CN113702967A - Vehicle target guiding and tracking method of ground unmanned platform and vehicle-mounted system - Google Patents

Vehicle target guiding and tracking method of ground unmanned platform and vehicle-mounted system Download PDF

Info

Publication number
CN113702967A
CN113702967A CN202111122185.XA CN202111122185A CN113702967A CN 113702967 A CN113702967 A CN 113702967A CN 202111122185 A CN202111122185 A CN 202111122185A CN 113702967 A CN113702967 A CN 113702967A
Authority
CN
China
Prior art keywords
vehicle
target
tracking
millimeter wave
wave radar
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202111122185.XA
Other languages
Chinese (zh)
Other versions
CN113702967B (en
Inventor
李宁
高建锋
苏波
卢彩霞
余雪玮
刘雪妍
李众
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China North Vehicle Research Institute
Original Assignee
China North Vehicle Research Institute
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China North Vehicle Research Institute filed Critical China North Vehicle Research Institute
Priority to CN202111122185.XA priority Critical patent/CN113702967B/en
Publication of CN113702967A publication Critical patent/CN113702967A/en
Application granted granted Critical
Publication of CN113702967B publication Critical patent/CN113702967B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/86—Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/66—Radar-tracking systems; Analogous systems
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/86—Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
    • G01S13/865—Combination of radar systems with lidar systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N7/00—Computing arrangements based on specific mathematical models
    • G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Remote Sensing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Theoretical Computer Science (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Physics (AREA)
  • Mathematical Analysis (AREA)
  • Data Mining & Analysis (AREA)
  • Pure & Applied Mathematics (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • Computational Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Algebra (AREA)
  • Probability & Statistics with Applications (AREA)
  • Traffic Control Systems (AREA)
  • Radar Systems Or Details Thereof (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

The invention relates to a method for identifying and tracking a vehicle target guided by a ground unmanned platform and a vehicle-mounted system, belonging to the technical field of semi-autonomous navigation of the ground unmanned platform. The autonomous vehicle guide target identification and tracking method and the vehicle-mounted system provided by the invention provide a safe and reliable guide target identification and tracking scheme, can effectively realize guide-following unmanned formation transportation, save manpower support in the material transportation process, improve the intelligent level of a formation transportation system, and simultaneously improve the safety and reliability of the unmanned autonomous formation transportation system.

Description

Vehicle target guiding and tracking method of ground unmanned platform and vehicle-mounted system
Technical Field
The invention belongs to the technical field of semi-autonomous navigation of a ground unmanned platform, and particularly relates to a method for identifying and tracking a guide vehicle target of the ground unmanned platform and a vehicle-mounted system.
Background
The guiding-following system of the ground unmanned platform is a practical semi-autonomous motor control mode, utilizes a perception sensor carried by the unmanned platform to identify and continuously track a target of a guide vehicle, does not need to transform the guide vehicle, realizes formation transportation of the guiding-autonomous following of the unmanned vehicle of the manned vehicle, can be applied to material transportation guarantee, can effectively reduce drivers, and simultaneously improves the intelligent level of long-distance transportation.
In the prior art, the target identification and tracking implementation mode of the ground unmanned platform guidance-following system has the following main problems:
1. and target identification and tracking based on the visual image. On one hand, the vision-based target identification result needs to be converted into a Cartesian coordinate system of the vehicle body, and therefore coordinate conversion precision errors exist, and accurate tracking control of the following vehicle is not facilitated. On the other hand, the vision sensor is greatly influenced by illumination, view angle shielding and the like, and particularly when the vision sensor turns or passes through a tunnel with severely changed illumination, the target is easily lost. In addition, the vision sensor is greatly influenced by severe weather such as rain, snow, fog and the like, and cannot provide a target identification and tracking result for a guiding-following task under all-weather conditions.
2. And target identification and tracking based on the millimeter wave radar. The millimeter wave radar can effectively track the dynamic target, the discrimination degree of a static vehicle is not high, and the initialization failure of the tracked target is easily caused when the vehicle target is initialized. Furthermore, in the event of a loss of the target, it is difficult to efficiently retrieve the target.
3. And target identification and tracking based on the laser radar. The laser radar can identify and track the vehicle target through geometric modeling, but the radar point cloud becomes sparse along with the increase of the distance, the detection distance of the vehicle target is limited, and accidents are easily caused in the high-speed tracking process of near-distance tracking, so that certain safety risks exist.
4. A target tracking method for transmitting position information based on radio communication. The method needs to build a positioning system and a radio communication system on the guide vehicle, and the guide vehicle is greatly improved and has no universality and economy. Meanwhile, potential safety risks such as radio transmission delay and electromagnetic interference influence exist, the potential safety risks are influenced by communication delay, the position precision of the guided vehicle is difficult to guarantee, and the control precision of the following vehicle is influenced.
Disclosure of Invention
Technical problem to be solved
The technical problem to be solved by the invention is as follows: how to realize the target recognition and continuous tracking of the guide vehicle is used for the autonomous vehicle following of the ground unmanned platform, thereby realizing the semi-autonomous maneuvering unmanned formation transportation guarantee.
(II) technical scheme
In order to solve the technical problems, the invention provides a method for identifying and tracking a guide vehicle target of a ground unmanned platform, which is realized by utilizing a vehicle-mounted system, wherein the system comprises combined navigation equipment, a three-dimensional laser radar, a millimeter wave radar and a vehicle-mounted industrial personal computer; after the guided vehicle runs for a certain distance, matching the tracking result of the millimeter wave radar with the tracking result of the three-dimensional laser radar after the target tracking result based on the point cloud data of the three-dimensional laser radar is stable, and switching to target tracking based on the millimeter wave radar; in the continuous tracking process, the attitude information provided by the integrated navigation equipment is used for integrating the historical track of target tracking, and the movement trend information of the guided vehicle is calculated by using a Kalman predictor in the vehicle-mounted industrial personal computer.
Preferably, the millimeter wave radar and the three-dimensional laser radar are both horizontally arranged in front of the vehicle; the inertial navigation equipment in the combined navigation equipment is arranged in the vehicle body, and the Y-axis direction is parallel to the central axis of the vehicle body in the advancing direction; the GPS/Beidou antenna in the combined navigation equipment is arranged on the outer side of the vehicle body and is not shielded; the vehicle-mounted industrial personal computer is installed in the unmanned platform vehicle body, the origin of a local coordinate system of the vehicle body is defined as the center of a rear axle of the vehicle body, the advancing direction of the vehicle body is the Y-axis forward direction, the horizontal right side perpendicular to the advancing direction of the vehicle body is the X-axis forward direction, the horizontal right side perpendicular to the advancing direction of the vehicle body is perpendicular to the horizontal plane, and the direction of the sky along the vehicle body is the Z-axis forward direction.
Preferably, before the movement trend information of the guided vehicle is obtained through calculation, external calibration parameters of the three-dimensional laser radar, the millimeter wave radar and the unmanned platform are obtained through combined calibration, and based on the external calibration parameters, the data of the millimeter wave radar, the three-dimensional laser radar, the GPS/Beidou antenna and the inertial navigation equipment are unified to a local coordinate system of the vehicle body by using a formula (1), so that the reference coordinate unification of the data is realized;
Figure BDA0003277648240000031
in the formula (1), psensor＝(xs,ys,zs)TRepresenting the coordinates of the data in a three-dimensional lidar coordinate system, pvehicle＝(xv,yv,zv)TRepresenting the coordinates of the data in the local coordinate system of the vehicle body,
Figure BDA0003277648240000032
in order to be a matrix of rotations,
Figure BDA0003277648240000033
the elements in the rotation matrix and the translation matrix are external calibration parameters.
Preferably, in the method, the states of guiding vehicle target identification and tracking are divided into four working states, namely target identification based on three-dimensional laser radar, target tracking based on millimeter wave radar, target tracking based on kalman prediction, and the like, and the implementation flow of each working state is as follows:
step 1: starting the guide vehicle;
step 2: entering a target identification state based on the three-dimensional laser radar, guiding vehicle target confirmation, and turning to the step 3;
and step 3: target tracking based on the three-dimensional laser radar is effective, and the step 4 is carried out, otherwise, the step 7 is carried out;
and 4, step 4: matching with a target detection result based on the millimeter wave radar, if so, turning to the step 5, otherwise, returning to the step 3;
and 5: carrying out target tracking based on a millimeter wave radar;
step 6: if the target is valid, returning to the step 5; otherwise, returning to the step 3;
and 7: performing target detection based on Kalman prediction;
and 8: judging the result of target detection based on Kalman prediction, if so, returning to the step 2, otherwise, returning to the step 7;
the above process is finished after receiving the end instruction, otherwise, the process is executed circularly all the time.
Preferably, in the method, according to a guiding-following maneuvering process, guiding of the ground unmanned platform is divided into 4 sub-processes of starting guiding-following, guiding-following in a continuous process, guiding-following started after parking, and guiding-following when a target is lost.
Preferably, the starting guiding-following subprocess is a flow of a method for identifying and tracking a target tracked by an autonomous vehicle of a ground unmanned platform under the starting condition of a guided vehicle, and comprises the following steps:
step 1: the method comprises the following steps that a guide vehicle is statically parked in a certain range in front of an unmanned platform, and a guide vehicle target identification and tracking program is started;
step 2: carrying out point cloud data acquisition and feature extraction on the guided vehicle through a three-dimensional laser radar, and identifying a target of the guided vehicle;
and step 3: the target identification result of the guided vehicle based on the three-dimensional laser radar is stable, and target initialization is completed;
and 4, step 4: starting target continuous tracking based on a laser radar, and converting a detection result of a local coordinate system of a vehicle body to a global coordinate system according to vehicle posture information acquired by integrated navigation equipment to form a historical tracking track;
and 5: the guiding vehicle dynamically and flexibly runs, and starts the unmanned platform to guide to advance according to the local position information tracked by the target;
step 6: starting vehicle target tracking based on the millimeter wave radar;
and 7: matching a dynamic target detection result of the millimeter wave radar with the continuous tracking target position information of the laser radar by using a Hungarian matching algorithm, and executing the step 8 after successful matching; otherwise, returning to the step 5;
and 8: continuously tracking the vehicle target based on the millimeter wave radar;
and step 9: estimating the position of the guided vehicle at the next moment by using a Kalman estimator according to the current target tracking position;
step 10: and setting the region of interest according to the predicted position, and returning to the step 8.
Preferably, the guiding-following sub-process in the continuous process is a process of detecting the target state of the guided vehicle and judging the transverse and longitudinal states of the guided vehicle in the tracking continuous process, and specifically includes the following steps:
step 1: acquiring the relative speed of the guided vehicle by using a millimeter wave radar;
step 2: calculating to obtain the speed information of the guided vehicle by combining the speed information of the vehicle provided by the combined navigation equipment;
and step 3: recording the local coordinate position of a guide vehicle target under each frame of data, and converting a target tracking result under a vehicle body local coordinate system to a global coordinate system according to vehicle posture information acquired by the integrated navigation equipment to form a historical track;
and 4, step 4: continuously detecting T periods, and judging the speed state of the guided vehicle by using a Bayesian network, wherein the speed state comprises uniform speed, acceleration, deceleration, sudden stop, parking and starting;
and 5: and predicting the transverse states of the vehicle, including straight running, left turning and right turning, by using a Kalman predictor according to the historical track information of the guided vehicle.
Preferably, the guidance-following subprocess started after parking is a process flow of target relocation and continuous tracking of the guided vehicle under the condition that the guided vehicle is started again after parking, and comprises the following steps:
step 1: judging whether the guide vehicle target under the millimeter wave radar is lost or not, if not, executing the step 2, otherwise, executing the step 3;
step 2: setting an area of interest, acquiring dynamic information of the guided vehicle by using a millimeter wave radar when the guided vehicle dynamically moves, and tracking a dynamic target of the guided vehicle based on the millimeter wave radar;
and step 3: and repeating the process of the target tracking identification and tracking method of the ground unmanned platform autonomous vehicle under the starting condition of the guided vehicle.
Preferably, the guidance-following sub-process under the target loss is a target tracking process processing flow under the conditions that the guidance vehicle is blocked, the target is lost temporarily and the like, and comprises the following steps:
step 1: if a millimeter wave radar detection result exists in the range of the region of interest, executing the step 2, otherwise, executing the step 3;
step 2: continuing target tracking based on the millimeter wave radar;
and step 3: judging whether a guide vehicle target tracking result based on the three-dimensional laser radar exists in the region of interest, if so, outputting the result, and executing the step 4, otherwise, executing the step 5;
and 4, step 4: matching a target detection result based on the millimeter wave radar with a target detection result based on the three-dimensional laser radar, if the results are matched, executing the step 2, otherwise, returning to the step 3;
and 5: predicting target information at the next moment by using a prediction result of a Kalman predictor according to historical track information, and outputting the predicted information;
step 6: searching for a target in the global range by using a laser radar, identifying the target of the guided vehicle, returning to the step 5 if no identification result exists, and otherwise, executing the step 7;
and 7: and repeating the process of the target tracking identification and tracking method of the ground unmanned platform autonomous vehicle under the starting condition of the guided vehicle.
The invention also provides a vehicle-mounted system adopted in the implementation process of the method.
(III) advantageous effects
The autonomous vehicle guide target identification and tracking method and the vehicle-mounted system provided by the invention provide a safe and reliable guide target identification and tracking scheme, can effectively realize guide-following unmanned formation transportation, save manpower support in the material transportation process, improve the intelligent level of a formation transportation system, and simultaneously improve the safety and reliability of the unmanned autonomous formation transportation system.
Drawings
FIG. 1 is a state diagram of the integrated guided vehicle target identification and tracking of the present invention;
FIG. 2 is a diagram illustrating the prediction of the target movement trend of the guided vehicle according to the present invention;
FIG. 3 is an overall flow diagram of the present invention;
FIG. 4 is a state diagram of guided vehicle target identification and tracking in accordance with the present invention;
FIG. 5 is an exploded view of the guide-follow target recognition and tracking process of the present invention.
Detailed Description
In order to make the objects, contents, and advantages of the present invention clearer, the following detailed description of the embodiments of the present invention will be made in conjunction with the accompanying drawings and examples.
The existing ground unmanned platform guiding-following system is limited by the limitation of a single sensor, and has defects in the aspects of speed, safety, tracking distance and the like. Meanwhile, the design of the guide-following system considers the economy and the universality, and the transformation of the guide vehicle is reduced as much as possible. In order to solve the problems, the invention provides a ground unmanned platform guided vehicle target identification and tracking method based on multi-source information fusion and a vehicle-mounted system, and particularly relates to an autonomous vehicle guided target identification and tracking method of a ground unmanned platform and a related vehicle-mounted system. A series of perception sensors are carried on the ground unmanned platform, the guide vehicle is not required to be transformed, target recognition and continuous tracking can be carried out on the guide vehicle, autonomous vehicle following of the ground unmanned platform is achieved, and semi-autonomous and maneuvering unmanned formation transportation guarantee is achieved.
The vehicle-mounted sensor comprises a three-dimensional laser radar, a millimeter wave radar and a combined navigation system (GPS/Beidou + inertial navigation equipment), the three-dimensional laser radar is used for solving the target identification problem of the guided vehicle and the target loss problem during steering, the millimeter wave radar is used for solving the remote target tracking problem in the dynamic high-speed tracking process, meanwhile, the influence of severe weather such as rain, snow and fog is avoided, and the stable tracking of the guided target under all-weather conditions is guaranteed. The integrated navigation system is used for correlating historical data of tracking information, is used for target relocation when tracking is lost, ensures the tracking continuity and improves the safety and reliability of the system. The safe and effective tracking distance of the guiding vehicle target identification and tracking system based on multi-sensor information fusion can reach 100 meters, and the system has great significance for realizing high-speed and stable tracking of the ground unmanned platform guiding and tracking system.
In order to achieve the aim, the method for identifying and tracking the vehicle target guided by the ground unmanned platform and the relevant hardware equipment of the vehicle-mounted system comprise combined navigation equipment (GPS/Beidou + inertial navigation), a three-dimensional laser radar, a millimeter wave radar, a vehicle-mounted industrial personal computer and the like. The vehicle-mounted system acquires environment perception information through the three-dimensional laser radar and the millimeter wave radar, and acquires the attitude information of the unmanned platform by using the integrated navigation equipment.
Referring to a figure 1, the overall identification and tracking state diagram of the method utilizes point cloud data acquired by a three-dimensional laser radar to perform feature extraction and guided vehicle modeling, so as to realize identification and tracking information initialization of a guided vehicle target; after the guided vehicle runs for a certain distance, matching the tracking result of the millimeter wave radar with the tracking result of the three-dimensional laser radar after the target tracking result based on the point cloud data of the three-dimensional laser radar is stable, and switching to target tracking based on the millimeter wave radar; in the continuous tracking process, the attitude information provided by the integrated navigation equipment is used for integrating the historical track of target tracking, and the movement trend information of the guided vehicle is calculated by using a Kalman predictor in the vehicle-mounted industrial personal computer. On the basis of target prediction of the guided vehicle, an interested area detected by the guided vehicle at the next moment is reduced, on one hand, the real-time performance of target detection of the guided vehicle is improved, on the other hand, interference of other vehicles in an irrelevant area is filtered, when the target of the guided vehicle is lost for a short time due to interference of factors such as shielding and the like, the system can keep the position of the guided vehicle at the last moment with effective tracking, target prediction information is output by combining the track trend of historical tracking, and the target identification and tracking processes are repeated, so that safe, reliable, stable and continuous target tracking is realized.
In the arrangement of a ground unmanned platform vehicle-mounted system, a perception sensor comprises a millimeter wave radar and a three-dimensional laser radar which are horizontally arranged in front of a vehicle; the inertial navigation equipment in the combined navigation equipment is arranged in the vehicle body, and the Y-axis direction is parallel to the central axis of the vehicle body in the advancing direction; the GPS/Beidou antenna in the combined navigation equipment is arranged on the outer side of the vehicle body and is not shielded; the vehicle-mounted industrial personal computer is installed in the unmanned platform vehicle body. The origin of a local coordinate system of the vehicle body is defined as the center of a rear axle of the vehicle body, the advancing direction of the vehicle body is the positive direction of a Y axis, the horizontal right side perpendicular to the advancing direction of the vehicle body is the positive direction of an X axis, the horizontal right side perpendicular to the advancing direction of the vehicle body is the positive direction of a Z axis, and the horizontal right side perpendicular to the horizontal plane is directed to the sky along the vehicle body. And (3) obtaining external calibration parameters of each sensor and the unmanned platform through combined calibration, unifying data of the millimeter wave radar, the three-dimensional laser radar, the GPS/Beidou antenna and the inertial navigation equipment to a local coordinate system of the vehicle body based on the external calibration parameters by using a formula (1), and realizing the unification of reference coordinates of the data so as to facilitate data fusion processing. The output information of the guiding target comprises the motion trend information of the vehicle guiding vehicle in the local coordinate system of the unmanned platform vehicle body, and the information is calculated by the vehicle-mounted industrial personal computer and is provided for the vehicle-mounted control system to perform tracking control, as shown in fig. 3.
Figure BDA0003277648240000091
In the formula (1), psensor＝(xs,ys,zs)TRepresenting the coordinates of the data in a three-dimensional lidar coordinate system, pvehicle＝(xv,yv,zv)TRepresenting the coordinates of the data in the local coordinate system of the vehicle body,
Figure BDA0003277648240000092
in order to be a matrix of rotations,
Figure BDA0003277648240000093
the elements in the rotation matrix and the translation matrix are external calibration parameters.
Referring to fig. 2, the guided vehicle motion trend prediction in the unmanned platform guided vehicle target identification and tracking includes lateral motion trend estimation and longitudinal motion trend estimation, wherein the lateral motion trend estimation is obtained by using a kalman predictor to predict the historical tracking track position of the guided vehicle target, and specifically includes straight traveling, left turning and right turning; and estimating the longitudinal motion trend, namely analyzing and obtaining the longitudinal motion trend according to the historical motion speed of the target of the guided vehicle by using a Bayesian network, wherein the longitudinal motion trend comprises starting, accelerating, decelerating, uniform speed, scram and parking states.
Referring to fig. 4, in the guidance-following process implemented by the vehicle-mounted system, according to the actual working state, the states of guiding vehicle target identification and tracking are divided into four working states, namely target identification based on a three-dimensional laser radar, target tracking based on a millimeter wave radar, and target tracking based on kalman prediction, and the implementation flows of the working states are as follows:
step 1: starting the guide vehicle;
step 2: entering a target identification state based on the three-dimensional laser radar, guiding vehicle target confirmation, and turning to the step 3;
and step 3: target tracking based on the three-dimensional laser radar is effective, and the step 4 is carried out, otherwise, the step 7 is carried out;
and 4, step 4: matching with a target detection result based on the millimeter wave radar, if so, turning to the step 5, otherwise, returning to the step 3;
and 5: carrying out target tracking based on a millimeter wave radar;
step 6: if the target is valid, returning to the step 5; otherwise, returning to the step 3;
and 7: performing target detection based on Kalman prediction;
and 8: judging the result of target detection based on Kalman prediction, if so, returning to the step 2, otherwise, returning to the step 7;
the above process is finished after receiving the end instruction, otherwise, the process is executed circularly all the time.
Referring to fig. 5, according to the maneuvering process of guidance-following, guidance of the ground unmanned platform is divided into 4 sub-processes of starting guidance-following, guidance-following in the continuous process, guidance-following started again after parking, and guidance-following when the target is lost, and target identification and tracking of the guided vehicle in the 4 sub-processes are respectively explained.
Launch guidance-following subprocess: the process of the ground unmanned platform autonomous vehicle tracking target recognition and tracking method under the starting condition of the guide vehicle comprises the following steps:
step 1: the method comprises the following steps that a guide vehicle is statically parked in a certain range in front of an unmanned platform, and a guide vehicle target identification and tracking program is started;
step 2: carrying out point cloud data acquisition and feature extraction on the guided vehicle through a three-dimensional laser radar, and identifying a target of the guided vehicle;
and step 3: the target identification result of the guided vehicle based on the three-dimensional laser radar is stable, and target initialization is completed;
and 4, step 4: continuously tracking and starting a target based on a laser radar, and converting a detection result of a local coordinate system of a vehicle body to a global coordinate system according to vehicle posture information acquired by integrated navigation equipment to form a historical tracking track;
and 5: the guiding vehicle dynamically and flexibly runs, and starts the unmanned platform to guide to advance according to the local position information tracked by the target;
step 6: starting vehicle target tracking based on the millimeter wave radar;
and 7: matching a dynamic target detection result of the millimeter wave radar with the continuous tracking target position information of the laser radar by using a Hungarian matching algorithm, and turning to the step 8 if the matching is successful; otherwise, turning to the step 5;
and 8: continuously tracking the vehicle target based on the millimeter wave radar;
and step 9: estimating the position of the guided vehicle at the next moment by using a Kalman estimator according to the current target tracking position;
step 10: and setting the region of interest according to the predicted position, and returning to the step 8.
Leading-following sub-process in continuous process: detecting the target state of the guided vehicle in the continuous tracking process, and judging the transverse state and the longitudinal state of the guided vehicle, wherein the specific process comprises the following steps:
step 1: acquiring the relative speed of the guided vehicle by using a millimeter wave radar;
step 2: calculating to obtain the speed information of the guided vehicle by combining the speed information of the vehicle provided by the combined navigation equipment;
and step 3: recording the local coordinate position of a guide vehicle target under each frame of data, and converting a target tracking result under a vehicle body local coordinate system to a global coordinate system according to vehicle posture information acquired by the integrated navigation equipment to form a historical track;
and 4, step 4: continuously detecting T periods, and judging the speed state of the guided vehicle by using a Bayesian network, wherein the speed state comprises uniform speed, acceleration, deceleration, sudden stop, parking, starting and the like;
and 5: and predicting the transverse states of the vehicle, including straight running, left turning and right turning, by using a Kalman predictor according to the historical track information of the guided vehicle.
Boot-follower sub-process restarted after parking: after the guided vehicle stops, the guided vehicle target repositioning and continuous tracking processing flow under the starting condition is as follows:
step 1: judging whether the guide vehicle target under the millimeter wave radar is lost or not, and turning to the step 2, otherwise, turning to the step 3;
step 2: setting an area of interest, acquiring dynamic information of the guided vehicle by using a millimeter wave radar when the guided vehicle dynamically moves, and tracking a dynamic target of the guided vehicle based on the millimeter wave radar;
and step 3: and repeating the process of the target tracking identification and tracking method of the ground unmanned platform autonomous vehicle under the starting condition of the guided vehicle.
The guide-follower sub-process with target lost: the target tracking process under the conditions that the guide vehicle is shielded, the target is temporarily lost and the like comprises the following processing flows:
step 1: if a millimeter wave radar detection result exists in the region of interest, turning to the step 2, otherwise, turning to the step 3;
step 2: continuing target tracking based on the millimeter wave radar;
and step 3: judging whether a guide vehicle target tracking result based on the three-dimensional laser radar exists in the region of interest, outputting the result, and turning to the step 4, otherwise, turning to the step 5;
and 4, step 4: matching a target detection result based on the millimeter wave radar with a target detection result based on the three-dimensional laser radar, if the results are matched, turning to the step 2, otherwise, turning to the step 3;
and 5: predicting target information at the next moment by using a prediction result of a Kalman predictor according to historical track information, and outputting the predicted information;
step 6: searching for a target in the global range by using a laser radar, identifying the target of the guided vehicle, turning to the step 5 if no identification result exists, and turning to the step 7 if no identification result exists;
and 7: and repeating the process of the target tracking identification and tracking method of the ground unmanned platform autonomous vehicle under the starting condition of the guided vehicle.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.

Claims (10)

1. A method for identifying and tracking a guide vehicle target of a ground unmanned platform is characterized in that the method is realized by utilizing a vehicle-mounted system, the system comprises a combined navigation device, a three-dimensional laser radar, a millimeter wave radar and a vehicle-mounted industrial personal computer, in the method, point cloud data obtained by the three-dimensional laser radar is utilized for feature extraction and guide vehicle modeling, and identification and tracking information initialization of the guide vehicle target are realized; after the guided vehicle runs for a certain distance, matching the tracking result of the millimeter wave radar with the tracking result of the three-dimensional laser radar after the target tracking result based on the point cloud data of the three-dimensional laser radar is stable, and switching to target tracking based on the millimeter wave radar; in the continuous tracking process, the attitude information provided by the integrated navigation equipment is used for integrating the historical track of target tracking, and the movement trend information of the guided vehicle is calculated by using a Kalman predictor in the vehicle-mounted industrial personal computer.
2. The method of claim 1, wherein both the millimeter wave radar and the three-dimensional lidar are mounted horizontally in front of a vehicle; the inertial navigation equipment in the combined navigation equipment is arranged in the vehicle body, and the Y-axis direction is parallel to the central axis of the vehicle body in the advancing direction; the GPS/Beidou antenna in the combined navigation equipment is arranged on the outer side of the vehicle body and is not shielded; the vehicle-mounted industrial personal computer is installed in the unmanned platform vehicle body, the origin of a local coordinate system of the vehicle body is defined as the center of a rear axle of the vehicle body, the advancing direction of the vehicle body is the Y-axis forward direction, the horizontal right side perpendicular to the advancing direction of the vehicle body is the X-axis forward direction, the horizontal right side perpendicular to the advancing direction of the vehicle body is perpendicular to the horizontal plane, and the direction of the sky along the vehicle body is the Z-axis forward direction.
3. The method of claim 1, wherein before the motion trend information of the guided vehicle is calculated, external calibration parameters of the three-dimensional laser radar, the millimeter wave radar and the unmanned platform are obtained through combined calibration, and based on the external calibration parameters, data of the millimeter wave radar, the three-dimensional laser radar, the GPS/Beidou antenna and the inertial navigation equipment are unified to a local coordinate system of the vehicle body by using a formula (1), so that the reference coordinates of the data are unified;
Figure FDA0003277648230000011
in the formula (1), psensor＝(xs,ys,zs)TRepresenting the coordinates of the data in a three-dimensional lidar coordinate system, pvehicle＝(xv,yv,zv)TRepresenting the coordinates of the data in the local coordinate system of the vehicle body,
Figure FDA0003277648230000021
in order to be a matrix of rotations,
Figure FDA0003277648230000022
the elements in the rotation matrix and the translation matrix are external calibration parameters.
4. The method of claim 1, wherein the states of guiding vehicle target recognition and tracking are divided into four working states of target recognition based on three-dimensional laser radar, target tracking based on millimeter wave radar, target tracking based on kalman prediction, and the realization flow of each working state is as follows:
step 1: starting the guide vehicle;
step 2: entering a target identification state based on the three-dimensional laser radar, guiding vehicle target confirmation, and turning to the step 3;
and step 3: target tracking based on the three-dimensional laser radar is effective, and the step 4 is carried out, otherwise, the step 7 is carried out;
and 4, step 4: matching with a target detection result based on the millimeter wave radar, if so, turning to the step 5, otherwise, returning to the step 3;
and 5: carrying out target tracking based on a millimeter wave radar;
step 6: if the target is valid, returning to the step 5; otherwise, returning to the step 3;
and 7: performing target detection based on Kalman prediction;
and 8: judging the result of target detection based on Kalman prediction, if so, returning to the step 2, otherwise, returning to the step 7;
the above process is finished after receiving the end instruction, otherwise, the process is executed circularly all the time.
5. The method as claimed in claim 1, characterized in that in the method, the guidance of the ground unmanned platform is divided into 4 sub-processes of starting guidance-following, guidance-following in a continuous process, guidance-following started again after parking, guidance-following with target lost, according to a maneuvering process of guidance-following.
6. The method as claimed in claim 5, wherein the launch guidance-following sub-process is a flow of a ground unmanned platform autonomous vehicle tracking target recognition and tracking method in a launch condition of the lead vehicle, comprising the steps of:
step 11: the method comprises the following steps that a guide vehicle is statically parked in a certain range in front of an unmanned platform, and a guide vehicle target identification and tracking program is started;
step 12: carrying out point cloud data acquisition and feature extraction on the guided vehicle through a three-dimensional laser radar, and identifying a target of the guided vehicle;
step 13: the target identification result of the guided vehicle based on the three-dimensional laser radar is stable, and target initialization is completed;
step 14: starting target continuous tracking based on a laser radar, and converting a detection result of a local coordinate system of a vehicle body to a global coordinate system according to vehicle posture information acquired by integrated navigation equipment to form a historical tracking track;
step 15: the guiding vehicle dynamically and flexibly runs, and starts the unmanned platform to guide to advance according to the local position information tracked by the target;
step 16: starting vehicle target tracking based on the millimeter wave radar;
and step 17: matching the dynamic target detection result of the millimeter wave radar with the continuous tracking target position information of the laser radar by using a Hungarian matching algorithm, and executing the step 18 after successful matching; otherwise, returning to the step 15;
step 18: continuously tracking the vehicle target based on the millimeter wave radar;
step 19: estimating the position of the guided vehicle at the next moment by using a Kalman estimator according to the current target tracking position;
step 110: and setting the region of interest according to the predicted position, and returning to the step 18.
7. The method as claimed in claim 5, wherein the guiding-following sub-process in the continuous process is a process of detecting the target state of the guided vehicle and judging the transverse and longitudinal states of the guided vehicle in the tracking continuous process, and specifically comprises the following steps:
step 21: acquiring the relative speed of the guided vehicle by using a millimeter wave radar;
step 22: calculating to obtain the speed information of the guided vehicle by combining the speed information of the vehicle provided by the combined navigation equipment;
step 23: recording the local coordinate position of a guide vehicle target under each frame of data, and converting a target tracking result under a vehicle body local coordinate system to a global coordinate system according to vehicle posture information acquired by the integrated navigation equipment to form a historical track;
step 24: continuously detecting T periods, and judging the speed state of the guided vehicle by using a Bayesian network, wherein the speed state comprises uniform speed, acceleration, deceleration, sudden stop, parking and starting;
step 25: and predicting the transverse states of the vehicle, including straight running, left turning and right turning, by using a Kalman predictor according to the historical track information of the guided vehicle.
8. The method of claim 6, wherein the boot-follower sub-process of restarting after parking is a process of target repositioning and tracking continuation of the lead vehicle under a condition of restarting after parking of the lead vehicle, comprising the steps of:
step 31: judging whether the guide vehicle target under the millimeter wave radar is lost or not, if not, executing the step 32, otherwise, executing the step 33;
step 32: setting an area of interest, acquiring dynamic information of the guided vehicle by using a millimeter wave radar when the guided vehicle dynamically moves, and tracking a dynamic target of the guided vehicle based on the millimeter wave radar;
step 33: and repeating the process of the target tracking identification and tracking method of the ground unmanned platform autonomous vehicle under the starting condition of the guided vehicle.
9. The method of claim 6, wherein the guidance-following sub-process under target loss is a target tracking process flow under the condition that the guided vehicle is blocked, the target is temporarily lost and the like, and the method comprises the following steps:
step 41: if the millimeter wave radar detection result exists in the range of the region of interest, executing step 42, otherwise, executing step 43;
step 42: continuing target tracking based on the millimeter wave radar;
step 43: judging whether a guide vehicle target tracking result based on the three-dimensional laser radar exists in the region of interest, if so, outputting the result, and executing the step 44, otherwise, executing the step 45;
step 44: matching the target detection result based on the millimeter wave radar with the target detection result based on the three-dimensional laser radar, if the results are matched, executing the step 42, otherwise, returning to the step 43;
step 45: predicting target information at the next moment by using a prediction result of a Kalman predictor according to historical track information, and outputting the predicted information;
step 46: searching for a target in the global range by using the laser radar, identifying the target of the guided vehicle, returning to the step 45 if no identification result exists, and otherwise, executing the step 47;
step 47: and repeating the process of the target tracking identification and tracking method of the ground unmanned platform autonomous vehicle under the starting condition of the guided vehicle.
10. An on-board system for use in carrying out the method of any one of claims 1 to 9.
CN202111122185.XA 2021-09-24 2021-09-24 Method for identifying and tracking guided vehicle target of ground unmanned platform and vehicle-mounted system Active CN113702967B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111122185.XA CN113702967B (en) 2021-09-24 2021-09-24 Method for identifying and tracking guided vehicle target of ground unmanned platform and vehicle-mounted system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111122185.XA CN113702967B (en) 2021-09-24 2021-09-24 Method for identifying and tracking guided vehicle target of ground unmanned platform and vehicle-mounted system

Publications (2)

Publication Number Publication Date
CN113702967A true CN113702967A (en) 2021-11-26
CN113702967B CN113702967B (en) 2023-07-28

Family

ID=78661892

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111122185.XA Active CN113702967B (en) 2021-09-24 2021-09-24 Method for identifying and tracking guided vehicle target of ground unmanned platform and vehicle-mounted system

Country Status (1)

Country Link
CN (1) CN113702967B (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107609522A (en) * 2017-09-19 2018-01-19 东华大学 A kind of information fusion vehicle detecting system based on laser radar and machine vision
JP2018092483A (en) * 2016-12-06 2018-06-14 トヨタ自動車株式会社 Object recognition device
CN109739266A (en) * 2018-12-03 2019-05-10 中国北方车辆研究所 A kind of follow-up control method of the unmanned shipping platform in ground
CN109829386A (en) * 2019-01-04 2019-05-31 清华大学 Intelligent vehicle based on Multi-source Information Fusion can traffic areas detection method
CN110175186A (en) * 2019-05-15 2019-08-27 中国舰船研究设计中心 A kind of intelligent ship environmental threat target apperception system and method
WO2021077287A1 (en) * 2019-10-22 2021-04-29 华为技术有限公司 Detection method, detection device, and storage medium
WO2022156176A1 (en) * 2021-01-22 2022-07-28 上海西井信息科技有限公司 Multi-radar and camera joint calibration method, system and device, and storage medium

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2018092483A (en) * 2016-12-06 2018-06-14 トヨタ自動車株式会社 Object recognition device
CN107609522A (en) * 2017-09-19 2018-01-19 东华大学 A kind of information fusion vehicle detecting system based on laser radar and machine vision
CN109739266A (en) * 2018-12-03 2019-05-10 中国北方车辆研究所 A kind of follow-up control method of the unmanned shipping platform in ground
CN109829386A (en) * 2019-01-04 2019-05-31 清华大学 Intelligent vehicle based on Multi-source Information Fusion can traffic areas detection method
CN110175186A (en) * 2019-05-15 2019-08-27 中国舰船研究设计中心 A kind of intelligent ship environmental threat target apperception system and method
WO2021077287A1 (en) * 2019-10-22 2021-04-29 华为技术有限公司 Detection method, detection device, and storage medium
WO2022156176A1 (en) * 2021-01-22 2022-07-28 上海西井信息科技有限公司 Multi-radar and camera joint calibration method, system and device, and storage medium

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
刘全周等: "改进的交互式卡尔曼滤波对雷达数据处理技术研究", 《机械科学与技术》, vol. 39, no. 08, pages 1248 - 1255 *
金立生等: "基于优化DeepSort的前方车辆多目标跟踪", 《浙江大学学报(工学版)》, vol. 55, no. 6, pages 1056 - 1064 *

Also Published As

Publication number Publication date
CN113702967B (en) 2023-07-28

Similar Documents

Publication Publication Date Title
US11768286B2 (en) Method of determining the yaw rate of a target vehicle
CN107450530B (en) Vehicle control system, vehicle position determination device, method, and storage medium
CN109358340B (en) AGV indoor map construction method and system based on laser radar
US10705220B2 (en) System and method for ground and free-space detection
US11125567B2 (en) Methods and systems for mapping and localization for a vehicle
CN112154455B (en) Data processing method, equipment and movable platform
US10705534B2 (en) System and method for ground plane detection
US11945499B2 (en) Method and apparatus for trailer angle measurement and vehicle
CN114442101B (en) Vehicle navigation method, device, equipment and medium based on imaging millimeter wave radar
EP3945336A1 (en) Method and apparatus for positioning movable device, and movable device
CN113124864A (en) Water surface navigation method adopting machine vision and inertial navigation fusion
Babak et al. Control of autonomous ground vehicles: A brief technical review
CN111857121A (en) Patrol robot walking obstacle avoidance method and system based on inertial navigation and laser radar
CN114383598A (en) Tunnel construction operation vehicle and automatic driving system thereof
EP4160269A1 (en) Systems and methods for onboard analysis of sensor data for sensor fusion
CN113702967B (en) Method for identifying and tracking guided vehicle target of ground unmanned platform and vehicle-mounted system
CN113734197A (en) Unmanned intelligent control scheme based on data fusion
CN111862654A (en) Intelligent navigation method, application, intelligent navigation system and vehicle
US20230168363A1 (en) Method to detect radar installation error for pitch angle on autonomous vehicles
US20230242148A1 (en) Vehicle controller and vehicle control method
CN114379584B (en) Vehicle control method, device, vehicle, equipment and storage medium
CN111932883B (en) Method for guiding unmanned driving by utilizing broadcast communication of road side equipment
CN114834447B (en) Collision risk prediction method and device based on automatic parking trajectory
US20240051519A1 (en) Vehicle Localization Based on Pose Corrections from Remote Cameras
Fu et al. Research on On-Board Multi-Sensor Fusion Algorithm based on Data Correlation

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