CN111284502B - Method and system for detecting pose of tractor group - Google Patents
Method and system for detecting pose of tractor group Download PDFInfo
- Publication number
- CN111284502B CN111284502B CN202010160986.4A CN202010160986A CN111284502B CN 111284502 B CN111284502 B CN 111284502B CN 202010160986 A CN202010160986 A CN 202010160986A CN 111284502 B CN111284502 B CN 111284502B
- Authority
- CN
- China
- Prior art keywords
- data
- trailer
- pose
- coordinate
- data block
- 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
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
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/0098—Details of control systems ensuring comfort, safety or stability not otherwise provided for
-
- 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
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0062—Adapting control system settings
- B60W2050/0075—Automatic parameter input, automatic initialising or calibrating means
Abstract
The invention provides a method and a system for detecting the pose of a tractor set, wherein the method comprises the following steps: s1, setting a scanning range of the scanning unit to at least partially cover characteristic points of a hanging vehicle behind the traction vehicle head; s2, setting a global coordinate system by taking a preset position of the traction vehicle head as a reference point; s3, the calculation unit acquires the scanning data acquired by the scanning unit, and acquires data blocks after data segmentation processing; the S4 calculation unit calls the feature library comparison data block and identifies feature point data in the data block; and the S5 calculation unit calculates the orientation of the coordinate system where the feature point data are located according to the global coordinate system to obtain the pose of the feature point data, so that the pose of the mounting vehicle in the tractor set relative to the tractor head is effectively detected without modifying the mounting vehicle.
Description
Technical Field
The invention relates to the technical field of automatic driving, in particular to a method and a system for detecting the running pose of a trailer in a tractor group by using an object identification technical means.
Background
The tractor group is the most numerous vehicle type in the logistics scene, is also the most main vehicle type of unmanned storage, mainly is used for the transportation of goods between different places. A tractor consist usually consists of a tractor head providing traction and several rear trailers carrying cargo. During operation of a tractor-trailer combination, it is often necessary to transfer goods from each trailer to a freight platform to transfer the goods on the trailer to the freight platform.
The unmanned tractor set in the prior art mainly utilizes an advanced artificial intelligence technology to realize automatic operation of the tractor set, namely, the tractor set can automatically convey goods from an initial position to a target position without being controlled by a human driver. Similar to the unmanned system of a passenger car, the unmanned tractor set system mainly consists of three parts of perception, decision and control. The sensing module acquires environmental information around the road by using various sensors. The collected environmental information is processed and then sent to a decision module, and the behavior of the tractor is decided according to the current state. And the control module controls the tractor group according to the decision result.
In the current tractor set in the prior art, the detection of the pose of the trailer is mainly realized by additionally arranging a corresponding sensor in the trailer. For example, one method is to add an angle sensor at a trailer hook and feed back the angle of the trailer relative to the tractor head in real time, so as to calculate the pose of the trailer relative to the tractor head. The method has the disadvantages that the method mainly needs an angle sensor with higher precision and has high cost; meanwhile, the hook is a main stress point of the trailer, and abrasion is easily caused, so that the measurement precision and the service life are influenced.
Another prior art method is to add encoders to two wheels of a trailer to obtain the rotation angle of the two wheels, thereby indirectly calculating the pose of the trailer relative to a tractor head. The disadvantages of the method are mainly that the wheel inevitably slips during operation, thereby affecting the measurement accuracy, and the longer the running time is, the larger the accumulated error is; meanwhile, when a new trailer is hung on the traction vehicle head every time, the encoder needs to be subjected to zeroing calibration, the operation is complex, the requirement on the calibration precision is high, and the technical implementation obstacles are more.
In addition, the above two prior art schemes also have a common objective technical defect that the number of trailers is usually far greater than that of tractor heads in a general use scene, so that great refitting cost is generated no matter refitting the trailer hook or the trailer vehicle. In addition, the sensors on the trailer are powered and data transmitted, extra wiring is required to be added, and the maintenance cost of the system is increased while the technical implementation complexity is increased.
Disclosure of Invention
The invention mainly aims to provide a method and a system for detecting the pose of a tractor set, which are used for effectively detecting the pose of a mounting vehicle in the tractor set relative to a tractor head without modifying the mounting vehicle.
In order to achieve the above object, according to an aspect of the present invention, there is provided a method for detecting a pose of a tractor group, the method including the steps of:
s1, setting a scanning range of the scanning unit to at least partially cover characteristic points of a hanging vehicle behind the traction vehicle head; wherein the car feature points include: at least one of a wheel or a car;
s2, setting a global coordinate system by taking a preset position of the traction vehicle head as a reference point;
s3, the calculation unit acquires the scanning data acquired by the scanning unit, and acquires data blocks after data segmentation processing;
the S4 calculation unit calls the feature library comparison data block and identifies feature point data in the data block;
and the S5 calculation unit calculates the orientation of the coordinate system where the feature point data is located according to the global coordinate system, and acquires the pose of the feature point data.
Optionally, in the method for detecting the pose of the tractor group, the scanning data is coordinate point data, and the data segmentation processing step includes:
s3.1, analyzing coordinate point data from near to far relative to a reference point by adopting a clustering algorithm;
and S3.2, clustering to form a data block when the coordinate point data is judged to be approximately positioned on a straight line.
Optionally, the step of comparing the feature library in step S3 includes:
s4.1, generating a point cloud by the data block to be fitted with the outline of the feature model stored in the feature library to obtain feature point data;
and S4.2, marking the feature point data judged by the fitting in the step S4.1, wherein the feature point data comprises any one of a trailer data block, a platform truck data block and an obstacle data block.
Optionally, the step of calculating the relative coordinate position of the data block in step S4 includes:
s5.1, calculating the coordinate distance between the coordinate point of the trailer data block and the reference point, and judging that the trailer is the fifth section of trailer;
and S5.2, calculating the coordinate position of the coordinate point of the trailer data block in the global coordinate system, and judging the driving pose of the trailer.
Optionally, the method for detecting the pose of the tractor group further includes the following steps:
s5.3, calculating the coordinate distance between the coordinate point of the platform truck data block and the reference point, and judging the distance between the coordinate point of the platform truck data block and the trailer;
and S5.4, calculating the coordinate position of the coordinate point of the platform truck data block in the global coordinate system, and judging the relative pose of the platform truck and the trailer.
Optionally, the method for detecting the pose of the tractor group further includes the following steps:
s5.5, calculating the coordinate distance between the coordinate point of the obstacle data block and the reference point, and judging the distance between the coordinate point of the obstacle data block and the trailer;
and S5.6, calculating the coordinate position of the coordinate point of the obstacle data block in the global coordinate system, and judging the relative pose of the obstacle and the trailer.
Optionally, the scanning unit is disposed below the tractor vehicle and is configured to scan the baseline over at least a portion of at least one of the trailer wheels or the flatbed wheels.
Optionally, the feature library includes: at least one of trailer wheel characterization data or flatbed wheel characterization data.
Optionally, step S5 may be replaced by: and the calculating unit calculates the relative orientation in the coordinate system of the feature point data according to the global coordinate system to acquire the pose of the feature point data.
In order to achieve the above object, according to another aspect of the present invention, there is also provided a tractor group pose detection system including: the system comprises a scanning unit, a calculating unit, a storage unit and a power supply module, wherein the storage unit stores the position and the attitude detection method and the characteristic library of the tractor group, the scanning unit is fixed at a preset position of a tractor head and is in communication connection with the calculating unit to transmit scanning data, so that the calculating unit can call the position and the attitude detection method and the characteristic library of the tractor group stored in the storage unit to execute processing of the scanning data.
The method and the system for detecting the pose of the tractor group can effectively detect the pose of the mounting vehicle in the tractor group relative to the tractor head without modifying the mounting vehicle, have the advantages of low implementation cost, stable detection precision, high reliability, certain improvement of service life compared with the prior art, direct application to the tractor group in the prior art, low technical implementation difficulty, contribution to technical popularization and high commercial application value.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the invention and, together with the description, serve to explain the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic diagram of an exemplary configuration of a trailer of the present invention for a tractor consist pose detection system;
FIG. 2 is a schematic diagram of an exemplary configuration of a trailer of the present invention for a tractor consist pose detection system;
FIG. 3 is a schematic diagram of an exemplary configuration of a dolly of the tractor group pose detection system of the invention;
FIG. 4 is a schematic structural diagram of a tractor group pose detection system of the present invention;
FIG. 5 is an exemplary pose detection diagram of a tractor consist pose detection system of the present invention;
FIG. 6 is a step diagram of a method for detecting a pose of a tractor group according to the present invention.
Detailed Description
The following describes in detail embodiments of the present invention. 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.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings.
In order to make those skilled in the art better understand the technical solution of the present invention, the technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," as well as any variations thereof, are intended to cover non-exclusive inclusions.
The tractor group in this case is mainly a tractor group consisting of at least one tractor head providing traction and at least one following load group/multiple load groups loading cargo, and the load group is described in the context of the identity of a trailer/platform vehicle, depending on its function, as follows: the use for transporting goods may be a trailer, such as: the use of the transshipment of cargo may be a dolly, so it can be seen that the identity of the dolly/trailer may be interchanged between uses, where possible, rather than completely separate its own function or structure.
In addition, in some embodiments of the present disclosure, the tractor group may also be a tractor group composed of a plurality of groups of tractor heads and mounted carrier groups thereof, such as: one tractor head carries the platform car and the other tractor head carries the trailer, and the two tractor head carry the platform car and the trailer can be adapted to complete the loading/unloading transfer function under possible conditions, so the invention does not limit the number of the tractor head car and the trailer car in the tractor group, or whether the tractor head car and the trailer car are physically connected or are in independent operation forms.
(A)
Specifically, as shown in fig. 1 to 5, the system for detecting the pose of the tractor group provided by the present invention mainly includes: the system comprises a scanning unit, a calculating unit, a storage unit and a power supply module, wherein the power supply module is respectively used for supplying power for the scanning unit, the calculating unit and the storage module, the storage unit is stored with a tractor group pose detection method and a feature library, the scanning unit is fixed at a preset position of a tractor head and is in communication connection with the calculating unit, scanning data are transmitted, so that the calculating unit can call the tractor group pose detection method and the feature library stored in the storage unit to execute processing of the scanning data, and therefore the driving pose of the trailer/platform truck in the tractor group is detected.
Wherein this scanning unit under this embodiment is preferably lidar, and its scanning range covers the locomotive rear of drawing at least partially, and effective measurement distance as lidar needs to be greater than the total length of the trailer/flatcar of mount, and this lidar's effective measurement angle need can cover the trailer position of trailer/flatcar when going straight and turning. It should be noted that the scanning unit may also be used in the present implementation, for example: sonic radars, image scanning devices, and the like, as well as other prior art scanning devices, and thus any alternative embodiment that falls within the spirit of the present invention is within the scope of the present disclosure.
As shown in fig. 1-3, wherein the lidar is preferably symmetrically affixed to the rear of the tractor head such that the scanning baseline covers at least a portion of at least one of the trailer wheels or the flatbed wheels. It should be noted that the setting of the scanning baseline in this embodiment may vary according to the type of the feature points to be identified, for example, in this embodiment, the scanning range preferably covers the wheel and/or car area of each trailer/flatbed, so that at least one of the wheel or car of the trailer/flatbed within the scanning baseline range may be set as the feature point for the judgment of the subsequent scanning data. It is understood that the adjustment of the scanning baseline can be adjusted and changed according to the feature points to be identified, and is not limited, so that any scanning baseline adjustment manner and feature point change within the scope of the inventive concept are all within the disclosure of the embodiments of the present invention.
In addition, in order to adapt to the identification of the scanning data of the feature point, the feature library at least stores the feature data of the wheels of the trailer/platform truck, so that the scanning data acquired by the scanning unit can be compared with the feature data, and whether the feature data is the condition of the trailer/platform truck and the current driving pose thereof is judged. Specifically, in order to determine the relative position of the scanning data, a reference point of a data coordinate needs to be preset, for example, the position of the scanning device fixed at the traction vehicle head is set as the reference point to perform position solidification, and a global coordinate system is established by using the reference point, so that an absolute position point of the whole coordinate is determined, and a basis is provided for subsequently calculating the relative position of each scanning data.
And then, initializing and correcting the laser radar according to the reference point, namely, starting scanning, acquiring scanning data on the scanning baseline, and transmitting the scanning data to a computing unit, wherein the computing unit cannot be directly used for judging the pose after receiving the scanning data, and in order to improve the computing efficiency, firstly, the scanning data needs to be segmented to screen out qualified data blocks. Specifically, according to the preset feature points of the trailer/platform truck, such as the wheel feature points in the embodiment, the calculation unit analyzes the scanning point data of the laser radar from near to far by using a clustering algorithm, and if the points are approximately located on a straight line, the points are considered to belong to the same category; otherwise, restarting a cluster, thereby preliminarily screening the data blocks belonging to the same category.
The block of data will then be subject to object recognition to determine whether the block of data describes a certain trailer/platform in the tractor consist or an obstacle around the trailer. Wherein because trailer and platform truck all have regular geometric characteristics, consequently can carry out object identification according to the geometric characteristics of trailer or platform truck, judge when this object is a trailer or platform truck. The specific identification method comprises the following steps: fitting the outline of the trailer/platform truck and the characteristic model data in a preset characteristic library by converting the data block into the geometrical data of the laser point cloud, and mainly judging whether the characteristic point positions, namely the positions of wheels, in the outline of the trailer/platform truck exist or not; if the fitting can be successfully realized, classifying the feature model data according to the data type of the feature model in the adapted feature library, such as outputting a data block containing position data of corresponding feature points of the trailer/platform truck label; if the data block cannot be fit into the trailer/flatcar data block, the data block is judged as the surrounding obstacle data block.
According to the identification result, the calculation unit respectively calculates the various trailers, the platform cars and the obstacle data blocks so as to at least obtain the distance and the position of the trailers, the platform cars and the obstacle data blocks relative to the tractor head or the distance and the position of the trailers, the platform cars and the obstacle data blocks relative to the tractor head, and the specific calculation method comprises the following steps:
the calculation unit can calculate the orientation of each data block in the current coordinate according to the global coordinate system so as to judge the pose of each data block. Specifically, the distance between the coordinate point of the trailer data block and the coordinate of the reference point in the global coordinate system is calculated, so that the trailer can be judged as the fifth section of the trailer; and meanwhile, calculating the coordinate position of the coordinate point of the trailer data block in the global coordinate system, and judging the current running pose of the trailer.
As shown in fig. 5, the laser radars C1-C2 are respectively disposed on the tractor head B, and the detection ranges are set to be wider, and those skilled in the art can understand that in the present embodiment, the calculation amount and the implementation difficulty can be reduced according to the detection range reduction as shown in fig. 1, but the present embodiment provides a detailed inventive concept and a calculation process thereof, and preferably, a wide detection range is taken as an example for illustration, so that any other alternative embodiments that can reduce the detection range and be implemented along with the inventive concept are within the disclosure of the present invention.
In this embodiment, the reference point (origin) L of the global coordinate system is described by taking the location of the laser radar C1 as an example, wherein the tractor head B mounts the trailer a, and as shown in the figure, the feature point data block of the trailer a in the coordinate matrix is entirely in the form of a1-a4, so that it can be determined from the distance from the a1-a4 to the reference point L that it belongs to the several trailer sections, and it can be determined from the grid position of the coordinate whether it deviates from the preset reference of the X-axis and the Y-axis to determine whether it is in a rotating posture or a straight posture, and if it is required to accurately calculate the rotation angle, the rotation angle can be known by calculating the angle between the data block a1-a4 and the X-axis or the Y-axis, so as to accurately know the current posture of the trailer. Furthermore, it should be understood by those skilled in the art that if the accuracy of the calculation is further improved, the accuracy of the scanning device can be improved appropriately, and the accuracy of the global coordinate can be adjusted accordingly.
For the pose detection of the platform vehicle data block, the detection scheme of the trailer can be referred, and firstly, the coordinate distance between the characteristic point coordinate of the platform vehicle data block and the coordinate distance between the reference point L can be calculated, and the distance between the characteristic point coordinate of the platform vehicle data block and the trailer can be judged; and calculating the coordinate position of the characteristic point coordinate of the platform truck data block in the global coordinate system, and finally judging the relative pose of the platform truck D and the trailer A.
Specifically, as shown in fig. 5, the feature data blocks of the platform truck D in the coordinate matrix are entirely in the form of D1-D4, so that the distance from the trailer a can be determined from the distance from the reference point L to the D1-D4, and the position of the trailer a and the distance from each trailer can be further determined as needed, and in an alternative embodiment, the distance in coordinates between the data blocks D1-D4 and the data blocks a1-a4 can be calculated, so that the distance between the platform truck D and the trailer a can be obtained.
And then judging whether the grid position of the coordinate deviates from the preset reference of the X axis and the Y axis or not from the grid position of the coordinate so as to judge whether the grid position of the coordinate is in a rotating posture or a straight posture or not, if the rotating angle of the grid position is required to be accurately calculated, the rotating angle can be obtained by calculating the angle between the data blocks D1-D4 and the X axis or the Y axis, and the current posture condition of the platform truck D can be accurately known.
In an alternative embodiment, the angular relationships between D1-D4 and a1-a4 can be calculated, and the distance calculation step is assisted, so that the position and posture relationship data of the platform vehicle D and the corresponding/each trailer a can be obtained, and the position and posture relationship data can be used for adjusting the positions of the tractor groups by the tractor head to provide a control basis for completing the whole cargo transshipment operation. Therefore, the position and posture of the corresponding trailer/platform truck can be conveniently controlled and adjusted, the trailer/platform truck can gradually approach to each other, and the safe and accurate butt joint of the trailer and the platform truck is realized. Furthermore, it should be understood by those skilled in the art that if the accuracy of the calculation is further improved, the accuracy of the scanning device can be improved appropriately, and the accuracy of the global coordinate can be adjusted accordingly.
On the other hand, in order to improve the safety of the tractor group during running and provide a control basis for avoiding the obstacles during running of the tractor group, for the pose detection of the obstacle data block, the detection scheme of the trailer A and the platform vehicle D can be referred to, firstly, the coordinate distance between the characteristic point coordinate of the obstacle data block E and the reference point is calculated, and the distance between the characteristic point coordinate of the obstacle data block E and the trailer/platform vehicle is judged; and then calculating the coordinate position of the coordinate point of the obstacle data block E in the global coordinate system, and judging the relative pose of the obstacle and the trailer/platform truck.
Specifically, as shown in fig. 5, the feature point data block of the obstacle in the coordinate matrix is entirely in the form of E, so that the distance between the feature point data block and the trailer a/flatcar D can be determined from the distance between E and the reference point L, and the position of the feature point data block and the distance between the feature point data block and the trailer a/flatcar D can be further determined as required, and in an alternative embodiment, the distance between E and the data block a1-a4/D1-D4 in the coordinate can also be calculated, so that the distance between the obstacle and the trailer a/flatcar D can also be acquired to provide a control basis for obstacle avoidance.
On the other hand, in order to improve the detection precision, whether the grid position of the coordinate deviates from the preset reference of the X axis and the Y axis or not can be further judged so as to judge the posture of the obstacle or the posture position of the obstacle relative to the trailer A/the platform vehicle D, if the posture angle is required to be accurately calculated, the inclination angle can be known by calculating the angle between the data block E and the X axis or the Y axis, and the current posture condition of the obstacle can be accurately known.
In an alternative embodiment, the angular relationship between the E and the A1-A4/D1-D4 can be calculated, and the distance calculation step is assisted, so that the pose relationship data of the obstacle E and the platform vehicle D/trailer A can be obtained, the position between the tractor groups can be adjusted by the tractor head, a control basis is provided for avoiding the obstacle, and the running safety of the tractor groups is improved. Furthermore, it should be understood by those skilled in the art that if the accuracy of the calculation is further improved, the accuracy of the scanning device can be improved appropriately, and the accuracy of the global coordinate can be adjusted accordingly.
In conclusion, the system for detecting the position and the attitude of the tractor group provided by the invention can at least effectively detect the position and the attitude of a mounted vehicle in the tractor group relative to a tractor head without modifying a trailer, and has the advantages of low implementation cost, stable detection precision, high reliability, longer service life than the prior art, lower technical implementation difficulty, contribution to technical popularization and higher commercial application value, and the service life is improved to a certain extent.
(II)
As shown in fig. 6, another aspect of the present invention further provides a method for detecting a pose of a tractor group, so as to control the system for detecting a pose of a tractor group to detect a pose of a mounted vehicle in the tractor group relative to a tractor head, including the steps of:
s1, setting a scanning range of the scanning unit to at least partially cover characteristic points of a hanging vehicle behind the traction vehicle head; in an alternative embodiment, the scanning unit may be disposed below the tractor head and configured such that the scanning baseline covers at least a portion of at least one of the trailer wheels or the flatbed wheels.
S2, setting a global coordinate system by taking a preset position of the traction vehicle head as a reference point;
s3, the calculation unit acquires the scanning data acquired by the scanning unit, and acquires data blocks after data segmentation processing;
the S4 calculation unit calls the feature library comparison data block and identifies feature point data in the data block;
and the S5 calculation unit calculates the orientation of the coordinate system where the feature point data is located according to the global coordinate system, and acquires the pose of the feature point data. In an alternative embodiment, step S5 may be replaced with: and the calculating unit calculates the relative orientation in the coordinate system of the feature point data according to the global coordinate system to acquire the pose of the feature point data.
Wherein the scanning data is coordinate point data, and the data segmentation processing step comprises:
s3.1, analyzing coordinate point data from near to far relative to a reference point by adopting a clustering algorithm;
and S3.2, clustering to form a data block when the coordinate point data is judged to be approximately positioned on a straight line.
Wherein the step of comparing the feature library in step S3 includes:
s4.1, generating a point cloud by the data block to be fitted with the outline of the feature model stored in the feature library to obtain feature point data; wherein the feature library comprises: at least one of trailer wheel characterization data or flatbed wheel characterization data.
And S4.2, marking the feature point data judged by the fitting in the step S4.1, wherein the feature point data comprises any one of a trailer data block, a platform truck data block and an obstacle data block.
When the data block in the step S4 is a trailer data block, the step of calculating the relative coordinate position includes:
s5.1, calculating the coordinate distance between the coordinate point of the trailer data block and the reference point, and judging that the trailer is the fifth section of trailer;
and S5.2, calculating the coordinate position of the coordinate point of the trailer data block in the global coordinate system, and judging the driving pose of the trailer.
When the data block in step S4 is a platform truck data block, the step of calculating the relative coordinate position includes:
s5.3, calculating the coordinate distance between the coordinate point of the platform truck data block and the reference point, and judging the distance between the coordinate point of the platform truck data block and the trailer;
and S5.4, calculating the coordinate position of the coordinate point of the platform truck data block in the global coordinate system, and judging the relative pose of the platform truck and the trailer.
In an optional embodiment, S5.3 may also calculate a coordinate distance between the coordinate point of the flatcar data block and the coordinate point of the trailer data block, and determine the distance between the coordinate point of the flatcar data block and the trailer; and S5.4, calculating the coordinate position of the coordinate point of the platform truck data block relative to the coordinate point of the trailer data block in the global coordinate system, and judging the relative pose of the platform truck and the trailer.
When the data block in step S4 is an obstacle data block, the step of calculating the relative coordinate position includes:
s5.5, calculating the coordinate distance between the coordinate point of the obstacle data block and the reference point, and judging the distance between the coordinate point of the obstacle data block and the trailer;
and S5.6, calculating the coordinate position of the coordinate point of the obstacle data block in the global coordinate system, and judging the relative pose of the obstacle and the trailer.
In an alternative embodiment, S5.5 may also calculate a coordinate distance between the coordinate point of the obstacle data block and the coordinate point of the trailer/dolly data block, and determine the distance between the coordinate point of the obstacle data block and the trailer/dolly data block; and S5.6, calculating the coordinate position of the coordinate point of the obstacle data block relative to the coordinate point of the trailer/platform truck data block in the global coordinate system, and judging the relative pose of the obstacle and the trailer/platform truck.
Therefore, the method for detecting the position and the attitude of the tractor group at least can effectively control the system for detecting the position and the attitude of the trailer in the tractor group relative to the tractor head without modifying the trailer, has the advantages of lower implementation cost, stable detection precision, high reliability and longer service life compared with the prior art, can be directly applied to the tractor group in the prior art, has lower technical implementation difficulty, is beneficial to the popularization of the technology and has higher commercial application value.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise embodiments disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and the full scope and equivalents thereof, and any modification, equivalent replacement, or improvement made within the spirit and principle of the invention should be included in the protection scope of the invention.
It will be appreciated by those skilled in the art that, in addition to implementing the system, apparatus and various modules thereof provided by the present invention in the form of pure computer readable program code, the same procedures may be implemented entirely by logically programming method steps such that the system, apparatus and various modules thereof provided by the present invention are implemented in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Therefore, the system, the device and the modules thereof provided by the present invention can be considered as a hardware component, and the modules included in the system, the device and the modules thereof for implementing various programs can also be considered as structures in the hardware component; modules for performing various functions may also be considered to be both software programs for performing the methods and structures within hardware components.
In addition, all or part of the steps of the method according to the above embodiments may be implemented by a program instructing related hardware, where the program is stored in a storage medium and includes several instructions to enable a single chip, a chip, or a processor (processor) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In addition, any combination of various different implementation manners of the embodiments of the present invention is also possible, and the embodiments of the present invention should be considered as disclosed in the embodiments of the present invention as long as the combination does not depart from the spirit of the embodiments of the present invention.
Claims (10)
1. A method for detecting the pose of a tractor set comprises the following steps:
s1, setting a scanning range of the scanning unit to at least partially cover characteristic points of a hanging vehicle behind the traction vehicle head; wherein the car feature points include: at least one of a wheel or a car;
s2, setting a global coordinate system by taking a preset position of the traction vehicle head as a reference point;
s3, the calculation unit acquires the scanning data acquired by the scanning unit, and acquires data blocks after data segmentation processing;
the S4 calculation unit calls the feature library comparison data block and identifies feature point data in the data block;
and the S5 calculation unit calculates the orientation of the coordinate system where the feature point data is located according to the global coordinate system, and acquires the pose of the feature point data.
2. The method for detecting the pose of a consist of a traction vehicle as claimed in claim 1, wherein the scan data is coordinate point data, and the data segmentation processing step comprises:
s3.1, analyzing coordinate point data from near to far relative to a reference point by adopting a clustering algorithm;
and S3.2, clustering to form a data block when the coordinate point data is judged to be approximately positioned on a straight line.
3. The method for detecting the pose of a consist of locomotives according to claim 2, wherein the step of comparing the feature library in the step S4 comprises:
s4.1, generating a point cloud by the data block to be fitted with the outline of the feature model stored in the feature library to obtain feature point data;
and S4.2, marking the feature point data judged by the fitting in the step S4.1, wherein the feature point data comprises any one of a trailer data block, a platform truck data block and an obstacle data block.
4. The method for detecting the pose of a consist of a traction vehicle as claimed in claim 3, wherein the step of calculating the relative coordinate orientation of the data block in step S5 comprises:
s5.1, calculating the coordinate distance between the coordinate point of the trailer data block and the reference point, and judging that the trailer is the fifth section of trailer;
and S5.2, calculating the coordinate position of the coordinate point of the trailer data block in the global coordinate system, and judging the driving pose of the trailer.
5. The method for detecting the pose of a tractor consist as recited in claim 4, wherein the steps further comprise:
s5.3, calculating the coordinate distance between the coordinate point of the platform truck data block and the reference point, and judging the distance between the coordinate point of the platform truck data block and the trailer;
and S5.4, calculating the coordinate position of the coordinate point of the platform truck data block in the global coordinate system, and judging the relative pose of the platform truck and the trailer.
6. The method for detecting the pose of a tractor consist as recited in claim 4, wherein the steps further comprise:
s5.5, calculating the coordinate distance between the coordinate point of the obstacle data block and the reference point, and judging the distance between the coordinate point of the obstacle data block and the trailer;
and S5.6, calculating the coordinate position of the coordinate point of the obstacle data block in the global coordinate system, and judging the relative pose of the obstacle and the trailer.
7. The method for detecting the pose of a tractor consist as recited in claim 1, wherein the scanning unit is disposed below the tractor head and configured to scan a baseline covering at least a portion of at least one of the trailer wheels or the platform car wheels.
8. The method for detecting the pose of a tractor consist as recited in claim 1, wherein the feature library comprises: at least one of trailer wheel characterization data or flatbed wheel characterization data.
9. The method for detecting the pose of a tractor consist as recited in claim 1, wherein step S5 is: and the calculating unit calculates the relative orientation in the coordinate system of the feature point data according to the global coordinate system to acquire the pose of the feature point data.
10. A tractor consist pose detection system, comprising: scanning unit, computational element, memory cell, power module, its characterized in that, the memory cell storage includes: the method for detecting the pose of a tractor consist and the feature library as recited in any one of claims 1 to 9, wherein the scanning unit is fixed at a preset position of a tractor head and is in communication connection with the computing unit to transmit scanning data, so that the computing unit can retrieve the method for detecting the pose of the tractor consist and the feature library stored in the storage unit to process the scanning data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010160986.4A CN111284502B (en) | 2020-03-10 | 2020-03-10 | Method and system for detecting pose of tractor group |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010160986.4A CN111284502B (en) | 2020-03-10 | 2020-03-10 | Method and system for detecting pose of tractor group |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111284502A CN111284502A (en) | 2020-06-16 |
| CN111284502B true CN111284502B (en) | 2021-06-04 |
Family
ID=71017841
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010160986.4A Active CN111284502B (en) | 2020-03-10 | 2020-03-10 | Method and system for detecting pose of tractor group |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111284502B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114590333B (en) * | 2020-12-03 | 2023-07-14 | 宇通客车股份有限公司 | Automatic driving multisection trailer and pose determining method thereof |
| CN112396043B (en) * | 2021-01-21 | 2021-04-27 | 北京主线科技有限公司 | Vehicle environment information perception method and device, electronic equipment and storage medium |
| CN113296107A (en) * | 2021-06-23 | 2021-08-24 | 上海西井信息科技有限公司 | Method, system, equipment and storage medium for cooperatively detecting towing angle by sensor |
| CN113370894B (en) * | 2021-07-21 | 2023-04-07 | 贵州詹阳动力重工有限公司 | Tractor body positioning system |
| CN113805194B (en) * | 2021-07-30 | 2024-03-29 | 上海西井科技股份有限公司 | Composite navigation system, method, equipment and storage medium of unmanned vehicle functional component |
| CN114707103B (en) * | 2022-06-06 | 2022-10-18 | 民航成都物流技术有限公司 | Multi-trailer driving track calculation method based on single perception data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104503449A (en) * | 2014-11-24 | 2015-04-08 | 杭州申昊科技股份有限公司 | Positioning method based on environment line features |
| CN107561570A (en) * | 2017-10-16 | 2018-01-09 | 北京耘华科技有限公司 | A kind of position and orientation measurement method and system of tractor-trailer |
| CN108010053A (en) * | 2016-11-02 | 2018-05-08 | Lg电子株式会社 | Apparatus and method, vehicle and the computer-readable recording medium of panoramic view picture are provided |
| CN110335305A (en) * | 2018-11-01 | 2019-10-15 | 驭势科技（北京）有限公司 | A kind of determination method, apparatus, mobile unit and the storage medium of trailer pose |
| CN110412601A (en) * | 2019-06-14 | 2019-11-05 | 浙江工业大学 | A kind of head extension integral type semitrailer gabarit measurement method of parameters based on laser radar |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10391939B2 (en) * | 2016-09-01 | 2019-08-27 | GM Global Technology Operations LLC | Method and apparatus to determine trailer pose |
-
2020
- 2020-03-10 CN CN202010160986.4A patent/CN111284502B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104503449A (en) * | 2014-11-24 | 2015-04-08 | 杭州申昊科技股份有限公司 | Positioning method based on environment line features |
| CN108010053A (en) * | 2016-11-02 | 2018-05-08 | Lg电子株式会社 | Apparatus and method, vehicle and the computer-readable recording medium of panoramic view picture are provided |
| CN107561570A (en) * | 2017-10-16 | 2018-01-09 | 北京耘华科技有限公司 | A kind of position and orientation measurement method and system of tractor-trailer |
| CN110335305A (en) * | 2018-11-01 | 2019-10-15 | 驭势科技（北京）有限公司 | A kind of determination method, apparatus, mobile unit and the storage medium of trailer pose |
| CN110412601A (en) * | 2019-06-14 | 2019-11-05 | 浙江工业大学 | A kind of head extension integral type semitrailer gabarit measurement method of parameters based on laser radar |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111284502A (en) | 2020-06-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111284502B (en) | Method and system for detecting pose of tractor group | |
| US11669091B2 (en) | Configuring motion planning for a self-driving tractor unit | |
| CN109117709B (en) | Collision avoidance system for autonomous vehicles | |
| US11023782B2 (en) | Object detection device, vehicle control system, object detection method, and non-transitory computer readable medium | |
| CN110278405B (en) | Method, device and system for processing lateral image of automatic driving vehicle | |
| CN108931801B (en) | Automatic vehicle driving method and system in container terminal area | |
| EP3140777B1 (en) | Method for performing diagnosis of a camera system of a motor vehicle, camera system and motor vehicle | |
| US20220371199A1 (en) | System and method for connection of service lines to trailer fronts by automated trucks | |
| US11417120B2 (en) | Vehicle which indicates passenger movability, and method for controlling the same | |
| US11823508B2 (en) | Automated inspection of autonomous vehicle lights | |
| CN113557523A (en) | Method and device for operating a robot with improved object detection | |
| CN110588635A (en) | Docking a vehicle based on a camera with the aid of artificial intelligence | |
| US20220146632A1 (en) | System and method for operating a retractable sensor of an autonomous vehicle | |
| KR20230021737A (en) | Apparatus for verifying the position or orientation of a sensor in an autonomous vehicle | |
| JP2011113330A (en) | Object detection device and drive assist system | |
| US20220009500A1 (en) | Operational design domain detection for advanced driver assistance systems | |
| CN112766030A (en) | System and method for LED flicker and strip detection | |
| CN114945838A (en) | Posture/position detection system for detector and posture/position detection method for detector | |
| US11853035B2 (en) | Camera assisted docking system for commercial shipping assets in a dynamic information discovery protocol environment | |
| WO2022091620A1 (en) | Object tracking device and object tracking method | |
| CN117629254A (en) | Fusion positioning deviation early warning method, storage medium and intelligent device | |
| CN116483087A (en) | Walking control method and device of tractor and electronic equipment | |
| CN114666723A (en) | System and method for mobile platform positioning using ultra-wideband (UWB) signals | |
| CN113296107A (en) | Method, system, equipment and storage medium for cooperatively detecting towing angle by sensor | |
| CA3221324A1 (en) | Improved method and system for monitoring wheels |
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 |