Manipulating device and method for manipulating a twist lock

Abstract

A device and method for manipulating a twist lock, the twist lock being configured to lock a container (4) to a vehicle (1). The device includes a robot (2) that includes a gripper (201) configured to grip one of the twist locks to be mounted on a corner fitting of the container (4) or to be removed from the corner fitting; a vision sensor arranged on the robot (2) and configured to capture a first image of the corner fitting when the vehicle (1) is moving in a twist lock manipulation station; and a control unit. The control unit is configured to obtain the first image of the corner fitting from the vision sensor; determine a first position of the corner fitting at the moment when the first image is captured by the vision sensor based on the first image; determine a manipulation position of the gripper (201) for one of the twist locks based on the first position of the corner fitting and a position correction parameter representing a predicted displacement of the corner fitting within a predetermined response time of the robot (2), at which manipulation position the gripper (201) is to be aligned with the corner fitting; and send the manipulation position to the robot (2) such that the gripper (201) moves to the manipulation position to manipulate one of the twist locks during the movement of the vehicle (1).

Description

Technical Field

[0001] Exemplary embodiments of the present disclosure generally relate to the field of twist lock manipulation, and more particularly to an apparatus and method for manipulating twist locks on a moving vehicle having a robot. Background Art

[0002] Twist locks are typically used with containers to, for example, lock a container to a truck or a ship. When loading a container from a truck onto a ship, the container needs to be first unlocked from the truck by manipulating the twist locks and then transferred from the truck to the ship. When unloading a container from a ship, the container needs to be locked to the truck by manipulating the twist locks after being transferred to the truck. Modern ports aim to achieve efficient and automated container handling. However, twist lock manipulation has become a stumbling block for such an automated process.

[0003] Using a robot to install or remove a twist lock at a corner of a container is a viable solution for automatically manipulating twist locks. Figure 1 Illustrated is a conventional process for manipulating twist locks on a vehicle 1 in a twist lock manipulation station 3. Three twist locks (not shown), including two side twist locks and one intermediate twist lock, are provided at each side of the vehicle 1 to lock a container 4 to the vehicle 1. As Figure 1 shown in the left part of, the vehicle 1 drives into the twist lock manipulation station 3. At each side of the twist lock manipulation station 3, three robots 2 are fixed to the ground to manipulate the corresponding twist locks. Then, as Figure 1 shown in the central part of, the vehicle 1 stops at an appropriate position where the robots 2 at each side of the vehicle 1 manipulate the corresponding twist locks (e.g., remove a twist lock from the vehicle 1 or install a twist lock onto the vehicle 1). As Figure 1 shown in the right part of, after completing the manipulation of the twist locks, the vehicle 1 drives out of the twist lock manipulation station 3.

[0004] The above conventional solution for using robots 2 to manipulate twist locks has several defects to be improved. On the one hand, as Figure 1 shown, the manipulation of the twist locks is time - dispersed. The vehicle 1 drives into the twist lock manipulation station 3, stops at an appropriate position, and waits for the robots 2 to manipulate the twist locks. After completing the manipulation of all the twist locks, the vehicle 1 drives out of the twist lock manipulation station 3. To synchronize the manipulation of all the twist locks, each side of the vehicle 1 may be provided with no less than three robots, which may result in huge costs. On the other hand, the twist lock manipulation station 3 may occupy a large area. As Figure 1 shown, the total length of the twist lock manipulation station 3 is approximately three times the length of the container 4, which may result in a large turning circle of the moving path of the vehicle 1 and reduce the efficiency of the entire dock.

[0005] Therefore, an improved solution for using robots to manipulate twist locks is needed. Summary of the Invention

[0006] In view of the foregoing problems, exemplary embodiments of the present disclosure provide a solution for using a robot to manipulate twist locks.

[0007] In a first aspect, an exemplary embodiment of the present disclosure provides a device for manipulating a twist lock configured to lock a container to a vehicle. The device includes a robot including a gripper configured to grip one of the twist locks to be installed on a corner fitting of the container or to be removed from the corner fitting; a vision sensor disposed on the robot and configured to capture a first image of the corner fitting when the vehicle is moving in a twist lock manipulation station; and a control unit. The control unit is configured to obtain the first image of the corner fitting from the vision sensor; determine a first position of the corner fitting at the moment when the first image is captured by the vision sensor based on the first image; determine a manipulation position of the gripper for one of the twist locks based on the first position of the corner fitting and a position correction parameter representing a predicted displacement of the corner fitting within a predetermined response time of the robot, at which manipulation position the gripper is to be aligned with the corner fitting; and send the manipulation position to the robot such that the gripper moves to the manipulation position to manipulate one of the twist locks during the movement of the vehicle.

[0008] According to an embodiment of the present disclosure, due to the use of vision-based control technology and position correction technology, the robot can locate the corner fittings on the container in real time. Therefore, the robot has the ability to track and manipulate the twist locks on a moving vehicle. Moreover, only one robot is required for each side of the moving vehicle to manipulate the corresponding twist locks at each side of the vehicle. Compared with traditional solutions for manipulating twist locks, the number of robots used in the twist lock manipulation station can be greatly reduced, thereby reducing the total cost. Moreover, the area occupied by the twist lock manipulation station can also be reduced, thereby improving the overall efficiency of the terminal.

[0009] In some embodiments, the robot is fixed to the ground, or disposed on a movable base, or slidably disposed on a guide rail. For these embodiments, the robot can be disposed at any suitable location to effectively manipulate the twist locks on the vehicle.

[0010] In some embodiments, when the robot is arranged on a movable base or slidably arranged on a guide rail, the device further includes a proximity sensor arranged on the robot and configured to detect a rough position of the vehicle after the vehicle enters the twist-lock operation station. The control unit is further configured to obtain the rough position of the vehicle from the proximity sensor; and move the robot towards the vehicle based on the rough position of the vehicle. Through these embodiments, the proximity sensor can obtain the rough position of the vehicle in the twist-lock operation station, so that the robot can be guided to move towards the vehicle quickly. In this way, the operation speed of the twist-locks of the vehicle can also be increased, and the length of the twist-lock operation station can also be reduced.

[0011] In some embodiments, the control unit is further configured to move the robot towards the next twist-lock among these twist-locks after the operation of one of the twist-locks is completed. Through these embodiments, after the operation of one of the twist-locks is completed, the robot can move quickly towards the next twist-lock. In this way, the twist-locks at each side of the vehicle can be quickly operated one by one, thereby further increasing the operation speed of the twist-locks.

[0012] In some embodiments, the position correction parameter is preset. Through these embodiments, the vehicle can move at a substantially constant speed in the twist-lock operation station. For example, the vehicle can be an automatic container truck traveling at a constant speed.

[0013] In some embodiments, the control unit is further configured to dynamically determine the position correction parameter based on the speed of the vehicle and the predetermined response time of the robot. Through these embodiments, the position correction parameter can be dynamically determined based on the speed of the vehicle. Since the speed of the vehicle is a continuous physical quantity and does not change suddenly, it can be assumed to be constant within a short period of time. Therefore, the position correction parameter can ensure that the robot tracks the corner fitting in real time.

[0014] In some embodiments, the vision sensor is further configured to capture a second image and a third image of the corner fitting before capturing the first image of the corner fitting, and the control unit is further configured to: obtain the second image and the third image of the corner fitting from the vision sensor; determine the second position and the third position of the corner fitting at the moment when the second image and the third image are captured by the vision sensor respectively based on the second image and the third image; and determine the speed of the vehicle based on the second position and the third position of the corner fitting. Through these embodiments, the real-time speed of the corner fitting can be determined based on the images obtained by the vision sensor without any additional sensors.

[0015] In some embodiments, the speed of the vehicle is detected by a camera arranged in the twist-lock operation station or a GPS device arranged on the vehicle. Through these embodiments, the speed of the vehicle can be accurately determined by using a camera or a GPS device.

[0016] In a second aspect, an exemplary embodiment of the present disclosure provides a method for manipulating a twist lock configured to lock a container to a vehicle. The method includes: obtaining a first image of a corner fitting of the container from a vision sensor disposed on a robot, where the robot includes a gripper configured to grip one of the twist locks to be mounted on the corner fitting or to be disassembled from the corner fitting, and where the vision sensor is configured to capture the first image of the corner fitting when the vehicle is moving in a twist lock manipulation station; determining a first position of the corner fitting at the moment when the first image is captured by the vision sensor based on the first image; determining a manipulation position of the gripper for one of the twist locks at which the gripper is to be aligned with the corner fitting based on the first position of the corner fitting and a position correction parameter representing a predicted displacement of the corner fitting within a predetermined response time of the robot; and sending the manipulation position to the robot such that the gripper moves to the manipulation position to manipulate one of the twist locks during the movement of the vehicle.

[0017] In some embodiments, the robot is fixed to the ground, or disposed on a movable base, or slidably disposed on a guide rail.

[0018] In some embodiments, when the robot is disposed on a movable base or slidably disposed on a guide rail, the method further includes: obtaining a rough position of the vehicle detected by a proximity sensor disposed on the robot after the vehicle enters the twist lock manipulation station; and moving the robot towards the vehicle based on the rough position of the vehicle.

[0019] In some embodiments, the method further includes: moving the robot towards the next twist lock after completing the manipulation of one of the twist locks.

[0020] In some embodiments, the position correction parameter is preset.

[0021] In some embodiments, the method further includes: dynamically determining the position correction parameter based on the speed of the vehicle and the predetermined response time of the robot.

[0022] In some embodiments, the vision sensor is further configured to capture a second image and a third image of the corner fitting before capturing the first image of the corner fitting, and the method further includes: obtaining the second image and the third image of the corner fitting from the vision sensor; determining a second position and a third position of the corner fitting at the moments when the second image and the third image are captured by the vision sensor respectively based on the second image and the third image; and determining the speed of the vehicle based on the second position and the third position of the corner fitting.

[0023] In some embodiments, the speed of the vehicle is detected by a camera disposed in the twist lock operation station or a GPS device disposed on the vehicle.

[0024] In a third aspect, an exemplary embodiment of the present disclosure provides a system for manipulating a twist lock, the system including a computer processor coupled to a computer-readable memory unit, the memory unit including instructions that, when executed by the computer processor, implement the method according to the second aspect of the present disclosure.

[0025] In a fourth aspect, an example embodiment of the present disclosure provides a computer-readable medium having instructions stored thereon that, when executed on at least one processor, cause the at least one processor to perform the method according to the second aspect of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The drawings described herein are provided to further explain the present disclosure and form a part of the present disclosure. Example embodiments of the present disclosure and their descriptions are used to explain the present disclosure and not unduly limit the present disclosure.

[0027] Figure 1 Illustrates a conventional process for manipulating a twist lock on a vehicle in a twist lock operation station;

[0028] Figure 2 Illustrates an exemplary process for manipulating a twist lock on a vehicle in a twist lock operation station according to an embodiment of the present disclosure;

[0029] Figure 3 Illustrates an exemplary process for manipulating a first twist lock on a vehicle in a twist lock operation station according to an embodiment of the present disclosure;

[0030] Figure 4 Illustrates an exemplary process for manipulating a twist lock on a vehicle in a twist lock operation station according to an embodiment of the present disclosure;

[0031] Figure 5 Illustrates a schematic diagram of a robot disposed on a movable base according to an embodiment of the present disclosure;

[0032] Figure 6 Illustrates an exemplary process for manipulating a twist lock on a vehicle in a twist lock operation station according to an embodiment of the present disclosure;

[0033] Figure 7 Illustrates a schematic diagram of a robot disposed on a guide rail according to an embodiment of the present disclosure;

[0034] Figure 8 Illustrates a flowchart of a method for manipulating a twist lock according to an embodiment of the present disclosure; and

[0035] Figure 9The figure illustrates a schematic diagram of a system for manipulating twist locks according to an embodiment of the present disclosure.

[0036] Throughout the drawings, the same or similar reference numerals are used to denote the same or similar elements. Detailed implementation manners

[0037] Now, the principles of the present disclosure will be described with reference to several exemplary embodiments illustrated in the accompanying drawings. Although the exemplary embodiments of the present disclosure are illustrated in the drawings, it should be understood that the description of these embodiments is only for facilitating those skilled in the art to better understand and thus implement the present disclosure, rather than limiting the scope of the present disclosure in any way.

[0038] The term "comprising" or "including" and its variants should be construed as open-ended terms, meaning "including but not limited to". Unless the context clearly indicates otherwise, the term "or" should be construed as "and / or". The term "based on" should be understood as "at least partially based on". The term "operable to" means a function, action, movement, or state that can be achieved by an operation caused by a user or an external agency. The term "one embodiment" and "an embodiment" should be construed as "at least one embodiment". The term "another embodiment" should be construed as "at least one other embodiment". The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may be included hereinafter. Unless the context clearly indicates otherwise, the definitions of the terms are consistent throughout the specification.

[0039] As discussed above, in traditional twist lock manipulation schemes, each side of the vehicle needs to be provided with no less than three robots, which results in huge costs; moreover, traditional twist lock manipulation stations may occupy a relatively large area, which will lead to a large turning circle of the vehicle's moving path and reduce the efficiency of the entire dock. According to an embodiment of the present disclosure, in order to reduce the number of robots used in the twist lock manipulation station and the area occupied by the twist lock manipulation station, vision-based control technology and position correction technology are used to manipulate the twist locks when the vehicle is moving in the twist lock manipulation station. As will be described in detail in the following paragraphs, the above idea can be implemented in various ways.

[0040] Hereinafter, reference is made to Figures 2 to 9 for a detailed description of the principles of the present disclosure. First, reference is made to Figure 2 and Figure 3 , Figure 2 illustrates an exemplary process for manipulating the twist locks on the vehicle 1 in the twist lock manipulation station 3 according to an embodiment of the present disclosure, and Figure 3Illustrated is an exemplary process for manipulating a first twist lock on a vehicle 1 at a twist lock manipulation station 3 according to an embodiment of the present disclosure. The twist lock is configured to cooperate with the corner fittings of a container 4 to lock the container 4 to the vehicle 1. The first twist lock is arranged at the front of the vehicle 1, i.e., closer to the head of the vehicle 1 than the other twist locks.

[0041] According to an embodiment of the present invention, a plurality of corner fittings (not shown) are provided at each side of the container 4 to receive corresponding twist locks, thereby locking the container 4 to the vehicle 1. In some embodiments, the number of corner fittings at each side of the container 4 may be three, including two side corner fittings for cooperating with side twist locks and one intermediate corner fitting for cooperating with an intermediate twist lock. In other embodiments, the number of corner fittings at each side of the vehicle 1 may be more or less than three. The scope of the present disclosure is not intended to be limited thereto.

[0042] As Figure 2 and Figure 3 shown, in order to manipulate the twist locks at each side of the container 4, a robot 2 is arranged at each side of the vehicle 1. In some embodiments, the robot 2 may be fixed to the ground or other platforms. The robot 2 can be of any known type or other types available in the future. The robot 2 includes a gripper 201, which is configured to grip one of the twist locks to install it onto or disassemble it from the corner fittings of the container 4. The gripper 201 has the ability to handle side twist locks and intermediate twist locks.

[0043] According to an embodiment of the present invention, a vision sensor is arranged on the robot 2 to capture a first image of the corner fittings when the vehicle 1 is moving in the twist lock manipulation station 3. Based on the first image of the corner fittings, the position of the corner fittings can be determined by a control unit, as described in detail below.

[0044] The control unit described herein is configured to obtain the first image of the corner fittings from the vision sensor and determine the first position of the corner fittings based on the first image. The first position refers to the current position of the corner fittings when the vision sensor captures the first image. After determining the first position of the corner fittings, the gripper 201 needs to manipulate the corresponding twist lock. In some cases, when loading the container 4 from the vehicle 1 onto a ship, the gripper 201 may need to grip the twist lock and disassemble the twist lock from the corner fittings of the container 4. In some other cases, after the container 4 is unloaded from the ship onto the vehicle 1, the gripper 201 may need to grip the twist lock and install the twist lock onto the corner fittings of the container 4.

[0045] Since the twist lock moves continuously on the vehicle 1, the gripper 201 cannot successfully grip the twist lock at the first position. This is because when the gripper 201 moves to the first position, the twist lock may have reached the next position. To avoid the gripper 201 always moving to the previous position of the twist lock, a predicted position correction can be applied to the first position of the twist lock. Specifically, the control unit can determine the manipulation position of the gripper 201 for the twist lock to be manipulated based on the first position of the corner fitting and the position correction parameter. The gripper 201 is aligned with the corner fitting at the manipulation position. In other words, the gripper 201 can insert the twist lock into the corner fitting or successfully grip the twist lock mounted on the corner fitting at the manipulation position.

[0046] The position correction parameter represents the predicted displacement of the corner fitting within the predetermined response time of the robot 2. The predetermined response time of the robot 2 refers to the time from the moment when the vision sensor captures an image to the moment when the robot 2 reaches the desired position. When the vehicle 1 is moving slowly and steadily in the twist lock manipulation station 3, the operating speed of the robot 2 is relatively fast compared to the moving speed of the vehicle 1. Therefore, it can be assumed that the predetermined response time of the robot 2 is substantially constant.

[0047] Then, the control unit can send the manipulation position to the robot 2. The robot 2 can convert the operating position into the angular values of the joints of the robot 2. Thereafter, the motors of the joints rotate according to the angular values, and during the movement of the vehicle 1, the gripper 201 moves to the manipulation position to manipulate the twist lock.

[0048] The robot 2, the vision sensor, and the control unit as described above can form a device for manipulating the twist lock. When the vehicle 1 is moving in the twist lock manipulation station 3, the device for manipulating the twist lock is adapted to manipulate each of the twist locks one by one on one side of the vehicle 1. Taking the process of removing the twist lock from the corner fitting as an example, the specific operation of the device can be as follows. As Figure 2 and Figure 3 shown in the left part of, the first twist lock is manipulated by the robot 2. During the first twist lock being gripped by the gripper 201, the gripper 201 can move together with the first twist lock and perform the manipulation of the first twist lock. Then, as Figure 2 shown in the central part of, the robot 2 may wait for the second twist lock to arrive and then manipulate it. Finally, as Figure 2 shown in the right part of, the robot 2 may wait for the third twist lock to arrive and then manipulate it. The specific process of installing the twist lock onto the corner fitting is similar to the process of removing the twist lock as described above and will not be described in detail herein. The twist locks on the other side of the vehicle 1 can be manipulated in a similar manner and will not be described in detail herein.

[0049] Due to the use of vision-based control technology and position correction technology, the robot 2 can locate the corner fitting on the container 4 in real time. Therefore, the robot 2 has the ability to track and manipulate the twist lock on the moving vehicle 1. Moreover, only one robot 2 is required on each side of the moving vehicle 1 to manipulate the corresponding twist lock at each side of the vehicle 1. Compared with the traditional solutions for manipulating twist locks, the number of robots used in the twist lock manipulation station 3 can be greatly reduced, from six to two, thus reducing the total cost. Moreover, the area occupied by the twist lock manipulation station 3 can also be reduced. Specifically, the length of the twist lock manipulation station 3 can be reduced from three times the length of the container 4 to twice the length of the container 4, thereby improving the overall efficiency of the terminal.

[0050] In some embodiments, when the vehicle 1 moves at a substantially constant speed in the twist lock manipulation station 3, the position correction parameters can be preset. For example, the vehicle 1 can be an automated container truck traveling at a constant speed. In these cases, since both the predetermined response time of the robot 2 and the moving speed of the vehicle 1 are substantially constant, the predicted displacement of the corner fitting within the predetermined response time may be substantially constant. Therefore, by presetting the position correction parameters, the first position of the corner fitting can be accurately corrected to obtain the actual manipulation position of the gripper 201.

[0051] In some embodiments, when the vehicle 1 is driven by a driver, the moving speed of the vehicle 1 can vary slightly. In these cases, the control unit can also be configured to dynamically determine the position correction parameters based on the speed of the vehicle 1 and the predetermined response time of the robot 2. That is, the speed of the vehicle 1 can be multiplied by the predetermined response time of the robot 2 to obtain the predicted displacement of the corner fitting during the predetermined response time. Through these embodiments, the position correction parameters can be dynamically determined based on the speed of the vehicle 1. Since the speed of the vehicle 1 is a continuous physical quantity and does not change suddenly, it can be assumed to be constant within a short period of time. Therefore, the position correction parameters can ensure that the robot 2 tracks the corner fitting in real time. The speed of the vehicle 1 can be determined in various ways, as described in detail below.

[0052] In some embodiments, the vision sensor is further configured to capture a second image and a third image of the corner fitting before capturing a first image of the corner fitting. The control unit may obtain the second image and the third image of the corner fitting from the vision sensor. Then, the control unit determines a second position and a third position of the corner fitting when the vision sensor captures the second image and the third image respectively based on the second image and the third image. Then, the control unit determines the speed of the vehicle 1 based on the second position and the third position of the corner fitting. Specifically, since the time interval between capturing the second image and the third image is known, the speed of the vehicle 1 can be obtained based on the time interval and the second position and the third position of the corner fitting. Through these embodiments, the real-time speed of the corner fitting can be determined based on the images obtained by the vision sensor without any additional sensors.

[0053] In one embodiment, the speed of the vehicle 1 is detected by a camera arranged in the twist lock operation station 3. The camera may collect real-time images of the vehicle 1 and send them to the control unit. Then, the control unit may determine the speed of the vehicle 1 based on the collected real-time images. In another embodiment, the speed of the vehicle 1 is detected by a GPS device arranged on the vehicle 1. Through these embodiments, the speed of the vehicle 1 can be accurately determined by using a camera or a GPS device. In other embodiments, the speed of the vehicle 1 may be detected in other ways. The scope of the present disclosure is not intended to be limited thereto.

[0054] In some embodiments, the robot 2 may move in the twist lock operation station 3. Figures 4 to 7 An embodiment of the robot 2 is illustrated. As Figure 4 and Figure 5 shown, the robot 2 is arranged on a movable base 5 such as an automated guided vehicle (AGV). As Figure 6 and Figure 7 shown, the robot 2 is slidably arranged on the guide rail 6.

[0055] When the robot 2 is arranged on the movable base 5, the device for manipulating the twist lock further includes a proximity sensor arranged on the robot 2. The proximity sensor is configured to detect a rough position of the vehicle 1 after the vehicle 1 enters the twist lock operation station 3. Then, the control unit obtains the rough position of the vehicle 1 from the proximity sensor and makes the robot 2 move towards the vehicle 1 based on the rough position of the vehicle 1. Through these embodiments, the proximity sensor can obtain the rough position of the vehicle 1 in the twist lock operation station 3, so that the robot 2 can be guided to move quickly towards the vehicle 1. Then, the movable base 5 remains stationary while the robot 2 dynamically positions, tracks and manipulates the twist lock.

[0056] Taking the process of removing the twist lock from the corner fitting as an example, the specific operation of the device may be as follows. As Figure 4As shown on the left side of [Figure 0], after the movable base 5 moves close to the first twist lock, the movable base 5 remains stationary, enabling the robot 2 to manipulate the first twist lock. During the manipulation of the first twist lock by the gripper 201, the gripper 201 can move together with the first twist lock and perform the manipulation of the first twist lock. Then, as Figure 4 shown in the central part of [Figure 1], after the manipulation of the first twist lock is completed, the robot 2 may quickly move near the second twist lock; and when the movable base 5 remains stationary, the robot 2 dynamically positions, tracks, and manipulates the second twist lock. Finally, as Figure 4 shown on the right side of [Figure 2], after the manipulation of the second twist lock is completed, the robot 2 will quickly move near the third twist lock; and when the movable base 5 remains stationary, the robot 2 dynamically positions, tracks, and manipulates the third twist lock. The specific process of installing the twist lock onto the corner fitting is similar to the process of removing the twist lock as described above and will not be described in detail herein. The twist locks on the other side of the vehicle 1 can be manipulated in a similar manner and will not be described in detail herein.

[0057] Through the above control technology, the manipulation speed of the twist locks on the vehicle 1 can also be increased, and the length of the twist lock manipulation station 3 can also be reduced. Specifically, the length of the twist lock manipulation station 3 can be reduced from three times the length of the container 4 to approximately one time, thereby improving the overall efficiency of the dock.

[0058] Considering the traffic conditions at the dock and the mooring conditions of the ship, the robot 2 on the movable base 5 can move anywhere in the port. If a dock has a very urgent loading and unloading task, the robot 2 can move from another idle dock to the busy dock to support the manipulation of the twist locks at the busy dock.

[0059] Similarly, when the robot 2 is slidably arranged on the guide rail 6, the device for manipulating the twist lock further includes a proximity sensor arranged on the robot 2. The proximity sensor is configured to detect the rough position of the vehicle 1 after the vehicle 1 enters the twist lock manipulation station 3. Then, the control unit obtains the rough position of the vehicle 1 from the proximity sensor and makes the robot 2 move towards the vehicle 1 based on the rough position of the vehicle 1. Then, the movable base 5 remains stationary on the guide rail 6 while the robot 2 dynamically positions, tracks, and manipulates the twist lock.

[0060] Taking the process of removing the twist lock from the corner fitting as an example, the specific operation of the device for manipulating the twist lock can be as follows. As Figure 6 shown on the left side of [Figure 3], after the robot 2 moves near the first twist lock on the guide rail 6, the robot 2 remains stationary, enabling the first twist lock to be manipulated by the robot 2. During the manipulation of the first twist lock by the gripper 201, the gripper 201 can move together with the first twist lock and perform the manipulation of the first twist lock. Then, as Figure 6As shown in the central part of [Figure 0], after completing the manipulation of the first twist lock, the robot 2 may quickly move to near the second twist lock on the guide rail 6; and when the robot 2 is stationary, the robot 2 dynamically positions, tracks, and manipulates the second twist lock. Finally, as Figure 6 As shown in the right part of [Figure 1], after completing the manipulation of the second twist lock, the robot 2 may quickly move to near the third twist lock on the guide rail 6; and when the robot 2 is stationary, the robot 2 dynamically positions, tracks, and manipulates the third twist lock. The specific process of installing the twist lock onto the corner fitting is similar to the process of disassembling the twist lock as described above and will not be described in detail herein. The twist locks on the other side of the vehicle 1 can be handled in a similar manner and will not be described in detail herein.

[0061] Exemplary embodiments of the present disclosure also provide a method for manipulating a twist lock. Figure 8 The flowchart of a method 800 for manipulating a twist lock according to an embodiment of the present disclosure is illustrated. The method 800 includes: at 810, obtaining a first image of a corner fitting of a container from a vision sensor disposed on a robot, where the robot includes a gripper configured to grip one of the twist locks to be installed onto the corner fitting or the twist locks to be disassembled from the corner fitting, and where the vision sensor is configured to capture the first image of the corner fitting when the vehicle is moving in a twist lock manipulation station; at 820, determining a first position of the corner fitting at the moment when the first image is captured by the vision sensor based on the first image; at 830, determining a manipulation position of the gripper for one of the twist locks based on the first position of the corner fitting and a position correction parameter representing a predicted displacement of the corner fitting within a predetermined response time of the robot, at which manipulation position the gripper is to be aligned with the corner fitting; and at 840, sending the manipulation position to the robot such that the gripper moves to the manipulation position to manipulate one of the twist locks during the movement of the vehicle.

[0062] In some embodiments, the robot is fixed to the ground, or disposed on a movable base, or slidably disposed on a guide rail.

[0063] In some embodiments, when the robot is disposed on a movable base or slidably disposed on a guide rail, the method further includes: obtaining a rough position of the vehicle detected by a proximity sensor disposed on the robot after the vehicle enters the twist lock manipulation station; and moving the robot towards the vehicle based on the rough position of the vehicle.

[0064] In some embodiments, the method further includes: moving the robot towards the next twist lock after completing the manipulation of one of the twist locks.

[0065] In some embodiments, the position correction parameter is preset.

[0066] In some embodiments, the method further includes: dynamically determining a position correction parameter based on the speed of the vehicle and a predetermined response time of the robot.

[0067] In some embodiments, the vision sensor is further configured to capture a second image and a third image of the corner fitting before capturing a first image of the corner fitting, and the method further includes: obtaining the second image and the third image of the corner fitting from the vision sensor; respectively determining a second position and a third position of the corner fitting at the moment when the second image and the third image are captured by the vision sensor based on the second image and the third image; and determining the speed of the vehicle based on the second position and the third position of the corner fitting.

[0068] In some embodiments, the speed of the vehicle is detected by a camera arranged in the twist lock operation station or a GPS device arranged on the vehicle.

[0069] In some embodiments of the present invention, a system 900 for manipulating a twist lock is provided. Figure 9 The schematic diagram of a system 900 for manipulating a twist lock according to an embodiment of the present disclosure is illustrated. As Figure 9 shown, the system 900 may include a computer processor 910, and the computer processor 910 is coupled to a computer-readable memory unit 920, and the memory unit 920 includes instructions 922. When executed by the computer processor 910, the instructions 922 may implement the method for manipulating the twist lock as described in the previous paragraphs, and the details will be omitted hereinafter.

[0070] In some embodiments of the present invention, a computer-readable medium for manipulating a twist lock is provided. Instructions are stored on the computer-readable medium, and when executed on at least one processor, these instructions may cause the at least one processor to execute the method for manipulating the twist lock as described in the foregoing paragraphs, and the details will be omitted hereinafter.

[0071] Generally, various embodiments of the present disclosure may be implemented in hardware or special-purpose circuits, software, logic, or any combination thereof. Some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software, which may be executed by a controller, a microprocessor, or other computing devices. Although some aspects of the embodiments of the present disclosure are illustrated and described as block diagrams, flowcharts, or illustrated and described using some other graphical representations, it should be understood that the blocks, devices, systems, technologies, or methods described herein may be implemented as non-limiting examples in hardware, software, firmware, special-purpose circuits or logic, general hardware or controllers, or other computing devices, or some combination thereof.

[0072] The present disclosure also provides at least one computer program product tangibly stored on a non-transitory computer-readable storage medium. The computer program product includes computer-executable instructions being executed in a device on a target real or virtual processor, such as computer-executable instructions included in program modules for performing the processes or methods described above with reference to Figures 2 to 8 The processes or methods. Generally, program modules include routines, programs, libraries, objects, classes, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The functions of the program modules may be combined or separated among the program modules in a desirable manner in various embodiments. The machine-executable instructions of the program modules may be executed within a local device or a distributed device. In a distributed device, the program modules may be located in both a local storage medium and a remote storage medium.

[0073] The program code for performing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, a special purpose computer, or other programmable data processing apparatus, such that when the program codes are executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program code may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0074] The above program code may be embodied on a machine-readable medium, which may be any tangible medium that can contain or store a program used by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium may include an electrical connection with one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0075] Further, although the operations are depicted in a particular order, this should not be construed as requiring that the operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Similarly, although several specific implementation details are included in the above discussion, these details should not be construed as limiting the scope of the present disclosure, but rather as descriptions of features specific to particular embodiments. Certain features that are described in the context of separate embodiments may also be implemented in combination in a single embodiment. On the other hand, the various features that are described in the context of a single embodiment may also be implemented separately or in any suitable sub-combination in multiple embodiments.

[0076] Although the subject matter has been described in language specific to structural features and / or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the above specific features and acts are disclosed as example forms of implementing the claims.

Claims

1. A device for manipulating a twist lock, the twist lock being configured to lock a container to a vehicle, the device comprising: A robot, including a gripper configured to grip one of the twist locks to be installed on the corner fittings of the container or to be removed from the corner fittings of the container; A vision sensor disposed on the robot and configured to capture a first image of the corner fitting when the vehicle is moving in the twist lock manipulation station; And A control unit configured to: Obtain the first image of the corner fitting from the vision sensor; Determine a first position of the corner fitting at the moment when the first image is captured by the vision sensor based on the first image; Determine a manipulation position of the gripper for one of the twist locks based on the first position of the corner fitting and a position correction parameter representing a predicted displacement of the corner fitting within a predetermined response time of the robot, at which manipulation position the gripper is to be aligned with the corner fitting; And Send the manipulation position to the robot such that the gripper moves to the manipulation position to manipulate one of the twist locks during the movement of the vehicle.

2. The device according to claim 1, wherein the robot is fixed to the ground, or is arranged on a movable base, or is slidably arranged on a guide rail.

3. The device according to claim 2, wherein when the robot is arranged on the movable base, or is slidably arranged on the guide rail, the device further comprises a proximity sensor, the proximity sensor being arranged on the robot and being configured to detect a rough position of the vehicle after the vehicle enters the twist lock manipulation station, and wherein the control unit is further configured to: obtain the rough position of the vehicle from the proximity sensor; and move the robot towards the vehicle based on the rough position of the vehicle.

4. The device according to claim 3, wherein the control unit is further configured to: after completing the manipulation of one of the twist locks, move the robot towards the next twist lock among the twist locks.

5. The device according to claim 1, wherein the position correction parameter is preset.

6. The device according to claim 1, wherein the control unit is further configured to: dynamically determine the position correction parameter based on the speed of the vehicle and the predetermined response time of the robot.

7. The device according to claim 6, wherein the vision sensor is further configured to capture a second image and a third image of the corner fitting before capturing the first image of the corner fitting, and wherein the control unit is further configured to: obtain the second image and the third image of the corner fitting from the vision sensor; Based on the second image and the third image respectively, determine the second position and the third position of the corner fitting at the moment when the second image and the third image are captured by the vision sensor; and Determine the speed of the vehicle based on the second position and the third position of the corner fitting.

8. The apparatus according to claim 6, wherein the speed of the vehicle is detected by a camera arranged in the twist lock operation station or a GPS device arranged on the vehicle.

9. A method for operating a twist lock configured to lock a container to a vehicle, the method comprising: Obtain a first image of the corner fitting of the container from a vision sensor disposed on the robot, wherein the robot includes a gripper configured to grip one of the twist locks to be installed on the corner fitting or to be removed from the corner fitting, and wherein the vision sensor is configured to capture the first image of the corner fitting when the vehicle is moving in the twist lock manipulation station; Determine a first position of the corner fitting at the moment when the first image is captured by the vision sensor based on the first image; Determine a manipulation position of the gripper for one of the twist locks based on the first position of the corner fitting and a position correction parameter representing a predicted displacement of the corner fitting within a predetermined response time of the robot, at which manipulation position the gripper is to be aligned with the corner fitting; And Send the manipulation position to the robot such that the gripper moves to the manipulation position to manipulate one of the twist locks during the movement of the vehicle.

10. The method according to claim 9, wherein the robot is fixed to the ground, or arranged on a movable base, or slidably arranged on a guide rail.

11. The method according to claim 10, wherein when the robot is arranged on the movable base or slidably arranged on the guide rail, the method further comprises: After the vehicle enters the twist lock manipulation station, obtain a rough position of the vehicle detected by a proximity sensor disposed on the robot; And Cause the robot to move towards the vehicle based on the rough position of the vehicle.

12. The method according to claim 11, further comprising: After completing the manipulation of one of the twist locks, cause the robot to move towards the next twist lock among the twist locks.

13. The method according to claim 9, wherein the position correction parameter is preset.

14. The method according to claim 9, further comprising: Dynamically determine the position correction parameter based on the speed of the vehicle and the predetermined response time of the robot.

15. The method according to claim 14, wherein the vision sensor is further configured to capture a second image and a third image of the corner fitting before capturing the first image of the corner fitting, and wherein the method further comprises: Obtain a second image and a third image of the corner fitting from the vision sensor; Determine a second position and a third position of the corner fitting at the moments when the second image and the third image are captured by the vision sensor respectively based on the second image and the third image; And Determine the speed of the vehicle based on the second position and the third position of the corner fitting.

16. The method according to claim 14, wherein the speed of the vehicle is detected by a camera arranged in the twist lock operation station or a GPS device arranged on the vehicle.

17. A system for manipulating twist locks, comprising: A computer processor, coupled to a computer-readable memory unit, the memory unit including instructions which, when executed by the computer processor, implement the method according to any one of claims 9 to 16.

18. A computer-readable medium having instructions stored thereon that, when executed on at least one processor, cause the at least one processor to perform the method according to any one of claims 9 to 16.

Images