Indoor and outdoor line-following mark identification automatic operation vehicle

Abstract

The utility model discloses an automatic operation vehicle suitable for line-following mark identification indoors and outdoors. The working vehicle comprises a working vehicle body, a host system arranged on the working vehicle body, a first camera arranged on the top of the working vehicle body, and a second camera arranged on the lower side of the front end of the working vehicle body. The first camera and the second camera are in communication connection with the host system, the first camera is arranged along a first direction, the ground clearance of the first camera is 40-150cm, and the first direction is parallel to the advancing direction of the working vehicle; the first camera is used for identifying two-dimensional codes arranged at a plurality of preset positions, the shooting distance is 0.5-3, the second camera is arranged along a second direction, and the ground clearance is 10-15 cm. The scheme of line patrol and two-dimensional code recognition is adopted, indoor and outdoor automatic operation and automatic driving can be effectively deployed, the vehicle operation precision is high, the later maintenance cost is low, and the overall deployment scheme cost is low.

Description

Technical Field

[0001] The utility model relates to the technical field of line-following and mark-recognition, and in particular to an automatic line-following and mark-recognition operation vehicle suitable for indoor and outdoor use. Background Art

[0002] Generally, indoor and outdoor autonomous driving relies on high-precision maps or more complex image algorithms for scene recognition, and many outdoor algorithms have low universality, and are not universal for multiple different scenes or switching between indoor and outdoor scenes. At the same time, the cost is high, and the subsequent maintenance is cumbersome, which is not conducive to immediate deployment and use. Utility Model Content

[0003] In view of this, the purpose of the utility model is to propose an automatic line-following and mark-recognition operation vehicle suitable for indoor and outdoor use. The inventor found that the solution of line-following and QR code recognition can effectively deploy automatic operation and automatic driving indoors and outdoors, and the vehicle has high operation accuracy and can maintain a stopping error of ±3cm. At the same time, the subsequent maintenance cost is low, and the overall deployment solution cost is low. Furthermore, by setting the specific positions of the two cameras, the detection accuracy can be improved.

[0004] According to one aspect of the utility model, there is provided an automatic line-tracking and mark-recognition work vehicle suitable for indoor and outdoor use, comprising: a work vehicle body, a host system arranged on the work vehicle body, a first camera arranged on the top of the work vehicle body, and a second camera arranged on the lower side of the front end of the work vehicle body; the first camera and the second camera are communicatively connected with the host system, wherein:

[0005] The first camera is arranged along a first direction, which is parallel to the forward direction of the working vehicle; the first camera is used to identify the two-dimensional codes arranged at a plurality of preset positions, and the camera distance is 0.5-3m;

[0006] The second camera is arranged along a second direction, with a height of 10cm-15cm from the ground, and the angle between the second direction and the forward direction of the working vehicle forms an acute angle, and the acute angle ranges from 10° to 30°; the second camera is used to identify the preset lane line, and the camera distance is 0.8m;

[0007] The distance between the first camera and the second camera is 1.2 m.

[0008] In the above technical solution, two cameras for different functions are provided, two different cameras, one is used to identify the ground track line (different colors of lines can be used), and the ground track line is identified by an algorithm to keep the vehicle body always driving within the lane line; the other camera is used to identify the QR code in the scene, and the identification of the QR code can be used to locate the vehicle in the scene, so that the vehicle arrives at the specified position, and the remaining functions of the vehicle can be performed by identifying the QR code in the scene, including reversing into the warehouse, automatic recharging, etc.; the algorithm is used to combine the data output by the vehicle tracking line with the identified QR code data, and the data is fused at the terminal, and the vehicle behavior is judged by the fused data, such as reversing into the warehouse when arriving at the specified position, or making the vehicle perform autonomous operations in a closed working environment based on the obtained data; it should be noted that the recognition algorithm part of the two cameras is not the improved part of the utility model, and the improvement of the utility model lies in the setting of the camera and the specific position control; specifically:

[0009] The camera used for lane line recognition is arranged at the front of the vehicle, at the vehicle chassis position, the distance from the ground should be controlled at 10cm~15cm, the angle with the horizontal position should be controlled at 10°~30°, and the camera distance is 0.8m; the purpose of this setting is to eliminate interfering objects within the camera range and effectively identify lane lines.

[0010] The camera used to identify the QR code is placed on the top of the vehicle, 40cm-150cm above the ground, with an angle parallel to the horizontal plane and a camera distance of 0.5-3m. The purpose of this setting is to set the distance of the QR code within the effective range and effectively identify the QR code in the scene.

[0011] The distance between the first camera and the second camera is 1.2m. This setting is to avoid mutual interference between the two cameras and enhance the accuracy of the camera with specific functions.

[0012] In some embodiments, specific parameters of the first camera are as follows:

[0013] Focal length: 25mm, aperture: F2.0, size: 1 / 3", HFOV=70.8°, VFOV=55.6°.

[0014] In the above technical solution, the purpose of such setting is to use the camera to accurately capture the set QR code within the focal length range.

[0015] In some embodiments, specific parameters of the second camera are as follows:

[0016] Focal length: 2.8mm, aperture: F2.0, size: 1 / 3", HFOV=70.8°, VFOV=55.6°.

[0017] In the above technical solution, the purpose of such setting is to use a short focal length to more accurately identify lane lines.

[0018] In some embodiments, the two-dimensional code set at multiple preset positions is an AprilTag, and its format is TAG36H11.

[0019] In the above technical solution, the purpose of such setting is that the two-dimensional code in this format can output corresponding numbers, and the difference between individuals is large, and it is not easy to cause misrecognition.

[0020] In some embodiments, the first camera is disposed at the center of the top of the work vehicle body, and the height from the ground is 120 cm-150 cm.

[0021] In the above technical solution, the purpose of such setting is to take into account the placement situation of the actual scene, and this height can just avoid the influence of too high or too low position on the recognition accuracy.

[0022] In some embodiments, the first camera is disposed on either side of the center position of the top of the work vehicle body, and the height from the ground is 40 cm-70 cm.

[0023] In the above technical solution, the purpose of such setting is to effectively capture the required lane lines and avoid capturing some irrelevant objects that affect the recognition effect.

[0024] In some embodiments, the work vehicle body includes a chassis control bus for controlling the chassis of the work vehicle body, and the host is communicatively connected to the chassis control bus.

[0025] In the above technical solution, the purpose of such a setting is to be able to control the chassis gear position, speed, steering, etc. through a bus. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the embodiments of the utility model or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the utility model. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0027] Figure 1 It is a three-dimensional structural schematic diagram of an embodiment of the utility model of an automatic line-following and mark-recognizing operation vehicle suitable for indoor and outdoor use;

[0028] Figure 2 It is a side structural schematic diagram of an embodiment of the utility model of an automatic line-following and mark-recognizing operation vehicle suitable for indoor and outdoor use;

[0029] Figure 3 This is a schematic diagram of an optional solution of an embodiment of the utility model of an automatic line-following and mark-recognizing operation vehicle suitable for indoor and outdoor use;

[0030] Figure 4 The utility model is a schematic diagram of the working process of an automatic operation vehicle of an embodiment of the automatic operation vehicle for indoor and outdoor line following and marking identification. DETAILED DESCRIPTION

[0031] The present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It is particularly noted that the following embodiments are only used to illustrate the present invention, but do not limit the scope of the present invention. Similarly, the following embodiments are only partial embodiments of the present invention rather than all embodiments. All other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0032] The utility model provides an automatic line-following and mark-recognition operation vehicle suitable for indoor and outdoor use. The inventor has found that the line-following and QR code recognition solution can effectively deploy automatic operation and automatic driving indoor and outdoor, and the subsequent maintenance cost is low, and the overall deployment solution cost is low. Furthermore, by setting the specific positions of the two cameras, the detection accuracy can be improved.

[0033] See also Figure 1 , an automatic line-following and mark-recognition work vehicle suitable for indoor and outdoor use, comprising: a work vehicle 1 body, a host system 4 arranged on the work vehicle 1 body, a first camera 2 arranged on the top of the work vehicle 1 body, and a second camera 3 arranged on the lower side of the front end of the work vehicle 1 body; the first camera 2, the second camera 3 are connected to the host system 4 for communication

[0034] In this embodiment, the work vehicle body 1 can be a handling robot of CN110733817B, a mountain off-road robot chassis of CN108163094B, a robot vehicle of US20230322038A1 and a support assembly of its wheels. Since the work vehicle body is not an improved technical point of this case, this case will not describe in detail how the vehicle moves, how it moves and its movement principle. Those skilled in the art can select a suitable vehicle according to actual needs.

[0035] In this embodiment, the first camera 2 is arranged along a first direction A, and the first direction A is parallel to the forward direction G of the working vehicle; the first camera 2 is used to identify the two-dimensional code set at a plurality of preset positions, and the camera distance is 0.5-3m;

[0036] The second camera 3 is arranged along a second direction B, and the height L2 from the ground is 10cm-15cm. The angle α between the second direction B and the forward direction G of the working vehicle forms an acute angle, and the acute angle ranges from 10° to 30°. The second camera 3 is used to identify the preset lane line, and the camera distance is 0.8m.

[0037] The distance between the first camera and the second camera is 1.2 m.

[0038] In this embodiment, two cameras for different functions are provided, two different cameras, one is used to identify the ground track line (different colors of lines can be used), and the ground track line is identified by an algorithm to keep the vehicle body always driving within the lane line; the other camera is used to identify the QR code in the scene, and the identification of the QR code can be used to locate the vehicle in the scene, so that the vehicle arrives at the specified location, and the remaining functions of the vehicle can be performed by identifying the QR code in the scene, including reversing into the garage, automatic recharging, etc.; the algorithm is used to combine the data output by the vehicle tracking line with the identified QR code data, and the data is fused at the terminal, and the vehicle behavior is judged by the fused data, such as reversing into the garage when arriving at the specified location, or making the vehicle perform autonomous operations in a closed working environment based on the obtained data; it should be noted that the recognition algorithm part of the two cameras is not the improved part of the utility model, and the improvement of the utility model lies in the setting of the camera and the specific position control; specifically:

[0039] The second camera 3 used for lane line recognition is arranged at the front of the vehicle, at the vehicle chassis position, the distance from the ground should be controlled at 10cm~15cm, the angle with the horizontal position is controlled at 10°~30°, and the shooting distance is 0.8m; the purpose of this setting is to eliminate interfering objects within the shooting range and effectively identify lane lines.

[0040] The first camera 2 for identifying the QR code is arranged on the top of the vehicle, with a height L1 of 40cm-150cm from the ground, an angle parallel to the horizontal plane, and a camera distance of 0.5-3m. The purpose of this setting is to set the distance of the QR code within the effective range and effectively identify the QR code in the scene.

[0041] It should be noted that the camera distance refers to the distance at which the camera can effectively identify the QR code. By controlling the camera distance, the recognition accuracy is improved. At the same time, the distance control ensures that the work vehicle has enough reaction time and can complete the action when it reaches the specified position.

[0042] The distance between the first camera 2 and the second camera 3 is 1.2 m. The purpose of this arrangement is to avoid mutual interference between the two cameras and enhance the accuracy of the camera with a specific function.

[0043] In this embodiment, the specific parameters of the first camera 2 are as follows: focal length: 25 mm, aperture: F2.0, size: 1 / 3", HFOV = 70.8°, VFOV = 55.6°. The purpose of this setting is to use the camera to accurately capture the set QR code within the focal length range.

[0044] In this embodiment, the specific parameters of the second camera 3 are as follows: focal length: 2.8 mm, aperture: F2.0, size: 1 / 3", HFOV = 70.8°, VFOV = 55.6°. The purpose of this setting is to use a short focal length to more accurately identify the lane line.

[0045] In this embodiment, the two-dimensional code set at multiple preset positions is AprilTag, and its format is TAG36H11. The purpose of this setting is that the two-dimensional code in this format can output corresponding numbers, and the difference between individuals is large, and it is not easy to cause misrecognition.

[0046] In this embodiment, the first camera 2 is arranged at the center of the top of the vehicle 1, and the height L1 from the ground is 120cm-150cm. The purpose of such arrangement is to take into account the placement of the actual scene, and this height can just avoid the influence of too high or too low position on the recognition accuracy.

[0047] In this embodiment, as an optional implementation scheme, please refer to Figure 3 The first camera 2 is arranged on either side of the center position of the top of the work vehicle 1, and the height L4 from the ground is 40cm-70cm. The purpose of such arrangement is to effectively capture the required lane line and avoid capturing some irrelevant objects that affect the recognition effect.

[0048] In this embodiment, the work vehicle body includes a chassis control bus for controlling the chassis of the work vehicle body, and the host is communicatively connected to the chassis control bus. The purpose of this arrangement is to control the chassis gear, speed, steering, etc. through a bus.

[0049] The following are some examples:

[0050] In order to solve the above technical problems, a technical solution adopted in an embodiment of the utility model is: two cameras for different functions are provided, wherein the two different cameras, one is used to identify the ground track line (different colors of lines can be used), and identify the ground track line through an algorithm to keep the vehicle body always driving within the lane line; the other camera is used to identify the QR code in the scene, and the identification of the QR code can be used to position the vehicle in the scene, so that the vehicle arrives at the designated position, and the remaining functions of the vehicle can be performed by identifying the QR code in the scene, including reversing into the warehouse, automatic recharging, etc.; an algorithm is used to combine the data output by the vehicle following the line with the identified QR code data, and data fusion is performed at the terminal, and the vehicle behavior is judged by the fused data, such as reversing into the warehouse when arriving at the designated position, or enabling the vehicle to perform autonomous operations in a closed working environment based on the obtained data; the terminal's instructions are all output to the chassis through the vehicle's integrated CAN bus for behavior control, and the output data are signals such as gear position, speed, start and stop, and stop when encountering obstacles. The vehicle terminal obtains the line tracking data and the QR code data, performs data fusion, and uses algorithms to ensure that the vehicle always stays in the lane. It recognizes the QR code in the scene to start and stop the vehicle, arrive at the designated location, reverse into the garage, and perform other functions.

[0051] The beneficial effects of the embodiments of the utility model are as follows: different from the prior art, the utility model uses lane line and QR code recognition and data fusion to perform autonomous indoor operation and automatic driving. The vehicle layout is simple, and it can be deployed and put into use immediately in the required scene. The cost is lower than that of traditional lidar or visual mapping methods, and the subsequent maintenance cost and debugging cost are low, which is conducive to use by small and medium-sized enterprises.

[0052] For further information, see Figure 4 The working principle of the utility model is as follows Figure 4 As shown in the figure above, the second camera plays a role in maintaining the vehicle within the set range in the entire vehicle system. The vehicle relies on the second camera to identify the track line on the ground and relies on the lane line to adjust the vehicle during travel, so that the vehicle can always travel accurately in the required route. The line tracking data is the PID control value calculated by the algorithm, which can be used to control the steering of the chassis so that the track line is always in the center of the vehicle. The first camera plays a role in reaching the specified position in the entire system, judging the position of the vehicle in the environment, and some command judgments. The first camera recognizes the QR code in the scene. The valid value range of the QR code that can be output is 0 to 586. The first camera obtains the output value by recognizing the QR code, and then transmits it to the data terminal through the algorithm through the output value. For example, when the number 1 is recognized, the vehicle moves forward until the number 3 is recognized and the vehicle stops; or when the number 5 is recognized, the reverse parking instruction is executed. This method has a wide range of uses and will be changed according to the specific needs of the specific scene.

[0053] Data fusion is to fuse the data of the second camera with the data of the first camera, and drive the vehicle to operate autonomously through algorithms. For example, the logic of picking up objects along the line and reversing into the warehouse: the vehicle receives the instruction to reach the QR code No. 5 → the vehicle moves forward along the line → recognizes the QR code No. 5 → the vehicle stops → the vehicle picks up objects → the vehicle moves back along the line → recognizes the QR code No. 3 → performs reversing into the warehouse. This is a commonly used solution to drive the vehicle to operate autonomously through data fusion and algorithms. There are many solutions that can be set and adjusted according to specific needs.

[0054] In the above figure, the vehicle chassis receives the command sent by the host system, which may be the current position of the vehicle, the designated position to be reached, the linear velocity and angular velocity given by the terminal to the chassis, the vehicle's forward gear, reverse gear, parking gear and other instructions. At the same time, the vehicle will feedback the chassis information during operation, and the chassis information can be obtained in real time for easy viewing and maintenance. It should be noted that the specific control part is not the improvement point involved in the present invention, and will not be described in detail here. Those skilled in the art can set it according to actual needs.

[0055] The above descriptions are only some embodiments of the present invention, and do not limit the protection scope of the present invention. Any equivalent device or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. An automatic line-following and mark-recognition vehicle suitable for indoor and outdoor use. It is characterized in that include: A work vehicle body, a host system arranged on the work vehicle body, a first camera arranged on the top of the work vehicle body, and a second camera arranged on the lower side of the front end of the work vehicle body; the first camera and the second camera are communicatively connected with the host system, wherein: The first camera is arranged along a first direction at a height of 40 cm to 150 cm from the ground, and the first direction is parallel to the forward direction of the working vehicle; the first camera is used to identify the two-dimensional codes arranged at a plurality of preset positions, and the camera distance is 0.5 to 3 m; The second camera is arranged along a second direction, with a height of 10cm-15cm from the ground, and the angle between the second direction and the forward direction of the working vehicle forms an acute angle, and the acute angle ranges from 10° to 30°; the second camera is used to identify the preset lane line, and the camera distance is 0.8m; The distance between the first camera and the second camera is 1.2 m.

2. An automatic line-following and mark-recognition operation vehicle suitable for indoor and outdoor use as claimed in claim 1, It is characterized in that The specific parameters of the first camera are as follows: Focal length: 25mm, aperture: F2.0, size: 1 / 3", HFOV=70.8°, VFOV=55.6°.

3. The automatic line-following and mark-recognition operation vehicle suitable for indoor and outdoor use as claimed in claim 1, It is characterized in that The specific parameters of the second camera are as follows: Focal length: 2.8mm, aperture: F2.0, size: 1 / 3", HFOV=70.8°, VFOV=55.6°.

4. The automatic line-following and mark-recognition operation vehicle suitable for indoor and outdoor use as claimed in claim 1, It is characterized in that The two-dimensional code set at multiple preset positions is AprilTag, and its format is TAG36H11.

5. An automatic line-following and mark-recognition operation vehicle suitable for indoor and outdoor use as claimed in claim 1 or 4, It is characterized in that The first camera is arranged at the center position of the top of the working vehicle body, and the height from the ground is 120cm-150cm.

6. An automatic line-following and mark-recognition operation vehicle suitable for indoor and outdoor use as claimed in claim 1 or 4, It is characterized in that The first camera is arranged on either side of the center position of the top of the work vehicle body, and the height from the ground is 40cm-70cm.

7. The automatic line-following and mark-recognition operation vehicle suitable for indoor and outdoor use as claimed in claim 1, It is characterized in that The working vehicle body comprises a chassis control bus for controlling the working vehicle body chassis, and the host is communicatively connected with the chassis control bus.

Images