:

[0064] ΔT DTI +ΔT ART <ΔT HTTI (6)

[0065] According to the simulation experiment results, the anomaly detection time ΔT of the anomaly detection method based on data association provided by the embodiment of the present disclosure is DTI =0.2s.

[0066] For the hazard tolerance time interval ΔT HTTI The determination of target loss and false target is described separately:

[0067] a. When the target is lost, consider the vehicle with maximum acceleration a max Accelerate, the front car has the maximum acceleration a max The deceleration condition is the extreme condition. To avoid collision between the vehicle and the preceding vehicle, the hazard tolerance time ΔT is set according to the following formula: HTTI,l :

[0068]

[0069] Where, v s is the speed of the vehicle when the abnormal signal is detected by the anomaly detection method based on data association in this embodiment, v f is the speed of the preceding vehicle when the abnormal signal is detected by the abnormality detection method based on data association in this embodiment, d f2s It is the distance between the vehicle and the preceding vehicle when the abnormal signal is detected by the abnormality detection method based on data association in this embodiment.

[0070] b. In the case of a false target, consider the vehicle with maximum acceleration a max Decelerate, the following car accelerates at maximum speed a max The acceleration condition is an extreme condition. To avoid collision between the vehicle and the following vehicle, the hazard tolerance time ΔT is set according to the following formula: HTTI,f :

[0071]

[0072] Where, v b is the speed of the following vehicle when the abnormal signal is detected by the abnormality detection method based on data association in this embodiment, d s2b is the distance between the vehicle and the following vehicle when the abnormal signal is detected by the abnormality detection method based on data association of this embodiment;

[0073] For the determination of the first time threshold T2 (i.e., the abnormality duration threshold time for initiating the first level alarm and requesting the driver to take over the vehicle) and the second time threshold T3 (i.e., the abnormality duration threshold time for initiating the demotion strategy), the time required from the first level alarm to the driver taking over the vehicle is added with a certain margin time T MG (According to the existing experimental results, the driver's dangerous reaction time is 0.8s~2.0s, so the margin time T is selected MG is 2.0s), if the margin time T is exceeded MG If the driver still does not take over the vehicle, the degradation strategy is activated. The time required for the degradation strategy to take effect is T B (According to the simulation results, the time required for the degradation strategy to take effect is T B Based on the above factors, the first time threshold T2 and the second time threshold T3 are determined according to the following formulas:

[0074] T2=ΔT ART-T B -T MG (9)

[0075] T3=ΔT ART -T B (10)

[0076] Furthermore, different signal correction schemes are used for identified false targets and target loss:

[0077] For false targets, the signal correction solution adopted is to ignore the false targets and reselect the target to follow.

[0078] In response to target loss, the historical acceleration sequence of the target is learned based on the differential integrated moving average autoregressive (ARIMA) model, the acceleration sequence characteristics of the target are extracted, and the parameters of the ARIMA model are continuously modified until the predicted target acceleration and target acceleration change rate meet the requirements. The acceleration prediction model is obtained and used to predict the future time t pre The target acceleration sequence is substituted into the constant acceleration (CA) model to replace the constant acceleration in the original CA model. The predicted target position and velocity sequence are calculated, thereby using the predicted target motion information (including the target position and velocity) to compensate for the lost target motion information. The specific steps are as follows:

[0079] 21) Based on the ARIMA model, an acceleration prediction model for predicting the acceleration of the target is constructed according to the following formula:

[0080]

[0081] Where, is the d-order difference of the target acceleration at time T, is the d-order difference of the target acceleration at time Tj; ε T is the residual of acceleration at time T, ε T-j is the residual at time Tj; p,q,φ j ,θ j are the parameters of the ARIMA model, where p is the autoregressive (AR) order, q is the moving average (MA) order, and φ j is the autoregressive coefficient, θ j is the moving average coefficient.

[0082] 22) Follow the steps below to continuously modify the parameters of the ARIMA model to obtain the final acceleration prediction model:

[0083] 221) The KPSS (Kwiatkowski-Phillips-Schmidt-Shin) test is used to perform a stationarity test on the historical acceleration sequence of the target with signal loss to determine the differential order d. Specifically, if the historical acceleration sequence does not meet the stationarity requirement, the historical acceleration sequence is differentiated once and then the stationarity test is performed again. This cycle is repeated until the historical acceleration sequence meets the stationarity requirement. The number of differentials required for the historical acceleration sequence to meet the stationarity requirement is the differential order d.

[0084] 222) The autoregressive order p and the moving average order q are determined using a grid search method based on the Akaike Information Criterion (AIC) and the Bayesian Information Criterion (BIC). Specifically:

[0085] First, determine the two-dimensional search grid points (p v ,q v ) and calculate the AIC and BIC values of each two-dimensional search grid point. The calculation formula is as follows:

[0086] {(p v ,q v )|p v ∈[0,p max ],q v ∈[0,q max ] and p v ,q v ∈N} (12)

[0087]

[0088]

[0089] Where, is the two-dimensional search grid point (p v ,q v ), where N is the number of historical acceleration sequence samples of the target whose signal is lost.

[0090] Then determine the AIC(p v ,q v ) takes the minimum value, and the corresponding two-dimensional search grid point is recorded as and determine BIC(p v ,q v ) takes the minimum value, and the corresponding two-dimensional search grid point is recorded as

[0091]

[0092] That is, the estimated autoregressive order and moving average order.

[0093] 223) Using the maximum likelihood method to estimate the autoregressive coefficient φ j and the moving average coefficient θ j , specifically:

[0094] The reduced likelihood function used by the maximum likelihood method is l(β):

[0095]

[0096]

[0097] β=(φ1,φ2,…,φ j ,…,φ p ,θ1,θ2,…,θ j ,…,θ q ) T (18)

[0098] Where β is the vector of sliding mean coefficients of autoregressive coefficients; (r0, r1…, r N-1 )for The mean square error of

[0099] Calculate the minimum point of the reduced likelihood function l(β) to obtain the autoregressive coefficient φ j and the moving average coefficient θ j .

[0100] 224) The difference order d, autoregressive order p, moving average order q, and autoregressive coefficient φ obtained from steps 221) to 223) j and the moving average coefficient θ j , by the ARIMA model, the predicted target acceleration sequence is obtained t start is the moment when the target is lost, if

[0101] or

[0102] Then delete the corresponding two-dimensional search grid point (p,q), where J max is the maximum value of the vehicle acceleration rate of change.

[0103] 225) Repeat steps 221) to 224) until the predicted target acceleration and the predicted target acceleration change rate both meet the requirements, thereby obtaining a final acceleration prediction model.

[0104] 23) Use the acceleration prediction model obtained in step 22) to predict the future time t pre acceleration sequence of the internal target;

[0105] 24) Substitute the predicted target acceleration sequence into the constant acceleration (CA) model (assuming that information compensation is required for the preceding vehicle, and the preceding vehicle in CACC only has longitudinal motion, so the CA model is used), replacing the constant acceleration in the original CA model, and calculate the predicted target position and velocity sequence, thereby using the predicted target motion information to compensate for the lost target motion information.

[0106] Furthermore, during cruise control, the vehicle speed satisfies:

[0107] v des =v f_last -C (20) In the formula, v des is the expected vehicle speed in cruise control state, v f_last is the speed of the preceding vehicle when the abnormal signal is detected, and C is the speed difference between adjacent vehicles, C = 0.9 m / s.

[0108] A second embodiment of the present disclosure provides a function improvement device for a millimeter-wave radar in a cooperative adaptive cruise control system, comprising:

[0109] The CACC millimeter-wave radar anomaly detection module is used to determine whether the signal status of all targets currently detected by the CACC-oriented millimeter-wave radar is abnormal in the current cycle using a data association-based anomaly detection method. The signal status includes three conditions: target loss, false target, and normal target. Target loss and false target are defined as signal anomalies. If the current signal status is determined to be target loss or false target, it indicates that the millimeter-wave radar is functionally deficient or misused.

[0110] The CACC millimeter-wave radar risk reduction module is used to first initiate a signal correction plan when the CACC millimeter-wave radar anomaly detection module detects an abnormal signal status, and then decide to take one or more measures including abnormal alarm, takeover request and degradation processing to reduce the risk of the CACC millimeter-wave radar.

[0111] In order to implement the above embodiment, the embodiment of the present disclosure also proposes a computer-readable storage medium on which a computer program is stored. The program is executed by a processor to execute the function improvement method of the millimeter-wave radar of the cooperative adaptive cruise control system of the above embodiment.

[0112] Reference below Figure 5, which shows a schematic structural diagram of an electronic device suitable for implementing the embodiments of the present disclosure. It should be noted that the electronic devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs, desktop computers, and servers. Figure 5 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0113] like Figure 5 As shown, the electronic device may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 101, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 102 or a program loaded from a storage device 108 into a random access memory (RAM) 103. Various programs and data required for the operation of the electronic device are also stored in the RAM 103. The processing device 101, the ROM 102, and the RAM 103 are connected to each other via a bus 104. An input / output (I / O) interface 105 is also connected to the bus 104.

[0114] Typically, the following devices may be connected to the I / O interface 105: an input device 106 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, etc.; an output device 107 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 108 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 109. The communication device 109 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Figure 5 The electronic device is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead.

[0115] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, this embodiment includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network via the communication device 109, or installed from the storage device 108, or installed from the ROM 102. When the computer program is executed by the processing device 101, the above-mentioned functions defined in the method of the embodiment of the present disclosure are performed.

[0116] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or component. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0117] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0118] The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: in the current cycle, uses a data association-based anomaly detection method to determine the signal status of all targets currently detected by the millimeter-wave radar for the collaborative adaptive cruise control system, wherein the signal status includes three situations: target loss, false target and normal target, and target loss and false target are defined as signal anomalies; if the current signal status is determined to be target loss or false target, it means that the millimeter-wave radar has insufficient function or misuse of function, and a risk reduction method is initiated to reduce the risk of the CACC millimeter-wave radar; if the current signal status is determined to be normal target, wait for the arrival of the next cycle, and continue to determine the signal status of all targets detected by the millimeter-wave radar in the next cycle; the risk reduction method first initiates the signal correction plan, and then decides to take one or more measures among abnormal alarm, request takeover and downgrade processing.

[0119] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, Python, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0120] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0121] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of such features. Throughout the description of this application, "plurality" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0122] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0123] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection having one or more wires (electronic devices), a portable computer disk cartridge (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). Furthermore, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or otherwise processing it in a suitable manner if necessary, and then storing it in a computer memory.

[0124] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0125] Those skilled in the art will understand that all or part of the steps carried out in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, and the developed program can be stored in a computer-readable storage medium. When the program is executed, it includes one of the steps of the method embodiment or a combination thereof.

[0126] In addition, the functional units in the various embodiments of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into a module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0127] The storage medium mentioned above may be a read-only memory, a magnetic disk, or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application. Persons skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A method for improving the function of a millimeter-wave radar in a cooperative adaptive cruise control system, characterized in that: include: Target loss and false target anomaly detection based on data association, specifically including: 1) Track and predict all targets detected by the current millimeter-wave radar, and associate the measurement data of the current cycle with the state prediction information, where: For target i, let its time tT in the previous cycle s The measured state and the predicted state at the corresponding time t in the current cycle are respectively and x i (tT s ),y i (tT s ),θ i (tT s ) and v i (tT s ) are the target i detected by the millimeter wave radar at the last cycle time tT s The longitudinal position, lateral position, heading angle and speed of x i (t) pre ,y i (t) pre ,θ i (t) pre and v i (t) pre are the predicted longitudinal position, lateral position, heading angle and speed of target i at the current cycle time t; when the predicted state of target i is associated with the measurement data of target i detected by the millimeter-wave radar in the current cycle, the associated area Th of target i is set i , the associated region Th i Status information of all targets in The following conditions must be met: v th =a max T s Where x, y, θ, and v are longitudinal position, lateral position, heading angle, and velocity, respectively; x th ,y th ,θ th ,v th are the longitudinal distance threshold, lateral distance threshold, angle threshold and speed threshold of the associated area respectively; a max is the maximum acceleration of the target; If the associated region Th i If there is a target in the memory, select the associated area Th i The target with the smallest inner feature distance S is taken as the associated target, and the target i is determined to be successfully associated, and the number of times the target i is successfully associated is recorded As i (t), As i (t)=As i (tT s )+1,As i (tT s ) is the number of times target i was successfully associated in the previous cycle; if the associated area Th i If there is no target in the target, it is determined that target i is not successfully associated, and the number of times target i is successfully associated As is recorded. i (t)=As i (tT s ); the characteristic distance S is calculated according to the following formula: If the number of times target i is successfully associated is As i (t) When it is less than or equal to the set threshold As0, the target i is judged to be a false target; If target i is not successfully associated, target i is determined to be lost.

2. The function improvement method according to claim 1, characterized in that: The function improvement method also includes performing risk reduction processing on signals of identified false targets or target loss, including: First, activate the signal correction plan and the secondary alarm to alert the driver and monitor the duration of the signal abnormality; If the duration of the signal anomaly exceeds the first time threshold T2, a level 1 alarm is activated, requesting the driver to take over the vehicle and continue to monitor the duration of the signal anomaly. Otherwise, a level 2 alarm is used to remind the driver to pay attention until the duration of the signal anomaly exceeds the first time threshold T2. If the signal abnormality lasts longer than the second time threshold T3 and the driver has not taken over the vehicle, the downgrade plan is activated, the vehicle exits the cooperative adaptive cruise control system and adjusts to the cruise control state. Otherwise, the first level alarm continues to be used and the driver is requested to take over the vehicle until the driver takes over the vehicle or the downgrade plan is activated.

3. The function improvement method according to claim 2, characterized in that: The time interval from when the millimeter wave radar has insufficient or misused functions to when the insufficient or misused functions are detected by the target loss and false target anomaly detection based on data association is defined as the anomaly detection time ΔT DTI , the abnormality detection time ΔT DTI , the first time threshold T2 and the second time threshold T3 are set according to the following formulas: ΔT DTI <ΔT HTTI -ΔT ART T2=ΔT ART -T B -T MG T3=ΔT ART -T B Where, ΔT HTTI ΔT is the hazard tolerance time interval, which refers to the maximum time interval allowed for insufficient or misused functions of the millimeter-wave radar in the vehicle before a hazard event occurs; ART T is the abnormal response time, which refers to the time interval from when the millimeter wave radar function deficiency or function misuse is detected by the target loss and false target abnormality detection based on data association to when the vehicle enters a safe state; B The time required for the downgrade strategy to take effect; T MG is the margin time.

4. The function improvement method according to claim 3, characterized in that: For the target lost signal, consider the vehicle with maximum acceleration a max Accelerate, the front car has the maximum acceleration a max The deceleration condition is the extreme condition. To avoid collision between the vehicle and the preceding vehicle, the hazard tolerance time interval ΔT is set according to the following formula: HTTI，l : Where, v s is the speed of the vehicle when the data association-based target loss and false target anomaly detection detects a signal anomaly, v f is the speed of the preceding vehicle when the data association-based target loss and false target anomaly detection detects a signal anomaly, d f2s The distance between the vehicle and the preceding vehicle when the data association-based target loss and false target anomaly detection detects a signal anomaly.

5. The function improvement method according to claim 3, characterized in that: For the signal of the false target, consider the vehicle with maximum acceleration a max Decelerate, the following car accelerates at maximum speed a max The acceleration condition is the extreme condition. To avoid collision between the vehicle and the following vehicle, the hazard tolerance time interval ΔT is set according to the following formula: HTTI，f : Where, v s is the speed of the vehicle when the data association-based target loss and false target anomaly detection detects a signal anomaly, v b is the speed of the following vehicle when the data association-based target loss and false target anomaly detection detects a signal anomaly, d s2b The distance between the vehicle and the following vehicle when the data association-based target loss and false target anomaly detection detects a signal anomaly.

6. The function improvement method according to claim 2, characterized in that: For the signal of the false target, the signal correction solution adopted is to ignore the false target and reselect the target to follow.

7. The function improvement method according to claim 2, characterized in that: For the target lost signal, the signal correction scheme adopted is to use the predicted target motion information to compensate for the lost target motion information.

8. The function improvement method according to claim 7, characterized in that: The using the predicted target motion information to compensate for the lost target motion information includes: Based on the ARIMA model, the historical acceleration sequence of the target is learned, the acceleration sequence characteristics of the target are extracted, and the parameters of the ARIMA model are continuously modified until the predicted target acceleration and the target acceleration change rate meet the requirements. An acceleration prediction model is obtained, and the acceleration prediction model is used to predict the acceleration sequence of the target in the future time. The predicted target acceleration sequence is substituted into the CA model to replace the constant acceleration in the original CA model, and the predicted target position and velocity sequence are calculated, so as to use the predicted target motion information to compensate for the lost target motion information.

9. The function improvement method according to claim 8, characterized in that: The parameters of the ARIMA model that need to be modified include the difference order, the autoregressive order, the moving average order, the autoregressive coefficient and the moving average coefficient.

10. The function improvement method according to claim 9, characterized in that: Performing a stationarity test on the historical acceleration sequence of the target whose signal is lost by using a KPSS test to determine the differential order; Determining the autoregressive order and the moving average order using a grid search method based on Akaike Information Criterion and Bayesian Information Criterion; The autoregressive coefficient and the moving average coefficient are determined using a maximum likelihood method.

Images