Control method of robot, control device of robot, and robot

Abstract

The application provides a robot control method, a control device and a robot, and comprises the following steps: obtaining the width of a target road and the track width of the robot when the robot travels along the target road; comparing the width of the target road with the track width of the robot; and adjusting the operation of the robot according to the comparison result of the width of the target road and the track width of the robot. The technical scheme provided by the application solves the technical problem that the operation of the robot cannot be adjusted according to the condition of the target road in the prior art.

Description

Technical Field

[0001] This invention relates to the field of robotics, and more specifically, to a robot control method, a control device, and a robot. Background Technology

[0002] Currently, with the significant development of science and technology, transportation robots have entered all aspects of human life. Existing types of transportation robots include logistics robots, food delivery robots, agricultural robots, and so on. These robots differ in their application environments and functions. Generally, their application scenarios include, but are not limited to, normal roads, workshop surfaces, factory roads, and designated driving paths between different production lines. These robots often need to automatically avoid obstacles and move forward according to the usage and driving scenarios to reach the program-specified or user-defined target locations to complete the corresponding transportation or operational tasks.

[0003] However, in the actual operation of transportation robots, the width of roads often varies due to changes in road conditions and usage scenarios. Thus, robots with a fixed wheelbase can typically only pass through roads wider than or equal to their fixed wheelbase. When the road width is less than the robot's fixed wheelbase, the robot often cannot pass smoothly, which not only affects the smooth progress of transportation operations but may even cause damage to the robot's structure. Summary of the Invention

[0004] The main objective of this invention is to provide a robot control method, control device, and robot to solve the technical problem in the prior art that it is inconvenient to adjust the robot's operation according to the conditions of the target road.

[0005] To achieve the above objectives, according to one aspect of the present invention, a robot control method is provided, comprising:

[0006] Obtain the width of the target road and the wheelbase of the robot as it travels along the target road;

[0007] Compare the width of the target road with the wheelbase width of the robot;

[0008] The robot's operation is adjusted based on the comparison between the width of the target road and the wheelbase width of the robot.

[0009] Furthermore, based on the comparison between the width of the target road and the robot's wheelbase, the robot's operation is adjusted, including:

[0010] If the robot's wheelbase is less than or equal to the width of the target road, control the robot to continue traveling along the target road;

[0011] If the robot's wheelbase is wider than the target road width, adjust the robot's wheelbase and control the robot to continue traveling along the target road according to the adjusted wheelbase width.

[0012] Furthermore, when the robot's wheelbase is wider than the target road width, the robot's wheelbase is adjusted, including:

[0013] Compare the width of the target road with the robot's first preset wheelbase width;

[0014] If the width of the target road is less than the robot's first preset wheel track width, control the robot to stop moving;

[0015] If the width of the target road is greater than or equal to the robot's first preset wheelbase width, adjust the robot's wheelbase width to be less than or equal to the width of the target road, and control the robot to continue traveling along the target road.

[0016] Furthermore, the wheelbase width of the robot is adjusted, including:

[0017] Obtain the real-time rotation angle of the robot's rotating arm;

[0018] Obtain the width of the drive unit connected to the rotating arm, the travel width of the robot, and the length of the rotating arm. Calculate the target rotation angle of the rotating arm based on the width of the drive unit, the travel width of the robot, the length of the rotating arm, and the width of the target road.

[0019] The rotation of the rotating arm is controlled based on the real-time rotation angle and the target rotation angle of the rotating arm, so as to adjust the wheelbase width of the robot to the target wheelbase width.

[0020] Furthermore, the rotation of the rotating arm is controlled based on the real-time rotation angle of the rotating arm and the target rotation angle of the rotating arm, including:

[0021] The speed of the driving unit is obtained by performing PID calculation on the error between the real-time rotation angle of the rotating arm and the target rotation angle of the rotating arm.

[0022] The real-time rotation angle of the rotating arm is monitored, and when the real-time rotation angle of the rotating arm reaches the target rotation angle, the drive unit is controlled to stop driving the rotating arm.

[0023] Furthermore, after controlling the drive unit to stop driving the rotating arm, the method also includes:

[0024] Brake and lock the rotating arm to keep the robot's wheelbase width at the target wheelbase width.

[0025] Furthermore, when the robot's wheelbase is less than or equal to the width of the target road, the method also includes:

[0026] Obtain the robot's second preset wheelbase width and compare the robot's wheelbase width with the robot's second preset wheelbase width;

[0027] When the robot's wheelbase width is equal to the second preset wheelbase width, control the robot to continue traveling along the target road;

[0028] When the robot's wheelbase width is not equal to the second preset wheelbase width, the width of the target road is compared with the second preset wheelbase width; when the width of the target road is greater than or equal to the second preset wheelbase width, the robot's wheelbase width is adjusted to the second preset wheelbase width, and the robot is controlled to continue driving along the target road; when the width of the target road is less than the second preset wheelbase width, the robot is controlled to continue driving along the target road.

[0029] Furthermore, the width of the target road and the wheelbase of the robot are obtained when the robot travels along the target road, including:

[0030] Obtain the boundary of the drivable area of ​​the target road;

[0031] The width of the target road is determined based on the boundary of the drivable area of ​​the target road and the robot's pose information.

[0032] Furthermore, the boundaries of the drivable area of ​​the target road are obtained, including:

[0033] The system acquires images of the target road using the robot's image acquisition device, and uses a deep learning model to identify the drivable area of ​​the target road.

[0034] Furthermore, the width of the target road is determined based on the boundary of the drivable area of ​​the target road and the robot's pose information, including:

[0035] The width CD of the target road is calculated based on the robot's pitch angle β, the installation height h of the robot's image acquisition device, the pixel width b of the target road acquired by the robot's image acquisition device, the field of view θ1 of the upper half of the height of the image acquisition device, and the focal length f of the image acquisition device.

[0036] in,

[0037] Furthermore, the width of the target road is determined based on the boundary of the drivable area of ​​the target road and the robot's pose information, including:

[0038] The width DG of the target road is calculated based on the robot's pitch angle β, the robot's yaw angle α, the installation height h of the robot's image acquisition device, the pixel width b of the target road, the field of view θ1 of the upper half of the height of the image acquisition device, and the focal length f of the image acquisition device.

[0039] in,

[0040] According to another aspect of the present invention, a robot control device is provided, comprising:

[0041] The acquisition module is used to acquire the width of the target road and the wheelbase width of the robot when it travels along the target road.

[0042] The comparison module is used to compare the width of the target road with the wheelbase width of the robot;

[0043] The adjustment module is used to adjust the robot's operation based on the comparison between the width of the target road and the robot's wheelbase.

[0044] According to another aspect of the present invention, a robot is provided, employing the robot control method described above. The robot includes:

[0045] Chassis;

[0046] The rotating arm is rotatably mounted on the chassis;

[0047] The drive unit is connected to the rotating arm and is located at the end of the rotating arm away from the chassis. The drive unit is used to drive the rotating arm to rotate in order to adjust the operation of the robot.

[0048] One or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the robot control method provided above.

[0049] Furthermore, the robot also includes:

[0050] A slewing device is mounted on a chassis, and one end of a rotating arm near the chassis is connected to the slewing device so that the rotating arm is rotatably mounted on the chassis via the slewing device.

[0051] When the driving unit moves the rotating arm to the target wheel track width or when the robot is running, the brake of the slewing device is used to lock and brake the rotating arm to limit its rotation.

[0052] According to another aspect of the present invention, a non-volatile storage medium is provided, which stores a plurality of instructions applicable to being loaded by a processor and executed by the robot control method provided above.

[0053] By applying the technical solution of this invention, the robot's operation can be adaptively adjusted based on the comparison between the width of the target road and the robot's wheelbase width, thereby ensuring that the robot's wheelbase width matches the width of the target road and enabling the robot to travel smoothly on the target road. Therefore, it also solves the technical problem in the prior art that it is inconvenient to adjust the robot's operation according to the target road conditions, effectively guaranteeing the smooth operation of the robot. Attached Figure Description

[0054] The accompanying drawings, which form part of this application, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings:

[0055] Figure 1 A flowchart of a control method provided according to an embodiment of the present invention is shown;

[0056] Figure 2 A flowchart illustrating the adjustment of the wheelbase width of a robot according to an embodiment of the present invention is shown;

[0057] Figure 3 A schematic diagram of relevant measurement parameters of a camera considering only the pitch angle is shown according to an embodiment of the present invention;

[0058] Figure 4 It shows Figure 3 A schematic diagram of the projection in the image;

[0059] Figure 5 A schematic diagram of the width of a target road in the presence of obstacles is shown according to an embodiment of the present invention;

[0060] Figure 6 A schematic diagram of the rotation angle of the rotating arm according to an embodiment of the present invention is shown;

[0061] Figure 7 A schematic diagram of the structure of a robot running on a target road, according to an embodiment of the present invention, is shown.

[0062] The above figures include the following reference numerals:

[0063] 10. Image acquisition equipment; 20. Chassis; 30. Drive wheel; 40. Rotating arm; 50. Target road; 60. Obstacle. Detailed Implementation

[0064] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0065] like Figure 1 As shown, a robot control method is provided, which includes: acquiring the width of the target road 50 and the wheelbase width of the robot when the robot travels along the target road 50; comparing the width of the target road 50 with the wheelbase width of the robot; and adjusting the robot's operation based on the comparison result of the width of the target road 50 and the wheelbase width of the robot.

[0066] It should be noted that the robot's wheelbase width can refer to the spacing between the robot's drive and traveling components. Specifically, the drive and traveling components can be drive wheels 30 or drive tracks, etc. It should also be noted that the robot's operation includes, but is not limited to, adjustments to the robot's wheelbase width and adjustments to the robot's movement.

[0067] When the driving unit is a drive wheel 30, the wheelbase width of the robot refers to the distance between the two drive wheels 30 located at the front or the two drive wheels 30 located at the rear. Specifically, the width between two drive wheels 30 can refer to the distance between the outer sides of one drive wheel 30 (the outer side of one drive wheel 30 can refer to the side of that drive wheel 30 away from the other drive wheel 30) and the outer sides of the other drive wheel 30 (the outer side of the other drive wheel 30 can refer to the side of that drive wheel 30 away from the first drive wheel 30). The front and rear drive wheels 30 change according to the robot's traveling direction. When the robot's traveling direction changes, the front and rear drive wheels 30 of the robot will change accordingly.

[0068] When the driving unit is a tracked drive unit, the wheelbase width of the robot refers to the distance between the two drive tracks located on both sides of the robot. Specifically, the distance between the two drive tracks can refer to the distance between the outer edges of one drive track (which can refer to the side of the drive track away from the other drive track) and the outer edges of the other drive track (which can refer to the side of the other drive track away from the first drive track). The number and distribution of the drive tracks are not limited. Specifically, there can be, but is not limited to, two, four, six, or eight drive tracks, and the number of drive tracks can be evenly distributed on both sides of the robot to drive it forward.

[0069] The control method provided in this embodiment allows for easy adjustment of the robot's wheelbase width, or the robot's operating status, or both, based on a comparison between the width of the target road 50 and the robot's wheelbase width. This ensures the robot's wheelbase width matches the width of the target road 50, facilitating smooth passage on the target road 50. Therefore, it solves the technical problem in the prior art where adjusting the robot's operating status based on the target road 50 is inconvenient, effectively guaranteeing the robot's smooth operation and facilitating robot protection.

[0070] In this embodiment, the robot's operation is adjusted based on a comparison between the width of the target road 50 and the robot's wheelbase width. This includes: when the robot's wheelbase width is less than or equal to the width of the target road 50, controlling the robot to continue traveling along the target road 50; and when the robot's wheelbase width is greater than the width of the target road 50, adjusting the robot's wheelbase width and controlling the robot to continue traveling along the target road 50 according to the adjusted wheelbase width. Using this method, when the robot's wheelbase width is less than or equal to the width of the target road 50, the robot's wheelbase width is sufficient for travel on the target road 50, thus allowing the robot to continue traveling along the target road 50. When the robot's wheelbase width is greater than the width of the target road 50, the robot's wheelbase width will not be sufficient for travel on the target road 50. Therefore, it is necessary to adaptively adjust the robot's wheelbase width based on a combination of the robot's own wheelbase width adjustment range and the width of the target road 50, so that the robot can smoothly travel on the target road 50. Therefore, the above method can facilitate accurate determination of whether the robot can pass through the target road 50, and facilitate adaptive adjustment of the robot's wheelbase width when the robot cannot pass through smoothly.

[0071] Specifically, when the robot's wheelbase width is greater than the width of the target road 50, the robot's wheelbase width is adjusted, including: comparing the width of the target road 50 with the robot's first preset wheelbase width; when the width of the target road 50 is less than the robot's first preset wheelbase width, controlling the robot to stop moving; when the width of the target road 50 is greater than or equal to the robot's first preset wheelbase width, adjusting the robot's wheelbase width to be less than or equal to the width of the target road 50, and controlling the robot to continue moving along the target road 50. It should be noted that the first preset wheelbase width here refers to the robot's minimum wheelbase width. The above scheme can be understood as follows: when the width of the target road 50 is less than the robot's minimum wheelbase width, the robot cannot pass through the target road 50 regardless of the conditions, and therefore must stop moving to avoid damage caused by the robot forcibly passing through. When the width of the target road 50 is greater than or equal to the robot's minimum wheelbase width, adjusting the robot's wheelbase width to be less than or equal to the width of the target road 50 satisfies the condition that the robot can pass through the target road 50, and then the robot can be successfully controlled to move along the target road 50. The above judgment method can facilitate further refinement of the comparison and judgment steps, and make more accurate adaptive adjustments to the robot's wheelbase width based on the target road 50 and the robot's own conditions, so that the robot can operate in a smooth operating environment, thereby improving the smoothness of the robot's operation and facilitating effective protection of the robot.

[0072] When the robot stops moving, it can wait for staff to intervene. Alternatively, the robot can be equipped with communication modules such as Bluetooth and infrared to transmit its current stopped status to other terminal devices, thus informing relevant technical personnel.

[0073] like Figure 2As shown, in this embodiment, adjusting the wheelbase width of the robot includes: obtaining the real-time rotation angle δ of the robot's rotating arm 40; obtaining the width Z of the drive unit connected to the rotating arm 40, the robot's travel width X, and the length Y of the rotating arm 40; calculating the target rotation angle γ of the rotating arm 40 based on the width Z of the drive unit, the robot's travel width X, the length Y of the rotating arm 40, and the width DG of the target road 50; and controlling the rotation of the rotating arm 40 based on the real-time rotation angle δ and the target rotation angle γ to adjust the robot's wheelbase width to the target wheelbase width. This method facilitates further refinement of the specific wheelbase width adjustment method. Adjusting the rotation angle of the robot's rotating arm 40 to adjust the robot's wheelbase width is simple and easy to implement. The robot here can include, but is not limited to, wheeled robots and tracked robots. The corresponding calculation formula is: γ=arvsin(|(DG-2Z)-X|) / (2·Y).

[0074] It should be noted that the robot's travel width here can be understood as the maximum width of the chassis perpendicular to the robot's forward direction.

[0075] like Figure 6 As shown, the robot in this embodiment can be a square structure. The robot's travel width X can be understood as the side width perpendicular to the robot's forward direction. The width Z of the driving travel unit can be understood as the width of the driving wheel or driving track. The length Y of the rotating arm 40 can be understood as the distance between the two ends along the length extension direction of the rotating arm 40.

[0076] Specifically, such as Figure 6 and Figure 7 As shown, the target wheelbase calculation method for the robot is as follows: Assuming the width of the robot's drive wheels 30 is Z, and the width of the target road 50 is known to be DG, to ensure the robot remains completely within the target road 50, the target wheelbase width should be less than DG. Therefore, the target wheelbase width should be at least DG-2Z. Given the width of the vehicle as X and the length of the rotating arm 40 as Y, the real-time rotation angle δ of the rotating arm 40 is measured using a mechanical absolute encoder. Based on the width DG of the target road 50, the computer calculates the target rotation angle γ required for the rotating arm 40 and sends the value of the target angle γ to the robot's motion controller.

[0077] It should be noted that the real-time rotation angle δ of the rotating arm 40 may be fixed within a certain period of time, or it may change over time. The real-time rotation angle δ of the rotating arm 40 can be understood as the angle between the rotating arm 40 and the preset reference direction at the current moment, and the real-time rotation angle δ may change over time. The target rotation angle γ of the rotating arm 40 refers to the angle between the position of the rotating arm 40 corresponding to the target wheelbase of the robot and the preset reference direction. The target rotation angle γ of the rotating arm 40 will change with the target wheelbase of the robot. When the target wheelbase of the robot is determined, the corresponding target rotation angle γ of the rotating arm is also determined.

[0078] Specifically, the preset reference direction can be selected as the direction in which the rotating arm rotates to any angle. Preferably, the preset reference direction is selected as the direction in which the rotating arm 40 rotates to be parallel to the length direction of the chassis. For example, the preset reference direction can be selected as parallel to the length direction of the chassis, parallel to the forward direction of the robot, or other directions. Preferably, when the direction in which the rotating arm 40 rotates to be parallel to the length direction of the chassis is selected as the preset reference direction, it can also be understood that when the rotating arm 40 is in the direction parallel to the length direction of the chassis, the real-time rotation angle δ of the rotating arm 40 is 0. The real-time rotation angle of the rotating arm 40 refers to the angle between the real-time position of the rotating arm 40 and the direction in which the rotating arm 40 is parallel to the length direction of the chassis. The target rotation angle of the rotating arm 40 refers to the angle between the position of the rotating arm 40 corresponding to the target wheelbase of the robot and the direction in which the rotating arm 40 is parallel to the length direction of the chassis. The target rotation angle of the rotating arm 40 is often a fixed value calculated based on the above-mentioned relevant parameters. When the above-mentioned relevant parameters change, the target rotation angle of the rotating arm 40 will also change accordingly.

[0079] Specifically, an encoder can be used to provide real-time feedback on the rotation angle δ of the rotating arm 40. After calculating the target rotation angle γ of the rotating arm 40, the rotating arm 40 is adjusted. The encoder can monitor in real time whether the rotating arm 40 has rotated from its original position to the target angle γ. Here, the target rotation angle γ is an angle value calculated relative to the original position. Since the original position is different at different times, the preset reference direction of the target rotation angle γ is also different under different adjustment states.

[0080] In this embodiment, the rotation of the rotating arm 40 is controlled based on the real-time rotation angle δ and the target rotation angle γ of the rotating arm 40. This includes determining the rotational speed of the drive unit on the rotating arm 40 based on the real-time rotation angle δ and the target rotation angle γ. This method facilitates the control of the rotational speed of the drive unit on the rotating arm 40, ensuring that the real-time rotation angle eventually reaches the target rotation angle. This facilitates the adjustment of the wheelbase width to the target wheelbase width, ultimately achieving a smooth adjustment of the target wheelbase width.

[0081] Specifically, the rotational speed of the drive unit on the rotating arm 40 is determined based on the real-time rotation angle δ and the target rotation angle γ of the rotating arm 40. This includes performing a PID calculation on the error between the real-time rotation angle and the target rotation angle of the rotating arm 40 to obtain the rotational speed of the drive unit. Specifically, both the real-time rotation angle δ and the target rotation angle γ of the rotating arm 40 are input into the PID algorithm. The PID algorithm calculates the rotational speed of the drive unit based on the error between the real-time rotation angle δ and the target rotation angle γ of the rotating arm 40. The real-time rotation angle δ of the rotating arm 40 is monitored, and when the real-time rotation angle δ reaches the target rotation angle γ, the drive unit is controlled to stop driving the rotating arm 40. Using this method, the rotational speed of the drive unit can be controlled accordingly based on the monitoring of the real-time rotation angle. The control logic is simple and reliable, making it easy for the drive unit to rotate the rotating arm 40 to the target rotation angle, and thus also facilitating adjustment to the target wheelbase width.

[0082] It should be noted that the PID algorithm is a control algorithm in process control that combines the proportional (P), integral (I), and derivative (D) components of the deviation into one. It can correct the control based on the output feedback of the controlled object and can correct it according to the quota or standard when the actual deviation from the plan is measured.

[0083] In this embodiment, after the driving unit stops driving the rotating arm 40, the method further includes braking and locking the rotating arm 40 to maintain the robot's wheelbase width at the target wheelbase width. This method ensures that the robot's wheelbase width is stably maintained at the target wheelbase width, preventing changes in the wheelbase width during operation. This allows the robot to travel stably at the target wheelbase width, effectively guaranteeing the stability and safety of the robot during operation.

[0084] Specifically, given the real-time rotation angle δ of the current rotating arm 40 and the target rotation angle γ corresponding to the target wheelbase, the real-time rotation angle δ and the target rotation angle γ are input into the PID algorithm. The PID algorithm calculates the rotational speed of the drive wheel 30 by performing proportional, integral, and derivative operations based on the error between the target rotation angle γ and the actual rotation angle δ. This ultimately controls the drive wheel 30 to reach the target position. In other words, when the motion controller monitors the real-time feedback from the encoder that the rotation angle of the rotating arm 40 is γ, the drive wheel 30 is no longer driven. Simultaneously, the controller of the motion robot energizes the electromagnetic brake in the rotary device to lock and brake the rotating arm 40. Thus, when the rotating arm 40 rotates to the target rotation angle γ and is in the locked state...

[0085] Correspondingly, the robot in this embodiment includes a rotating device and a chassis 20. The rotating device is mounted on the chassis 20, and the end of the rotating arm 40 away from the drive wheel 30 is connected to the rotating device. When the drive wheel 30 drives the rotating arm 40 to rotate to the target rotation angle, the drive of the drive wheel 30 is stopped, and the rotation of the rotating arm 40 is braked and locked using the brake in the rotating device to effectively ensure the stability of the rotating arm 40 during operation.

[0086] Specifically, when the robot's wheelbase width is less than or equal to the width of the target road 50, the method further includes: obtaining a second preset wheelbase width for the robot and comparing the robot's current wheelbase width with the second preset wheelbase width; when the robot's wheelbase width is equal to the second preset wheelbase width, controlling the robot to continue traveling along the target road 50; when the robot's wheelbase width is not equal to the second preset wheelbase width, comparing the width of the target road 50 with the second preset wheelbase width; when the width of the target road 50 is greater than or equal to the second preset wheelbase width, adjusting the robot's wheelbase width to the second preset wheelbase width and controlling the robot to continue traveling along the target road 50; when the width of the target road 50 is less than the second preset wheelbase width, controlling the robot to continue traveling along the target road 50. Here, the second preset wheelbase width can be understood as the robot's most stable wheelbase width, which is calculated based on the robot's own structure to determine the wheelbase width corresponding to the robot's most stable state. This allows the robot to operate with the most stable wheel track, ensuring its most stable operating state and effectively guaranteeing its operational stability. It also helps prevent the robot from tipping over, thus improving its operational safety.

[0087] like Figure 3 and Figure 4As shown, in this embodiment, obtaining the width of the target road 50 includes: obtaining the boundary of the drivable area of ​​the target road 50; and determining the width of the target road 50 based on the boundary of the drivable area of ​​the target road 50 and the robot's pose information. This method facilitates improved accuracy in identifying the width of the target road 50, and also improves the accuracy of subsequent comparison, judgment, and corresponding control of the width of the target road 50 and the robot's wheelbase.

[0088] It should be noted that, for a target road 50 without obstacles, the width of the target road 50 can be understood as the distance between the two edges of the road. For example... Figure 5 As shown, for a target road 50 with obstacles 60, the width of the target road 50 can be understood as the distance between the obstacle and the two edges of the road, and the angular distance between the obstacle and the farther side of the two edges can be defined as the width of the target road 50. In the actual operation of the robot, the road surface it travels on is not completely smooth, especially when traveling in fields or wilderness, where the road surface is often uneven. Since changes in the robot's posture will affect the recognition sensor (corresponding to the image acquisition device 10), combining the robot's pose information to calculate the target road 50 can effectively improve the accuracy of road calculation.

[0089] In this embodiment, obtaining the boundary of the drivable area of ​​the target road 50 includes: acquiring an image of the target road 50 captured by the robot's image acquisition device 10; using a deep learning model to identify the image of the target road 50 to obtain the drivable area of ​​the target road 50. This method facilitates improving the accuracy of obtaining the boundary of the drivable area of ​​the target road 50, thereby making the acquisition of the width of the target road 50 more precise. Specifically, the image acquisition device 10 can be a camera.

[0090] Specifically, the deep learning model is used to identify the image of the target road 50, which includes using deep learning methods combined with region segmentation technology and lane detection technology to process the image of the target road 50, and obtaining the boundary of the drivable area of ​​the target road 50 based on the processing results.

[0091] It should be noted that the region segmentation technique in "processing images of target road 50 using deep learning methods combined with region segmentation and lane detection techniques" generally includes several parts such as data acquisition, preprocessing, region segmentation, feature extraction, pattern classification, and training. Region segmentation generally refers to dividing the data to be analyzed into regions, extracting the data segments of interest for further processing, and discarding other data to reduce the amount of data for subsequent processing. The lane detection technique in "processing images of target road 50 using deep learning methods combined with region segmentation and lane detection techniques" includes lane detection methods based on image processing, lane detection methods based on deep learning, lane detection methods based on LiDAR, and lane detection methods based on GPS. Among them, the lane detection method based on image processing processes the image in front of the vehicle to extract the position and direction of the lane lines. Commonly used image processing techniques include edge detection, color segmentation, and filtering. The lane detection method based on deep learning detects lane lines by training a neural network, which requires a large amount of data to train the neural network. The lane detection method based on LiDAR obtains the position and direction of the lane lines by scanning the surrounding environment. This method has high accuracy and strong robustness. Lane detection methods based on the Global Positioning System (GPS) determine the position and direction of vehicles using satellite signals. They are low-cost and widely applicable.

[0092] In this embodiment, the drivable area boundary of the target road 50 can be identified using the recognition sensors on the robot. Correspondingly, the lane detection technology is mainly a lane line detection method based on image processing.

[0093] The process of processing the image of the target road 50 using deep learning combined with region segmentation and lane detection techniques can be understood as follows: The target image is acquired using a recognition sensor. Then, a deep learning method (YOLOP model, used in panoramic driving perception networks to simultaneously perform traffic object detection, drivable area segmentation, and lane detection; YOLOP is a single-stage network containing a shared encoder and three task-specific decoders, including object detection, drivable area segmentation, and lane line segmentation) is used to process the image acquired by the recognition sensor, outputting the robot's drivable area. The width of the target road 50 is then calculated based on the boundaries of the obtained drivable area.

[0094] In one embodiment, determining the width of the target road 50 based on the boundary of the drivable area of ​​the target road 50 and the robot's pose information includes: calculating the width CD of the target road 50 based on the robot's pitch angle β, the installation height h of the robot's image acquisition device 10, the pixel width b of the target road 50 acquired by the robot's image acquisition device 10, the field of view θ1 of the upper half of the height field of the image acquisition device 10, and the focal length f of the image acquisition device 10; wherein, This method allows for the rapid calculation of the target road width 50 with only the pitch angle known, thus facilitating more accurate adaptive adjustments to the robot's wheelbase width.

[0095] In another embodiment, the width of the target road 50 is determined based on the boundary of the drivable area of ​​the target road 50 and the robot's pose information, including: calculating the width DG of the target road 50 based on the robot's pitch angle β, the robot's yaw angle α, the installation height h of the robot's image acquisition device 10, the pixel width b of the target road 50, the field of view θ1 of the upper half of the height of the image acquisition device 10, and the focal length f of the image acquisition device 10; wherein, By combining pitch and yaw angles in this way, the width of the target road 50 can be obtained more accurately, improving the accuracy of the calculation and facilitating subsequent precise adjustment of the robot's wheelbase width.

[0096] In another embodiment, knowing only the pitch angle, the width of the target road 50 is determined based on the boundary of the drivable area of ​​the target road 50 and the robot's pose information. This includes: calculating the width CD of the target road 50 based on the robot's pitch angle β, the installation height h of the robot's image acquisition device 10, the pixel width b of the target road 50 acquired by the robot's image acquisition device 10, the field of view θ1 of the upper half of the height of the image acquisition device 10, and the focal length f of the image acquisition device 10; wherein, Once the robot's yaw angle α is known, CD can be multiplied by cosα to obtain the width DG of the target road 50, thereby further improving the accuracy of the robot's wheelbase width calculation.

[0097] Preferably, a pose sensor for identifying the robot's pose information is installed at the geometric center of the robot. This pose sensor is preferably an IMU sensor (IMU is an abbreviation for Inertial Measurement Unit; an IMU sensor is an inertial sensor comprising a combined unit consisting of three accelerometers and three gyroscopes; the gyroscopes detect angular velocities in three directions, and the accelerometers detect accelerations in three directions). Using this IMU sensor, changes in the robot's pitch and yaw angles can be measured to monitor the robot's driving posture. By combining the parameters collected by the identification sensor with the parameters of the IMU sensor, the width of the target road 50 is calculated. Specifically, the IMU sensor parameters include the robot's pitch angle β and yaw angle α. The parameters collected by the identification sensor include the pixel width b of the target road 50, the field of view θ1 of the upper half of the image acquisition device 10, and the focal length f of the image acquisition device 10.

[0098] Embodiment 2 of the present invention provides a robot control device, which includes an acquisition module, a comparison module, and an adjustment module. The acquisition module acquires the width of the target road 50 and the wheelbase width of the robot when it travels along the target road 50. The comparison module compares the width of the target road with the wheelbase width of the robot. The adjustment module adjusts the robot's operation based on the comparison result between the width of the target road 50 and the wheelbase width of the robot.

[0099] Embodiment 3 of the present invention provides a robot, which includes a chassis 20, a rotating arm 40, a drive unit, and one or more processors and a memory. The rotating arm 40 is rotatably mounted on the chassis 20. The drive unit is connected to the rotating arm 40 and is located at the end of the rotating arm 40 away from the chassis 20. The drive unit is used to drive the rotating arm 40 to rotate in order to adjust the robot's operation. This method facilitates the control of the drive unit to rotate the rotating arm 40 to a target rotation angle, thereby adjusting the wheelbase width to the target wheelbase width. This allows the robot's wheelbase width to be adapted to the width of the target road 50, facilitating smooth passage and ensuring the robot's operational safety. The memory stores one or more programs, which, when executed by one or more processors, enable the processors to implement the robot control method described above.

[0100] Specifically, the robot in this embodiment also includes a rotary device, which is mounted on the chassis 20. One end of the rotating arm 40 near the chassis 20 is connected to the rotary device, allowing the rotating arm 40 to be rotatably mounted on the chassis 20 via the rotary device. When the driving unit moves the rotating arm 40 to the target wheelbase width, or when the robot is running, the brake of the rotary device is used to lock and brake the rotating arm 40, limiting its rotation. This structure ensures that the rotating arm 40 does not change position when it moves to the target wheelbase width or when the robot is running, thereby facilitating the stability of wheelbase width adjustment and robot operation.

[0101] Embodiment 4 of the present invention provides a non-volatile storage medium that stores multiple instructions applicable to the robot control method provided above, which is loaded and executed by a processor.

[0102] As can be seen from the above description, the embodiments of the present invention achieve the following technical effects: the robot can adjust its wheelbase according to the width of the identified target road to adapt to different road widths, thus broadening the robot's application and usage scenarios. This identification method is not limited to driving on normal roads, but also includes the robot's movement in workshops, factories, and between different production lines.

[0103] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments according to this application. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0104] Unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps described in these embodiments do not limit the scope of this application. It should also be understood that, for ease of description, the dimensions of the various parts shown in the drawings are not drawn to actual scale. Techniques, methods, and devices known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and devices should be considered part of the specification. In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values. It should be noted that similar reference numerals and letters in the following drawings denote similar items; therefore, once an item is defined in one drawing, it need not be further discussed in subsequent drawings.

[0105] In the description of this application, it should be understood that the orientation or positional relationship indicated by directional terms such as "front, back, up, down, left, right", "horizontal, vertical, horizontal" and "top, bottom" is usually based on the orientation or positional relationship shown in the accompanying drawings, and is only for the convenience of describing this application and simplifying the description. Unless otherwise stated, these directional terms do not indicate or imply that the device or element referred to must have a specific orientation or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation on the scope of protection of this application; the directional terms "inner" and "outer" refer to the inner and outer contours relative to the outline of each component itself.

[0106] For ease of description, spatial relative terms such as "above," "on top of," "on the upper surface of," "above," etc., are used herein to describe the spatial positional relationship of a device or feature as shown in the figures to other devices or features. It should be understood that spatial relative terms are intended to encompass different orientations in use or operation beyond the orientation of the device as described in the figures. For example, if the device in the figures were inverted, a device described as "above" or "on top of" other devices or structures would subsequently be positioned as "below" or "under" other devices or structures. Thus, the exemplary term "above" can include both "above" and "below." The device may also be positioned in other different ways (rotated 90 degrees or in other orientations), and the spatial relative descriptions used herein will be interpreted accordingly.

[0107] Furthermore, it should be noted that the use of terms such as "first" and "second" to define components is merely for the purpose of distinguishing the corresponding components. Unless otherwise stated, the above terms have no special meaning and therefore cannot be construed as limiting the scope of protection of this application.

[0108] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for controlling a robot, characterized in that, include: Obtain the width of the target road and the wheelbase width of the robot when it travels along the target road; Compare the width of the target road with the wheelbase width of the robot; Based on the comparison between the width of the target road and the wheelbase of the robot, the operation of the robot is adjusted. The acquisition of the width of the target road and the wheelbase width of the robot when it travels along the target road includes: Obtain the boundary of the drivable area of ​​the target road; The width of the target road is determined based on the boundary of the drivable area of ​​the target road and the robot's pose information; Obtaining the boundary of the drivable area of ​​the target road includes: The robot acquires images of the target road using its image acquisition device, and uses a deep learning model to identify the images of the target road to obtain the drivable area of ​​the target road. Determining the width of the target road based on the boundary of the drivable area of ​​the target road and the robot's pose information includes: The width CD of the target road is calculated based on the robot's pitch angle β, the installation height h of the robot's image acquisition device, the pixel width b of the target road acquired by the robot's image acquisition device, the field of view θ1 of the upper half of the height field of the image acquisition device, and the focal length f of the image acquisition device. in, .

2. The method according to claim 1, characterized in that, The step of adjusting the robot's operation based on a comparison between the width of the target road and the wheelbase width of the robot includes: If the wheelbase of the robot is less than or equal to the width of the target road, the robot is controlled to continue traveling along the target road. If the wheelbase of the robot is greater than the width of the target road, the wheelbase of the robot is adjusted, and the robot is controlled to continue traveling along the target road according to the adjusted wheelbase width.

3. The method according to claim 2, characterized in that, When the wheelbase width of the robot is greater than the width of the target road, adjusting the wheelbase width of the robot includes: The width of the target road is compared with the first preset wheelbase width of the robot; If the width of the target road is less than the robot's first preset wheel track width, control the robot to stop moving; If the width of the target road is greater than or equal to the first preset wheelbase width of the robot, the wheelbase width of the robot is adjusted to be less than or equal to the width of the target road, and the robot is controlled to continue traveling along the target road.

4. The method according to claim 1, characterized in that, The adjustment of the wheelbase width of the robot includes: Obtain the real-time rotation angle of the robot's rotating arm; The width of the drive unit connected to the rotating arm, the travel width of the robot, and the length of the rotating arm are obtained. The target rotation angle of the rotating arm is calculated based on the width of the drive unit, the travel width of the robot, the length of the rotating arm, and the width of the target road. The rotation of the rotating arm is controlled based on the real-time rotation angle and the target rotation angle of the rotating arm, so as to adjust the wheelbase width of the robot to the target wheelbase width.

5. The method according to claim 4, characterized in that, The step of controlling the rotation of the rotating arm based on the real-time rotation angle of the rotating arm and the target rotation angle of the rotating arm includes: The rotational speed of the drive unit is obtained by performing PID calculation on the error between the real-time rotation angle of the rotating arm and the target rotation angle of the rotating arm. The real-time rotation angle of the rotating arm is monitored, and when the real-time rotation angle of the rotating arm reaches the target rotation angle of the rotating arm, the driving unit is controlled to stop driving the rotating arm.

6. The method according to claim 5, characterized in that, After controlling the driving unit to stop driving the rotating arm, the method further includes: The rotating arm is braked and locked to maintain the robot's wheelbase width at the target wheelbase width.

7. The method according to claim 2, characterized in that, When the wheelbase of the robot is less than or equal to the width of the target road, the method further includes: Obtain the second preset wheelbase width of the robot, and compare the wheelbase width of the robot with the second preset wheelbase width of the robot; When the wheelbase width of the robot is equal to the second preset wheelbase width, the robot is controlled to continue traveling along the target road; When the robot's wheelbase width is not equal to the second preset wheelbase width, the width of the target road is compared with the second preset wheelbase width; when the width of the target road is greater than or equal to the second preset wheelbase width, the robot's wheelbase width is adjusted to the second preset wheelbase width, and the robot is controlled to continue traveling along the target road; when the width of the target road is less than the second preset wheelbase width, the robot is controlled to continue traveling along the target road.

8. The method according to claim 1, characterized in that, Determining the width of the target road based on the boundary of the drivable area of ​​the target road and the robot's pose information includes: The width DG of the target road is calculated based on the robot's pitch angle β, the robot's yaw angle α, the installation height h of the robot's image acquisition device, the pixel width b of the target road, the field of view θ1 of the upper half of the height of the image acquisition device, and the focal length f of the image acquisition device. in, .

9. A control device for a robot, characterized in that, include: The acquisition module is used to acquire the width of the target road and the wheelbase width of the robot when the robot travels along the target road; A comparison module is used to compare the width of the target road with the wheelbase width of the robot; The adjustment module is used to adjust the operation of the robot based on the comparison between the width of the target road and the wheelbase width of the robot.

10. A robot, characterized in that, include: Chassis; A rotating arm is rotatably mounted on the chassis; A drive unit is connected to the rotating arm and is located at the end of the rotating arm away from the chassis. The drive unit is used to drive the rotating arm to rotate in order to adjust the operation of the robot. In addition, one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the robot control method of any one of claims 1 to 8.

11. The robot according to claim 10, characterized in that, The robot also includes: A rotary device is mounted on the chassis, and one end of the rotating arm near the chassis is connected to the rotary device so that the rotating arm is rotatably mounted on the chassis via the rotary device; When the driving unit moves the rotating arm to the target wheel track width or when the robot is running, the brake of the slewing device is used to lock and brake the rotating arm to limit the rotation of the rotating arm.

Images