CN108819943B - Autonomous vehicle following system and method based on two-dimensional code - Google Patents
Autonomous vehicle following system and method based on two-dimensional code Download PDFInfo
- Publication number
- CN108819943B CN108819943B CN201810452787.3A CN201810452787A CN108819943B CN 108819943 B CN108819943 B CN 108819943B CN 201810452787 A CN201810452787 A CN 201810452787A CN 108819943 B CN108819943 B CN 108819943B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- dimensional code
- following
- data
- module
- 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
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000004364 calculation method Methods 0.000 claims abstract description 35
- 238000012545 processing Methods 0.000 claims abstract description 31
- 230000000007 visual effect Effects 0.000 claims abstract description 18
- 238000007405 data analysis Methods 0.000 claims abstract description 14
- 238000005259 measurement Methods 0.000 claims abstract description 13
- 230000003993 interaction Effects 0.000 claims description 46
- 238000004891 communication Methods 0.000 claims description 21
- 230000008569 process Effects 0.000 claims description 14
- 238000001514 detection method Methods 0.000 claims description 13
- 230000005540 biological transmission Effects 0.000 claims description 11
- 238000013500 data storage Methods 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 6
- 238000003825 pressing Methods 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 4
- SAZUGELZHZOXHB-UHFFFAOYSA-N acecarbromal Chemical compound CCC(Br)(CC)C(=O)NC(=O)NC(C)=O SAZUGELZHZOXHB-UHFFFAOYSA-N 0.000 claims description 2
- 238000003384 imaging method Methods 0.000 claims description 2
- 239000011159 matrix material Substances 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 description 5
- 230000008447 perception Effects 0.000 description 3
- 239000000523 sample Substances 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000004807 localization Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 238000011426 transformation method Methods 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000002567 autonomic effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000013332 literature search Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000035484 reaction time Effects 0.000 description 1
- 230000006798 recombination Effects 0.000 description 1
- 238000005215 recombination Methods 0.000 description 1
- 230000004044 response 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
- B60W30/14—Adaptive cruise control
- B60W30/16—Control of distance between vehicles, e.g. keeping a distance to preceding vehicle
- B60W30/165—Automatically following the path of a preceding lead vehicle, e.g. "electronic tow-bar"
-
- 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
- B60W2554/00—Input parameters relating to objects
- B60W2554/80—Spatial relation or speed relative to objects
- B60W2554/801—Lateral distance
-
- 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
- B60W2556/00—Input parameters relating to data
- B60W2556/45—External transmission of data to or from the vehicle
- B60W2556/65—Data transmitted between vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Traffic Control Systems (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention provides an autonomous car following system and method based on two-dimensional codes, wherein the system comprises the following components: the data acquisition unit acquires the visual images and the ultrasonic distance measurement data in real time and transmits the acquired data to the data analysis unit in real time; the data processing module receives the data of the data acquisition unit, if a target vehicle exists in front of the data processing module, the relative position and angle between the vehicles are estimated according to the visual image and the actual size of a two-dimensional code mark arranged on the vehicles, whether collision avoidance alarm is performed or not is judged by combining ultrasonic data, and the result is transmitted to the multi-vehicle cooperative positioning calculation module; the multi-vehicle cooperative positioning calculation module integrates the position information of all vehicles in the system to calculate so as to improve the self positioning precision and predict the position information of the target vehicle, and analyzes to obtain the speed and the direction turning angle of the vehicle which need to be adjusted. The invention improves the traveling safety of the motorcade, ensures the precision and the reliability of the following and has low cost price.
Description
Technical Field
The invention relates to the technical field of automatic driving and autonomous car following, in particular to an autonomous car following system and method based on two-dimensional codes.
Background
Accurate vehicle position information and relative position information between vehicles is the basis for many vehicle applications. The vehicle positioning accuracy of about 10m can be obtained by means of a Global Navigation Satellite System (GNSS) and a positioning enhancement technology, but the GNSS belongs to a single-node positioning technology, and obviously cannot meet the requirement of part applications such as vehicle safety in a vehicle self-organizing network on high positioning accuracy, and under the condition that GNSS signals are blocked, accurate position information between a vehicle and a vehicle is difficult to obtain. The relative position relation between vehicles is an important problem of autonomous vehicle following technology research, plays a key role in short-distance motorcade vehicle moving, short-distance motorcade cargo transportation and other applications, and the balance of price and precision is difficult to guarantee simultaneously by the existing perception technology such as radar, camera and the like, so that the realization of multi-vehicle autonomous tracking on the premise of guaranteeing cost and precision is always a research problem. In the application of motorcade travel and the like, convenient manual interaction is very important, so that the development of an economic, reliable and convenient automatic car following system is very necessary.
Through the literature search of the existing autonomous car following technology, Chinese patent application No. 201620830523.3, the patent name is: an autonomous car following system. This patent passes through perception environmental information such as millimeter wave radar, ultrasonic radar, vision, utilizes low-cost ultrasonic radar to carry out more accurate measurement to the relative distance of target closely, has compensatied the millimeter wave radar and has closely ranged the not enough that the error is big partially, and the recombination control unit then realizes autonomy with the car. Although the scheme can actively control the following running of the vehicle, the cost is greatly increased by using sensors such as millimeter wave radars and the like, multi-vehicle cooperative operation under the condition that the vehicle in the system is determined is not considered, and the multi-vehicle cooperation can effectively reduce manpower and reduce the probability of traffic accidents caused by fatigue of a driver or misoperation. Chinese patent application No. 201710183867.9, the patent names: a fleet formation driving system and method. The first car is by manual drive in this patent, other vehicles are for following the car, every car is equipped with location portion, communication portion, detection part and automatic driving control portion, detection part is used for measuring the positional information between the vehicle, communication portion on every car is connected with location portion, be responsible for simultaneously and adjacent vehicle interaction positional information, this scheme can realize the cooperative autonomic car of following between the vehicle, nevertheless to applications such as batch transfer motorcade, be difficult to realize low-cost and high accuracy autonomy with the car, and artificial interaction link is weak, only position differentiation between different vehicles, inconvenient vehicle numbering carries out, the first car consequently hardly obtains the quantity and the state of vehicle in vehicle sequencing and the real time monitoring motorcade, driving reliability remains to be improved.
Disclosure of Invention
Aiming at the problems in the prior art, the invention aims to provide an autonomous vehicle following system and method, under the condition that a vehicle in the system is fixed, the accurate relative position relation between the vehicle and a target vehicle can be obtained by utilizing visual information of a two-dimensional code and distance information of ultrasonic ranging, multi-vehicle communication is realized through a communication system, and fleet control is realized through manual interaction. Under the prerequisite of guaranteeing with the car precision, greatly reduced the tracking cost to the use of two-dimensional code has made things convenient for the first car to obtain the vehicle number, and the realization of the manual interaction of being convenient for has promoted the precision and the reliability with car system.
According to an aspect of the present invention, there is provided a two-dimensional code-based autonomous car following system, including:
the data acquisition unit is used for acquiring a visual image in front of the vehicle and ultrasonic ranging results of front and rear workshops in real time and transmitting the acquired data to the data analysis unit in real time;
the data analysis unit comprises a data processing module, a multi-vehicle cooperative positioning calculation module and a data transmission module, wherein: the data processing module receives the data of the data acquisition unit, if a target vehicle exists in front of the data acquisition unit, the relative position and angle between the vehicles are estimated according to the visual image and the actual size of a two-dimensional code mark arranged on the vehicle, whether collision avoidance alarm is performed or not is judged by combining ultrasonic data, and the result is transmitted to the multi-vehicle cooperative positioning calculation module; the multi-vehicle cooperative positioning calculation module integrates the positions of all vehicles in the system obtained by the data processing module and vehicle following or alarm state information to calculate so as to improve the positioning precision of the self-vehicle and predict the position information of a target vehicle (a front vehicle to be tracked), analyzes the speed and the direction rotation angle of the self-vehicle needing to be adjusted and converts the relative position information into absolute position information relative to the head vehicle; the data transmission module transmits the speed and the direction corner of the self-vehicle to be adjusted to a bottom layer control module of the self-vehicle for automatic positioning of the vehicle and simultaneously transmits the speed and the direction corner to a human-computer interaction unit;
and the human-computer interaction unit is used for setting vehicle parameters and displaying the vehicle state information and the absolute positioning information of the vehicle relative to the head vehicle, which are obtained by the data analysis unit, in real time.
Preferably, the system comprises a communication module for information transfer between vehicles, wherein: the following vehicle acquires the speed and direction corner information of the target vehicle through the communication module, so that the tracking is convenient, the position and state information of the following vehicle are sent to the head vehicle through the communication module, and the display of the human-computer interaction unit is convenient.
Preferably, the data acquisition module comprises an image data acquisition module and an ultrasonic ranging acquisition module, wherein the image data acquisition module acquires a visual image for two-dimensional code detection and pose estimation according to the visual image, the obtained result is used for accurately positioning a short-distance target, and the ultrasonic ranging data of the ultrasonic ranging acquisition module is used for safety alarm of collision avoidance.
More preferably, the data processing module processes the data in real time, if a target vehicle exists in front of the data processing module, the position of the two-dimensional code in the image is identified, the relative position of the current vehicle and the target vehicle is estimated, then the vehicle information of the vehicle, the ID of the two-dimensional code of the target vehicle and the relative position information of the target vehicle are sent to the multi-vehicle cooperative positioning calculation module, and if the target vehicle is not detected, only the information obtained by the ultrasonic ranging module is sent to the multi-vehicle cooperative positioning calculation module.
More preferably, a two-dimensional code mark is arranged behind each vehicle, the two-dimensional code on each vehicle has different IDs, if a target vehicle exists in front of the vehicle, the data processing module identifies the position of the two-dimensional code in the image and the ID corresponding to the two-dimensional code through a two-dimensional code detection method, on the premise that the actual size of the two-dimensional code is known, the relative position and the direction corner between the two vehicles are solved and estimated through a PnP problem, and the speed and the direction corner which need to be adjusted are obtained according to parameters in the system, the target and the state information of the vehicle.
More preferably, for the case of tracking failure in a short time, the pose estimation can still be carried out, if the long-time detection fails, a parking alarm is sent to the head car, and if no vehicle in the system fails to detect for a long time, the absolute position relation of other vehicles relative to the head car can be successively deduced according to the coordinate transformation principle and displayed on the human-computer interaction unit.
Preferably, the data analysis unit further comprises a data storage module, and the data storage module is used for storing the position of the vehicle, the relative position of the vehicle and the target vehicle, and the speed and the direction rotation angle of the vehicle needing to be adjusted in the system in real time, so that information interaction and calling among vehicles are facilitated.
According to another aspect of the invention, an autonomous car following method based on a two-dimensional code is provided, which comprises the following steps:
s1: setting two-dimensional code marks with different IDs on each vehicle, setting a vehicle mode, a vehicle following distance, a maximum vehicle speed limit and a vehicle following number through a man-machine interaction unit, preparing all vehicles, and sending vehicle following starting signals by a head vehicle;
s2: acquiring visual images and ultrasonic ranging data in real time, and sending the data to a data processing module;
s3: the data processing module processes visual image data in real time, if a target vehicle exists in front of the image, the position of the two-dimensional code in the image is identified, the current relative position of the two-dimensional code and the target vehicle is estimated, and then the vehicle information of the data processing module, the ID of the two-dimensional code of the target vehicle and the relative position information of the two-dimensional code and the target vehicle are sent to the multi-vehicle cooperative positioning calculation module;
s4: each vehicle transmits information with other vehicles through a network communication module, and a multi-vehicle cooperative positioning calculation module integrates the received vehicle information, analyzes and obtains the speed and the direction turning angle of each vehicle to be adjusted, and is used for vehicle control;
s5: the slave vehicle sends the speed and the direction rotation angle of the vehicle to be adjusted to the controller through the data transmission module according to the vehicle following requirement set by the system and the speed and the direction rotation angle of the vehicle obtained by S4 to automatically position the vehicle; the head car sends the state, relative position, absolute position and angle information which need to be adjusted of each vehicle and are obtained by the multi-vehicle cooperative positioning calculation module to the human-computer interaction unit in real time to display, so that safe operation of a driver is facilitated;
s6: and repeating the steps from S2 to S6 to update the data in real time, thereby realizing the whole process of positioning and following the car based on the two-dimensional code.
Preferably, when a target vehicle exists in the front of the data processing module, the data processing module identifies the position of the two-dimensional code in the image, estimates the relative position of the data processing module and the target vehicle, and simultaneously judges whether to perform collision avoidance alarm by combining ultrasonic data; and if the target vehicle is not detected, only sending the information obtained by the ultrasonic ranging module to the multi-vehicle cooperative positioning calculation module.
Preferably, the human-computer interaction unit provides the following operation functions:
-pressing the car following button after the car following is ready, sending a head car following signal;
the head car configures system parameters through the human-computer interaction unit, and after determining that the following car is ready, a starting signal is sent, and a following car mode is started;
during the following, the head car receives the alarm signal sent by the following car and performs a deceleration or stopping operation through the human-computer interaction unit;
-arriving at the destination, the head car pressing the dismissal button by means of the human-machine interaction unit, all the vehicles parking.
Compared with the prior art, the invention has the following beneficial effects:
1. according to the invention, the accurate measurement of the relative distance between the vehicles is realized by detecting the two-dimension code manual mark, and the autonomous tracking of other vehicles except the head vehicle can be realized by combining the human-computer interaction unit and the workshop network communication, so that the labor is saved;
2. according to the invention, the camera and the low-cost ultrasonic probe are only used for sensing environmental information, and the two-dimensional code artificial mark is combined, so that the relative distance of a close-distance target can be accurately measured (centimeter-level positioning accuracy can be achieved), and the following cost is greatly reduced on the premise of ensuring the accuracy.
3. According to the invention, the two-dimensional code mark is adopted for car following, the two-dimensional code is easy to carry and install and has an independent ID, the use is flexible, the car following can easily acquire the ID of the target vehicle according to the detection of the two-dimensional code, a user can conveniently acquire the serial number and the state of the vehicle in the system, and the car following and the dispersing signals are sent and started according to the state of the vehicle, so that the traveling safety of a motorcade is improved.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments with reference to the following drawings:
fig. 1 is a schematic view of a vehicle two-dimensional code (aprilat) layout according to an embodiment of the present invention;
FIG. 2 is a schematic block diagram of a system in accordance with an embodiment of the present invention;
fig. 3 is a flow chart of a method implementation according to an embodiment of the present invention.
Detailed Description
The present invention will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the invention, but are not intended to limit the invention in any way. It should be noted that variations and modifications can be made by persons skilled in the art without departing from the spirit of the invention. All falling within the scope of the present invention.
In the following embodiments, all vehicles participating in multi-vehicle cooperative positioning are provided with communication equipment, an ultrasonic distance measurement module and a camera are arranged in the front of the vehicle, and a two-dimensional code magnetic stripe, a vehicle-mounted control system and a man-machine interaction component are adsorbed at the lower right side of a rear window of the vehicle, wherein the vehicle-mounted control system comprises a vehicle information data acquisition and storage module, a multi-vehicle cooperative positioning calculation module and a data transmission module. The vehicles communicate with each other via a network.
Referring to fig. 1, the two-dimensional code is arranged at the lower right of a rear window of a vehicle and arranged in a manner of adsorbing a magnetic stripe of the two-dimensional code.
Referring to fig. 2, a block diagram of a preferred embodiment of the autonomous vehicle following system based on two-dimensional code of the present invention is shown, wherein the system includes: data acquisition unit, data analysis unit, man-machine interaction unit, wherein:
the data acquisition unit comprises an ultrasonic ranging acquisition module and an image data acquisition module, the data acquisition module acquires visual and ultrasonic ranging original data in real time and transmits the acquired original data to the data analysis unit in a wired or wireless manner in real time;
the data analysis unit comprises a data processing module, a multi-vehicle cooperative positioning calculation module, a data storage module and a data transmission module, wherein the data processing module processes received ultrasonic data and image data in real time, analyzes to obtain the relative position of the vehicle and the target vehicle ID, and transmits the result to the multi-vehicle cooperative positioning calculation module; the multi-vehicle cooperative positioning computing module integrates the position, state and ID information of all vehicles in the system, analyzes the speed and direction turning angle of the vehicle to be adjusted according to the relative position to control the vehicle, sends a warning for the long-time detection failure parking with too long distance, too large turning angle and too long time to the head vehicle through the communication module (here, the communication module is required to receive the speed of the front vehicle and the turning angle of a steering wheel), and calculates the absolute position of each vehicle relative to the head vehicle according to a coordinate transformation method; the data storage module stores the position and state of the vehicle in the system, the relative position of the vehicle and the target vehicle, and the speed and the direction rotation angle of the vehicle needing to be adjusted in real time; the data transmission module CAN transmit the speed and direction rotation angle of each vehicle to be adjusted to a bottom layer control module of a following vehicle through a CAN bus to automatically position the vehicle on one hand, and CAN transmit the speed and direction rotation angle to a human-computer interaction unit in a wired or wireless mode on the other hand;
the man-machine interaction unit is used for setting initial vehicle parameters and displaying information obtained by the data analysis unit in real time, so that the head vehicle can know the system state conveniently, and the reliability of the system is improved.
As a preferred embodiment, as shown in fig. 2, the vehicles communicate with each other through a ZigBee network, and the multi-vehicle cooperative localization calculation module integrates the location information of all the vehicles in the system, performs calculation to improve the self localization accuracy and predict the location information of the target vehicle, and analyzes the speed and the direction rotation angle of the vehicle that need to be adjusted.
As a preferred embodiment, as shown in fig. 2, the data storage module stores the position of the vehicle, the relative position of the vehicle and the target vehicle, and the speed and direction rotation angle of the vehicle, which need to be adjusted, in the system in real time, so as to facilitate information interaction and call between vehicles.
As a preferred embodiment, as shown in fig. 2, the data transmission module can transmit the position of each vehicle, the relative position between itself and the target vehicle, and the speed and direction rotation angle to be adjusted to the underlying control module for automatic vehicle positioning, and can transmit the position, the relative position, the speed and the direction rotation angle to be adjusted to the human-computer interaction unit through a 4G network.
As a preferred embodiment, as shown in fig. 2, the human-computer interaction unit may adopt a tablet computer, and mainly performs vehicle parameter setting and displays information obtained by the data analysis unit in real time to assist a driver to perform safety operations.
Referring to fig. 3, a flowchart of a preferred embodiment of an autonomous car following method based on a two-dimensional code is shown, and the specific operations include the following steps:
step 1: setting two-dimensional code marks with different IDs on each vehicle, setting a vehicle mode, a vehicle following distance, a maximum vehicle speed limit and a vehicle following number through a man-machine interaction unit, preparing all vehicles, and sending vehicle following starting signals by a head vehicle;
step 2: the ultrasonic distance measurement module and the image data acquisition module acquire distance data and an original image in real time and send the data to the data processing module of the processor in a wired or wireless mode;
and step 3: the data processing module processes data in real time, two-dimension code manual marks are adsorbed behind each vehicle in the system, if a target vehicle exists in front of the system, the position of the two-dimension code in an image and the ID corresponding to the two-dimension code of the target vehicle are identified through an image algorithm, and on the premise that the actual size of the two-dimension code is known, in the embodiment, the position and the direction of the two-dimension code relative to the visual sensor can be calculated by adopting the following formula:
p＝λK[R t]P
wherein P is the coordinate of the two-dimensional code under the camera imaging coordinate system, P is the coordinate of the two-dimensional code in the world coordinate system (the center of the two-dimensional code is the origin), K is the camera reference matrix, λ is the scale information, and R, t are the position and the posture of the camera coordinate system relative to the world coordinate system. The relative position and direction of two workshops can be estimated through solving the PnP problem, centimeter-level positioning accuracy can be achieved in the vehicle tracking process, then distance data obtained through ultrasonic measurement, vehicle information of the two-dimensional code of the target vehicle, the ID of the two-dimensional code of the target vehicle and relative position information of the target vehicle are sent to the multi-vehicle cooperative positioning calculation module, and if the target vehicle is not detected, information obtained through the ultrasonic distance measurement module is only sent to the multi-vehicle cooperative positioning calculation module;
and 4, step 4: the vehicles in the system transmit information with other vehicles through network communication, each following vehicle receives position information of a front vehicle, the received vehicle information is integrated by the multi-vehicle cooperative positioning calculation module, and the relative position between the vehicles is converted into an absolute position relative to a head vehicle according to a coordinate transformation method.
In this embodiment, the tracking distance and the warning distance between two vehicles are estimated according to the vehicle speeds and the system response time, and the calculation formula of the warning distance between the vehicles is as follows:
where d is the minimum distance for parking, TfThe reaction time of the system (generally 200-600 ms), vfrontFor the speed of the preceding vehicle, vbackTo the rear vehicle speed, asFor rear vehicle braking distance, afrontIf the acceleration is the acceleration of the front vehicle, if the front vehicle decelerates, calculating an alarm distance, and judging whether to perform braking intervention or not by combining the current distance and ultrasonic data; then, the vehicle tracking distance is calculated according to the following formula:
Dc＝k×d+(vbackTf-0.5×aback×Tf 2)-(vfrontTf-0.5×afront×Tf 2) (3)
k is generally 1.2-1.8, the speed of each vehicle needing to be adjusted can be analyzed by combining the initialized adjusting distance and the current vehicle distance and the safe tracking distance, and the direction corner of the vehicle needing to be adjusted is analyzed according to the direction information of the front vehicle and the direction information between the vehicles.
The method comprises the steps that the current vehicle needs to receive speed and corner information of a target vehicle, pose estimation can still be carried out on the condition that tracking fails in a short time (1-5 s), if detection fails for a long time, a parking alarm is sent to a head vehicle, and if no vehicle fails to detect for a long time in a system, the absolute position relation of other vehicles relative to the head vehicle can be successively deduced according to a coordinate transformation principle;
and 5: the slave vehicle is transmitted to a vehicle following bottom layer control module to automatically position the vehicle according to the vehicle following requirement set by the system and the speed and direction turning angle of the vehicle to be adjusted, which are obtained in the step 4; the head vehicle receives the states of all vehicles, relative positions of the vehicles and absolute positions relative to the head vehicle, which are obtained by the multi-vehicle cooperative positioning calculation module, in real time through the vehicle-to-vehicle communication module, and sends the states, the relative positions of the vehicles and the absolute positions relative to the head vehicle to the human-computer interaction unit in a wired or wireless mode for displaying, so that safe operation of a driver is facilitated;
step 6: and (5) repeating the step 2 to the step 5, and updating the data in real time, so that the whole process of positioning and car following based on the two-dimensional code is realized.
In the method, the man-machine interaction unit can provide the following simple operation functions:
1: arranging vehicles in a line, placing two-dimensional code artificial marks with different IDs behind the vehicles, pressing a vehicle following button after the vehicle following vehicles are prepared, and sending a signal for the head vehicle and the vehicle following;
2: the head car configures system parameters (such as the number of following cars, the ID of the following two-dimensional code is determined, the ID does not need to be set, and only the step 1 needs to be sequentially attached and placed) through the human-computer interaction unit, and after the following cars are determined to be ready, a starting signal is sent, and a following mode is started;
3: in the following process, the head car receives an alarm signal sent by the following car and carries out corresponding operation (deceleration or parking);
4: when the vehicle arrives at the destination, the head vehicle presses the dismissal button through the human-computer interaction unit, and all vehicles stop.
Further, a data storage module is adopted to store the vehicle information, the relative position information between the vehicles and the position and angle information of the vehicle needing to be adjusted in the system obtained in the step 4 in real time.
According to the embodiment of the invention, the pose estimation is carried out by detecting the two-dimensional code, the accurate measurement of the relative distance of the vehicle is realized, meanwhile, the collision avoidance alarm is carried out by the ultrasonic module, the speed and the direction which need to be adjusted and the network communication of a workshop are obtained by combining the parameters set by the human-computer interaction unit and the vehicle information analysis, and the autonomous tracking of other vehicles except the head vehicle can be realized. Because the two-dimensional code marks are easy to carry and install, the use is flexible, the independent ID exists, the head car can conveniently acquire the vehicle sequencing, the human-computer interaction unit can conveniently monitor the positions and the states of all vehicles in real time, and the traveling safety of a motorcade is improved. Compared with other autonomous car following systems, the system ensures the precision and the reliability of car following and has low cost price.
In an embodiment of the present invention, an embodiment of the present invention is further provided with reference to fig. 2 to 3, in which:
the two-dimensional code adopts an AprilTag two-dimensional code, and of course, other two-dimensional codes can be adopted in other embodiments;
the data processing platform adopts a NUC processor, and other processors can be adopted in other embodiments;
the April tag two-dimensional code artificial mark has the size of 30cm multiplied by 30cm, is adsorbed at the lower right of a rear window of a vehicle by adopting a magnetic stripe, if a target vehicle exists in the front of the April tag two-dimensional code artificial mark, an AXIS P1265 camera arranged on the front window of the vehicle identifies the position of the April tag in an image, estimates the current relative position of the April tag and the target vehicle by combining ultrasonic probe data, and transmits the result to a multi-vehicle cooperative positioning calculation module;
the image data acquisition module adopts a visual sensor.
In this embodiment, the AprilTag-based autonomous following implementation process may refer to the following steps:
step 1: the method comprises the following steps that vehicles in a system are arranged in a row, each vehicle adsorbs AprilTag marks with different IDs, a vehicle mode (divided into a head vehicle and a following vehicle, wherein a head vehicle driver drives) is set through a head vehicle human-computer interaction unit, and parameters such as the vehicle ID, the minimum parking distance (generally 1-2 m), the adjusting distance (1-2 m), the maximum vehicle speed limit (generally less than 30km/h), the number of following vehicles (3-5) and the like are recorded; after the following vehicle is determined to be ready, sending a signal to the head vehicle, sending a starting signal to the head vehicle through the man-machine interaction unit, and starting the following vehicle mode;
step 2: the ultrasonic distance measurement module and the image data acquisition module acquire distance data and an original image in real time and send the data to the data processing module;
and step 3: the data processing module processes data in real time, an April tag artificial mark is adsorbed behind each vehicle in the system, if a target vehicle exists in front of the April tag artificial mark, the position of the April tag in an image is identified, the current relative position of the April tag and the target vehicle is estimated, then vehicle information of the April tag, the ID of the target vehicle and the relative position information of the target vehicle are sent to the multi-vehicle cooperative positioning calculation module, and if the target vehicle is not detected, information obtained by the ultrasonic ranging module is only sent to the multi-vehicle cooperative positioning calculation module;
and 4, step 4: all vehicles in the system transmit information with other vehicles through ZigBee communication, a multi-vehicle cooperative positioning calculation module integrates the received vehicle information, judges whether collision avoidance alarming is carried out or not by combining ultrasonic data, obtains the speed and direction corner of the vehicle to be adjusted according to relative position analysis to carry out vehicle control, and sends a parking alarm which is too far away from the first vehicle, too large in corner and failed in long-time detection to the first vehicle through a communication module; if the system has the vehicle ID detected and no vehicle detection fails, the corresponding positions of other vehicles relative to the head vehicle can be successively deduced according to the coordinate transformation principle;
and 5: the slave vehicle is transmitted to a vehicle following control unit through a CAN bus to automatically position the vehicle according to the vehicle following requirement set by the system and the speed and direction rotation angle of the vehicle to be adjusted obtained in the step 4; the head vehicle sends the state of each vehicle, the relative position of a workshop, the absolute position relative to the head vehicle, the ID and the position and angle information needing to be adjusted, which are obtained by the multi-vehicle cooperative positioning calculation module, to the human-computer interaction unit through the 4G network in real time for displaying;
step 6: the data storage module stores the vehicle information, the relative position information between the vehicles and the position and angle information of the vehicle needing to be adjusted in the system obtained in the step 4 in real time;
and 7: and (5) repeating the step (2) to the step (6) to update the data in real time, thereby realizing the whole process of positioning and following the vehicle based on AprilTag.
The invention realizes the automatic driving of other vehicles outside the head car, greatly reduces the manpower, and users can set parameters by themselves, and can acquire the speed and direction corner information between the vehicles, the ID information of the target vehicle and the absolute position information relative to the head car in real time and display the information in real time through the man-machine interaction unit so as to assist the safe operation of the drivers; through detecting the artificial mark of AprilTag, can realize the accurate measurement to closely target relative distance (can reach centimetre level positioning accuracy), and the perception module only has camera and low-priced ultrasonic probe, has promoted with the precision and the reliability of car system, and with low costs price.
It should be noted that, the steps in the autonomous car following implementation method provided by the present invention may be implemented by using corresponding modules, devices, units, and the like in the autonomous car following implementation system, and a person skilled in the art may refer to the technical scheme of the system to implement the step flow of the method, that is, an embodiment in the system may be understood as a preferred example for implementing the method, and details are not described here.
Those skilled in the art will appreciate that, in addition to implementing the system and its various devices provided by the present invention in purely computer readable program code means, the method steps can be fully programmed to implement the same functions by implementing the system and its various devices in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Therefore, the system and various devices thereof provided by the present invention can be regarded as a hardware component, and the devices included in the system and various devices thereof for realizing various functions can also be regarded as structures in the hardware component; means for performing the functions may also be regarded as structures within both software modules and hardware components for performing the methods.
The foregoing description of specific embodiments of the present invention has been presented. It is to be understood that the present invention is not limited to the specific embodiments described above, and that various changes or modifications may be made by one skilled in the art within the scope of the appended claims without departing from the spirit of the invention. The embodiments and features of the embodiments of the present application may be combined with each other arbitrarily without conflict.
Claims (10)
1. The utility model provides an independently with car system based on two-dimensional code which characterized in that includes:
the data acquisition unit is used for acquiring a visual image in front of the vehicle and ultrasonic ranging results of front and rear workshops in real time and transmitting the acquired data to the data analysis unit in real time;
the data analysis unit comprises a data processing module, a multi-vehicle cooperative positioning calculation module and a data transmission module, wherein: the data processing module receives the data of the data acquisition unit, if a target vehicle exists in front of the data acquisition unit, the relative position and angle between the vehicles are estimated according to the visual image and the actual size of a two-dimensional code mark arranged on the vehicle, whether collision avoidance alarm is performed or not is judged by combining ultrasonic data, and the result is transmitted to the multi-vehicle cooperative positioning calculation module; the multi-vehicle cooperative positioning calculation module integrates the positions of all vehicles in the system obtained by the data processing module and vehicle following or alarm state information to calculate so as to improve the positioning accuracy of the self-vehicle and the position information of a front vehicle to be tracked, namely a predicted target vehicle, analyzes the speed and the direction rotation angle of the self-vehicle needing to be adjusted and converts the relative position information into absolute position information relative to the head vehicle; the data transmission module transmits the speed and the direction corner of the self-vehicle to be adjusted to a bottom layer control module of the self-vehicle for automatic positioning of the vehicle and simultaneously transmits the speed and the direction corner to a human-computer interaction unit;
and the human-computer interaction unit is used for setting vehicle parameters and displaying the vehicle state information and the absolute position information of the vehicle relative to the head vehicle, which are obtained by the data analysis unit, in real time.
2. The autonomous car-following system based on the two-dimensional code according to claim 1, wherein the system comprises a communication module for information transmission between vehicles, wherein: the following vehicle acquires the speed and direction corner information of the target vehicle through the communication module, so that the tracking is convenient, the position and state information of the following vehicle are sent to the head vehicle through the communication module, and the display of the human-computer interaction unit is convenient.
3. The autonomous vehicle following system based on the two-dimension code of claim 1, wherein the data acquisition module comprises an image data acquisition module and an ultrasonic distance measurement acquisition module, wherein the image data acquisition module acquires a visual image for two-dimension code detection and pose estimation based on the visual image, the obtained result accurately positions a close-distance target, and the ultrasonic distance measurement data of the ultrasonic distance measurement acquisition module is used for safety alarm for collision avoidance.
4. The autonomous vehicle following system based on the two-dimensional code according to claim 3, wherein the data processing module processes the data in real time, if a target vehicle exists ahead, the position of the two-dimensional code in the image is identified, the current relative position between the two-dimensional code and the target vehicle is estimated, then the vehicle information of the vehicle, the ID of the two-dimensional code of the target vehicle and the relative position information of the target vehicle are sent to the multi-vehicle cooperative positioning calculation module, and if the target vehicle is not detected, only the information obtained by the ultrasonic ranging module is sent to the multi-vehicle cooperative positioning calculation module.
5. The autonomous vehicle following system based on the two-dimensional code according to claim 4, wherein a two-dimensional code mark is arranged behind each vehicle, the two-dimensional code on each vehicle has different IDs, if a target vehicle exists in front of the vehicle, the data processing module identifies the position of the two-dimensional code in the image and the ID corresponding to the two-dimensional code through a two-dimensional code detection method, under the premise that the actual size of the two-dimensional code is known, the relative position and the direction rotation angle of the two vehicles are solved and estimated through a PnP problem, and the speed and the direction rotation angle which need to be adjusted are obtained according to parameters in the system, the target and the state information of the vehicle;
the method for solving and estimating the relative position and the direction rotation angle of the two workshops through the PnP problem comprises the following steps:
the position and orientation of the two-dimensional code relative to the vision sensor is calculated using the following formula:
wherein P is the coordinate of the two-dimensional code under the camera imaging coordinate system, P is the coordinate of the two-dimensional code in the world coordinate system, the center of the two-dimensional code is also the origin, K is the camera reference matrix, lambda is the scale information, and R, t are the position and the posture of the camera coordinate system relative to the world coordinate system.
6. The autonomous vehicle following system based on the two-dimension code as claimed in claim 5, wherein for the case of tracking failure in a short time, the pose estimation can still be performed, if the long-time detection fails, a parking alarm is sent to the head vehicle, and if no vehicle in the system fails to detect for a long time, the absolute position relationship of other vehicles relative to the head vehicle can be successively deduced according to the coordinate transformation principle and displayed on the human-computer interaction unit.
7. The autonomous vehicle following system based on the two-dimensional code according to any one of claims 1-6, wherein the data analysis unit further comprises a data storage module, and the data storage module stores the position of the vehicle, the relative position of the vehicle and the target vehicle, and the speed and direction rotation angle of the vehicle to be adjusted in the system in real time, so that information interaction and calling among vehicles are facilitated.
8. An autonomous car following method based on two-dimensional codes is characterized by comprising the following steps:
s1: setting two-dimensional code marks with different IDs on each vehicle, setting a vehicle mode, a vehicle following distance, a maximum vehicle speed limit and a vehicle following number through a man-machine interaction unit, preparing all vehicles, and sending vehicle following starting signals by a head vehicle;
s2: acquiring visual images and ultrasonic ranging data in real time, and sending the data to a data processing module;
s3: the data processing module processes visual image data in real time, if a target vehicle exists in front of the image, the position of the two-dimensional code in the image is identified, the current relative position of the two-dimensional code and the target vehicle is estimated, and then the vehicle information of the data processing module, the ID of the two-dimensional code of the target vehicle and the relative position information of the two-dimensional code and the target vehicle are sent to the multi-vehicle cooperative positioning calculation module;
s4: each vehicle transmits information with other vehicles through a network communication module, and a multi-vehicle cooperative positioning calculation module integrates the received vehicle information, analyzes and obtains the speed and the direction turning angle of each vehicle to be adjusted, and is used for vehicle control;
s5: the slave vehicle sends the speed and the direction rotation angle of the vehicle to be adjusted to the controller through the data transmission module according to the vehicle following requirement set by the system and the speed and the direction rotation angle of the vehicle obtained by S4 to automatically position the vehicle; the head vehicle sends the state, relative position, absolute position and angle information which need to be adjusted of each vehicle and are obtained by the multi-vehicle cooperative positioning calculation module to the human-computer interaction unit in real time to be displayed;
s6: and repeating the steps from S2 to S6 to update the data in real time, thereby realizing the whole process of positioning and following the car based on the two-dimensional code.
9. The autonomous vehicle following method based on the two-dimensional code according to claim 8, wherein when a target vehicle exists in front of the data processing module, the data processing module identifies the position of the two-dimensional code in the image, estimates the relative position of the current vehicle and the target vehicle, and simultaneously judges whether to perform collision avoidance warning by combining ultrasonic data; and if the target vehicle is not detected, only sending the information obtained by the ultrasonic ranging module to the multi-vehicle cooperative positioning calculation module.
10. The autonomous car-following method based on the two-dimensional code according to claim 8 or 9, wherein the human-computer interaction unit provides the following operation functions:
-pressing the car following button after the car following is ready, sending a head car following signal;
the head car configures system parameters through the human-computer interaction unit, and after determining that the following car is ready, a starting signal is sent, and a following car mode is started;
during the following, the head car receives the alarm signal sent by the following car and performs a deceleration or stopping operation through the human-computer interaction unit;
-arriving at the destination, the head car pressing the dismissal button by means of the human-machine interaction unit, all the vehicles parking.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810452787.3A CN108819943B (en) | 2018-05-13 | 2018-05-13 | Autonomous vehicle following system and method based on two-dimensional code |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810452787.3A CN108819943B (en) | 2018-05-13 | 2018-05-13 | Autonomous vehicle following system and method based on two-dimensional code |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108819943A CN108819943A (en) | 2018-11-16 |
| CN108819943B true CN108819943B (en) | 2020-02-04 |
Family
ID=64148788
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810452787.3A Active CN108819943B (en) | 2018-05-13 | 2018-05-13 | Autonomous vehicle following system and method based on two-dimensional code |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108819943B (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10373323B1 (en) * | 2019-01-29 | 2019-08-06 | StradVision, Inc. | Method and device for merging object detection information detected by each of object detectors corresponding to each camera nearby for the purpose of collaborative driving by using V2X-enabled applications, sensor fusion via multiple vehicles |
| CN111627247B (en) * | 2019-02-28 | 2022-02-18 | 上海汽车集团股份有限公司 | Multi-vehicle formation control method and device |
| CN109737971B (en) * | 2019-03-18 | 2020-12-04 | 爱驰汽车有限公司 | Vehicle-mounted auxiliary navigation positioning system, method, equipment and storage medium |
| CN110163912B (en) * | 2019-04-29 | 2022-01-11 | 广州达泊智能科技有限公司 | Two-dimensional code pose calibration method, device and system |
| DE102019211984A1 (en) * | 2019-08-09 | 2021-02-11 | Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V. | Device, method for controlling the same and device network or swarm |
| CN110974284A (en) * | 2019-10-29 | 2020-04-10 | 神经元信息技术(深圳)有限公司 | X-ray protection equipment with image recognition target tracking function |
| CN112859825A (en) * | 2019-11-26 | 2021-05-28 | 财团法人车辆研究测试中心 | Automatic driving coordination system and control method |
| CN112068603A (en) * | 2020-08-10 | 2020-12-11 | 上海交通大学 | Unmanned vehicle following system and method based on event camera |
| CN113257045A (en) * | 2021-07-14 | 2021-08-13 | 四川腾盾科技有限公司 | Unmanned aerial vehicle control method based on large-scale fixed wing unmanned aerial vehicle electronic fence |
| CN114007047B (en) * | 2021-11-02 | 2024-03-15 | 广西电网有限责任公司贺州供电局 | Machine vision-based real-time monitoring and alarming system for operation of power transformation site |
| CN113998547B (en) * | 2021-11-15 | 2024-06-07 | 广东天凛高新科技有限公司 | Mobilizable intelligent butt joint cable drum |
| CN113955592B (en) * | 2021-11-15 | 2024-06-07 | 广东天凛高新科技有限公司 | Movable intelligent butt joint cable drum working method |
| CN115218904A (en) * | 2022-06-13 | 2022-10-21 | 深圳市优必选科技股份有限公司 | Following navigation method, device, computer readable storage medium and mobile device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102076542A (en) * | 2009-03-04 | 2011-05-25 | 丰田自动车株式会社 | Follow-up run control device |
| CN103857550A (en) * | 2011-08-03 | 2014-06-11 | 大陆-特韦斯贸易合伙股份公司及两合公司 | Method and system for adaptively controlling distance and speed and for stopping a motor vehicle, and a motor vehicle which works with same |
| US9073548B2 (en) * | 2012-02-13 | 2015-07-07 | Denso Corporation | Vehicle-mounted radar apparatus |
| CN105882656A (en) * | 2016-04-22 | 2016-08-24 | 奇瑞汽车股份有限公司 | Car following method and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| BR112014016946A8 (en) * | 2012-01-12 | 2017-07-04 | Honda Motor Co Ltd | synchronized driving assistance system and synchronized driving assistance system |
-
2018
- 2018-05-13 CN CN201810452787.3A patent/CN108819943B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102076542A (en) * | 2009-03-04 | 2011-05-25 | 丰田自动车株式会社 | Follow-up run control device |
| CN103857550A (en) * | 2011-08-03 | 2014-06-11 | 大陆-特韦斯贸易合伙股份公司及两合公司 | Method and system for adaptively controlling distance and speed and for stopping a motor vehicle, and a motor vehicle which works with same |
| US9073548B2 (en) * | 2012-02-13 | 2015-07-07 | Denso Corporation | Vehicle-mounted radar apparatus |
| CN105882656A (en) * | 2016-04-22 | 2016-08-24 | 奇瑞汽车股份有限公司 | Car following method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108819943A (en) | 2018-11-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108819943B (en) | Autonomous vehicle following system and method based on two-dimensional code | |
| CN109421738B (en) | Method and apparatus for monitoring autonomous vehicles | |
| CN104583724B (en) | Method and apparatus for determining vehicle location in environment is surveyed and drawn | |
| CN106043299A (en) | Vehicle control apparatus | |
| US10706563B2 (en) | State and position prediction of observed vehicles using optical tracking of wheel rotation | |
| CN113264047B (en) | Vehicle control device and non-volatile storage medium storing vehicle control program | |
| CN109421739A (en) | Method and apparatus for monitoring autonomous vehicle | |
| CN110262469A (en) | A kind of automatic ride control system and method applied to agricultural vehicle | |
| CN108616810A (en) | A kind of fleet is independently with vehicle system, mancarried device and method | |
| CN110471415A (en) | Vehicle and its control method and system with automatic driving mode | |
| US11353867B1 (en) | Redundant lateral velocity determination and use in secondary vehicle control systems | |
| WO2015129175A1 (en) | Automated driving device | |
| US10380757B2 (en) | Detecting vehicle movement through wheel movement | |
| CN109841088A (en) | Vehicle drive assist system and method | |
| CN107657825A (en) | Park method and device | |
| CN110103952A (en) | Assist method, equipment, medium and the system of vehicle drive | |
| US11623641B2 (en) | Following target identification system and following target identification method | |
| CN112824837A (en) | Vehicle attitude detection with fiducial markers | |
| US20190180623A1 (en) | Collision prediction method and device | |
| US20230264698A1 (en) | Drive planning device, storage medium storing computer program for drive planning and drive planning method | |
| CN112602107A (en) | Information providing method for vehicle dispatching system, vehicle dispatching system and information providing device | |
| CN110333510A (en) | A kind of list radar is parked localization method and system | |
| CN110155043B (en) | Automatic parking two-dimensional positioning method | |
| CN112068603A (en) | Unmanned vehicle following system and method based on event camera | |
| CN115042806B (en) | Method and device for displaying paths of passenger car parking and electronic equipment |
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 |