CN111532274B - Intelligent vehicle lane change auxiliary system and method based on multi-sensor data fusion - Google Patents
Intelligent vehicle lane change auxiliary system and method based on multi-sensor data fusion Download PDFInfo
- Publication number
- CN111532274B CN111532274B CN202010127272.3A CN202010127272A CN111532274B CN 111532274 B CN111532274 B CN 111532274B CN 202010127272 A CN202010127272 A CN 202010127272A CN 111532274 B CN111532274 B CN 111532274B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- target
- millimeter wave
- lane
- wave radar
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000008859 change Effects 0.000 title claims abstract description 41
- 230000004927 fusion Effects 0.000 title claims abstract description 33
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000001914 filtration Methods 0.000 claims abstract description 17
- 238000012545 processing Methods 0.000 claims description 11
- 230000001133 acceleration Effects 0.000 claims description 10
- 238000005315 distribution function Methods 0.000 claims description 8
- 230000007613 environmental effect Effects 0.000 claims description 8
- 238000007499 fusion processing Methods 0.000 claims description 8
- 230000003321 amplification Effects 0.000 claims description 7
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 7
- 230000015572 biosynthetic process Effects 0.000 claims description 6
- 238000003786 synthesis reaction Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000007689 inspection Methods 0.000 claims description 2
- 230000009916 joint effect Effects 0.000 claims description 2
- 238000012360 testing method Methods 0.000 claims description 2
- 238000001514 detection method Methods 0.000 abstract description 19
- 238000012544 monitoring process Methods 0.000 abstract description 14
- 230000010354 integration Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 6
- 230000007547 defect Effects 0.000 description 5
- 238000005259 measurement Methods 0.000 description 5
- 230000003068 static effect Effects 0.000 description 5
- 206010039203 Road traffic accident Diseases 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000009434 installation Methods 0.000 description 3
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 239000000243 solution Substances 0.000 description 2
- 241001061260 Emmelichthys struhsakeri Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000002347 injection Methods 0.000 description 1
- 239000007924 injection Substances 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
- B60W30/18—Propelling the vehicle
- B60W30/18009—Propelling the vehicle related to particular drive situations
- B60W30/18163—Lane change; Overtaking manoeuvres
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/08—Interaction between the driver and the control system
- B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
-
- B60W2420/408—
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Human Computer Interaction (AREA)
- Traffic Control Systems (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention provides an intelligent vehicle lane change auxiliary system and method based on multi-sensor data fusion, wherein lane change monitoring is carried out through millimeter wave radar sensors with different frequency Hertz numbers, which are arranged at four corners of an automobile, 77GHz millimeter wave radar sensors are respectively arranged at the left front part and the left rear part of the automobile, and 24GHz millimeter wave radar sensors are respectively arranged at the right front part and the right rear part of the automobile. The detection ranges of the millimeter wave radar sensors with different frequencies respectively arranged in front of and behind the automobile have certain overlapping areas and non-overlapping areas. Firstly, primary selection is carried out on surrounding vehicle targets on each sensor, then validity check is carried out on the surrounding vehicle targets according to the Kalman filtering principle, and finally decision-level signal integration is carried out on a coincidence area by adopting a D-S evidence theory according to the sensing range advantages of millimeter wave radar sensors with different frequencies. The invention fully integrates the detection advantages and characteristics of each sensor, comprehensively detects the surrounding environment of the automobile and judges whether the lane change is in a dangerous state or not in time.
Description
Technical Field
The invention belongs to the field of intelligent and safe driving assistance of automobiles, and particularly relates to an intelligent lane changing assistance method for monitoring a peripheral driving environment through multi-sensor data fusion.
Background
The intelligent vehicle system is a comprehensive system integrating functions of environment perception, planning decision, multi-level auxiliary driving and the like, and is a typical, multi-disciplinary, comprehensive combination of high technology and high and new technology, wherein lane changing driving has a large risk due to the fact that lanes need to be changed rapidly. If the driver does not estimate the position and relative speed of the surrounding vehicles in lane changing, the driver is likely to misjudge and mistakenly change lanes, and further unnecessary traffic accidents are likely to be caused, so that property loss or casualties are caused. Therefore, an intelligent driving assistance system (ADAS) is developed, which can accurately measure dangerous vehicles in blind areas of rear-view mirrors on two sides of an automobile and correspondingly monitor the vehicles in a certain distance range behind the automobile.
At present, a great number of researchers at home and abroad mainly carry out sufficient lane change feasibility analysis on the relative motion relationship between a vehicle and a vehicle in a blind area of a rearview mirror and a vehicle behind a target lane within a certain distance (within 60 meters) in the lane change process. Such as the blind spot monitoring system of Toyota, land Rover and BMW vehicle series, or the automatic driving system of Oddi vehicle series, the technology has been made relatively mature and reliable. However, the above systems have no monitoring capability for the dangerous vehicles which are decelerated and slow in front of the target lane in a long distance (more than 60 meters) and accelerated and fast in back of the target lane in a long distance (more than 60 meters). If a driver meets the two conditions on the highway, the driver himself or herself can judge the condition without accuracy, and the overtaking and lane changing are forced under the condition, and particularly when both vehicles are in a fast driving state, serious traffic accidents are easily caused. In addition, in order to ensure hardware redundancy, the conventional lane changing auxiliary system usually adopts double 24GHz millimeter wave radars as sensor input equipment to perform data fusion on double radars with the same model, the measurement errors and measurement limitation conditions of the radars with the same model are often consistent, and the data fusion on the radars with the same model often cannot obtain a more accurate result, so that the lane changing auxiliary system has a few disadvantages.
Disclosure of Invention
Aiming at the defects of the conventional lane change auxiliary system, in order to overcome the defects, the invention adopts corresponding data processing and data fusion means based on the front and rear 77GHz and 24GHz millimeter wave radar sensors of the automobile, fully exerts the advantages of the sensors with different frequencies, and carries out monitoring and early warning on the dangerous vehicles with long distance (more than 60 meters) of a target lane; meanwhile, decision-level data fusion processing is carried out on monitoring superposition areas among the radars with different frequencies, a more accurate monitoring early warning result is obtained, the safety of the lane changing auxiliary system is more accurately and comprehensively improved, and the possibility of traffic accidents is reduced to a greater extent.
In order to achieve the technical purpose, the technical scheme of the invention is as follows: a data fusion lane change auxiliary method based on intelligent vehicle multi-sensors comprises the following steps: 1) the intelligent lane changing auxiliary system comprises a data acquisition unit, a signal amplification unit, an independent data processing unit, a data fusion control unit and a warning and early warning unit; 2) the data acquisition unit simultaneously acquires the driving data of the target lane at the left front and the left rear of the vehicle and the vehicle in the lane at a long distance (0-120 m) and the driving data of the vehicle at the right front and the right rear of the vehicle at a short distance (within 60 m), amplifies the data signals and transmits the amplified data signals to the independent data processing unit through the CAN bus; 3) the independent data processing unit respectively preprocesses the acquired data, performs initial selection and target validity check on the target vehicle, and firstly generally judges whether the vehicle is a dangerous vehicle; 4) the data fusion control unit receives the signal of the independent data processing unit, carries out decision-making level data fusion processing on the monitored coincident region, independently judges the non-coincident region, generates an early warning control instruction and transmits the early warning instruction to the warning early warning unit; 5) and the warning early warning unit carries out corresponding acousto-optic and steering intervention early warning according to the received signal.
The sensors of the data acquisition unit are two 77GHz millimeter wave radar sensors and two 24GHz millimeter wave radar sensors.
The installation position and the installation layout of the sensor are as follows: the 77GHz millimeter wave radar sensors with far detectable distance and narrow detection area are respectively arranged at the left front part and the left rear part of the automobile, and the 24GHz millimeter wave radar sensors with near detectable distance and wide detection area are respectively arranged at the right front part and the right rear part of the automobile.
The target lane is mainly the left lane of the vehicle, and the information of the vehicle on the left lane is mainly detected because the state stipulates that the vehicle should overtake the left lane on the highway.
An intelligent vehicle multi-sensor data fusion lane change auxiliary method is realized through the system, and comprises the following specific steps:
s1: acquiring environmental information in a range of 120 meters in front of and behind the lane and the target lane by using a left front 77GHz sensor and a left rear 77GHz sensor, and acquiring environmental information in front of and behind the vehicle by using a right front 24GHz sensor and a right rear 24GHz sensor;
s2: the method comprises the following steps of respectively and independently preprocessing four collected sensor data in front of and behind the automobile to realize the initial selection of a vehicle target;
s3: target validity inspection based on Kalman filtering is independently carried out on vehicle targets preliminarily selected by the four millimeter wave radar sensors;
s4: independently judging the detected non-coincident areas in front of or behind the automobile to judge whether a slow-speed vehicle is decelerated in a long distance in front of the target lane and whether an accelerated fast-speed vehicle is accelerated in a long distance behind the target lane;
s5: monitoring the overlapping area of the front sensor and the rear sensor of the automobile respectively by adopting a D-S evidence theory, namely performing data fusion on two generated independent evidences subjected to target validity check, and ensuring the reliability of detection to the maximum extent;
s6: the result processed by the data fusion control unit is transmitted to a warning and early warning unit;
s7: and the warning early warning unit carries out sound, flash and steering reverse intervention early warning according to the judgment result.
The environmental information collected by the sensor in step S1 includes: relative velocity v of each target vehicle and the host vehiclerRelative distance xrAnd relative angle
And the like.
The main method for independently preprocessing the sensor data in step S2 includes filtering empty signal objects, filtering stationary objects, and filtering false objects.
The main method for checking the validity of the target in the step S3 is as follows:
due to the uncertainty of millimeter wave radar detection, errors in the detection method and the like, the target should be further checked for validity, and the vehicle target is checked for validity by adopting a Kalman filtering prediction method. The high-order third-order Kalman filtering method is used for predicting effective vehicle target information in the period, and the state is assumed
Wherein xn,j,vn,j,
Respectively representing the longitudinal relative distance, relative speed and relative acceleration of the valid vehicle object measured during the nth cycle. The target vehicle state prediction for the next cycle is as follows:
in the above formula, T is the scanning period of the millimeter wave radar, and the value is 0.04s, x(n+1)|n、v(n+1)|n、
And respectively representing the longitudinal relative distance, the relative speed and the relative acceleration of the predicted value of the target vehicle in the (n + 1) th period. Comparing and verifying the initially selected vehicle target information of the (n + 1) th period with the effective vehicle target information predicted value of the nth period obtained by the formula, wherein the comparison criterion is as follows:
|xn+1-x(n+1)|n|≤|Δx|
|vn+1-v(n+1)|n|≤|Δv|
in the above formula, xn+1、vn+1、
Respectively representing the longitudinal relative distance, the relative speed and the relative acceleration of the two vehicles in the (n + 1) th period; Δ x, Δ v,
Respectively, represent the maximum error allowed for the comparison criterion. In the present invention, the set error is:
and regarding the primary vehicle targets in the n +1 th period, if the primary vehicle targets conform to the formula, the primary vehicle targets are considered to be consistent with the effective vehicle targets in the n th period, and target vehicle information is updated, namely, if the effective vehicle targets in the two periods are consistent with dangerous vehicles, the primary vehicle targets are classified as dangerous vehicles, and if the effective vehicle targets in the two periods are consistent with non-dangerous vehicles, the primary vehicle targets are classified as non-dangerous vehicles. If the formula is not satisfied, target inconsistency is required to be processed, and for monitoring the target in the overlapped area, a D-S evidence theory is used for data fusion processing to determine whether the target is a dangerous vehicle; for the non-coincident region target, the vehicle target is assumed to be valid by default, and the safety is guaranteed to the maximum extent, namely if the results of the judgment of the nth period and the (n + 1) th period of the non-coincident region are that one is a dangerous vehicle and the other is a non-dangerous vehicle, the non-coincident region is determined to be a dangerous vehicle.
Further, the fusion process in step S5 is performed by the following steps:
a. target synthesis: combining the observation results of two independent sensors with different frequencies in the overlapped area into a total output result (ID); the D-S evidence theory can derive basic probability distribution functions for evidence sources from two independent sensors, and then a Dempster combination rule in the D-S evidence theory can calculate a new basic probability distribution function which reflects fusion information and is generated by the joint action of the two evidences, and a total output result is synthesized according to the probability distribution function, namely whether a dangerous vehicle target is determined or not;
b. target inference: the method logically generates a target vehicle report with certain confidence coefficient according to certain confidence coefficient to obtain the observation result of the sensor and deduce the observation result, and the observation result of the sensor is expanded into the target vehicle report; according to a probability distribution function generated by a D-S evidence theory, a target vehicle report with certain confidence coefficient is formed, namely whether a dangerous vehicle really exists or not is judged, and whether the dangerous vehicle really exists or not is judged;
c. target updating: the two different frequency sensors themselves are typically randomly error-prone, so that a set of reports generated by the two time-independent same frequency sensors is more reliable than a report generated by either sensor. Therefore, prior to inference and synthesis of two different frequency sensors, the observed data of the respective frequency sensors are combined (updated); that is, for the primary selected vehicle target in the n +1 th cycle, if the set error is satisfied, the primary selected vehicle target is considered to be identical to the valid vehicle target in the n-th cycle, and the target vehicle information is updated for this.
As a further step, the intelligent provision of lane change information during the road change in step S7 is to alert the driver by a corresponding audible, visual or steering intervention warning, based on the relative distance x between the vehiclesrAnd relative velocity vrJudging whether the vehicle is in a dangerous state, if so, displaying a green lamp, and not giving an alarm by the buzzer; if the alarm is in the warning state, the alarm is changed into a flashing yellow light, and the buzzer rings once every two seconds; if the state is a dangerous state, the state is converted into a red light state, and the buzzer rings once per second; if the driver does not see or hear the prompting information of lane change assistance in time, and then the lane change is forcibly carried out, besides sound or flash alarm, corresponding torque intervention is carried out on the steering through a steering interface feedback unit connected into the power steering module, and the driver is timely reminded not to make a lane change behavior at the moment.
The invention adopts the above double-layer guarantee technical scheme, and has the following outstanding advantages: 1) the invention successfully monitors the vehicles which decelerate slowly at the front and accelerate quickly at the rear of the target lane in a long distance by adopting the combination of 24GHz and 77GHz frequency millimeter wave radar sensors. The defect of the conventional lane changing auxiliary system is overcome, and the lane changing safety is improved. 2) According to the invention, two different frequency sensors are adopted for collecting information, so that the collected information is more comprehensive, the fault tolerance is stronger, and the problems of measurement errors and consistent measurement limitations of the redundant radar sensors with the same type are solved. 3) The method adopts a double-layer guarantee scheme of firstly carrying out independent processing on data and secondly carrying out decision-making level data fusion, and respectively processes the monitoring coincidence region and the non-coincidence region, thereby not only ensuring the accuracy of data judgment, but also ensuring the timeliness of decision making. 4) The steering feedback interface is introduced into the warning and early warning module, so that the phenomenon that a driver carelessly ignores the reminding of sound or flash signals is effectively avoided, and the driver is timely fed back through the touch of the steering wheel. The invention makes up the defects of the existing lane changing auxiliary system and improves the safety of the intelligent driving auxiliary system.
Drawings
The invention has the following figures 5:
FIG. 1 is a diagram of a millimeter wave radar mounting location and a monitoring area on an automobile;
FIG. 2 is a flowchart illustrating the operation of the lane change support system according to the present invention;
FIG. 3 is a schematic diagram of a data fusion lane change support system according to the present invention;
FIG. 4 is a circuit diagram of a signal amplification module of the data fusion lane change auxiliary system according to the present invention;
FIG. 5 is a circuit diagram of a warning and early warning module of the data fusion lane change auxiliary system of the present invention.
Detailed Description
The technical solution of the present invention is further specifically described below by way of examples with reference to the accompanying drawings.
The invention mainly provides an intelligent vehicle lane change auxiliary method based on data fusion of 77GHz and 24GHz radar sensors. The method mainly comprises the steps that 77GHz millimeter wave radar sensors are arranged in the front left part and the rear left part of an automobile, and 24GHz millimeter wave radar sensors are arranged in the front right part and the rear right part of the automobile for detection. The effective detection distance of the 77GHz millimeter wave radar sensor is long, and can reach 120m at most, but the angle of the detection area is narrow, and is about 30 degrees; and the effective detection distance of the 24GHz millimeter wave radar sensor is short and is only 60m, but the detection area angle is wide and is about 130 degrees. The installation position and the monitorable region of the millimeter wave radar are shown in fig. 1. The detection range of the millimeter wave radar sensors with different frequencies can have a certain overlapping area (a yellow important area in fig. 1) and a non-overlapping area, firstly, primary selection of surrounding vehicle targets is carried out on each sensor, and then, validity check is carried out on the surrounding vehicle targets according to the Kalman filtering principle. And finally, performing decision-level signal integration on the overlapped area by adopting a D-S evidence theory according to the advantages of the sensing ranges of the millimeter wave radar sensors with different frequencies. The detection advantages and characteristics of each sensor are fully integrated, the surrounding environment of the automobile is comprehensively detected, whether the lane changing is in a dangerous state or not is judged in time, a driver is warned through corresponding sound, light and steering intervention, and the signal acquisition, detection and processing flow is shown in fig. 2. By means of the sensor arrangement scheme, remote dangerous vehicle information (an area in a blue wire frame in fig. 1) can be effectively monitored, data fusion is carried out on information collected by sensors with different frequencies, and the defect of data fusion between redundant sensors of the same type is effectively overcome.
The utility model provides an intelligent vehicle multisensor data fusion auxiliary system that trades lane, mainly includes following module: the system comprises millimeter wave radar modules with different frequencies for acquiring information in real time, an amplifier module for amplifying dual-channel radar signals, a radar signal processor module for performing target verification and data fusion processing on the amplified signals, and a warning and early warning module. As shown in fig. 3, the millimeter wave radar modules with different frequencies simultaneously acquire the driving data of the target lane at the front left side and the rear left side of the vehicle and the vehicle in the lane at a long distance (0-120 m), and the driving data of the vehicle at the front right side and the rear right side of the vehicle at a short distance (within 60 m), and send data signals to the dual-channel amplifier module for amplification; then the data is transmitted to the processor module through the CAN bus, and the data is subjected to target vehicle primary selection, target validity check and data fusion in sequence; the processor module generates an early warning control instruction and transmits the early warning instruction to the warning early warning module, and the warning early warning module carries out corresponding acousto-optic and steering intervention early warning according to the received signal.
An intelligent vehicle multi-sensor data fusion lane change auxiliary method is realized through the system, and comprises the following specific steps:
s1: 77GHz millimeter wave radar sensors with far detectable distances and narrow detection areas are respectively arranged at the left front part and the left rear part of the automobile, and 24GHz millimeter wave radar sensors with near detectable distances and wide detection areas are respectively arranged at the right front part and the right rear part of the automobile; through the front left and back left 77GHz sensorsThis lane and target lane are gathered 120 meters internal environment information around, gather vehicle front and back environmental information through right front and right back 24GHz sensor, and the environmental information that the sensor gathered includes: relative velocity v of each target vehicle and the host vehiclerRelative distance xrAnd relative angle
Etc.;
s2: the collected data of the four sensors at the front and the rear of the automobile are input into an amplifier for amplification, and a schematic diagram of the amplifier is shown in FIG. 4. The two paths of sensor signals are respectively IF LC I and IF LC Q, an LMP7716MM/NOPB chip is selected to amplify the signals, and 3.3V power supply voltage is adopted to be matched with a peripheral capacitance resistance device to finish the amplification of the sensor signals. Meanwhile, the two-stage amplification structure has higher external gain, better signal-to-noise ratio and higher bandwidth.
S3: and then, independently preprocessing the data respectively to realize the initial selection of the vehicle target, wherein the specific implementation steps are as follows:
a. filtering a null signal target: the millimeter wave radar can track 64 vehicle targets because data output of the millimeter wave radar is 64 channels, a large number of detected empty channels exist in most cases because no detection target appears, and the data output after being amplified by a radar signal amplifier is the default minimum value, namely the relative speed vr0m/s, relative distance xr0m, relative angle
Therefore, when a certain output meets the above condition, the signal can be judged to be a null signal, and the null signal is filtered;
b. filtering out a static target: in the monitoring environment of the millimeter wave radar with different frequencies, objects approaching to a static state, such as guard rails, trees or roadside pedestrians, must appear, and the most critical danger in lane change assistance is that the objects rapidly move dynamically, so the static objects should be filtered. The relative angle and the relative distance of the static target are basically not different from those of the normal dynamic target, but the absolute speed of the static target is 0 m/s. Therefore, if the angle between the line between the target and the vehicle and the speed direction of the vehicle is α, the relative speed of the stationary target to the vehicle should be close to the vehicle speed, and the following equation should be satisfied:
vr cos α＝-v
that is, the absolute value of the sum of the vehicle speed of the stationary target and the absolute speed of the vehicle should be theoretically equal to 0, but the stationary target is considered to be filtered in consideration of low-speed traveling objects such as roadside pedestrians, and the like, and the minimum value of the error is set to be 1m/s in consideration of the existence of the measurement error, and the stationary target satisfying the following conditions is filtered:
|vr cos α+v|≤1(m/s)
c. filtering out false targets:
the false targets refer to targets which do not have objective correspondence or have extremely short occurrence time and no practical significance, or targets which have poor consistency and large data jumping fluctuation and are caused by accidental interference of the millimeter wave radar, and the targets are false targets. Can be filtered out by the following inequality:
|αr(n+1)-αr(n)|≥2°
|xr(n+1)-xr(n)|≥4m
|vr(n+1)-vr(n)|≥4m/s
n is a sampling point serial number of the millimeter wave radar (the radar describes the motion state of the same target at different time points), and n is (1,2,3,4, 5.);
s4: target validity tests based on Kalman filtering are independently carried out on vehicle targets initially selected by four millimeter wave radar sensors, high-order three-order Kalman filtering method is used for predicting effective vehicle target information in a period, and a state is assumed
Wherein xn,j,vn,j,
Respectively representing the longitudinal relative distance, relative speed and relative acceleration of the valid vehicle object measured during the nth cycle. The target vehicle state prediction for the next cycle is as follows:
in the above formula, T is the scanning period of the millimeter wave radar, and the value is 0.04s, x(n+1)|n、v(n+1)|n、
And respectively representing the longitudinal relative distance, the relative speed and the relative acceleration of the predicted value of the target vehicle in the (n + 1) th period. Comparing and verifying the initially selected vehicle target information of the (n + 1) th period with the effective vehicle target information predicted value of the nth period obtained by the formula, wherein the comparison criterion is as follows:
|xn+1-x(n+1)|n|≤|Δx|
|vn+1-v(n+1)|n|≤|Δv|
in the above formula, xn+1、vn+1、
Respectively representing the longitudinal relative distance, the relative speed and the relative acceleration of the two vehicles in the (n + 1) th period; Δ x, Δ v,
Respectively, represent the maximum error allowed for the comparison criterion. In the present invention, the set error is:
for the primary vehicle target in the n +1 th period, if the primary vehicle target meets the formula, the primary vehicle target is considered to be consistent with the effective vehicle target in the n th period, and target vehicle information is updated; if the above formula is not satisfied, the target inconsistency is handled. And for monitoring the targets in the overlapped area, performing data fusion processing decision by using a D-S evidence theory, and for the targets in the non-overlapped area, assuming that the vehicle targets are effective by default, thereby ensuring the safety to the maximum extent.
S5: independently judging the detected non-coincident areas in front of or behind the automobile to judge whether a slow-speed vehicle is decelerated in a long distance in front of the target lane and whether an accelerated fast-speed vehicle is accelerated in a long distance behind the target lane; the independent data processing unit judges the speed of the vehicle by detecting data of the radar sensor, then differentiates the speed and solves the acceleration to judge whether the vehicle decelerates or accelerates;
s6: monitoring the overlapping area of the front sensor and the rear sensor of the automobile respectively by adopting a D-S evidence theory, namely performing data fusion on two generated independent evidences subjected to target validity check, and ensuring the reliability of detection to the maximum extent;
a. target synthesis: combining the observation results of two independent sensors with different frequencies in the overlapped area into a total output result (ID);
b. target inference: the method logically generates a target vehicle report with certain confidence coefficient according to certain confidence coefficient to obtain the observation result of the sensor and deduce the observation result, and the observation result of the sensor is expanded into the target vehicle report;
c. target updating: the two different frequency sensors themselves are typically random errors, so a set of consecutive reports from the same frequency sensor sufficiently independent in time is more reliable than any single report. Thus, prior to reasoning and synthesis of two different frequency sensors, the observed data of the respective frequency sensors are combined (updated).
S7: the result processed by the data fusion control unit is transmitted to a warning and early warning unit;
s8: and the warning early warning unit carries out sound, flash and steering reverse intervention early warning according to the judgment result. PoliceThe early warning schematic diagram is shown in fig. 5, whether a display chip of an LED _ BUSY pin is BUSY (during power-on), the LED _ DETECT interface is externally connected with two indicator lights, meanwhile, the DETECT _ SIGNAL end outputs different buzzer sound frequency according to the judgment of the danger degree, the DETECT _ OUT output SIGNAL is similar to the DETECT _ SIGNAL, different frequencies are output according to the emergency degree of the situation, and in order to prevent a steering interface ground loop or noise injection, isolated digital output is used to ensure the stability of the output SIGNAL. According to the relative distance xrAnd relative velocity vrJudging whether the state is a dangerous state, if the state is in a safe state, displaying a green lamp, and not giving an alarm by a buzzer; if the alarm is in the warning state, the alarm is changed into a flashing yellow light, and the buzzer rings once every two seconds; if the state is a dangerous state, the state is converted into a red light state, and the buzzer rings once per second; if the driver does not see or hear the prompting information of lane change assistance in time, and then the lane change is forcibly carried out, besides sound or flash alarm, corresponding torque intervention is carried out on the steering through a steering interface feedback unit connected into the power steering module through frequency, and the driver is timely reminded not to make a lane change behavior at the moment.
The intelligent vehicle multi-sensor data fusion lane change auxiliary system is an intelligent early warning system applied to a highway and used for preventing collision when a vehicle changes lanes, and the intelligent early warning system can monitor far and near dangerous vehicles in front and behind the vehicle through millimeter wave radars with different frequencies, and provides accurate lane change information and lane change danger prompt for the vehicle lane change. The lane change auxiliary system multi-sensor data fusion is to analyze and judge the target vehicle information in the environment by means of data acquisition, data processing, data fusion and the like according to the far and near environment information of the front and the rear of the automobile, such as the relative speed, the relative distance, the direction angle and the like of a far and rear target running vehicle and the vehicle, acquired by two groups of radar sensors with different frequencies, so that the danger degree of changing the road is accurately given, and effective basis and timely lane change danger prompt are provided for drivers to change the lane change behavior.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be able to cover the technical scope of the present invention within the technical scope of the present invention, and the technical solution of the present invention and the inventive concept of the present invention are equivalent to or changed within the technical scope of the present invention.
Claims (6)
1. The lane change auxiliary method based on the intelligent vehicle multi-sensor data fusion lane change auxiliary system comprises the following steps: the system comprises radars with different frequencies, a signal amplification unit, a data processing unit, a data fusion control unit and a warning and early warning unit, wherein the radars with different frequencies are used for acquiring the front and rear environmental information of the vehicle in real time; the radar signal acquisition areas with different frequencies comprise non-overlapping areas and overlapping areas; the radars with different frequencies are a 77GHz millimeter wave radar sensor and a 24GHz millimeter wave radar sensor; the number of the 77GHz millimeter wave radar sensors is two, and the two sensors are arranged at the left front part and the left rear part of the automobile; two 24GHz millimeter wave radar sensors are arranged at the front right and the rear right of the automobile; the method is characterized by comprising the following specific steps:
s1: collecting the environmental information of the front and the back of the lane where the vehicle is located and the target lane by using a 77GHz sensor at the front and the back of the left, and collecting the environmental information of the front and the back of the vehicle by using a 24GHz sensor at the front and the back of the right;
s2: the method comprises the following steps of respectively and independently preprocessing four collected sensor data in front of and behind the automobile to realize the initial selection of a vehicle target;
s3: target validity inspection based on Kalman filtering is independently carried out on vehicle targets preliminarily selected by the four millimeter wave radar sensors;
s4: independently judging the non-coincident region detected in front of or behind the automobile to judge whether a slow-speed vehicle is decelerated in a long distance in front of the target lane and whether an accelerated fast-speed vehicle is accelerated in a long distance behind the target lane;
s5: respectively carrying out data fusion on the superposed areas monitored by the two sensors in front of and behind the automobile, namely two independent evidences which are generated and are subjected to target validity test, by adopting a D-S evidence theory;
s6: transmitting the processed results of the steps S4 and S5 to a warning and early warning unit;
s7: and the warning early warning unit carries out sound, flash and steering reverse intervention early warning according to the judgment result.
2. The lane change assisting method according to claim 1, wherein the environment information in step S1 includes: relative velocity v of each target vehicle and the host vehiclerRelative distance xrAnd relative angle
3. The lane-change assisting method according to claim 1, wherein the preprocessing in step S2 is performed by filtering a null signal object, filtering a stationary object and filtering a false object.
4. The lane change assisting method according to claim 1, wherein step S3 includes:
step S3.1: hypothetical states
Wherein xn,j,vn,j,
Respectively representing the longitudinal relative distance, the relative speed and the relative acceleration of the effective vehicle target measured in the nth period;
step S3.2: the target vehicle state for the next cycle is predicted as follows:
in the above formula, T is the scanning period of the millimeter wave radar, x(n+1)|n、v(n+1)|n、
Respectively representing the longitudinal relative distance, the relative speed and the relative acceleration of the predicted value of the target vehicle in the (n + 1) th period;
step S3.3: comparing and verifying the initially selected vehicle target information of the (n + 1) th period with the effective vehicle target information predicted value of the nth period obtained by the formula, wherein the comparison criterion is as follows:
|xn+1-x(n+1)|n|≤|Δx|
|vn+1-v(n+1)|n|≤|Δv|
in the above formula, xn+1、vn+1、
Respectively representing the longitudinal relative distance, the relative speed and the relative acceleration of the two vehicles in the (n + 1) th period; Δ x, Δ v,
Respectively representing the maximum error allowed for the comparison criterion;
step S3.4: for the primary vehicle target in the n +1 th period, if the formula (2) is satisfied, the primary vehicle target is considered to be consistent with the effective vehicle target in the n th period, target vehicle information is updated on the target vehicle, otherwise, target inconsistency processing is performed, and for the target in the monitored overlapping area, data fusion processing is performed by using a D-S evidence theory to determine whether the target is a dangerous vehicle; for the non-coincident region target, the vehicle target is assumed to be valid by default, and the safety is guaranteed to the maximum extent, namely if the results of the judgment of the nth period and the (n + 1) th period of the non-coincident region are that one is a dangerous vehicle and the other is a non-dangerous vehicle, the non-coincident region is determined to be a dangerous vehicle.
5. The lane change assisting method according to any one of claims 1 to 4, wherein the fusion process in step S5 is performed by the following steps:
a. target synthesis: the D-S evidence theory derives basic probability distribution functions for evidence sources from two independent sensors, then a Dempster combination rule in the D-S evidence theory calculates a new basic probability distribution function which reflects fusion information and is generated by the joint action of the two evidences, and a total output result is synthesized according to the probability distribution function, namely whether a dangerous vehicle target is determined or not;
b. target inference: according to a probability distribution function generated by a D-S evidence theory, a target vehicle report with certain confidence coefficient is formed, namely whether a dangerous vehicle really exists or not is judged, and whether the dangerous vehicle really exists or not is judged;
c. target updating: random errors generally exist in the two different frequency sensors, so that a group of reports generated by the two independent same-frequency sensors in time is more reliable than a report generated by any one sensor; thus, prior to inferencing and synthesis of two different frequency sensors, the observed data of the respective frequency sensors are combined.
6. The lane change support method according to claim 1, wherein when the road is changed in step S7, the intelligently provided lane change information is used to alert the driver by a corresponding sound, light or steering intervention warning; according to the relative distance x between vehiclesrAnd relative velocity vrJudging whether the vehicle is in a dangerous state, if so, displaying a green lamp, and not giving an alarm by the buzzer; if the alarm is in the warning state, the alarm is changed into a flashing yellow light, and the buzzer rings once every two seconds; if the state is a dangerous state, the state is converted into a red light state, and the buzzer rings once per second; if the driver is absentThe lane changing assisting device can timely see or hear the prompting information of lane changing assistance, and then forcibly changes lanes, and besides sound or flash alarm, the device can also perform corresponding torque intervention on steering through a steering interface feedback unit connected to the steering assisting module, and timely remind a driver of not making a lane changing behavior at the moment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010127272.3A CN111532274B (en) | 2020-02-28 | 2020-02-28 | Intelligent vehicle lane change auxiliary system and method based on multi-sensor data fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010127272.3A CN111532274B (en) | 2020-02-28 | 2020-02-28 | Intelligent vehicle lane change auxiliary system and method based on multi-sensor data fusion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111532274A CN111532274A (en) | 2020-08-14 |
| CN111532274B true CN111532274B (en) | 2021-04-27 |
Family
ID=71969173
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010127272.3A Active CN111532274B (en) | 2020-02-28 | 2020-02-28 | Intelligent vehicle lane change auxiliary system and method based on multi-sensor data fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111532274B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112394726B (en) * | 2020-10-20 | 2023-08-04 | 自然资源部第一海洋研究所 | Unmanned ship obstacle fusion detection method based on evidence theory |
| CN113093191B (en) * | 2021-03-31 | 2022-07-05 | 武汉大学 | Road vehicle detection system based on millimeter wave radar |
| CN113178081B (en) * | 2021-05-17 | 2022-05-03 | 中移智行网络科技有限公司 | Vehicle immission early warning method and device and electronic equipment |
| CN113791410B (en) * | 2021-08-20 | 2023-10-24 | 北京市公安局公安交通管理局 | Road environment comprehensive cognition method based on multi-sensor information fusion |
| CN113895439B (en) * | 2021-11-02 | 2022-08-12 | 东南大学 | Automatic driving lane change behavior decision method based on probability fusion of vehicle-mounted multisource sensors |
| CN115407273B (en) * | 2022-08-29 | 2024-01-05 | 哈尔滨工业大学（威海） | Monitoring, reminding and alarming device and method for specific security area |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102303605A (en) * | 2011-06-30 | 2012-01-04 | 中国汽车技术研究中心 | Multi-sensor information fusion-based collision and departure pre-warning device and method |
| CN202163431U (en) * | 2011-06-30 | 2012-03-14 | 中国汽车技术研究中心 | Collision and traffic lane deviation pre-alarming device based on integrated information of sensors |
| CN103065501A (en) * | 2012-12-14 | 2013-04-24 | 清华大学 | Automobile lane changing early-warning method and lane changing early-warning system |
| CN106708040A (en) * | 2016-12-09 | 2017-05-24 | 重庆长安汽车股份有限公司 | Sensor module of automatic driving system, automatic driving system and automatic driving method |
| CN106740838A (en) * | 2016-12-10 | 2017-05-31 | 江门市蓬江区弘亿电子科技有限公司 | A kind of vehicle risk early warning system |
| CN206734295U (en) * | 2016-12-21 | 2017-12-12 | 驭势科技（北京）有限公司 | A kind of detection system for being used to detect Vehicle target and its application |
| CN107512263A (en) * | 2017-04-05 | 2017-12-26 | 吉利汽车研究院（宁波）有限公司 | A kind of lane change blind area danger accessory system |
| CN108106629A (en) * | 2017-12-07 | 2018-06-01 | 风度（常州）汽车研发院有限公司 | Evade the path guide method to knock into the back, device and Vehicular intelligent driving assistance system |
-
2020
- 2020-02-28 CN CN202010127272.3A patent/CN111532274B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102303605A (en) * | 2011-06-30 | 2012-01-04 | 中国汽车技术研究中心 | Multi-sensor information fusion-based collision and departure pre-warning device and method |
| CN202163431U (en) * | 2011-06-30 | 2012-03-14 | 中国汽车技术研究中心 | Collision and traffic lane deviation pre-alarming device based on integrated information of sensors |
| CN103065501A (en) * | 2012-12-14 | 2013-04-24 | 清华大学 | Automobile lane changing early-warning method and lane changing early-warning system |
| CN106708040A (en) * | 2016-12-09 | 2017-05-24 | 重庆长安汽车股份有限公司 | Sensor module of automatic driving system, automatic driving system and automatic driving method |
| CN106740838A (en) * | 2016-12-10 | 2017-05-31 | 江门市蓬江区弘亿电子科技有限公司 | A kind of vehicle risk early warning system |
| CN206734295U (en) * | 2016-12-21 | 2017-12-12 | 驭势科技（北京）有限公司 | A kind of detection system for being used to detect Vehicle target and its application |
| CN107512263A (en) * | 2017-04-05 | 2017-12-26 | 吉利汽车研究院（宁波）有限公司 | A kind of lane change blind area danger accessory system |
| CN108106629A (en) * | 2017-12-07 | 2018-06-01 | 风度（常州）汽车研发院有限公司 | Evade the path guide method to knock into the back, device and Vehicular intelligent driving assistance system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111532274A (en) | 2020-08-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111532274B (en) | Intelligent vehicle lane change auxiliary system and method based on multi-sensor data fusion | |
| CN106428001B (en) | A kind of lane change method for early warning and system for vehicle | |
| CN107512263A (en) | A kind of lane change blind area danger accessory system | |
| CN103112451B (en) | A kind of Automobile automatic collision avoidance system and method | |
| US8718916B2 (en) | Object detecting device, and object detecting method | |
| CN106448190B (en) | Real-time monitoring and early warning device and method for traffic flow around self-vehicle on highway | |
| CN105480229A (en) | Intelligent lane change assisting system and method based on information fusion | |
| CN104290745A (en) | Semi-automatic driving system for vehicle and method thereof | |
| CN102963361A (en) | Method of operating a vehicle safety system | |
| CN102498413A (en) | Vehicle having active blind spot lighting and method | |
| CN109515435A (en) | The method and device that collision prevention of vehicle is reminded | |
| CN106428003B (en) | Early warning device and method for lane departure of highway vehicles in bad weather | |
| CN106740838A (en) | A kind of vehicle risk early warning system | |
| CN107180533A (en) | Road method for early warning and device | |
| CN114155707A (en) | Intelligent traffic safety driving visual warning system and method | |
| CN111469835A (en) | Vehicle auxiliary driving system and method based on topological map | |
| CN113470433A (en) | Vehicle inner wheel difference region danger early warning method and system based on V2I, vehicle and roadside equipment | |
| CN206671554U (en) | A kind of anti-car crass based on FUSION WITH MULTISENSOR DETECTION early warning system by all kinds of means | |
| CN205417368U (en) | Highway driving safety precaution device based on ITS | |
| CN105270258A (en) | Automotive steering safety assistance system | |
| CN106740461B (en) | Side-turning early warning device and method for hinged seismic source vehicle | |
| CN111038380A (en) | Forward collision early warning method and system | |
| CN113183876A (en) | Early warning prompt system for preventing vehicle collision | |
| CN113525401A (en) | Early warning method for assisting automobile driving and millimeter wave radar system | |
| CN113470432A (en) | Vehicle inner wheel difference region danger early warning method and system based on V2V and vehicle |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |