CN115482685A - Vehicle early warning control method and system and vehicle - Google Patents
Vehicle early warning control method and system and vehicle Download PDFInfo
- Publication number
- CN115482685A CN115482685A CN202210905252.3A CN202210905252A CN115482685A CN 115482685 A CN115482685 A CN 115482685A CN 202210905252 A CN202210905252 A CN 202210905252A CN 115482685 A CN115482685 A CN 115482685A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- early warning
- information
- fusion
- driver
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 230000004927 fusion Effects 0.000 claims abstract description 80
- 230000008447 perception Effects 0.000 claims abstract description 46
- 230000004913 activation Effects 0.000 claims abstract description 18
- 230000008569 process Effects 0.000 claims abstract description 17
- 230000006870 function Effects 0.000 claims abstract description 15
- 230000003213 activating effect Effects 0.000 claims abstract description 8
- 230000009467 reduction Effects 0.000 claims description 8
- 238000012545 processing Methods 0.000 description 11
- 238000007499 fusion processing Methods 0.000 description 9
- 230000001133 acceleration Effects 0.000 description 8
- 238000004891 communication Methods 0.000 description 8
- 238000001914 filtration Methods 0.000 description 7
- 239000011159 matrix material Substances 0.000 description 5
- 238000005259 measurement Methods 0.000 description 5
- 238000001514 detection method Methods 0.000 description 4
- 238000005070 sampling Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000001360 synchronised effect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000035484 reaction time Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013213 extrapolation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/0112—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from the vehicle, e.g. floating car data [FCD]
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/0116—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from roadside infrastructure, e.g. beacons
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
Abstract
The invention relates to the technical field of vehicle early warning, and discloses a vehicle early warning control method, a system and a vehicle, which comprises the following steps: s1: acquiring TSR identification information, judging whether the TSR identification information belongs to an activation scene for activating a vehicle early warning function, if so, executing S2, otherwise, terminating the process; s2: after the vehicle early warning function is activated, the vehicle enters a sensing area to perform vehicle road sensing fusion to obtain vehicle road sensing fusion information; s3: whether an early warning instruction needs to be issued to a driver or not is judged through the vehicle road perception fusion information, if yes, the vehicle is controlled to issue the early warning instruction to the driver, and if not, the process is terminated. The method comprises the steps of pre-storing an activation scene on a vehicle early warning control system, judging whether a vehicle activates a related scene flag or not through the acquired TSR identification information, and further acquiring a more detailed traffic information state in front through vehicle road perception fusion information after the scene flag is determined to be activated, so that the vehicle can acquire a traffic light or traffic signboard information state in front in advance.
Description
Technical Field
The invention relates to the technical field of vehicle early warning, in particular to a vehicle early warning control method and system and a vehicle.
Background
Safe driving is the first rigid requirement of automobile users, and vehicle collision is a main factor causing traffic accidents during driving. For example, when passing through an intersection, a vehicle in front blocks a traffic light or a traffic signboard, or the traffic light and the traffic signboard are blurred and confused when encountering the intersection, or due to limited vehicle perception capability, several scenes in which information of the traffic light and the traffic signboard in front cannot be accurately acquired are the main reasons for collision of the vehicle.
In the prior art, the traffic information of a front intersection is obtained in advance through the vehicle-mounted TSR information broadcasting function of a single vehicle, but the current information of a real intersection cannot be transmitted to a vehicle end and fused with the vehicle end information in time, so that the real and effective vehicle running environment information cannot be obtained, and an accurate vehicle running early warning signal cannot be transmitted to a driver.
Disclosure of Invention
The invention provides a vehicle early warning control method, a vehicle early warning control system and a vehicle, and aims to solve the problem that in the prior art, accidents occur to the vehicle due to the fact that real and effective vehicle running environment information cannot be obtained and accurate early warning signals cannot be transmitted.
The technical content of the invention comprises:
a vehicle early warning control method comprises the following steps:
s1: acquiring TSR identification information, judging whether the TSR identification information belongs to an activation scene for activating a vehicle early warning function, if so, executing S2, otherwise, terminating the process;
s2: after the vehicle early warning function is activated, the vehicle enters a sensing area to perform vehicle road sensing fusion to obtain vehicle road sensing fusion information;
s3: whether an early warning instruction needs to be issued to a driver or not is judged through the vehicle road perception fusion information, if yes, the vehicle is controlled to issue the early warning instruction to the driver, and if not, the process is terminated.
Further, the S1 includes:
the activation scenario includes:
the traffic light is shielded in the TSR identification;
traffic light fuzzy or confusing scenes during TSR identification;
traffic signs obscure or confuse scenes during TSR recognition.
Further, the S2 includes:
the vehicle road perception fusion information comprises combination of vehicle end perception fusion information and road side perception fusion information.
Further, the S3 includes: judging whether an early warning instruction needs to be issued to a driver or not through the vehicle road perception fusion information, and obtaining a judgment result;
the judgment result comprises:
when the current traffic light state is a green light, calculating whether the vehicle can safely pass through the intersection safety line or not by combining the current vehicle motion state;
when the traffic light of the front side is a red light or a yellow light, calculating the early warning distance of the vehicle by combining the current vehicle motion state;
and when the current traffic signboard information is the speed limit or other specific areas needing speed reduction, calculating whether the vehicle exceeds the highest speed limit value or not by combining the current vehicle motion state.
Further, when the traffic light state of the front side is green, calculating whether the vehicle can safely pass through the intersection safety line by combining the current vehicle motion state, including:
if the vehicle can not safely pass through the intersection safety line, controlling the vehicle to issue an early warning instruction to a driver;
if the vehicle can safely pass through the intersection safety line, the process is terminated, and the driver normally runs.
Further, when the traffic signboard information in front is the speed limit or other specific areas needing speed reduction, the current vehicle motion state is combined to calculate whether the vehicle exceeds the highest value of the speed limit, including:
if the vehicle does not exceed the maximum speed limit value, controlling the early warning system to issue a normal driving instruction to the driver;
and if the vehicle exceeds the highest speed limit value, controlling the early warning system to issue a driving early warning instruction to the driver.
The invention also provides a vehicle early warning control system, which realizes the steps of the vehicle early warning control method, and comprises the following steps:
an acquisition unit configured to acquire TSR identification information;
the first judgment unit is used for judging whether the TSR identification information belongs to an activation scene for activating the vehicle early warning function;
the sensing unit is used for acquiring the vehicle road sensing fusion information of the vehicle;
the second judgment unit is used for judging whether an early warning instruction needs to be issued to the driver or not through the vehicle road perception fusion information;
and the early warning unit is used for controlling the vehicle to issue an early warning instruction to the driver.
Further, the sensing unit includes:
the road side unit is used for acquiring road side end fusion perception information;
and the vehicle-mounted unit is used for acquiring the vehicle-end fusion perception information.
The invention also provides a vehicle, and the steps of the vehicle early warning control method are realized.
The beneficial effects of the invention at least comprise: according to the invention, the activation scene is prestored on the vehicle early warning control system, whether the vehicle activates the related scene flag is judged through the acquired TSR identification information, after the scene flag is determined to be activated, the more detailed traffic information state in front is further acquired through the vehicle road perception fusion information, so that the vehicle can acquire the information state of the traffic light or the traffic signboard in front in advance, the traffic environment is sensed and judged in advance, and whether an early warning instruction, such as related early warning instructions of warning, active deceleration or emergency braking and the like, needs to be issued to a driver or not is judged according to the judgment, so that the purpose of safe driving of the vehicle is achieved.
Drawings
Fig. 1 is a schematic flow structure diagram of a vehicle early warning control method provided in embodiment 1 of the present invention.
Fig. 2 is a schematic view of a flow architecture of the roadside awareness fusion algorithm provided in embodiment 1 of the present invention.
Fig. 3 is a schematic view of a flow architecture of a vehicle-road-awareness fusion algorithm provided in embodiment 1 of the present invention.
Fig. 4 is a schematic flow structure diagram of a vehicle early warning control system provided in embodiment 2 of the present invention.
Fig. 5 is a schematic flow structure diagram of a vehicle early warning implementation method in embodiment 3 of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without inventive step based on the embodiments of the present invention, are within the scope of protection of the present invention.
Example 1
Referring to fig. 1 to 3, the present invention provides a vehicle early warning control method, including the following steps:
s1: acquiring TSR identification information, judging whether the TSR identification information belongs to an activation scene for activating a vehicle early warning function, if so, executing S2, otherwise, terminating the process;
s2: after the vehicle early warning function is activated, the vehicle enters a sensing area to perform vehicle road sensing fusion to obtain vehicle road sensing fusion information;
s3: whether an early warning instruction needs to be issued to a driver or not is judged through the vehicle road perception fusion information, if yes, the vehicle is controlled to issue the early warning instruction to the driver, and if not, the process is terminated.
Further, the S1 includes:
the activation scenario includes:
the traffic light is shielded in TSR identification;
traffic light fuzzy or confusable scenes during TSR identification;
traffic signs obscure or confuse scenes during TSR recognition.
Further, the S2 includes:
the vehicle road perception fusion information is the combination of vehicle end perception fusion information and road side perception fusion information.
Further, the S3 includes: judging whether an early warning instruction needs to be issued to a driver or not through the vehicle road perception fusion information, and obtaining a judgment result;
the judgment result comprises:
when the traffic light state at the front side is green, calculating whether the vehicle can safely pass through a safety line at the intersection or not by combining the current vehicle motion state;
when the traffic light of the front side is a red light or a yellow light, calculating the early warning distance of the vehicle by combining the current vehicle motion state;
and when the current traffic signboard information is the speed limit or other specific areas needing speed reduction, calculating whether the vehicle exceeds the highest speed limit value or not by combining the current vehicle motion state.
Further, when the traffic light state of the current side is green, calculating whether the vehicle can safely pass through the intersection safety line by combining the motion state of the current vehicle, including:
if the vehicle can not safely pass through the intersection safety line, controlling the vehicle to issue an early warning instruction to a driver;
if the vehicle can safely pass through the intersection safety line, the process is terminated, and the driver normally runs.
Further, when the traffic signboard information in front is the speed limit or other specific areas needing speed reduction, the current vehicle motion state is combined to calculate whether the vehicle exceeds the highest value of the speed limit, including:
if the vehicle does not exceed the maximum speed limit value, controlling the early warning system to issue a normal driving instruction to the driver;
and if the vehicle exceeds the maximum speed limit value, the control early warning system issues a driving early warning instruction to the driver.
In the embodiment, the state information of the traffic lights or the information of the traffic signs is acquired by the road side unit and sent to the vehicle-mounted unit, and the communication coverage range of the road side unit can reach 200-300 meters, so that the early warning distance is mainly considered when the vehicle passes through the traffic light intersection or the traffic signs under the state of complying with the traffic regulations and the vehicle runs at risk and sends out the vehicle running early warning information.
The activation scene of the vehicle early warning control method comprises three conditions, when a traffic light of the intersection is shielded in TSR recognition, or when the traffic light of the intersection is fuzzy or easily confused in TSR recognition, whether the vehicle early warning is mainly considered in two aspects: firstly, traffic light state information and secondly, early warning distance.
Firstly, judging the traveling direction of a lane where a vehicle is located at present, then judging the state of a traffic light through V2X information, when the obtained traffic light is in a red/yellow light state, comprehensively judging the motion state of the vehicle and the traffic light information, obtaining the current early warning distance of the vehicle, reminding a driver after the vehicle enters the early warning distance, and after receiving the reminding, actively taking braking measures and implementing deceleration measures.
Calculating the distance traveled by the vehicle before the vehicle can be stopped at a low deceleration and a low deceleration under an ideal state and the temperature is reduced to a stop line, namely the early warning distance of the vehicle, and calculating the early warning distance by the following formula:
wherein v is SV At an initial vehicle speed, t svd ,t rbr Respectively driver reaction time and brake system response time, a 1 The deceleration is a mild braking deceleration and a vector value, the acceleration is a positive value, and the deceleration is a negative value; d pre To warn of safe distances. Since the vehicle decelerates to a stop (speed 0 km/h), the-v in the formula 2 sv Is 0 2 -v 2 sv The process is simplified.
When get v SV ＝72km/h，t svd ＝0.5s，t rbr ＝0.6s，a 1 ＝0.2g，b pre If =25m, S at that time can be calculated 0 =149m. Namely, after the vehicle enters the communication range of the road side unit, the motion state of the vehicle and the traffic light information are comprehensively judged, and after the vehicle enters the early warning distance S 0 Then, an early warning instruction is issued to the driver, and the driver actively takes braking measures after receiving the early warning instruction, so that the method is practicalApplying a deceleration.
When the acquired traffic light is in a green light state, whether the green light is in a countdown state needs to be further judged, if the green light starts to count down, whether the vehicle can safely pass through the intersection is further judged, if the vehicle cannot pass through the intersection, the vehicle needs to be safely stopped outside a stop line and early warned in time, and if the vehicle does not normally pass through the intersection, the vehicle needs to be stopped outside the stop line and early warned in time.
When the vehicle cannot pass through the intersection before the green light is finished, the judgment is made according to the vehicle running information, and whether the vehicle can pass through the intersection is calculated by the formula (2), namely:
if TTC > t sv If so, the vehicle normally passes; if TTC < t sv And if so, the vehicle gives out early warning, and the early warning distance is calculated by referring to the formula (1). Wherein d is sv Distance of the host car to the safety line, v sv Is the current speed of the host vehicle, t sv The time when the host vehicle reaches the safety line according to the current speed is given.
When the last of the activation scenarios occurs: traffic signs obscure or confuse scenes during TSR recognition.
When meeting this kind of condition, judge whether need send the early warning to the driver, two aspects are mainly considered: firstly, traffic signboard information and secondly, early warning distance are obtained, firstly, early-stage measurement and positioning are carried out on the traffic signboard through a road side unit, then, the traffic signboard information and the traffic signboard position are input into the road side unit, and the traffic signboard information and the traffic signboard position are sent to an on-board unit.
The traffic signboard information mainly comprises a speed limit sign, a construction sign, a school area sign and the like. At this time, the vehicle speeds v should be compared sv And sending corresponding early warning instructions to the vehicle according to the speed limit marking information. And if the speed of the vehicle is greater than the speed limit information, the vehicle is gently decelerated to the highest speed limit to pass through the road section, otherwise, the vehicle normally runs. The distance that the vehicle decelerates to the highest speed limit is calculated by equation (3):
wherein S is lim Distance required for vehicle deceleration to maximum speed limit, v lim For the highest speed limit of the traffic signboard, t svd 、t rbr Respectively driver reaction time and brake system response time, a 1 The deceleration is mild braking, is vector value, the acceleration is positive value, and the deceleration is negative value.
When get v lim ＝72km/h，t svd ＝0.5s，t rbr ＝0.6s，a 1 ＝0.2g，v lim (ii) =30km/h means that S can be calculated lim ＝131m。
Namely, after the vehicle enters the communication range of the road side unit, the motion state of the vehicle and the information of the traffic signboard are comprehensively judged, and when the vehicle enters the early warning distance S lim And then, issuing an early warning instruction to the driver, and actively taking a braking measure after the driver receives the early warning instruction of the vehicle to realize the safe passing when the speed is reduced to the specified speed.
The vehicle comprehensively judges the vehicle through the vehicle perception fusion information, and then determines whether the vehicle needs to issue an early warning instruction or not through a judgment result. When the vehicle sends the traffic light information or the traffic signboard information acquired by the road side unit to the vehicle-mounted unit, the vehicle is combined with the vehicle motion state and the vehicle motion environment acquired by the vehicle-mounted unit to acquire more accurate traffic information. The method comprises the steps that dangerous targets sensed by a vehicle end are obtained through vehicle end fusion, a roadside unit fuses the targets sensed by the roadside and broadcasts vehicles, the sensed targets of the vehicle end and the received roadside sensed targets are synchronized in time and space, and finally, a most dangerous target is output according to vehicle side fusion sensing and is supplied to an early warning unit to judge whether early warning is needed or not.
Specifically, the road side unit fuses the sensed traffic light information or traffic signboard information, the vehicle-mounted unit fuses the sensed vehicle motion state and the vehicle motion environment, and finally the road side fusion information of the road side unit is fused with the vehicle side fusion information of the vehicle-mounted unit to obtain more accurate traffic information to be supplied to the vehicle to judge whether early warning is needed or not.
The target after the vehicle-end fusion processing mainly comprises information including a timestamp, a target ID, coordinates (the distance from the target to the center line of the vehicle head), and a relative speed V x 、V y Acceleration A x And the like. Receiving a vehicle end perception target result at a vehicle controller, firstly calibrating the space positions of a camera and a radar, and then carrying out time synchronization on data of the camera and the radar by using a time synchronization method based on Lagrange interpolation; after the data of the camera and the radar are subjected to space-time synchronization, targets from different sensors need to be paired according to a certain rule, in the embodiment, a Global Nearest Neighbor (GNN) algorithm is adopted to match the targets, when a performance function E of the GNN algorithm is in a range of a threshold value from 0 to Eth and an E value is minimum, the GNN algorithm and the GNN algorithm are considered to be the same target, then a kalman filtering method is used to perform data tracking on the matched target and the target which is not matched with the camera/radar, and meanwhile, a weighting method is used to fuse the matched target data. And finally, selecting the CIPV/P target, the target which is not matched with the camera, the CIPV/P target converted into the absolute position and the target parameter which is not matched with the camera converted into the absolute position by using a designed rule method as the input of the sensing unit and the early warning unit.
The vehicle-end fusion process comprises the following steps:
1. preprocessing different information sensed by different sensors, including processing X, Y, vx, vy, ax and Ay of the target measured by the sensors, and removing an invalid target, an opposite target, an empty target and the like;
2. converting target data acquired by different sensors into the same coordinate system for space synchronization, and synchronizing the target data X, Y, vx, vy, ax and Ay acquired by the sensors in different sampling periods to the same time point for time synchronization by using a space-time synchronization algorithm, namely a Lagrange interpolation method;
the lagrange interpolation method includes: and predicting radar data by using a constant acceleration model, then using the time of a camera as the input of a Lagrange interpolation method, and interpolating target parameters measured by the radar at the k-1 moment, the k moment and the k +1 moment by using a Lagrange interpolation formula, thereby obtaining the radar measured value which is the same as the camera moment.
The radar sampling period is faster than the camera sampling period, so the camera sampling period is used as a reference.
3. Judging whether the data measured by different sensors belong to the same target by using a correlation matching algorithm, wherein the embodiment adopts a GNN algorithm;
the GNN algorithm includes: 1) Using the camera measurement value and the radar measurement value after the time-space synchronization as the input of the GNN algorithm; 2) Using designed weighting function formulas
Calculating a performance index, wherein e in the formula is represented as an error; 3) When the performance index meets the related threshold, judging that the data measured by different sensors are the same target;
4. and performing fusion tracking. The target fusion is that the state parameters of the same target are provided by different sensors at the same time, and the two sets of parameters have certain deviation, so that fusion processing needs to be performed on the target parameters measured by the different sensors by using a fusion algorithm, and the target is fused by using a Kalman filtering algorithm in the embodiment; the tracking is to estimate the future motion state of the target by using a motion model of the target and observation data of the target, the motion model of the target used in the embodiment is a constant acceleration motion model, and the state quantity is (X, Y, V) x 、V y 、A X 、A y ) T Wherein X is a longitudinal distance, Y is a transverse distance, vx is a longitudinal speed, vy is a transverse speed, ax is a longitudinal acceleration, and Ay is a transverse acceleration;
processing by a Kalman filtering algorithm: by using time synchronized camera measurements (X, Y, V) x 、V y 、A X 、A y ) T Radar measurements (X, Y, V) x 、V y 、A X 、A y ) T As input of Kalman filtering, predicting a target state; then theUpdating an error covariance matrix P by using the state matrix F; calculating Kalman filtering gain K by using an error covariance matrix P, an observation matrix H and a covariance matrix R of sensor noise; (X, Y, V x 、V y 、A X 、A y ) T Updating the measured value X; finally, the covariance error P is updated.
5. And (4) outputting the dangerous target. By using a regular algorithm and a currently obtained fusion result of different sensor targets, the most dangerous target type and the most dangerous target state are screened from the targets and converted into the target state under an absolute coordinate system, so that important reference information is provided for a subsequent early warning unit and a sensing unit.
For the road side sensing algorithm, in the embodiment, only the target level fusion sensing algorithm of the camera similar to the vehicle end and the millimeter wave radar is considered, so that the sensor such as the camera at the road side and the millimeter wave radar is required to provide target level data of the detection result. The existing road side camera generally does not have the function of outputting a target level result, and the target level result refers to information such as a target position, speed and the like, so that a corresponding image detection algorithm needs to be matched to realize target level result output. The embodiment meets the image processing requirement of the camera, needs reasonably configured hardware and algorithm software, and ensures that the image processing delay of the road side perception algorithm is controlled within 70 ms.
Aiming at the characteristics of the road side camera and the delay of single target and multi-target detection, the maximum delay value is selected according to the single target delay time and the multi-target delay time, and the data reading consistency is ensured by transmitting the detection data of the target.
Under the above premise, the road side fusion senses that the received data is target-level result data output by the road side camera and the millimeter wave radar, and includes information such as target ID and type, position, speed, and the like.
The roadside fusion process comprises:
for a conventional fusion perception algorithm process, firstly, data preprocessing is needed, and empty targets and invalid targets are removed; according to the reference vehicle-end fusion method, absolute time interpolation matching is adopted to perform time synchronization of the camera sensing result and the radar sensing result; similar to temporal alignment, spatial alignment also employs absolute position information. The partial timestamp information and the longitude and latitude positioning information can be provided by the road side unit, and the longitude and latitude coordinates of the road side unit can be set according to absolute positioning accuracy when the road side system is calibrated, but the whole system needs to meet the accuracy requirement (using RTK positioning as a position reference). And timestamp information, wherein a camera shutter is triggered by the millimeter waves at the road side, so that the time consistency of the two devices is ensured, and the timestamp adopts sensor time. The space is synchronized through roadside absolute positioning information. After the space-time synchronization is finished, GNN correlation matching and Kalman filtering weighting fusion are still adopted, and finally fused target information is output. The target after the road side fusion processing is the same as the target after the vehicle end fusion processing, and mainly comprises a timestamp, a dangerous target ID, coordinates, a relative speed, a relative acceleration and the like.
And packaging the target result subjected to the road side fusion processing into corresponding formatted data in the edge computing node according to the format requirement of the road side unit, sending the formatted data to the road side unit by using a communication protocol specified by the road side unit, and broadcasting by the road side unit. The vehicle-mounted unit receives the broadcast information of the road side unit within the communication range, and transmits the related information to the vehicle controller for subsequent vehicle-road fusion perception processing.
And aiming at the analysis of the vehicle-mounted controller on the vehicle-mounted unit, data analysis is carried out according to an analysis method provided by a supplier, so that the vehicle-mounted controller can analyze, read and process the data of the vehicle-mounted unit through a developed analysis program.
The input of the vehicle-road perception fusion algorithm is a final vehicle-end fusion perception result output after vehicle-end fusion perception processing and a final roadside fusion perception result output after roadside fusion perception processing, and in the vehicle-end and roadside fusion algorithm, the final output result is processed into absolute longitude and latitude coordinate data and a speed under a world coordinate system through various fusion perception algorithm modules, namely, the spatial alignment is completed. The vehicle-road fusion perception algorithm needs to complete time alignment processing and subsequent association matching, kalman filtering fusion, multi-target matching tracking and the like.
For the vehicle-side and road-side sensing results, due to the difference of transmission topologies and considering more links involved in road-side camera image processing, sensing fusion, RSU-OBU data communication and OBU transparent transmission data analysis, great time delay cannot be avoided, and the preliminary estimation of the embodiment may reach 0.2s.
The vehicle-side fused sensing information and the roadside fused sensing information are based on earth coordinates, and space synchronization is not needed. In terms of time, due to time consumption of multiple processes such as an algorithm and signal transmission, roadside fusion sensing information generates a certain delay relative to vehicle-side fusion sensing information, and for roadside fusion sensing information with a certain delay, preliminary extrapolation prediction is performed on a roadside perception target list according to a specific time delay size through testing and counting the time delay, influences caused by the delay are compensated, and then subsequent vehicle-side fusion algorithm processing is performed.
The method is characterized in that a vehicle-road fusion algorithm is consistent with vehicle-side and roadside fusion sensing, three steps of GNN association matching, kalman weighting fusion and GNN multi-target matching are adopted for fusion processing, the specific algorithm is the same as the description of a vehicle-side sensing algorithm, and the difference is that the fused two parts of information are changed into information after vehicle-side fusion and information after roadside fusion from information of a camera and a millimeter wave radar of a vehicle side.
After the vehicle-road fusion processing, the information of the target matched with the vehicle-road can be obtained, meanwhile, the unmatched vehicle-end target and the road-side target are reserved, and the three parts are superposed to be used as a final vehicle-road fusion perception information list and sent to the early warning unit for target behavior prediction and decision processing.
Example 2
With reference to embodiment 1 and fig. 4, this embodiment further provides a vehicle early warning control system, which implements the steps of the vehicle early warning control method according to any one of embodiments 1, and includes:
an acquisition unit configured to acquire TSR identification information;
the first judgment unit is used for judging whether the TSR identification information belongs to an activation scene for activating the vehicle early warning function; this embodiment provides 3 activation scenarios, which are:
scene 1: the traffic light is shielded in TSR identification;
scene 2: traffic light fuzzy or confusing scenes during TSR identification;
scene 3: traffic signs obscure or confuse scenes during TSR recognition.
And when the vehicle is judged to belong to any one of the 3 scenes, activating the scene flag, and entering a perception area to acquire the vehicle road perception fusion information.
The sensing unit is used for acquiring the vehicle road sensing fusion information of the vehicle;
the second judgment unit is used for judging whether an early warning instruction needs to be issued to the driver or not through the vehicle road perception fusion information;
and the early warning unit is used for controlling the vehicle to issue an early warning instruction to the driver.
Further, the sensing unit includes:
the road side unit is used for acquiring road side end fusion perception information;
and the vehicle-mounted unit is used for acquiring the vehicle-end fusion perception information.
Further, the second determination unit includes:
when the vehicle activation scene is scene 1 or scene 2, the road side unit broadcasts the traffic light state information, the traffic light state may be a green light or a red/yellow light, and the second judging unit judges whether the vehicle can normally run through the intersection safety line or whether an early warning instruction needs to be issued to the driver according to the vehicle path perception fusion information;
when the vehicle activation scene is scene 3, the road side unit broadcasts traffic signboard information or other specific areas needing speed reduction, and at the moment, the second judging unit judges whether the vehicle normally runs or whether an early warning instruction needs to be issued to a driver according to the vehicle perception fusion information;
if the early warning instruction is issued to the driver, the vehicle can normally run after meeting the crossing safety line or the speed meeting the speed limit requirement that the vehicle can normally run.
The embodiment monitors the traffic light state information or the traffic signboard information in real time through the road side unit and distributes the traffic light information and the traffic signboard information, so as to judge whether the current running state of the vehicle can safely pass through the position of the traffic light or the traffic signboard, and further to distribute the early warning instruction at a proper position, thereby achieving the purpose of safe driving.
The early warning triggering principle of the vehicle in the embodiment is as follows: when the vehicle enters the communication range of the road side unit and has a certain distance from the traffic light and the traffic signboard, the driver can be ensured to have time and can safely pass through the traffic light or the traffic signboard through proper operation after the early warning instruction is issued.
The calculation of the warning distance is calculated by using the formula (1), the formula (2) and the formula (3) in the embodiment 1.
The trigger conditions for the early warning include:
the vehicle enters the communication range of the road side unit;
the current speed cannot safely pass through the traffic light/traffic signboard;
the distance between the vehicle and the traffic light/traffic signboard is less than the calculated early warning distance.
The control involved in the present embodiment is mainly control of the HMI, i.e., control of the warning function. When the vehicle needs to carry out driving early warning, the early warning unit sends a corresponding control signal to the HMI interface, and the driving of the sound and the image is used as a driver to make an early warning instruction.
When the driver takes over and exits the early warning mode, for example, in a mild brake stop state, when the driver performs a brake operation but deceleration is insufficient, the early warning unit continues to issue an early warning instruction to the driver, and continuously calculates the time for passing through the front road condition.
Example 3
With reference to embodiment 2 and fig. 5, the present embodiment provides a vehicle early warning implementation method, including:
the vehicle is pre-stored with 3 activation scenes, namely scene 1, scene 2 and scene 3;
the early warning system judges whether the vehicle activates any one of the 3 scenes flag through the TSR identification information, if so, the next step is carried out, otherwise, the process is ended;
after the early warning system activates a related scene flag, enabling the vehicle to enter a sensing area, carrying out vehicle-road sensing fusion and acquiring vehicle-road sensing fusion information;
according to the activated scene flag and the sensing fusion information of the vehicle and the road, when the road side unit issues the state information of the traffic light, the traffic light is judged to be a green light or a red/yellow light, then whether the vehicle can safely pass through a safety line of the intersection is judged in the green light state, if yes, the vehicle normally runs, otherwise, an early warning instruction is issued to the driver; when the road side unit issues the traffic signboard information, judging whether the current vehicle speed meets the signboard requirement or not according to the fact that the traffic signboard is speed-limiting or other signboards in specific areas needing speed reduction, if so, the vehicle normally runs, and otherwise, issuing an early warning instruction to a driver; and after the early warning instruction is issued, the driver performs corresponding operation according to the instruction and recovers the normal running of the vehicle after the event A or the event B. The event A means that the vehicle can pass through a safety line at the intersection when the traffic light is green, and the event B means that the vehicle speed does not exceed the highest speed limit of the traffic signboard.
Example 4
With reference to embodiment 1 and embodiment 2, the present embodiment provides a vehicle, and the steps of the vehicle warning control method according to any one of embodiment 1 are implemented.
The technical scheme provided by the invention can enable the vehicle to acquire the traffic information state ahead in advance, sense and judge the traffic environment in advance, and judge whether an early warning instruction, such as a warning, active deceleration or emergency braking related early warning instruction, needs to be issued to the driver according to the judgment, so that the vehicle achieves the purpose of safe driving.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes performed by the present specification and drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (9)
1. A vehicle early warning control method is characterized by comprising the following steps: the method comprises the following steps:
s1: acquiring TSR identification information, judging whether the TSR identification information belongs to an activation scene for activating a vehicle early warning function, if so, executing S2, otherwise, terminating the process;
s2: after the vehicle early warning function is activated, the vehicle enters a sensing area to perform vehicle road sensing fusion to obtain vehicle road sensing fusion information;
s3: whether an early warning instruction needs to be issued to a driver or not is judged through the vehicle road perception fusion information, if yes, the vehicle is controlled to issue the early warning instruction to the driver, and if not, the process is terminated.
2. The vehicle early warning control method according to claim 1, characterized in that: the S1 comprises:
the activation scenario includes:
the traffic light is shielded in TSR identification;
traffic light fuzzy or confusable scenes during TSR identification;
the traffic signboard blurs or confuses the scene when the TSR discerns.
3. The vehicle early warning control method according to claim 1, characterized in that: the S2 comprises the following steps:
the vehicle road perception fusion information comprises combination of vehicle end perception fusion information and road side perception fusion information.
4. The vehicle early warning control method according to claim 1, characterized in that: the S3 comprises the following steps: judging whether an early warning instruction needs to be issued to a driver or not through the vehicle road perception fusion information, and obtaining a judgment result;
the judgment result comprises:
when the current traffic light state is a green light, calculating whether the vehicle can safely pass through the intersection safety line or not by combining the current vehicle motion state;
when the traffic light of the front side is a red light or a yellow light, calculating the early warning distance of the vehicle by combining the current vehicle motion state;
and when the current traffic signboard information is the speed limit or other specific areas needing speed reduction, calculating whether the vehicle exceeds the highest speed limit value or not by combining the current vehicle motion state.
5. The vehicle early warning control method according to claim 4, characterized in that: when the traffic light state of the front side is green, whether the vehicle can safely pass through the intersection safety line or not is calculated by combining the motion state of the current vehicle, and the method comprises the following steps:
if the vehicle can not safely pass through the intersection safety line, controlling the vehicle to issue an early warning instruction to a driver;
if the vehicle can safely pass through the intersection safety line, the process is terminated, and the driver normally runs.
6. The vehicle warning control method according to claim 4, wherein: when the traffic signboard information of the current party is a speed limit or other specific areas needing speed reduction, the current vehicle motion state is combined to calculate whether the vehicle exceeds the highest value of the speed limit, and the method comprises the following steps:
if the vehicle does not exceed the maximum speed limit value, controlling the early warning system to issue a normal driving instruction to the driver;
and if the vehicle exceeds the highest speed limit value, controlling the early warning system to issue a driving early warning instruction to the driver.
7. A vehicle early warning control system that implements the steps of the vehicle early warning control method of any one of claims 1 to 6, characterized in that: the method comprises the following steps:
an acquisition unit configured to acquire TSR identification information;
the first judgment unit is used for judging whether the TSR identification information belongs to an activation scene for activating the vehicle early warning function;
the sensing unit is used for acquiring the vehicle road sensing fusion information of the vehicle;
the second judgment unit is used for judging whether an early warning instruction needs to be issued to the driver or not through the vehicle road perception fusion information;
and the early warning unit is used for controlling the vehicle to issue an early warning instruction to the driver.
8. The vehicle warning control system as claimed in claim 7, wherein: the sensing unit includes:
the road side unit is used for acquiring road side end fusion perception information;
and the vehicle-mounted unit is used for acquiring the vehicle-end fusion perception information.
9. A vehicle, characterized in that: the steps of implementing the vehicle warning control method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210905252.3A CN115482685A (en) | 2022-07-29 | 2022-07-29 | Vehicle early warning control method and system and vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210905252.3A CN115482685A (en) | 2022-07-29 | 2022-07-29 | Vehicle early warning control method and system and vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115482685A true CN115482685A (en) | 2022-12-16 |
Family
ID=84420846
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210905252.3A Pending CN115482685A (en) | 2022-07-29 | 2022-07-29 | Vehicle early warning control method and system and vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115482685A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116052454A (en) * | 2023-01-06 | 2023-05-02 | 中国第一汽车股份有限公司 | Vehicle driving data determining method and device and electronic equipment |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008302849A (en) * | 2007-06-08 | 2008-12-18 | Sumitomo Electric Ind Ltd | Vehicle driving support system, driving support device, vehicle, and vehicle driving support method |
| CN104464333A (en) * | 2014-12-02 | 2015-03-25 | 曹永飞 | Traffic signal information push method and system applied to vehicular access collaborative technology |
| CN106023628A (en) * | 2016-07-21 | 2016-10-12 | 浙江吉利汽车研究院有限公司 | Speed-limiting auxiliary system and speed-limiting auxiliary method for vehicle |
| CN106882190A (en) * | 2017-03-16 | 2017-06-23 | 广东轻工职业技术学院 | A kind of intersection driving accessory system and driving auxiliary control method |
| CN207367374U (en) * | 2017-10-17 | 2018-05-15 | 上海市政工程设计研究总院（集团）有限公司 | Intelligent transportation sign board and intelligent transportation system |
| CN112364707A (en) * | 2020-10-20 | 2021-02-12 | 华南理工大学 | System and method for over-the-horizon sensing of intelligent vehicle on complex road conditions |
| CN113129606A (en) * | 2020-01-15 | 2021-07-16 | 宁波吉利汽车研究开发有限公司 | Road signal lamp early warning method, device and medium |
| CN113232649A (en) * | 2021-04-26 | 2021-08-10 | 上汽大通汽车有限公司 | Crossing traffic anti-collision device and method based on V2X |
| CN113460076A (en) * | 2020-03-30 | 2021-10-01 | 本田技研工业株式会社 | Vehicle control device |
| CN113705458A (en) * | 2021-08-30 | 2021-11-26 | 上汽通用五菱汽车股份有限公司 | Traffic sign recognition method, system and storage medium |
| CN114005281A (en) * | 2021-11-25 | 2022-02-01 | 深圳市凯立德科技股份有限公司 | Intersection green wave guiding method, vehicle-mounted unit and computer readable storage medium |
| CN114724384A (en) * | 2022-02-25 | 2022-07-08 | 奥特酷智能科技(南京)有限公司 | Auxiliary driving system based on automatic detection of traffic signal lamp |
-
2022
- 2022-07-29 CN CN202210905252.3A patent/CN115482685A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008302849A (en) * | 2007-06-08 | 2008-12-18 | Sumitomo Electric Ind Ltd | Vehicle driving support system, driving support device, vehicle, and vehicle driving support method |
| CN104464333A (en) * | 2014-12-02 | 2015-03-25 | 曹永飞 | Traffic signal information push method and system applied to vehicular access collaborative technology |
| CN106023628A (en) * | 2016-07-21 | 2016-10-12 | 浙江吉利汽车研究院有限公司 | Speed-limiting auxiliary system and speed-limiting auxiliary method for vehicle |
| CN106882190A (en) * | 2017-03-16 | 2017-06-23 | 广东轻工职业技术学院 | A kind of intersection driving accessory system and driving auxiliary control method |
| CN207367374U (en) * | 2017-10-17 | 2018-05-15 | 上海市政工程设计研究总院（集团）有限公司 | Intelligent transportation sign board and intelligent transportation system |
| CN113129606A (en) * | 2020-01-15 | 2021-07-16 | 宁波吉利汽车研究开发有限公司 | Road signal lamp early warning method, device and medium |
| CN113460076A (en) * | 2020-03-30 | 2021-10-01 | 本田技研工业株式会社 | Vehicle control device |
| CN112364707A (en) * | 2020-10-20 | 2021-02-12 | 华南理工大学 | System and method for over-the-horizon sensing of intelligent vehicle on complex road conditions |
| CN113232649A (en) * | 2021-04-26 | 2021-08-10 | 上汽大通汽车有限公司 | Crossing traffic anti-collision device and method based on V2X |
| CN113705458A (en) * | 2021-08-30 | 2021-11-26 | 上汽通用五菱汽车股份有限公司 | Traffic sign recognition method, system and storage medium |
| CN114005281A (en) * | 2021-11-25 | 2022-02-01 | 深圳市凯立德科技股份有限公司 | Intersection green wave guiding method, vehicle-mounted unit and computer readable storage medium |
| CN114724384A (en) * | 2022-02-25 | 2022-07-08 | 奥特酷智能科技(南京)有限公司 | Auxiliary driving system based on automatic detection of traffic signal lamp |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116052454A (en) * | 2023-01-06 | 2023-05-02 | 中国第一汽车股份有限公司 | Vehicle driving data determining method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107346612B (en) | Vehicle anti-collision method and system based on Internet of vehicles | |
| US8179281B2 (en) | Method and apparatus for identifying concealed objects in road traffic | |
| KR102221321B1 (en) | Method for providing information about a anticipated driving intention of a vehicle | |
| JP3766909B2 (en) | Driving environment recognition method and apparatus | |
| US20180056998A1 (en) | System and Method for Multi-Vehicle Path Planning Technical Field | |
| US10832577B2 (en) | Method and system for determining road users with potential for interaction | |
| US10446035B2 (en) | Collision avoidance device for vehicle, collision avoidance method, and non-transitory storage medium storing program | |
| KR101511858B1 (en) | Advanced Driver Assistance System(ADAS) and controlling method for the same | |
| KR20080004835A (en) | Apparatus and method for generating a auxiliary information of moving vehicles for driver | |
| JP7038830B2 (en) | Satellite-assisted identification method of vehicle position | |
| CN113085852A (en) | Behavior early warning method and device for automatic driving vehicle and cloud equipment | |
| US11501539B2 (en) | Vehicle control system, sensing device and sensing data processing method | |
| CN115482685A (en) | Vehicle early warning control method and system and vehicle | |
| Adla et al. | Automotive collision avoidance methodologies Sensor-based and ITS-based | |
| Tang | Pedestrian protection using the integration of v2v communication and pedestrian automatic emergency braking system | |
| JP5354193B2 (en) | Vehicle driving support device | |
| KR20220111749A (en) | Tracking system for self driving cars | |
| CN112083412A (en) | Fusion method of millimeter wave radar and C-V2X system, system and electronic equipment thereof | |
| KR20120020971A (en) | Method for extension of vehicle sensing range through communication, and system thereof | |
| JP2021068315A (en) | Estimation method and estimation system of lane condition | |
| CN116434578B (en) | Emergency vehicle yield reminding method and system | |
| US20240105060A1 (en) | Automotive cooperative map-free lane-level relative localization based on inter-vehicular communication | |
| Guo et al. | Sensing strategy of autonomous emergency braking based on V2X in non-line-of-sight scenarios | |
| US20220386091A1 (en) | Motorcycle monitoring system | |
| Sarkar | Driver Assistance Technologies |
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 |