WO2024108439A1

WO2024108439A1 - Driverless forklift obstacle avoidance and obstacle bypassing method and system integrating 3d visual camera and radar

Info

Publication number: WO2024108439A1
Application number: PCT/CN2022/133814
Authority: WO
Inventors: 张魏魏
Original assignee: 滁州市哈工库讯智能科技有限公司
Priority date: 2022-11-23
Filing date: 2022-11-23
Publication date: 2024-05-30

Abstract

A driverless forklift obstacle avoidance and obstacle bypassing method and system integrating a 3D visual camera (430) and a radar. The driverless forklift obstacle avoidance and obstacle bypassing system integrating a 3D visual camera and a radar comprises a forklift housing (100), moving wheels (200), a driving assembly (300), an obstacle detection assembly (400), and a fork (500). The forklift housing (100) comprises a bottom plate (110) and a protective housing (120) connected to the bottom plate (110). The moving wheels (200) are arranged at four corners of the bottom plate (110), and pass through the bottom plate (110) from the bottom thereof. The driving assembly (300) is mounted inside the forklift housing (100), one part of the driving assembly (300) extends to the top of the protective housing (120), and the other part of the driving assembly (300) is connected to steering input ends of the moving wheels (200). The obstacle detection assembly (400) is located directly above the protective housing (120), and is connected to the extending part of the driving assembly (300). The fork (500) is mounted in front of the forklift housing (100) to fork goods. The driverless forklift obstacle avoidance and obstacle bypassing system integrating a 3D visual camera and a radar communicates with and is controlled by an upper computer, so that manual operation is not needed, and manpower resources are saved.

Description

Unmanned forklift obstacle avoidance and circumvention method and system integrating 3D vision camera and radar

Technical Field

The present invention relates to the technical field of forklifts, and in particular to an obstacle avoidance and circumvention method and system for unmanned forklifts integrating a 3D visual camera and a radar.

Background technique

A forklift refers to a variety of wheeled handling vehicles that are used for loading and unloading, stacking and short-distance transportation of palletized goods. The structural characteristics and working performance of the forklift are indicated by technical parameters such as rated lifting capacity, load center distance, and mast inclination angle. It is usually divided into types such as internal combustion forklifts and electric forklifts.

Forklifts are often needed to move goods in factory logistics, but most existing forklifts require manual operation, which takes up a lot of manpower.

Summary of the invention

The purpose of this section is to summarize some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

In view of the above problems and/or the problems existing in the existing forklifts, the present invention is proposed.

Therefore, the purpose of the present invention is to provide an unmanned forklift obstacle avoidance and circumvention method and system that integrates 3D vision camera and radar, which communicates with the host computer under control and can automatically avoid and circumvent obstacles without manual operation, thus saving human resources.

To solve the above technical problems, according to one aspect of the present invention, the present invention provides the following technical solutions:

An unmanned forklift obstacle avoidance and bypassing system integrating 3D vision camera and radar, comprising:

A vehicle housing, comprising a bottom plate and a protective shell connected to the bottom plate;

Moving wheels are arranged at the four corners of the bottom plate and extend out from the bottom;

A driving assembly is installed inside the vehicle shell, wherein a portion of the driving assembly extends to the top of the protective shell, and another portion is connected to the steering input end of the moving wheel;

an obstacle detection assembly, located directly above the protective shell and connected to an extended portion of the drive assembly;

A cargo fork is installed in front of the vehicle body to fork and pick up the cargo;

Among them, in a normal state, the moving wheel drives the vehicle body to move forward according to the instruction of the control unit, and at the same time the obstacle detection component detects whether there is an obstacle in front of the movement;

When the obstacle detection component finds an obstacle at a certain distance in front, the driving component drives the moving wheel and the obstacle detection component to turn 90° as a whole, and then continue to move forward after the rotation. At the same time, the obstacle detection component detects whether the above obstacle has been crossed. If it has been crossed, the control unit replans the route according to the instructions of the upper computer and controls the movement of the moving wheel or the driving component.

As a preferred solution of the obstacle avoidance and bypassing system for unmanned forklifts integrating 3D vision cameras and radars described in the present invention, the driving assembly includes a main gear plate, four driven gears surrounding the main gear plate, a driven transmission shaft coaxially arranged with the driven gears, a transmission belt meshing with the driven gears, an active transmission shaft coaxially arranged with the main gear plate, and a steering drive motor installed on the bottom plate and having an output end connected to the active transmission shaft;

Among them, two symmetrical driven gears are meshed with the main gear plate, one end of the driven transmission shaft is connected to the steering input end of the moving wheel, and the other end is rotatably connected to the top of the inner wall of the protective shell.

As a preferred solution of the unmanned forklift obstacle avoidance and circumvention system integrating 3D visual camera and radar described in the present invention, the obstacle detection component includes a rectangular rotating head connected to the active transmission shaft, a radar detection component installed on one side of the rotating head, and two visual cameras installed on the other side of the rotating head;

Wherein, the mounting surfaces of the two visual cameras are perpendicular to the mounting surface of the radar detection component.

As a preferred solution of the unmanned forklift obstacle avoidance and bypassing system integrating a 3D vision camera and a radar described in the present invention, the radar detection component includes a radar wave transmitting end and a radar wave receiving end.

As a preferred solution of the unmanned forklift obstacle avoidance and circumvention system integrating a 3D vision camera and a radar as described in the present invention, the moving wheel includes a seat body, a walking assembly installed on the seat body, and a steering transmission assembly installed on the seat body for driving the walking assembly to turn, and the input end of the steering transmission assembly is connected to the driven transmission shaft.

As a preferred solution of the obstacle avoidance and bypassing system for unmanned forklifts integrating 3D vision cameras and radars described in the present invention, the seat body includes a first support seat and a second support seat connected to the base by an axle pin and located above the base;

The travel assembly includes a rotating disk rotatably connected to the axial hole of the base through a bearing and symmetrically provided with supporting ears at the bottom, a supporting shaft rod arranged between the two supporting ears, a travel wheel coaxially connected to the supporting shaft rod and having a first bevel gear on the side wall, a second bevel gear meshing with the travel wheel, a travel transmission spur gear located above the rotating disk and coaxially connected to the second bevel gear through the shaft rod, and a travel drive motor installed on the first support seat and having a travel drive gear at the output end meshing with the travel transmission spur gear;

The steering transmission assembly comprises a reduction motor mounted on the second support seat, a first steering transmission shaft rod and a second steering transmission shaft rod mounted on the second support seat;

The output end of the reduction motor is provided with a reduction transmission gear, and the first steering transmission shaft is provided with a first steering transmission gear and a second steering transmission gear meshing with the reduction transmission gear;

The second steering transmission shaft is provided with a third steering transmission gear and a fourth steering transmission gear meshed with the second steering transmission gear, and the fourth steering transmission gear meshes with the tooth groove of the rotating disk through a steering transmission gear belt.

As a preferred solution of the unmanned forklift obstacle avoidance and obstacle bypassing system integrating 3D vision camera and radar described in the present invention, the fork includes a rectangular frame, a lifting drive motor installed on the bottom frame of the rectangular frame, a screw rod with one end connected to the output end of the lifting drive motor and the other end connected to the top frame of the rectangular frame, a sliding plate slidably connected to the vertical frame of the rectangular frame and with a moving block on the rear side wall engaged with the screw rod, and a fork frame arranged perpendicular to the sliding plate.

A method for unmanned forklift obstacle avoidance and bypassing that integrates 3D vision camera and radar, the specific steps are as follows:

S1. The control unit of the unmanned forklift drives the moving wheels to move forward according to the walking route planned by the host computer, and adjusts the walking direction of the moving wheels by driving the driving component. At the same time, the radar detection component of the obstacle detection component emits radar waves forward to detect whether there are obstacles within a certain distance ahead;

S2. When the obstacle detection component detects an obstacle within a certain distance ahead, the control unit controls the moving wheel to stop moving, and sends a steering command to the driving component. The driving component drives the moving wheel and the obstacle detection component to turn 90° as a whole. The radar detection component of the obstacle detection component continues to detect whether there is an obstacle ahead after the turn. At the same time, after the turn, the two visual cameras face the previously detected obstacle, obtain the depth image of the obstacle, and construct a three-dimensional model of the road scene of the obstacle ahead, and transmit it to the control unit;

S3. Then the control unit sends a walking command to the moving wheel, and the moving wheel continues to move forward after the rotation. At the same time, the control unit determines in real time whether the unmanned forklift bypasses the obstacle based on the three-dimensional model of the road scene of the obstacle in front constructed by the two visual cameras. When it is determined that the unmanned forklift bypasses the obstacle, the control unit continues to move forward according to the planned route.

As a preferred solution of the obstacle avoidance and circumvention method for an unmanned forklift integrating a 3D visual camera and a radar described in the present invention, the specific steps of the control unit determining in real time whether the unmanned forklift circumvents the obstacle based on the three-dimensional model of the road scene of the obstacle ahead constructed by two visual cameras are as follows:

The visual camera acquires the depth image of the obstacle, builds a three-dimensional model of the road scene ahead of the obstacle, and transmits it to the control unit;

The control unit determines the length of the obstacle based on the acquired depth image of the obstacle, and controls the unmanned forklift to move forward after rotation to a distance equal to the length of the obstacle. At the same time, the control unit determines whether there are any obstacles in the obstacle road scene directly in front of the vehicle constructed by the vision camera. When the distance controlled to move the unmanned forklift forward after rotation is greater than the length of the obstacle, and the obstacle road scene directly in front of the vehicle constructed by the vision camera does not have any obstacles, the control unit determines to bypass the obstacle.

Compared with the prior art, the present invention has the following beneficial effects:

1. The present invention integrates 3D visual cameras and radars, and communicates with a host computer to walk along a planned route. When the radar detection component detects an obstacle ahead, the driving component drives the moving wheels and the obstacle detection component to turn 90 degrees as a whole to avoid the obstacle and continue to move forward. The detection component after turning continues to detect the obstacle condition in front after the turning through the radar detection component. At the same time, after the turning, the two visual cameras are facing the previously detected obstacles, obtain the depth image of the obstacles, and construct a three-dimensional model of the obstacle road scene ahead. The control unit drives the moving wheels to walk a corresponding distance according to the depth image of the obstacles taken by the visual cameras and the three-dimensional model of the obstacle road scene ahead to see if they can bypass the obstacles. Compared with traditional forklifts, obstacle avoidance and bypassing can be automatically achieved without manual operation, saving human resources.

2. The innovative design of the moving wheel of the present invention is highly integrated and compact, which saves space. It can be driven by itself and can be controlled to turn to drive the unmanned forklift to adjust the walking direction, thereby meeting the movement and turning requirements of the unmanned forklift.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the present invention will be described in detail below in combination with the accompanying drawings and detailed embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

FIG1 is a schematic diagram of the overall structure of an unmanned forklift obstacle avoidance and bypassing system that integrates a 3D vision camera and a radar according to the present invention;

FIG2 is a schematic diagram of a portion of the structure of the unmanned forklift obstacle avoidance and bypassing system integrating a 3D vision camera and a radar for removing a fork according to the present invention;

FIG3 is an assembly diagram of the bottom plate, moving wheels, driving components and obstacle detection components of the obstacle avoidance and bypassing system for unmanned forklifts integrating 3D vision cameras and radars according to the present invention;

FIG4 is a schematic diagram of a portion of the structure of FIG3 of the unmanned forklift obstacle avoidance and bypassing system integrating a 3D vision camera and a radar according to the present invention;

FIG5 is a schematic diagram of the overall structure of the mobile wheels of the obstacle avoidance and bypassing system for an unmanned forklift integrating a 3D vision camera and a radar according to the present invention;

6 is a schematic diagram of the first direction structure of the mobile wheel removal seat of the unmanned forklift obstacle avoidance and circumvention system integrating a 3D vision camera and a radar according to the present invention;

7 is a schematic diagram of the second direction structure of the mobile wheel removal seat of the unmanned forklift obstacle avoidance and circumvention system integrating 3D vision camera and radar according to the present invention;

FIG8 is a schematic diagram of the third direction structure of the mobile wheel removal seat of the unmanned forklift obstacle avoidance and circumvention system integrating 3D vision camera and radar according to the present invention;

9 is a schematic diagram of the first direction structure of the fork of the unmanned forklift obstacle avoidance and bypassing system integrating the 3D vision camera and the radar of the present invention;

10 is a schematic diagram of the second direction structure of the fork of the unmanned forklift obstacle avoidance and bypassing system integrating 3D vision camera and radar according to the present invention.

Detailed ways

In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

Secondly, the present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention in detail, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

In order to make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

The present invention provides an obstacle avoidance and circumvention method and system for an unmanned forklift integrating a 3D visual camera and a radar, which is controlled by communication with a host computer and can automatically avoid and circumvent obstacles without manual operation, thus saving human resources.

Example 1

1-2 and 9-10 show the structural schematic diagrams of the first embodiment of the unmanned forklift obstacle avoidance and obstacle avoidance system integrating 3D vision camera and radar. Please refer to FIG1-2. The unmanned forklift obstacle avoidance and obstacle avoidance system integrating 3D vision camera and radar includes a vehicle body 100, moving wheels 200, a driving assembly 300, an obstacle detection assembly 400 and a fork 500.

The vehicle housing 100 includes a bottom plate 110 and a protective shell 120 connected to the bottom plate 110 . The bottom plate 110 is used to install the moving wheels 200 , the driving assembly 300 and the fork 500 .

The moving wheels 200 are arranged at the four corners of the base plate 110 and extend out from the bottom, and can drive the unmanned forklift to move by itself and be controlled to achieve steering.

The driving assembly 300 is installed inside the vehicle body 100 , wherein a portion of the driving assembly 300 extends to the top of the protective shell 120 for connecting with the obstacle detection assembly 400 , and the other portion is connected to the steering input end of the moving wheel 200 .

The obstacle detection component 400 is located directly above the protective shell 120 and connected to the extended portion of the driving component 300. In the present embodiment, it includes a rectangular rotating head 410, a radar detection component 420 installed on one side of the rotating head 410, and two visual cameras 430 installed on the other side of the rotating head 410, wherein the mounting surfaces of the two visual cameras 430 are perpendicular to the mounting surface of the radar detection component 420, and the radar detection component 420 includes a radar wave transmitting end 420a and a radar wave receiving end 420b. When in use, the radar detection component 420 transmits a radar detection wave forward. If the radar wave receiving end 420b can receive the reflected radar wave signal, it indicates that there is an obstacle within a certain distance range ahead of the detection. At this time, the driving component 300 drives the obstacle detection component 400 to rotate 90°. After turning, the two visual cameras 430 are facing the previously detected obstacle, obtain the depth image of the obstacle, and construct a three-dimensional model of the road scene of the obstacle ahead, and transmit it to the control unit.

The cargo fork 500 is installed at the front position of the vehicle body 100 to fork the cargo. In the present embodiment, the cargo fork 500 includes a rectangular frame 510, a lifting drive motor 520 installed on the bottom frame 510a of the rectangular frame 510, a screw rod 530 having one end connected to the output end of the lifting drive motor 520 and the other end connected to the top frame 510c of the rectangular frame 510, a sliding plate 540 slidably connected to the vertical frame 510b of the rectangular frame 510 and having a moving block 540a meshing with the screw rod 530 on the rear side wall, and a fork frame 550 vertically arranged to the sliding plate 540. When in use, the lifting drive motor 520 drives the screw rod 530 to rotate. When the screw rod 530 rotates, the sliding plate 540 is driven to move up and down through the moving block 540a, thereby driving the fork frame 550 to move up and down to fork and deliver the cargo.

In this unmanned forklift obstacle avoidance and circumvention system that integrates 3D vision cameras and radars, under normal conditions, the moving wheel 200 drives the vehicle body 100 to move forward by itself according to the instructions of the control unit, and at the same time, the obstacle detection component 400 detects whether there is an obstacle in front of the movement. When the obstacle detection component 400 finds that there is an obstacle at a certain distance in front, the driving component 300 drives the moving wheel 200 and the obstacle detection component 400 to turn 90° as a whole, and then continue to move forward after the rotation. At the same time, the obstacle detection component 400 detects whether the above-mentioned obstacle is crossed. If it is crossed, the control unit re-plans the route according to the instructions of the upper computer and controls the moving wheel 200 or the driving component 300 to move.

Example 2

FIG3 to FIG8 are partial structural schematic diagrams of a second embodiment of the unmanned forklift obstacle avoidance and bypassing system integrating a 3D visual camera and a radar according to the present invention. Please refer to FIG3 to FIG8. Different from the above embodiment, in this embodiment:

The driving assembly 300 includes a main gear plate 310, four driven gears 320 surrounding the main gear plate 310, a driven transmission shaft 330 coaxially arranged with the driven gears 320, a transmission belt 340 meshing with the driven gears 320, an active transmission shaft 350 coaxially arranged with the main gear plate 310, and a steering drive motor 360 installed on the base plate 110 and having an output end connected to the active transmission shaft 350, wherein two mutually symmetrical driven gears 320 are meshed with the main gear plate 310, one end of the driven transmission shaft 330 is connected to the steering input end of the moving wheel 200, and the other end is rotatably connected to the top of the inner wall of the protective shell 120, when the steering drive motor 360 drives the active transmission shaft 350, the active transmission shaft 350 drives the obstacle detection assembly 400 to rotate, and at the same time, the main gear plate 310 rotates along with the active transmission shaft 350. The two driven gears 320 meshing therewith are driven to rotate, and under the transmission action of the transmission belt 340 , the four driven gears 320 rotate synchronously together to drive the driven transmission shaft 330 coaxially connected therewith to rotate, thereby driving the moving wheel 200 to turn.

The moving wheel 200 includes a base 210 , a traveling assembly 220 mounted on the base 210 , and a steering transmission assembly 230 mounted on the base 210 for driving the traveling assembly 220 to turn. The input end of the steering transmission assembly 230 is connected to the driven transmission shaft 330 .

The seat body 210 includes a first support seat 210b and a second support seat 210c connected to the base 210a by an axle pin and located above the base 210a;

The walking assembly 220 includes a rotating disk 220a which is rotatably connected to the shaft hole of the base 210a through a bearing and has support ears 220a-2 symmetrically arranged at the bottom, a support shaft 220b arranged between the two support ears 220a-2, a walking wheel 220c which is coaxially connected to the support shaft 220b and has a first bevel gear 220c-1 on the side wall, a second bevel gear 220d meshing with the walking wheel 220c, and a walking wheel 220c which is located above the rotating disk 220a and is coaxially connected to the second bevel gear 220d through the shaft. The transmission spur gear 220e and the walking drive motor 220f are installed on the first support seat 210b and the walking drive gear 220f-1 at the output end is meshed with the walking transmission spur gear 220e. During normal walking, the walking drive motor 220f drives the walking transmission spur gear 220e to rotate through the walking drive gear 220f-1, and the second bevel gear 220d rotates together with the walking transmission spur gear 220e. The second bevel gear drives the walking wheel 220c to move by meshing with the first bevel gear 220c-1.

The steering transmission assembly 230 includes a reduction motor 230a installed on the second support seat 210c, a first steering transmission shaft 230b installed on the second support seat 210c, and a second steering transmission shaft 230, the output end of the reduction motor 230a has a reduction transmission gear 230a-1, the first steering transmission shaft 230b has a first steering transmission gear 230b-1 and a second steering transmission gear 230b-2 meshed with the reduction transmission gear 230a-1, the second steering transmission shaft 230 has a third steering transmission gear 230c-1 and a fourth steering transmission gear 230c-2 meshed with the second steering transmission gear 230b-2, the fourth steering transmission gear 230c-2 is connected to the tooth groove of the rotating disk 220a through the steering transmission gear belt 230d 220a-1 is engaged. When in use, the input end of the reduction motor 230a is subjected to the steering driving force of the driven transmission shaft 330, and the first steering transmission shaft 230b is driven to rotate through the reduction transmission gear 230a-1 and the first steering transmission gear 230b-1. When the first steering transmission shaft 230b rotates, the second steering transmission shaft 230 is driven to rotate through the second steering transmission gear 230b-2 and the third steering transmission gear 230c-1. The second steering transmission shaft 230 drives the rotating disk 220a to rotate through the fourth steering transmission gear 230c-2 and the steering transmission gear belt 230d, thereby realizing the steering of the walking component 220.

Example 3

The method of the obstacle avoidance and bypassing system of an unmanned forklift integrating 3D vision camera and radar is as follows:

S1. The control unit of the unmanned forklift drives the moving wheel 200 to move forward according to the walking route planned by the upper computer, and adjusts the walking direction of the moving wheel 200 by driving the driving component 300. At the same time, the radar detection component 420 of the obstacle detection component 400 emits radar waves forward to detect whether there are obstacles within a certain distance ahead;

S2. When the obstacle detection component 400 detects an obstacle within a certain distance ahead, the control unit controls the moving wheel 200 to stop moving, and sends a steering command to the driving component 300. The driving component 300 drives the moving wheel 200 and the obstacle detection component 400 to turn 90° as a whole. The radar detection component 420 of the obstacle detection component 400 continues to detect whether there is an obstacle ahead after the turn. At the same time, after the turn, the two visual cameras 430 are facing the previously detected obstacles to obtain the depth image of the obstacles, and construct a three-dimensional model of the road scene of the obstacles ahead, and transmit it to the control unit;

S3, then the control unit sends a walking command to the moving wheel 200, and the moving wheel 200 continues to move forward after the rotation. At the same time, the control unit determines in real time whether the unmanned forklift bypasses the obstacle according to the three-dimensional model of the obstacle road scene in front constructed by the two visual cameras 430. When it is determined that the unmanned forklift bypasses the obstacle, the control unit continues to walk forward according to the planned route. The specific steps of the control unit determining in real time whether the unmanned forklift bypasses the obstacle according to the three-dimensional model of the obstacle road scene in front constructed by the two visual cameras 430 are as follows: the visual camera 430 obtains the depth image of the obstacle, and constructs the three-dimensional model of the obstacle road scene in front, and transmits it to the control unit; the control unit determines the length of the obstacle according to the acquired depth image of the obstacle, and controls the unmanned forklift to move forward to the distance of the length of the obstacle after the rotation. At the same time, the control unit determines whether there is still an obstacle in the obstacle road scene in front constructed by the visual camera 430. When the distance controlled to move the unmanned forklift to the front after the rotation is greater than the distance of the length of the obstacle, and the obstacle road scene in front constructed by the visual camera 430 does not have an obstacle, it is determined to bypass the obstacle.

Although the present invention has been described above with reference to the embodiments, various modifications may be made thereto and parts thereof may be replaced by equivalents without departing from the scope of the present invention. In particular, as long as there is no structural conflict, the various features in the embodiments disclosed in the present invention may be used in combination with each other in any manner, and the fact that these combinations are not exhaustively described in this specification is only for the sake of omitting space and saving resources. Therefore, the present invention is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

An unmanned forklift obstacle avoidance and bypassing system integrating 3D vision camera and radar, characterized by comprising:

A vehicle housing (100) comprises a bottom plate (110) and a protective shell (120) connected to the bottom plate (110);

Moving wheels (200) are arranged at the four corners of the bottom plate (110) and extend out from the bottom;

A drive assembly (300) is installed inside the vehicle housing (100), wherein a portion of the drive assembly (300) extends to the top of the protective shell (120), and another portion is connected to the steering input end of the moving wheel (200);

An obstacle detection assembly (400) is located directly above the protective shell (120) and is connected to an extended portion of the driving assembly (300);

A cargo fork (500) is installed in front of the vehicle body (100) to fork and pick up cargo;

Wherein, in a normal state, the moving wheel (200) automatically drives the vehicle body (100) to move forward according to the instruction of the control unit, and at the same time, the obstacle detection component (400) detects whether there is an obstacle in front of the movement;

When the obstacle detection component (400) finds that there is an obstacle at a certain distance directly in front, the driving component (300) drives the moving wheel (200) and the obstacle detection component (400) to turn 90 degrees as a whole, and then continue to move forward after the rotation. At the same time, the obstacle detection component (400) detects whether the obstacle has been crossed. If the obstacle has been crossed, the control unit replans the route according to the instructions of the host computer and controls the moving wheel (200) or the driving component (300) to move.
The unmanned forklift obstacle avoidance and circumvention system integrating 3D vision camera and radar according to claim 1 is characterized in that the driving assembly (300) includes a main gear plate (310), four driven gears (320) surrounding the main gear plate (310), a driven transmission shaft (330) coaxially arranged with the driven gear (320), a transmission belt (340) meshing with the driven gear (320), an active transmission shaft (350) coaxially arranged with the main gear plate (310), and a steering drive motor (360) installed on the base plate (110) and having an output end connected to the active transmission shaft (350);

Among them, two mutually symmetrical driven gears (320) are meshed with the main gear plate (310), one end of the driven transmission shaft (330) is connected to the steering input end of the moving wheel (200), and the other end is rotatably connected to the top of the inner wall of the protective shell (120).
The unmanned forklift obstacle avoidance and circumvention system integrating 3D visual camera and radar according to claim 2 is characterized in that the obstacle detection component (400) comprises a rotating head (410) connected to the active transmission shaft (350) and in a rectangular shape, a radar detection component (420) installed on one side of the rotating head (410), and two visual cameras (430) installed on the other side of the rotating head (410);

The mounting surfaces of the two visual cameras (430) are perpendicular to the mounting surface of the radar detection component (420).
According to the unmanned forklift obstacle avoidance and circumvention system integrating a 3D vision camera and a radar as described in claim 3, it is characterized in that the radar detection component (420) includes a radar wave transmitting end (420a) and a radar wave receiving end (420b).
According to the unmanned forklift obstacle avoidance and circumvention system integrating 3D vision camera and radar as described in claim 2, it is characterized in that the moving wheel (200) includes a seat body (210), a walking component (220) installed on the seat body (210), and a steering transmission component (230) installed on the seat body (210) to drive the walking component (220) to turn, and the input end of the steering transmission component (230) is connected to the driven transmission shaft (330).
The unmanned forklift obstacle avoidance and circumvention system integrating 3D vision camera and radar according to claim 5 is characterized in that the seat body (210) includes a base (210a) connected to the base (210a) by an axle pin and a first support seat (210b) and a second support seat (210c) located above the base (210a);

The walking assembly (220) comprises a rotating disk (220a) rotatably connected to the shaft hole of the base (210a) through a bearing and having support ears (220a-2) symmetrically arranged at the bottom, a support shaft (220b) arranged between the two support ears (220a-2), a walking wheel (220c) coaxially connected to the support shaft (220b) and having a first bevel gear (220c-1) on the side wall, a second bevel gear (220d) meshing with the walking wheel (220c), a walking transmission spur gear (220e) located above the rotating disk (220a) and coaxially connected to the second bevel gear (220d) through the shaft, and a walking drive motor (220f) installed on the first support seat (210b) and having a walking drive gear (220f-1) at the output end meshing with the walking transmission spur gear (220e);

The steering transmission assembly (230) comprises a reduction motor (230a) mounted on the second support seat (210c), a first steering transmission shaft (230b) mounted on the second support seat (210c), and a second steering transmission shaft (230);

The output end of the reduction motor (230a) is provided with a reduction transmission gear (230a-1), and the first steering transmission shaft (230b) is provided with a first steering transmission gear (230b-1) and a second steering transmission gear (230b-2) meshed with the reduction transmission gear (230a-1);

The second steering transmission shaft (230) has a third steering transmission gear (230c-1) and a fourth steering transmission gear (230c-2) meshed with the second steering transmission gear (230b-2), and the fourth steering transmission gear (230c-2) meshes with the tooth groove (220a-1) of the rotating disk (220a) through a steering transmission gear belt (230d).
The unmanned forklift obstacle avoidance and obstacle bypassing system integrating 3D vision camera and radar according to claim 1 is characterized in that the fork (500) includes a rectangular frame (510), a lifting drive motor (520) installed on the bottom frame (510a) of the rectangular frame (510), a screw rod (530) having one end connected to the output end of the lifting drive motor (520) and the other end connected to the top frame (510c) of the rectangular frame (510), a sliding plate (540) which is slidably connected to the vertical frame (510b) of the rectangular frame (510) and has a moving block (540a) on the rear side wall that engages with the screw rod (530), and a fork frame (550) arranged vertically to the sliding plate (540).
A method for an unmanned forklift obstacle avoidance and bypassing system integrating a 3D vision camera and a radar as claimed in any one of claims 1 to 7, characterized in that the specific steps are as follows:

S1. The control unit of the unmanned forklift drives the moving wheel (200) to move forward according to the moving route planned by the upper computer, and adjusts the moving direction of the moving wheel (200) by driving the driving component (300). At the same time, the radar detection component (420) of the obstacle detection component (400) emits radar waves forward to detect whether there is an obstacle within a certain distance ahead;

S2. When the obstacle detection component (400) detects an obstacle within a certain distance ahead, the control unit controls the moving wheel (200) to stop moving, and the control unit sends a steering command to the driving component (300). The driving component (300) drives the moving wheel (200) and the obstacle detection component (400) to turn 90 degrees as a whole. The radar detection component (420) of the obstacle detection component (400) continues to detect whether there is an obstacle ahead after the turn. At the same time, after the turn, the two visual cameras (430) face the previously detected obstacle to obtain a depth image of the obstacle, and construct a three-dimensional model of the road scene of the obstacle ahead, and transmit it to the control unit;

S3, the control unit then sends a walking instruction to the moving wheel (200), and the moving wheel (200) continues to move forward after the rotation. At the same time, the control unit determines in real time whether the unmanned forklift has bypassed the obstacle based on the three-dimensional model of the road scene of the obstacle ahead constructed by the two visual cameras (430). When it is determined that the unmanned forklift has bypassed the obstacle, the control unit continues to move forward according to the planned route.
The obstacle avoidance and circumvention method for unmanned forklifts integrating 3D vision cameras and radars according to claim 8 is characterized in that the control unit determines in real time whether the unmanned forklift has circumvented the obstacle based on the three-dimensional model of the road scene of the obstacle ahead constructed by the two vision cameras (430). The specific steps are as follows:

The visual camera (430) acquires a depth image of the obstacle, constructs a three-dimensional model of the road scene of the obstacle ahead, and transmits it to the control unit;

The control unit determines the length of the obstacle based on the acquired depth image of the obstacle, and controls the unmanned forklift to move forward after the rotation to a distance equal to the length of the obstacle. At the same time, the control unit determines whether the obstacle road scene directly in front of the visual camera (430) still has an obstacle. When the distance controlled by the unmanned forklift to move forward after the rotation is greater than the distance equal to the length of the obstacle, and the obstacle road scene directly in front of the visual camera (430) does not have an obstacle, it is determined to bypass the obstacle.