CN116443006A - Tractor, docking method of towed target and electronic equipment - Google Patents

Abstract

The invention discloses a docking method of a tractor and a towed target, belonging to the technical field of intelligent driving; the method comprises the following steps: acquiring spatial distribution information of all sampling points in target point cloud data; fitting a reference parameter of the target based on the distribution information; determining a target position using the reference parameter; planning the traction path based on the target location; according to the technical scheme, the problem that the tractor and the docking device of the tractor cannot be correctly docked due to the fact that the target is offset caused by phenomena such as bulge and/or edge tilting and/or swinging possibly occurs when the target grows along with time is solved, and the technical effect of accurately docking the tractor and the towed target is achieved.

Description

Tractor, docking method of towed target and electronic equipment

Technical Field

The invention relates to the technical field of intelligent driving, in particular to a docking method of a tractor and a towed target and electronic equipment.

Background

When goods are transported in an airport or the like, a towed target or a supporting plate is required to be adopted, and the towed target or the supporting plate is butted by a tractor to realize the goods transportation. The process comprises the following steps: the automatic driving tractor reaches the docking position through the automatic driving route, and after the docking position is reached, the tractor automatically hangs the towed target or the identifier on the supporting plate according to the location of the towed target or the identifier on the supporting plate.

However, due to the complex field environment, there may be a deviation in the alignment process due to the influence of the tractor running accuracy, the noise of the field environment on the marker, and the like.

Therefore, how to accurately dock a tractor and a towed target is a technical problem to be solved.

Disclosure of Invention

The technical problem of how to accurately dock the tractor with the towed target in the background technology is solved.

According to a first aspect, the present application provides a towing vehicle having radar disposed thereon and a towed target having a towing device and at least two targets disposed thereon, the docking method comprising: acquiring spatial distribution information of all sampling points in target point cloud data; fitting a reference parameter of the target based on the distribution information; determining a target position using the reference parameter; planning the traction path based on the target position.

Optionally, the reference parameter includes a reference straight line, and the targets are two; optionally said determining a reference parameter of the target based on the distribution information comprises: optionally, respectively determining transverse distribution information of all sampling points in each target in the transverse direction of the current target, wherein the transverse direction is the direction respectively facing the other target; optionally connecting sampling points which are in central symmetry in the two targets based on the transverse distribution information to obtain a plurality of connecting lines; optionally fitting the centers of the plurality of connecting lines to a center straight line as the reference straight line.

Optionally, the determining the target position using the reference parameter includes: optionally calculating a second vertical distance from all sampling points to a plane in which the reference straight line is located, wherein the plane in which the reference straight line is located is perpendicular to the planes in which the two targets are located; optionally filtering out the sampling points with the second vertical distance smaller than a second preset value, wherein the second vertical distance is the vertical distance from the current sampling point to the reference straight line; the target position is optionally calculated based on the sample points remaining after filtering.

Optionally, the reference parameter comprises a reference plane; optionally said determining a reference parameter of the target based on the distribution information comprises: optionally determining longitudinal distribution information of all sampling points in each target along the direction towards the tractor; optionally determining a reference plane in which the target is located based on the longitudinal distribution information.

Optionally, the determining the reference plane in which the target is located based on the longitudinal distribution information includes: optionally calculating a first vertical distance of all sampling points to the reference plane; optionally filtering out the sampling points with the first vertical distance larger than a first preset value; the target position is optionally calculated based on the sample points remaining after filtering.

Optionally, the acquiring the spatial distribution information of all sampling points in the target point cloud data includes: optionally acquiring point cloud data; optionally determining the target point cloud data based on reflectivity; and optionally calculating coordinate information of the target point cloud data in a three-dimensional space to determine the spatial distribution information.

Optionally, the docking method further comprises:

acquiring point cloud data of the target and the point cloud data change information; determining an observation position of the docking device based on the point cloud data; determining a predicted position of the docking device based on the N historical target positions; combining the point cloud data change information to fuse the observation position and the prediction position to obtain the current target position of the docking device; and planning a path based on the current target position.

Optionally, a docking device and at least three targets are arranged on the towed target, wherein at least two targets are positioning targets of the docking device, at least one target cooperates with other targets to form a verification code of the towed target, a radar is arranged on the tractor, and the docking method comprises the following steps: acquiring point cloud data of each target; determining a target belonging to a target towed target based on the point cloud data and the check code; determining a localization target among the target of interest; determining a target position of the docking device based on the positioning target; and planning a docking path based on the target position.

According to a second aspect, the present application further provides an electronic device, including a processor, a communication interface, a memory and a communication bus, where the processor, the communication interface and the memory complete communication with each other through the communication bus, and the memory is configured to store a computer program; the processor is configured to execute the method of docking the tractor and the towed target according to any one of the above by running the computer program stored on the memory.

According to a third aspect, the present application also provides a computer readable storage medium having a computer program stored therein, wherein the computer program is arranged to perform, when run, the method of docking a tractor with a towed target of any of the above.

In an embodiment of the present application, there is provided a method of docking a tractor with a towed target, the method comprising: acquiring spatial distribution information of all sampling points in target point cloud data; fitting a reference parameter of the target based on the distribution information; determining a target position using the reference parameter; planning the traction path based on the target location; according to the technical scheme, the problem that the tractor and the docking device of the tractor cannot be correctly docked due to the fact that the target is offset caused by phenomena such as bulge and/or edge tilting and/or swinging possibly occurs when the target grows along with time is solved, and the technical effect of accurately docking the tractor and the towed target is achieved.

Drawings

The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention and do not constitute a limitation on the invention. In the drawings:

FIG. 1 is a schematic illustration of an exemplary tractor and towed target in the present related art;

FIG. 2 is a flow chart of an exemplary method of docking a tractor with a towed target in accordance with an embodiment of the present invention;

FIG. 3 is a schematic view of a reference straight line from a top view of a target in one embodiment of the invention;

FIG. 4 is a schematic view of a reference plan view of a target in one embodiment of the invention;

fig. 5 is a schematic structural diagram of an exemplary electronic device according to an embodiment of the present invention.

Detailed Description

For a clearer understanding of the technical features, objects and effects of the present invention, embodiments of the present invention will now be described with reference to the drawings, in which like reference numerals refer to identical or structurally similar but functionally identical components throughout the separate views.

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.

As described in the background art, the process of docking a tractor with a towed target is completely different from the existing automatic driving path planning, the tractor is docked with the towed target based on a fixed marker, the tractor is driven to a fixed point, for example, a hook is arranged on the tractor, a docking device is arranged on a supporting plate, and when docking is completed, the hook needs to be hooked on the docking device, so that the docking precision may be in the decimeter level or the centimeter level, and the existing automatic driving scheme cannot meet the current requirement. In addition, the existing butt joint positioning mode often adopts a positioning mode of a laser radar, a target of the laser radar is arranged on a towed target, and the position of the butt joint device is determined by collecting point cloud data of the target and the position relation between the target and the butt joint device. However, because the field environment is complex, especially for the laser radar positioning mode, more influencing factors may exist on the field, such as shaking of the target, strong reflective objects around the target, reflective bands on the working clothes of field operators, and the like, if the operators approach the laser radar field of view, the reflective bands may form target noise points, or the operators pass through between the tractor and the towed target to form shielding for the target, and positioning data similar to the target is formed while real data is lost, so that positioning deviation is overlarge.

However, after the excessive positioning deviation caused by the technical problems is corrected, the problem of inaccurate target positioning data still exists; the inventor researches that the existing target is usually set to be a plane type, usually a reflective patch attached to a towed target, and as time increases, the reflective patch surface may bulge, and the edge may have a edge tilting phenomenon, and when the target is blown by wind, the edge may have a swinging phenomenon, which may cause the target to deviate, the positioning deviation is too large, and the deviation of the target may cause the problem that the towing device and the docking device of the towing vehicle cannot dock correctly.

Based on this, in order to solve the above-mentioned problems, an embodiment of the present application provides a docking method of a tractor and a towed target, as shown in fig. 1, where a radar is disposed on the tractor, at least two targets of a target number are disposed on the towed target, the radar emits laser light according to a fixed direction, and receives reflected light, and forms point cloud data of the targets based on reflectivity, and specifically, referring to a step schematic diagram of the docking method shown in fig. 2, the docking method may include:

s10, acquiring spatial distribution information of all sampling points in the target point cloud data. After the target point cloud data are acquired, analyzing distribution information of sampling points in the point cloud data based on the target point cloud data; the spatial distribution information at least comprises distribution information of sampling points in the point cloud data, which are oriented to the direction of the tractor (the direction perpendicular to the plane in which the targets are located), and distribution information of sampling points in the point cloud data, which are oriented to the direction of the targets (the direction of the plane in which at least two targets are located); it can be understood that the distribution information of the sampling points in the point cloud data at least includes the density, the number, the position, the distribution of the sampling points in each area, and the like. In this embodiment, the spatial distribution information may be determined in real time, or may be determined at intervals of a preset period.

S20, fitting reference parameters of the target based on the distribution information; the reference parameter of the target is spatial distribution information of all sampling points in target point cloud data under normal phenomena such as bulge and/or edge curling and/or swinging of the target; the reference parameter includes at least a reference parameter determined based on distribution information of sampling points in the point cloud data in a normal state, the sampling points being oriented in a direction of the tractor (a direction perpendicular to a plane in which the targets are located) and distribution information of sampling points in the point cloud data between the targets and a target direction (a direction of a plane in which at least two targets are located).

S30, determining a target position by utilizing the reference parameters; after fitting the reference parameters of the target based on the distribution information, the reference parameters of the target may be fitted based on the distribution information, for example; for example, the fitting degree of the existing distribution information and the distribution information in the normal state can be analyzed based on the reference parameter; for example, the sampling points which can be fitted with the distribution information in the normal state in the distribution information of the sampling points are reserved as correct sampling points which do not have the phenomena such as bulge and/or edge tilting and/or swinging, and the sampling points which cannot be fitted with the distribution information in the normal state in the distribution information of the sampling points are removed as abnormal sampling points which have the phenomena such as bulge and/or edge tilting and/or swinging, so that the abnormal sampling points are removed through the reference parameters, and the target position is determined.

S40, planning the traction path based on the target position. Wherein after determining a target position, the traction path is planned based on the target position.

Through the technical scheme, the spatial distribution information of all sampling points in the target point cloud data is obtained; fitting a reference parameter of the target based on the distribution information; determining a target position using the reference parameter; planning the traction path based on the target location; the method solves the problem that in the prior art, when the target grows along with time, the target possibly deviates from the target caused by phenomena such as bulge and/or edge tilting and/or swinging, so that the traction device and the docking device of the tractor cannot be correctly docked, and achieves the technical effect of accurately docking the tractor and the towed target.

As an alternative embodiment, the reference parameter includes a reference straight line, and the targets are two; the determining the reference parameters of the target based on the distribution information comprises: respectively determining transverse distribution information of all sampling points in each target in the transverse direction of the current target, wherein the transverse direction is the direction respectively facing the other target; connecting sampling points which are in central symmetry in the two targets based on the transverse distribution information to obtain a plurality of connecting lines; and fitting the centers of the connecting lines into a center straight line serving as the reference straight line.

For the technical scheme, when two targets are distributed on the same plane, when each target is in a normal state, sampling points between the two targets are centrosymmetric, and the symmetry center is the symmetry axis of the two targets on the plane; based on the above, when the targets are in a normal state, the transverse distribution of all sampling points in each target in the transverse direction in the current target is centrosymmetric based on the symmetry axes of the two targets on the plane; therefore, the symmetry axes of the two targets on the plane are taken as a center straight line, and the center straight line is taken as the reference straight line.

As an exemplary embodiment, as shown in fig. 3, the determining the reference plane in which the target is located based on the longitudinal distribution information includes: calculating first vertical distances from all sampling points to the reference plane; filtering out the sampling points with the first vertical distance larger than a first preset value; and calculating the target position based on the residual sampling points after filtering. Fig. 3 is a schematic diagram of a reference plane showing the fitting of the target after edge lifting, swelling and tilting, and in this embodiment, a small amount of point cloud data is taken as an example for illustration.

For the technical scheme, in the actual use process, the plane pasted by the target is not necessarily a smooth plane or a certain error can exist when the radar receives laser due to the fact that the plane pasted by the target is uneven under normal conditions, so that the reference plane is not a smooth plane; illustratively, calculating the maximum value of the concave-convex distances of the concave-convex surfaces of the reference plane, and taking the average value of the maximum values as a first preset value; calculating a first vertical distance between all sampling points and the reference plane, and filtering out the sampling points with the vertical distance larger than a first preset value when the first vertical distance is larger than the first preset value, wherein the sampling points are characterized by the phenomena of bulging and/or edge curling and/or swinging and the like.

As an exemplary embodiment, as shown in fig. 4, the determining the target position using the reference parameter includes: calculating second vertical distances from all sampling points to a plane where the reference straight line is located, wherein the plane where the reference straight line is located is vertical to the planes where the two targets are located; filtering out the sampling points with the second vertical distance smaller than a second preset value, wherein the second vertical distance is the vertical distance from the current sampling point to the reference straight line; and calculating the target position based on the residual sampling points after filtering. Fig. 4 is a schematic diagram of a reference line fitted by performing routine for the conditions such as edge lifting, bulge and inclination of the target, and in this embodiment, a small amount of point cloud data is taken as an example for illustration.

For the above technical solution, when the target has phenomena such as bulge and/or edge tilting and/or swinging, the distribution of the sampling points has vertical offset, horizontal offset, front-back offset along with the occurrence of the phenomena of the target, and is far away from the center straight line in all directions; in one aspect, when the sampling point deviates from the center straight line, a first distance between the deviated sampling point and a plane where the reference straight line is located is smaller than a vertical distance between the sampling point and the reference straight line; therefore, if the second vertical distance of the sampling point is smaller than the second preset value, the sampling point is considered to be the sampling point with the problem, and the sampling point is filtered.

On the other hand, when the laser emitted from the radar returns to the radar, the reflection angle of the target light path in which the above phenomenon occurs is smaller than that of the normal target light path, the laser identified by the radar is closer to the reference straight line than the normal laser, and the first distance from the plane of the reference straight line is smaller than the perpendicular distance from the sampling point to the reference straight line.

As an alternative embodiment, the reference parameter comprises a reference plane; the determining the reference parameters of the target based on the distribution information comprises: respectively determining longitudinal distribution information of all sampling points in each target along the direction towards the tractor; and determining a reference plane where the target is located based on the longitudinal distribution information.

For example, when two targets are distributed on the same plane, when each target is in a normal state, reflection points of the two targets should fall on a reference plane parallel to the plane of the target, and the distance between the reference plane and the plane of the target is the distance between a tractor and the target; thus, a plane parallel to the plane in which the target is located may be determined as a reference plane based on the longitudinal distribution information.

For example, when the longitudinal information of the sampling point can be fitted to the reference plane, the sampling point is confirmed to be the sampling point in which the phenomena such as bulge and/or edge curling and/or swinging do not occur; when the longitudinal information of the sampling points can not be integrated with the reference plane, confirming that the sampling points are sampling points with the phenomena of bulge, edge warping, swing and the like, and filtering the sampling points.

Through the implementation mode, the problem that the tractor and the towed target are not accurately butted due to the phenomena of bulging, edge warping, swinging and the like of the target is solved; on the basis, the application also provides other alternative tractors and methods for docking the towed targets.

As an alternative embodiment, the docking method further comprises: and acquiring point cloud data of the target and the point cloud data change information. The point cloud change information may be obtained by comparing the point cloud at the current time with the point cloud data at the previous N times, for example, the point cloud data is increased, the point cloud data is decreased, and the point cloud position is changed. The side information may also be the degree of change of the point cloud data, that is, the increasing amount, the decreasing amount, the proportion of the point cloud data where the abnormal position occurs, and the like of the point cloud data. In this embodiment, the determination may be performed in real time, or may be performed at intervals of a preset period.

And determining the observation position of the docking device based on the point cloud data. As an exemplary embodiment, the point cloud data may be filtered according to the distribution of the point cloud data, for example, a region with the point cloud data density reaching a preset degree may be used as a region of interest of the target, and shape information of the target is used for further screening to determine the point cloud data belonging to the target. And determining the center position of the target by utilizing point cloud data belonging to the target, namely positioning the position information of the target. And determining the observation position of the docking device by using the position information of the target and the relative position relation between the target and the docking device. In this embodiment, the relative positional relationship between the target and the docking device is a fixed positional relationship. After the target is installed, the relative position relationship between the target and the docking device can be determined.

A predicted position of the dock is determined based on the N historical target positions. As an exemplary embodiment, during docking, when the tractor reaches the position where docking begins, docking path planning is performed by the first acquired observation position of the docking device, and the tractor travels along the planned docking path. In the running process, the position of the docking device at the next moment is predicted by using the N observation values, in this embodiment, the docking path is often a smoother curve, and the position of the docking device is often fixed, so that the prediction of the next position can be performed according to the path track traveled before and the observation position before, and in this embodiment, the observation position can be the position information observed by the docking device tractor relative to the tractor.

And combining the point cloud data change information to fuse the observation position and the prediction position to obtain the current target position of the docking device. In this embodiment, when the predicted position and the observed position completely coincide, either one may be selected as the target position. When the predicted position and the observed position are different and coincide, possible reasons are that the target receives interference and noise point cloud data appear. Resulting in inaccurate calculation of the observation position. It is also possible to accumulate errors in the predicted position as the prediction increases. The observed and predicted positions may be fused to determine the target position, alternatively, the fusion may be performed by taking the average of the observed and predicted positions. The observed position may be corrected based on the predicted position.

Under the condition that a target is not interfered with the travel of a tractor, the point cloud data of the target may change, for example, the distance is more and more, the point cloud data is more and more, the speed is slower and more, the point cloud data is also gradually increased, so that under normal conditions, the change of the point cloud data is a regular or linear change, the interference often causes the change degree of the point cloud to change, namely, the change rate changes, and therefore, the fusion authority or fusion mode of the observation position and the prediction position can be distributed based on the change information of the point cloud data. The method can ensure that the fused target position is more accurate when the predicted position and the observed position are fused.

As an alternative embodiment, a docking device and at least three targets are arranged on the towed target, wherein at least two targets are positioning targets of the docking device, at least one target cooperates with other targets to form a verification code of the towed target, and a radar is arranged on the tractor, and the docking method further comprises: acquiring point cloud data of each target; determining a target belonging to a target to be towed based on the point cloud data and the check code; determining a localization target among the target targets of interest; determining a target position of the docking device based on the positioning target; and planning a docking path based on the target position.

According to the method, the positioning targets used for determining the position information of the towed targets are arranged on the towed targets, targets which can be matched with the positioning targets to form different check codes are arranged, when the radar detects a plurality of targets, point cloud data of each detected target are firstly acquired, the check codes corresponding to the towed targets are identified, the towed targets can be determined, the positioning targets on the towed targets are acquired, the specific positions of the towed targets are determined through the positioning targets, then the butt joint paths of the towing vehicle and the towed targets are planned, accurate butt joint is realized, the situation that the towed targets cannot be accurately determined when the radar simultaneously identifies the targets is avoided, and the accuracy of tracking the towed targets is improved.

Fig. 3 is a schematic diagram of an electronic device according to an embodiment of the invention.

As shown in fig. 3, the present application also provides an electronic device comprising a processor, a memory, and execution instructions stored on the memory, the execution instructions being configured to, when executed by the processor, enable the electronic device to perform the above-described method of docking a tractor with a towed target. Optionally also memory and a bus, and furthermore the electronics man allows to include the hardware required for other services.

Optionally also memory and a bus, and the electronic device allows to include the hardware required for other services. The memory may include memory and non-volatile memory (non-volatile memory) and provide the processor with instructions and data for execution. By way of example, the Memory may be a Random-Access Memory (RAM), and the non-volatile Memory may be at least 1 disk Memory.

Wherein the bus is used to interconnect the processor, memory, and network interfaces together. The bus may be an ISA (Industry Standard Architecture ) bus, a PCI (Peripheral Component Interconnect, peripheral component interconnect standard) bus, an EISA (Extended Industry Standard Architecture ) bus, and the like. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, only one bi-directional arrow is shown in fig. 3, but this does not represent only one bus or one type of bus.

In one possible implementation manner of the electronic device, the processor may first read the corresponding execution instruction from the nonvolatile memory to the memory and then execute the execution instruction, or may first obtain the corresponding execution instruction from another device and then execute the execution instruction. The processor, when executing the execution instructions stored in the memory, can implement the docking method of any one of the tractors and the towed targets described above in the present disclosure.

It will be appreciated by those skilled in the art that the above-described method of docking a tractor with a towed target may be applied to or implemented by a processor. The processor is illustratively an integrated circuit chip having the capability of processing signals. During execution of the above-described method for docking a tractor with a towed target by a processor, the steps of the above-described method for docking a tractor with a towed target may be performed by instructions in the form of integrated logic circuits in hardware or software in the processor. Further, the processor may be a general purpose processor such as a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a Field-programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, a microprocessor, and any other conventional processor.

Those skilled in the art will also appreciate that the steps of the above described embodiments of the method of docking a tractor and towed target of the present disclosure may be performed by a hardware decoding processor or by a combination of hardware and software modules in the decoding processor. The software modules may be located in other well-known storage media such as ram, flash memory, rom, eeprom, registers, etc. The storage medium is located in the memory, and the processor, after reading the information in the memory, in combination with its hardware, performs the steps of the above-described embodiment of the docking method of the tractor and the towed target.

According to yet another aspect of embodiments of the present application, there is also provided a storage medium. Alternatively, in the present embodiment, the above-described storage medium may be used for executing the program code of the docking method of the towing vehicle and the towed target.

Alternatively, in this embodiment, the storage medium may be located on at least one network device of the plurality of network devices in the network shown in the above embodiment.

Alternatively, in the present embodiment, the storage medium is configured to store program code for performing the steps of:

acquiring spatial distribution information of all sampling points in target point cloud data;

fitting a reference parameter of the target based on the distribution information;

determining a target position using the reference parameter;

based on the target position planning the traction path.

Alternatively, specific examples in the present embodiment may refer to examples described in the above embodiments, which are not described in detail in the present embodiment.

Alternatively, in the present embodiment, the storage medium may include, but is not limited to: various media capable of storing program codes, such as a U disk, ROM, RAM, a mobile hard disk, a magnetic disk or an optical disk.

The foregoing embodiment numbers of the present application are merely for describing, and do not represent advantages or disadvantages of the embodiments.

The integrated units in the above embodiments may be stored in the above-described computer-readable storage medium if implemented in the form of software functional units and sold or used as separate products. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a storage medium, including several instructions to cause one or more computer devices (which may be personal computers, servers or network devices, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application.

In the foregoing embodiments of the present application, the descriptions of the embodiments are emphasized, and for a portion of this disclosure that is not described in detail in this embodiment, reference is made to the related descriptions of other embodiments.

In several embodiments provided in the present application, it should be understood that the disclosed client may be implemented in other manners. The above-described embodiments of the apparatus are merely exemplary, and the division of the units, such as the division of the units, is merely a logical function division, and may be implemented in another manner, for example, multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some interfaces, units or modules, or may be in electrical or other forms.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution provided in the present embodiment.

Thus far, the technical solution of the present disclosure has been described in connection with the foregoing embodiments, but it is easily understood by those skilled in the art that the protective scope of the present disclosure is not limited to only these specific embodiments. The technical solutions in the above embodiments may be split and combined by those skilled in the art without departing from the technical principles of the present disclosure, and equivalent modifications or substitutions may be made to related technical features, which all fall within the scope of the present disclosure.

Thus far, the technical solution of the present disclosure has been described in connection with the foregoing embodiments, but it is easily understood by those skilled in the art that the protective scope of the present disclosure is not limited to only these specific embodiments. The technical solutions in the above embodiments may be split and combined by those skilled in the art without departing from the technical principles of the present disclosure, and equivalent modifications or substitutions may be made to related technical features, which all fall within the scope of the present disclosure.

In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.

The foregoing is merely exemplary of the present invention and is not intended to limit the present invention. Various modifications and variations of the present invention will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the invention are to be included in the scope of the claims of the present invention.

Claims (10)

1. A method of docking a towing vehicle and a towed target, wherein a radar is provided on the towing vehicle, and a towing device and at least two targets are provided on the towed target, the method comprising:

acquiring spatial distribution information of all sampling points in target point cloud data;

fitting a reference parameter of the target based on the spatial distribution information;

determining a target position using the reference parameter;

planning the traction path based on the target position.

2. The method of docking a tractor and a towed target according to claim 1,

the reference parameters include a reference plane;

the determining the reference parameters of the target based on the spatial distribution information comprises:

respectively determining longitudinal distribution information of all sampling points in each target along the direction towards the tractor;

and determining a reference plane where the target is located based on the longitudinal distribution information.

3. The method of interfacing a tractor and a towed target according to claim 2, wherein said determining a reference plane in which said target is located based on said longitudinal distribution information includes:

calculating first vertical distances from all sampling points to the reference plane;

filtering out the sampling points with the first vertical distance larger than a first preset value;

and fitting the reference plane based on the residual sampling points after filtering.

4. The method of docking a tractor and a towed target according to claim 1, wherein said reference parameter includes a reference straight line, said target being two;

the determining the reference parameters of the target based on the spatial distribution information comprises:

respectively determining transverse distribution information of all sampling points in each target in the transverse direction of the current target, wherein the transverse direction is the direction respectively facing the other target;

connecting sampling points which are in central symmetry in the two targets based on the transverse distribution information to obtain a plurality of connecting lines;

and fitting the centers of the connecting lines into a center straight line serving as the reference straight line, wherein the reference straight line is perpendicular to the planes of the two targets.

5. The method of docking a tractor and a towed target according to claim 4, wherein said determining a target position using said reference parameter includes:

calculating second vertical distances from all sampling points to a plane where the reference straight line is located, wherein the plane where the reference straight line is located intersects with the planes where the two targets are located;

filtering out the sampling points with the second vertical distance smaller than a second preset value, wherein the second vertical distance is the vertical distance from the current sampling point to the reference straight line;

and calculating the target position based on the residual sampling points after filtering.

6. The method of docking a tractor and a towed target according to claim 1, wherein said obtaining spatial distribution information of all sampling points in the target point cloud data includes:

acquiring point cloud data;

determining the target point cloud data based on reflectivity;

and calculating coordinate information of the target point cloud data in a three-dimensional space to determine the space distribution information.

7. The method of docking a tractor and a towed target according to any of claims 1-6, wherein said docking method further includes:

acquiring point cloud data of the target and the point cloud data change information;

determining an observation position of the docking device based on the point cloud data;

determining a predicted position of the docking device based on the N historical target positions;

combining the point cloud data change information to fuse the observation position and the prediction position to obtain the current target position of the docking device;

and planning a path based on the current target position.

8. The method of docking a tractor and a towed target according to any of claims 1-6, wherein a docking device and at least three targets are provided on the towed target, wherein at least two targets are positioning targets of the docking device, at least one target cooperates with other targets to form a verification code for the towed target, the tractor is provided with a radar, the docking method further comprising:

acquiring point cloud data of each target;

determining a target belonging to a target towed target based on the point cloud data and the check code;

determining a localization target among the target of interest;

determining a target position of the docking device based on the positioning target;

and planning a docking path based on the target position.

9. An electronic device comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus, characterized in that,

the memory is used for storing a computer program;

the processor for performing the method of docking a tractor and a towed object according to any of claims 1 to 8 by running the computer program stored on the memory.

10. A computer readable storage medium, characterized in that the storage medium has stored therein a computer program, wherein the computer program is arranged to execute the docking method of a tractor and a towed object according to any of the claims 1 to 8 at run-time.