Autonomous unloading method of a trolley and autonomous unloading trolley

Abstract

The present invention provides an autonomous unloading method of a trolley and an autonomous unloading trolley, wherein the autonomous unloading method comprises: the trolley autonomously navigates and moves to the position of the door of the carriage according to the positional relationship between the trolley and the carriage; the depth direction of the carriage is defined as the X-axis, the width direction of the carriage is defined as the Y-axis, and the height direction of the carriage is defined as the Z-axis; an image in the carriage is acquired through a 3D vision system, and image recognition and point cloud segmentation are performed on the acquired image, so as to obtain size information and position information of each packaging box; the center coordinates of a grasping surface are calculated according to the size information and position information of each packaging box; the center coordinates of all grasping surfaces are sorted, and a grasping order of the packaging boxes is defined; wherein the sorting comprises: first sorting by the X-axis, then sorting by the Z-axis, and then sorting by the Y-axis, so as to realize grasping from near to far and from top to bottom along the Y-axis direction; and a mechanical arm is controlled to grasp the packaging boxes in order according to the sorting result and the distance between the trolley and the packaging box.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics, and in particular to an autonomous unloading method of a trolley and an autonomous unloading trolley. Background Art

[0002] In large logistics centers, docks, cold chain transportation, and other containerized cargo loading and unloading scenarios, manual labor is currently the primary method for loading and unloading cargo, with neatly stacked cargo. However, traditional manual loading and unloading presents a challenge in handling a wide variety of cargo types. Furthermore, loading and unloading stations and train cars are typically not equipped with air conditioning. Constantly moving cargo within cramped train cars, exposed to cold winters and scorching summers, is subject to odors, heat, and dust, creating workplace inconveniences. Furthermore, the sheer volume and weight of cargo, coupled with the need to continuously and quickly complete tasks, means virtually every worker suffers from illnesses related to long-term labor. For large-scale manufacturing enterprises, annual loading and unloading labor costs can reach tens of millions of yuan, and these costs continue to rise.

[0003] Therefore, how to achieve intelligent loading and unloading has become the focus of those skilled in the art. Summary of the Invention

[0004] The purpose of the present invention is to provide an autonomous unloading method for a trolley and an autonomous unloading trolley, which can realize intelligent autonomous unloading.

[0005] In order to achieve the above object, the present invention provides a method for autonomous unloading of a trolley, comprising:

[0006] The car autonomously navigates and moves to the door position based on its positional relationship with the carriage;

[0007] Define the depth direction of the carriage as the X-axis, the width direction as the Y-axis, and the height direction as the Z-axis. Use a 3D vision system to acquire images of the interior of the carriage, perform image recognition and point cloud segmentation on the acquired images, and thus obtain the size and position information of each packaging box.

[0008] Calculating the center coordinates of the gripping surface based on the size information and position information of each packaging box;

[0009] Sorting the center coordinates of all the gripping surfaces to define the order in which the packaging boxes are gripped;

[0010] The sorting includes: sorting by X axis first, sorting by Z axis second, and sorting by Y axis third, so as to achieve grabbing from near to far and from top to bottom along the Y axis direction;

[0011] According to the sorting result and the distance between the trolley and the packaging box, the robotic arm is controlled to grab the packaging boxes in sequence.

[0012] In an optional solution, the method for obtaining the size information and position information of each packaging box includes: performing image recognition and point cloud segmentation on the acquired image, thereby obtaining the size information and position information of each packaging box.

[0013] In an optional solution, the method for obtaining images inside the vehicle compartment includes: automatically recording the position information of each packaging box each time a photo of the current field of view is taken, and adjusting the field of view angle for the next shot based on the position information.

[0014] In an optional solution, the method for the robotic arm to grasp the packaging box includes: when the height of the packaging box to be grasped is greater than a preset threshold, controlling the robotic arm to grasp it from the side of the packaging box; when the height of the packaging box to be grasped is not greater than the preset threshold, controlling the robotic arm to grasp it from the top of the packaging box.

[0015] In an optional solution, before sorting the center coordinates of all the grasping surfaces, the method further includes: when the height of the packaging box to be grasped is greater than the preset threshold, filtering the point clouds of the packaging boxes below the preset threshold by point cloud filtering;

[0016] When the height of the packaging box to be grasped is not greater than the preset threshold, the point cloud of the packaging box with a height above the preset threshold is filtered out through point cloud filtering.

[0017] In an optional solution, when the number of packages grasped at one time is one, the center coordinates of the grasping surface are the center coordinates of the grasping surface of a single package box; when the number of packages grasped at one time is greater than one, the center coordinates of the grasping surface are the center coordinates of the grasping surface of multiple packages as a whole.

[0018] In an optional solution, after the trolley moves to the position of the carriage door, the method further includes: obtaining the distance between the trolley and the outermost packaging box, and adjusting the position of the trolley according to the grasping distance of the robotic arm.

[0019] In an optional solution, the method for obtaining the distance between the trolley and the outermost packaging box includes: obtaining images of the outermost packaging boxes, processing them to obtain point cloud data, and obtaining the distance between the trolley and the outermost packaging box based on the point cloud data.

[0020] The present invention also provides an autonomous unloading trolley, comprising:

[0021] Car body;

[0022] a mechanical arm rotatably disposed on the vehicle body;

[0023] A grabbing unit, provided at the end of the robotic arm, for grabbing a packaging box;

[0024] A 3D vision module is provided on the vehicle body and is used to acquire images inside the vehicle compartment and perform point cloud processing on the acquired images to obtain the size and position information of each packaging box;

[0025] a calculation and sorting module, in communication with the 3D vision module, calculating the center coordinates of the gripping surfaces based on the size and position information of each packaging box; sorting the center coordinates of all the gripping surfaces to define a gripping order for the packaging boxes; wherein the sorting includes: first sorting by the X-axis, then sorting by the Z-axis, and then sorting by the Y-axis, thereby achieving gripping from near to far and from top to bottom along the Y-axis;

[0026] The control module controls the robotic arm to grab the packaging boxes in sequence according to the sorting result and the distance between the trolley and the packaging boxes.

[0027] In an optional solution, the gripping module is a vacuum suction cup, and the vacuum suction cup includes a plurality of suction nozzles;

[0028] The number of the vacuum suction cups is one or a plurality of vacuum suction cups that work independently, and the control module controls the number of vacuum suction cups that work according to the size of the grasping.

[0029] In an optional solution, the autonomous unloading trolley further includes a bracket, which rotates coaxially with the robotic arm, and the 3D vision module includes a first binocular camera and a second binocular camera, which are arranged on the bracket one above the other.

[0030] The beneficial effects of the present invention are:

[0031] The present invention obtains images inside the carriage, processes the size information and position information of each packaging box, grabs the packaging box according to preset grabbing rules, and realizes intelligent unloading of the packaging box. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The above and other objects, features and advantages of the present invention will become more apparent through a more detailed description of exemplary embodiments of the present invention with reference to the accompanying drawings, in which like reference numerals generally represent like components.

[0033] Figure 1 The figure is a flow chart of a method for autonomous unloading of a trolley in one embodiment of the present invention.

[0034] Figure 2 This is a schematic structural diagram of an autonomous unloading vehicle in one embodiment of the present invention.

[0035] Figure 3 Schematic diagram of the unloading sequence of packaging boxes in one embodiment of the present invention. DETAILED DESCRIPTION

[0036] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. The advantages and features of the present invention will become more apparent from the following description and drawings. However, it should be noted that the technical solutions of the present invention can be implemented in a variety of different forms and are not limited to the specific embodiments described herein. The drawings are highly simplified and not to exact scale, and are intended solely to facilitate and clearly illustrate the embodiments of the present invention.

[0037] It should be understood that when an element or layer is referred to as being "on," "adjacent to," "connected to," or "coupled to" another element or layer, it can be directly on, adjacent to, connected to, or coupled to the other element or layer, or there can be intervening elements or layers. Conversely, when an element is referred to as being "directly on," "directly adjacent to," "directly connected to," or "directly coupled to" another element or layer, there are no intervening elements or layers. It should be understood that although the terms first, second, third, etc. may be used to describe various elements, components, regions, layers, and / or parts, these elements, components, regions, layers, and / or parts should not be limited by these terms. These terms are merely used to distinguish one element, component, region, layer, or part from another element, component, region, layer, or part. Thus, a first element, component, region, layer, or part discussed below may be represented as a second element, component, region, layer, or part without departing from the teachings of the present invention.

[0038] Spatially relative terms such as "under," "beneath," "below," "under," "above," "above," etc., may be used herein for convenience of description to describe the relationship of one element or feature shown in the figures to other elements or features. It should be understood that the spatially relative terms are intended to include different orientations of the device in use and operation in addition to the orientations shown in the figures. For example, if the device in the drawings is flipped, then the elements or features described as "under" or "beneath" or "beneath" the other elements will be oriented as "over" the other elements or features. Thus, the exemplary terms "under" and "under" may include both the upper and lower orientations. The device may be oriented otherwise (rotated 90 degrees or in other orientations) and the spatial descriptors used herein are interpreted accordingly.

[0039] The terminology used herein is intended only to describe specific embodiments and is not intended to limit the present invention. When used herein, the singular forms "a," "an," and "the" are intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the terms "comprising" and / or "including," when used in this specification, identify the presence of the recited features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups. When used herein, the term "and / or" includes any and all combinations of the relevant listed items.

[0040] Example 1

[0041] Reference Figure 1 This embodiment provides a method for autonomous unloading of a trolley, comprising:

[0042] The car autonomously navigates and moves to the door position based on its positional relationship with the carriage;

[0043] Define the depth direction of the carriage as the X-axis, the width direction as the Y-axis, and the height direction as the Z-axis. Use a 3D vision system to acquire images of the interior of the carriage, perform image recognition and point cloud segmentation on the acquired images, and thus obtain the size and position information of each packaging box.

[0044] Calculating the center coordinates of the gripping surface based on the size information and position information of each packaging box;

[0045] Sorting the center coordinates of all the gripping surfaces to define the order in which the packaging boxes are gripped;

[0046] The sorting includes: sorting by X axis first, sorting by Z axis second, and sorting by Y axis third, so as to achieve grabbing from near to far and from top to bottom along the Y axis direction;

[0047] The robotic arm is controlled to grab the packaging box according to the sorting result and the distance between the trolley and the packaging box.

[0048] Specifically, the trolley is equipped with a laser radar navigation device, which can navigate based on the laser radar. By monitoring changes in the surrounding environment in real time, it can autonomously plan the optimal path and move to the position of the car door. The trolley is also equipped with an infrared sensing system that can sense the presence of people nearby to ensure that no harm is caused to personnel during operation. After arriving at the designated location, the image of each outermost box in the car is obtained and processed to obtain point cloud data. Based on the point cloud data, the distance between the trolley and the outermost box is determined. Then, based on the grasping distance of the robotic arm, the position of the trolley is precisely adjusted so that the grasping range of the robotic arm can cover the width of the trolley without moving the trolley left or right, and can grasp the box.

[0049] After the position is adjusted, the 3D vision system captures images of the interior of the vehicle, performs image recognition and point cloud segmentation on the captured images, and obtains the size and position information of each packaging box. Due to the limited field of view, it is impossible to simultaneously capture a full range of images of the interior of the vehicle. Therefore, each time a photo of the current field of view is taken, the position information of each packaging box is automatically recorded, and the field of view for the next shot is adjusted based on this position information. Capturing and image processing are performed simultaneously. When the capture is complete, the image processing is also completed, the next capture coordinates are obtained, and the next capture can be carried out immediately. This parallel processing method can improve work efficiency.

[0050] Depending on the settings, the robotic arm can grasp a single box at a time or multiple boxes simultaneously. When grasping a single box at a time, the center coordinates of the grasping surface are those of the single box. When grasping more than one box at a time, the center coordinates of the grasping surface are those of the entire grasping surface.

[0051] After obtaining the center coordinates of each grasping surface, the center coordinates of all grasping surfaces are sorted according to a preset grasping rule. The depth of the carriage is defined as the X-axis, the width as the Y-axis, and the height as the Z-axis. The grasping rule is as follows: sort by X-axis first, then by Z-axis, and finally by Y-axis, achieving grasping from near to far and from top to bottom along the Y-axis. Specifically, with the position of the trolley as the primary perspective, the box in the upper left corner of the carriage is grasped first. At this point, boxes in the same row have the same X-axis and Z-axis coordinates. "Same" here allows for a certain degree of error. Due to varying sizes or uneven placement of boxes, the surfaces of boxes in the same row may not be perfectly aligned. For example, a tolerance of 10 mm is designed. During sorting, if the two data values ​​differ by less than 10 mm, the two boxes are considered to have the same coordinate values ​​for that axis (i.e., they are in the same row). Then, the boxes are grasped sequentially from left to right. Once the boxes in that row are grasped, the next row is moved to the next row and the grasping continues from left to right. This enables grasping from near to far, left to right, and top to bottom. When capturing an image of a box, the center coordinates of the grasping surface of the first box on the far left are automatically recorded. For boxes in the same row (arranged along the Y axis), when grasping the second box, the X- and Z-axis coordinates of the second box must be the same as those of the first box. This continues until all boxes in the row are grasped. Of course, the grasping order can also be from right to left.

[0052] Reference Figure 3 , describe the sorting method with a specific example. Figure 3A schematic diagram of the unloading order of the packaging boxes in the vehicle is shown with the position of the trolley as the main perspective. The center coordinates of the gripping surfaces of the packaging boxes marked 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, and 12 in the figure are (X1, Y2, Z1), (X1, Y3, Z1), (X1, Y1, Z2), (X1, Y2, Z2), (X1, Y3, Z2), (X1, Y1, Z3), (X1, Y2, Z3), (X1, Y3, Z3), (X2, Y1, Z1), (X2, Y2, Z1), and (X2, Y3, Z1). Figure 3 The box in the upper left corner has been removed, and its gripping surface center coordinates are (X1, Y1, Z1). Assume that, after acquiring an image of the vehicle interior, the 3D vision system processes the gripping surface center coordinates of the 12 boxes (including boxes located in different / same rows and different / same columns). After obtaining multiple gripping surface center coordinates, this embodiment first sorts these gripping surface center coordinates along the X-axis. It can be seen that boxes numbered 2-9 all have the same X-axis coordinates (including the first box already removed) and are grasped with priority over boxes numbered 10, 11, and 12. The boxes numbered 2-9 are then sorted along the Z-axis. It can be seen that the first group of boxes numbered 2 and 3 takes precedence over the second group of boxes numbered 4, 5, and 6, which in turn takes precedence over the third group of boxes numbered 7, 8, and 9. The three groups of boxes are then sorted along the Y-axis in order. It can be seen that box numbered 2 takes precedence over box numbered 3. The box numbered 3 takes precedence over the box numbered 4, which takes precedence over the box numbered 5. After sorting by the center coordinates of the grasping surface, the order of grasping is 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, and 12.

[0053] In this embodiment, a preset threshold (e.g., half the height of the carriage) is set. When the height of the box to be grasped exceeds the preset threshold, the robotic arm is controlled to grasp the box from the side. When the height of the box to be grasped is not greater than the preset threshold, the robotic arm is controlled to grasp the box from the top. In other words, the side facing the carriage serves as the grasping surface for boxes located at a higher position, while the top surface serves as the grasping surface for boxes located at a lower position. This improves the efficiency of the robotic arm in grasping boxes.

[0054] In this embodiment, before sorting the center coordinates of all gripping surfaces, the following steps are further performed: when the height of the to-be-grabbed packaging box is greater than a preset threshold, point cloud filtering is performed to remove the point cloud of packaging boxes below the preset threshold; when the height of the to-be-grabbed packaging box is less than the preset threshold, point cloud filtering is performed to remove the point cloud of packaging boxes above the preset threshold. This reduces unnecessary sorting work and improves processing speed.

[0055] After grabbing the package box near the outside, the robot arm may not be able to grab the package box in the carriage. At this time, it can be judged whether the robot arm can grab the package box based on the X-axis coordinate of the package box and the grabbing distance of the robot arm. If it cannot be grabbed, the car is controlled to move toward the carriage.

[0056] Example 2

[0057] Reference Figure 2 , this embodiment provides an autonomous unloading vehicle, comprising:

[0058] Car body 1;

[0059] A mechanical arm 2 is rotatably disposed on the vehicle body 1;

[0060] A grabbing unit 3 is provided at the end of the robotic arm 2 and is used to grab the packaging box;

[0061] A 3D vision module is provided on the vehicle body 1 and is used to acquire images inside the vehicle compartment and perform point cloud processing on the acquired images to obtain the size and position information of each packaging box;

[0062] a calculation and sorting module, in communication with the 3D vision module, calculating the center coordinates of the gripping surfaces based on the size and position information of each packaging box; sorting the center coordinates of all the gripping surfaces to define a gripping order for the packaging boxes; wherein the sorting includes: first sorting by the X-axis, then sorting by the Z-axis, and then sorting by the Y-axis, thereby achieving gripping from near to far and from top to bottom along the Y-axis;

[0063] The control module controls the robotic arm to grab the packaging boxes in sequence according to the sorting result and the distance between the trolley and the packaging boxes.

[0064] Specifically, the chassis of the unloading trolley adopts a crawler design, which can meet a variety of complex working conditions such as climbing, parking, crossing gaps, and vertical obstacle crossing. It can also rotate and turn on the spot. The trolley is equipped with a lidar navigation device that can monitor changes in the surrounding environment in real time and autonomously plan the optimal path to avoid collisions with obstacles and improve movement efficiency. The unloading trolley can also be equipped with an infrared sensing system that can sense whether there are people around to ensure that no harm is caused to personnel during operation. After the unloading trolley arrives at the designated location, the unloading trolley collects the 3D information of the packaging box through the 3D vision module and segments the packaging box through point cloud segmentation technology, thereby achieving accurate grasping and placement of objects.

[0065] To ensure that all items in containerized containers of varying heights are within the robot's reach, a lifting mechanism is installed at the connection between the lower end of the robot arm 2 and the vehicle body 1. This ensures that the robot arm's reach height can be adjusted, ensuring that the robot arm 2 is never unable to reach or grasp items. The robot arm is a 7-axis arm, achieving a balance of flexibility and precision.

[0066] In this embodiment, the grasping module is a vacuum suction cup, which includes multiple suction nozzles; the number of the vacuum suction cups is one or multiple independently working ones, and the control module controls the working number of the vacuum suction cups according to the grasping size (such as the number of packaging boxes).

[0067] In this embodiment, the autonomous unloading vehicle also includes a bracket 4, which rotates coaxially with the robotic arm 2. A 3D vision module is mounted on bracket 4. As bracket 4 rotates, it captures images of the boxes in the container and performs image segmentation using an image segmentation algorithm, preparing for the next box to be captured by the robotic arm. Each time the robotic arm captures and rotates 90° to place the box, because bracket 4 and robotic arm 2 rotate coaxially, the 3D vision module directly scans all the boxes inside, performs image processing, and prepares for the next capture. This cycle repeats until the capture is complete. In another embodiment, the 3D vision module does not need to capture a full range of images within the vehicle compartment. Each time a photo of the current field of view is taken, the 3D vision module automatically records the location information of each box and adjusts the field of view for the next capture based on this location information.

[0068] In this embodiment, the 3D vision module includes a first binocular camera and a second binocular camera, which are arranged one above the other on the bracket 4. The first binocular camera is angled downward to capture images of the lower half of the vehicle compartment, and the second binocular camera is angled upward to capture images of the upper half of the vehicle compartment.

[0069] In this embodiment, the bracket 4 is further provided with an illumination lamp to provide the required illumination for the 3D vision module.

[0070] In the above two embodiments, by acquiring images inside the vehicle compartment, the size information and position information of each packaging box are obtained through processing, and the packaging box is grasped according to the preset grasping rules to realize intelligent unloading of the packaging box.

[0071] The above description is only a description of the preferred embodiments of the present invention and does not limit the scope of the present invention. Any changes and modifications made by ordinary technicians in the field of the present invention based on the above disclosure shall fall within the scope of protection of the claims.

Claims

1. A method for autonomous unloading of a trolley, characterized in that: include: The car autonomously navigates and moves to the door position of the carriage according to its positional relationship with the carriage; Define the depth direction of the carriage as the X-axis, the width direction of the carriage as the Y-axis, and the height direction of the carriage as the Z-axis; obtain the image inside the carriage through the 3D vision system, perform image recognition and point cloud segmentation on the acquired image, so as to obtain the size information and position information of each packaging box; The method for obtaining an image in a vehicle box comprises: Each time a photo of the current field of view is taken, the position information of each packaging box is automatically recorded, and the field of view angle for the next shot is adjusted according to the position information; Calculating the center coordinates of the gripping surface according to the size information and position information of each packaging box; Sorting the center coordinates of all the grasping surfaces to define the grasping order of the packaging boxes; The sorting includes: sorting by X axis first, then sorting by Z axis, and then sorting by Y axis, so as to achieve grabbing from near to far and from top to bottom along the Y axis direction; According to the sorting result and the distance between the trolley and the packaging box, the robotic arm is controlled to grab the packaging boxes in order; The shooting and image processing are performed while grasping. When the grasping is completed, the image processing is also completed, and the next grasping coordinates are obtained, and the next grasping can be performed immediately.

2. The autonomous unloading method of a trolley as claimed in claim 1, characterized in that: The method for the robot arm to grab the packaging box includes: presetting a threshold value of the height at which the packaging box is grabbed; When the height of the package box to be grasped is greater than a preset threshold, the robot arm is controlled to grasp it from the side of the package box; when the height of the package box to be grasped is not greater than the preset threshold, the robot arm is controlled to grasp it from the upper surface of the package box.

3. The autonomous unloading method of a trolley as claimed in claim 2, characterized in that: Before sorting the center coordinates of all the grasping surfaces, the method further includes: When the height of the packaging box to be grasped is greater than the preset threshold, point clouds of packaging boxes with a height below the preset threshold are filtered out through point cloud filtering; When the height of the packaging box to be grasped is not greater than the preset threshold, the point cloud of the packaging box with a height above the preset threshold is filtered out through point cloud filtering.

4. The autonomous unloading method of a trolley as claimed in claim 1, characterized in that: When the number of packages grasped at one time is one, the center coordinates of the grasping surface are the center coordinates of the grasping surface of a single package box; when the number of packages grasped at one time is greater than one, the center coordinates of the grasping surface are the center coordinates of the grasping surface of multiple packages as a whole.

5. The autonomous unloading method of a trolley as claimed in claim 1, characterized in that: After the trolley moves to the carriage door position, the method further includes: Get the distance between the trolley and the outermost packaging box, and adjust the position of the trolley according to the grasping distance of the robot arm.

6. The autonomous unloading method of a trolley as claimed in claim 5, characterized in that: Methods for obtaining the distance between the trolley and the outermost packaging box include: The images of the outermost packaging boxes are obtained, and point cloud data is obtained by processing. According to the point cloud data, the distance between the trolley and the outermost packaging boxes is obtained.

7. An autonomous unloading vehicle, characterized in that: Autonomous unloading is performed using the autonomous unloading method according to any one of claims 1 to 6, wherein the autonomous unloading vehicle comprises: The main body of the trolley; A mechanical arm is rotatably arranged on the vehicle body; A grabbing unit, arranged at the end of the mechanical arm, for grabbing a packaging box; A 3D vision module is provided on the main body of the trolley, and is used to obtain images in the compartment, and to perform point cloud processing on the obtained images to obtain the size and position information of each packaging box; A calculation and sorting module is connected to the 3D vision module for calculating the center coordinates of the grasping surface according to the size and position information of each packaging box; the center coordinates of all the grasping surfaces are sorted to define the grasping order of the packaging boxes; wherein the sorting includes: sorting by X-axis first, then by Z-axis, and then by Y-axis, so as to realize grasping from near to far and from top to bottom along the Y-axis direction; The control module controls the robot arm to grab the packaging boxes in sequence according to the sorting result and the distance between the trolley and the packaging boxes.

8. The autonomous unloading vehicle according to claim 7, characterized in that: The gripping unit is a vacuum suction cup, and the vacuum suction cup includes a plurality of suction nozzles; The number of the vacuum suction cups is one or a plurality of vacuum suction cups that work independently, and the control module controls the number of vacuum suction cups that work according to the size of the grasping.

9. The autonomous unloading vehicle according to claim 7, characterized in that: The autonomous unloading trolley also includes a bracket, which rotates coaxially with the robotic arm. The 3D vision module includes a first binocular camera and a second binocular camera, and the first binocular camera and the second binocular camera are arranged on the bracket up and down.

Images