Carrying control method and system of nuclear accident rescue carrying robot, carrying robot and carrying robot system

Abstract

The invention relates to a carrying control method and system of a nuclear accident rescue carrying robot, the carrying robot and a carrying robot system. The method comprises the following steps: acquiring image data of a target object, and identifying to obtain the type of the target object; determining an initial clamping force of the target object according to the type, if the type of the target object belongs to a first type, judging whether the target object is damaged, and if the target object is not damaged, querying a preset clamping force corresponding to the type to obtain the initial clamping force; and controlling the carrying robot to carry the target object according to the initial clamping force. By identifying the type of the target object and querying the corresponding preset clamping force when the target object belongs to the first type and is not damaged, the appropriate initial clamping force can be quickly and accurately determined for carrying, multiple carrying attempts on the target object are not needed, the control accuracy is improved, and the carrying efficiency is improved. And the working efficiency and the rescue efficiency of the transfer robot are further improved, so that other rescue equipment or personnel can enter an accident scene in time.

Description

Technical Field

[0001] The present invention relates to the field of nuclear accident rescue, and in particular to a transport control method and system of a nuclear accident rescue transport robot, a transport robot and a transport robot system. Background Art

[0002] The environment at the nuclear accident site is complex, and there are usually obstacles such as damaged equipment and collapsed buildings, which block the passage route and bring obstacles to rescue. Since the nuclear accident site is highly radioactive, robots are needed to dismantle and move obstacles so that other rescue equipment or personnel can enter the accident site. The obstacles that the handling robot needs to carry are of various types and have a very large weight range. Therefore, it is difficult to accurately determine the clamping force of the robot arm during the robot's autonomous handling process. In the prior art, the handling robot needs to try to carry it many times and constantly adjust the clamping force to determine the appropriate clamping force of the obstacle. Sometimes, in order to avoid damaging some dangerous items, it is also necessary to gradually increase the clamping force of the attempted grasping from small to large to gradually determine the appropriate clamping force. This results in a long time to determine the clamping force of the obstacle being carried, and the working efficiency and rescue efficiency of the handling robot are low. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a transport control method and system for a nuclear accident rescue transport robot, a transport robot and a transport robot system.

[0004] The technical solution adopted by the present invention to solve the technical problem is: to provide a handling control method of a nuclear accident rescue handling robot, comprising the following steps:

[0005] Acquire image data of a target object and identify the type of the target object;

[0006] Determine the initial clamping force of the target object according to the type; wherein, if the type of the target object belongs to the first type, determine whether the target object is damaged, and if not damaged, query the preset clamping force corresponding to the type to obtain the initial clamping force;

[0007] The transport robot is controlled to transport the target object according to the initial clamping force.

[0008] Furthermore, the identifying the type of the target object includes:

[0009] The image data is identified using a trained recognition model to obtain the type of the target object.

[0010] Further, determining the initial clamping force of the target object according to the type includes:

[0011] If the type of the target object belongs to the second type, the specification information of the target object is obtained according to the image data analysis, and the weight information is calculated based on the specification information to determine the initial clamping force.

[0012] Furthermore, after determining whether the target object is damaged, the method further includes:

[0013] If damaged, the specification information of the target object is obtained according to the analysis of the image data, and the weight information is calculated based on the specification information to determine the initial clamping force.

[0014] Further, the specification information includes volume information, and the specification information of the target object obtained by analyzing the image data includes:

[0015] Image data of the target object at different angles are acquired, and the volume information is obtained by analyzing the image data using a binocular vision method.

[0016] Further, the transport robot includes a mechanical arm, and controlling the transport robot to transport the target object according to the initial clamping force includes:

[0017] After the robotic arm clamps the target object, a model predictive control algorithm is used to adjust the actual clamping force of the robotic arm to reach the initial clamping force.

[0018] Further, the mechanical arm includes a clamping drive component and a clamping component, and the clamping drive component controls the clamping force of the clamping component on the target object according to the pressure parameter; and the use of the model predictive control algorithm to adjust the actual clamping force of the mechanical arm to reach the initial clamping force includes:

[0019] According to the actual clamping force and the initial clamping force, a target pressure parameter of the clamping drive assembly is calculated based on a model predictive control algorithm;

[0020] Acquiring actual pressure parameters of the clamping drive assembly;

[0021] According to the actual pressure parameter and the target pressure parameter, a PID algorithm is used to perform PID feedback regulation on the clamping drive assembly to control the clamping assembly to achieve a clamping force corresponding to the target pressure parameter.

[0022] The present invention also provides a handling control system of a nuclear accident rescue handling robot, which is applied to the handling control method of the nuclear accident rescue handling robot described in any one of the above items, comprising:

[0023] A clamping force determination module, used to obtain image data of a target object, identify the type of the target object, and determine an initial clamping force of the target object according to the type;

[0024] The clamping force determination module includes: a clamping force classification determination module, which is used to determine whether the target object is damaged when the type of the target object belongs to the first type, and if not damaged, query the preset clamping force corresponding to the type to obtain the initial clamping force;

[0025] A transport control module is used to control the transport robot to transport the target object according to the initial clamping force.

[0026] Furthermore, the clamping force determination module further includes:

[0027] The target recognition module is used to use the trained recognition model to recognize the image data and obtain the type of the target object.

[0028] Furthermore, the clamping force classification determination module is also used to, when the type of the target object belongs to the second type, obtain specification information of the target object based on the image data analysis, and calculate the weight information based on the specification information, so as to determine the initial clamping force; and when the type of the target object belongs to the second type, determine whether the target object is damaged, and if damaged, obtain the specification information of the target object based on the image data analysis, and calculate the weight information based on the specification information, so as to determine the initial clamping force.

[0029] Further, the transport control module includes a pressure parameter adjustment module and a clamping force adjustment module;

[0030] The pressure parameter adjustment module is used to calculate the target pressure parameter of the clamping drive assembly based on the model predictive control algorithm according to the actual clamping force and the initial clamping force;

[0031] The clamping force adjustment module is used to obtain the actual pressure parameter of the clamping drive component; according to the actual pressure parameter and the target pressure parameter, a PID algorithm is used to perform PID feedback adjustment on the clamping drive component to control the clamping component to reach the clamping force corresponding to the target pressure parameter.

[0032] The present invention also provides a transport robot, comprising a transport control system of any one of the above-mentioned nuclear accident rescue transport robots.

[0033] The present invention also provides a transport robot system, comprising a transport robot and a server;

[0034] The transport robot comprises a transport control module of the transport control system of the nuclear accident rescue transport robot described in any one of the above items;

[0035] The server includes the clamping force determination module of the handling control system of the nuclear accident rescue handling robot as described in any one of the above items.

[0036] The nuclear accident rescue handling robot handling control method and system, handling robot and handling robot system implementing the present invention have the following beneficial effects: by identifying the type of the target object and querying the corresponding preset clamping force when the target object belongs to the first type and is not damaged, the appropriate initial clamping force can be quickly and accurately determined for handling, without the need to make multiple handling attempts on the target object, thereby improving the control accuracy and further improving the working efficiency and rescue efficiency of the handling robot, so that other rescue equipment or personnel can enter the accident scene in time. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The present invention will be further described below with reference to the accompanying drawings and embodiments, in which:

[0038] Figure 1 It is a flow chart of an embodiment of a method for controlling a transport of a nuclear accident rescue transport robot according to the present invention;

[0039] Figure 2 It is a structural schematic diagram of an embodiment of a transport control system of a nuclear accident rescue transport robot of the present invention;

[0040] Figure 3 It is a flow chart of the dual closed-loop force control mode provided by the present invention. DETAILED DESCRIPTION

[0041] In order to have a clearer understanding of the technical features, purposes and effects of the present invention, specific embodiments of the present invention are now described in detail with reference to the accompanying drawings.

[0042] The handling control method and system of the nuclear accident rescue handling robot provided by the present invention can be used to control the handling robot. The handling robot can use a mechanical arm to carry obstacles or other objects from A to B according to a set trajectory. The mechanical arm is a multi-degree-of-freedom mechanical arm, including a support arm, a clamping drive component and a clamping component. Among them, the clamping component is arranged at one end of the support arm, and is used to grasp the object, which can adopt a clamping claw. The clamping drive component is arranged inside the support arm or at other appropriate positions, and is used to provide a power source to drive the clamping component, which can adopt a clamping oil cylinder, a clamping cylinder or other driving devices.

[0043] like Figure 1 As shown, in one embodiment of the transport control method of the nuclear accident rescue transport robot of the present invention, the following steps are included:

[0044] S1. Acquire image data of a target object and identify the type of the target object.

[0045] Specifically, the target object is an object that the handling robot needs to carry, which may be an obstacle that affects passage or an object that does not affect passage. The image data of the target object is obtained by an image detection module arranged on the handling robot, for example, by using a camera to take pictures of the object image at the nuclear accident site, so that the image data of the target object at the nuclear accident site can be collected. In some cases, the handling robot will also work in collaboration with other robots, such as an exploration robot or other handling robots dedicated to exploring the on-site environment. Therefore, in other embodiments, the image data of the target object collected by other robots can also be obtained.

[0046] Furthermore, the trained recognition model is used to identify the image data to obtain the type of the target object. Objects at the nuclear accident site are mainly divided into the following two categories: the second type is items that have no preset specifications before damage, such as reinforced concrete building fragments, etc., and the weight and size information cannot be preset; the first type is items that have preset specifications before damage, such as nuclear power equipment, raw materials or waste liquid containers, etc., and the weight and size of these items can be preset.

[0047] The model can adopt a neural network or other recognition models. The training method is: a large number of sample images of the first and second types of objects are used as input, and the annotation information of the sample images is used as output to train the neural network to obtain a fine-grained object recognition model. Among them, the sample images include but are not limited to nuclear equipment images, building images, images of different object materials, etc., and some of the objects are damaged and the other objects are not damaged. The annotation information of the image marks the specific type of the object. For undamaged objects, information such as size, volume, weight, and material can also be marked. For damaged items, material information is also marked. Since the size, volume, and weight cannot be determined, there is no need to mark the size, volume, and weight. The trained neural network can identify the type of the object through the local part of the object. Other training methods can also be used in other embodiments. In addition, a binary classification model can also be used to accumulate samples and optimize the training of the model to improve the accuracy of the recognition model.

[0048] The image data of the target object is input into the trained recognition model, and the corresponding annotation information can be obtained after recognition, thereby determining the specific type of the target object.

[0049] S2. Determine the initial clamping force of the target object according to the type. The initial clamping force is the initial clamping force used by the clamping assembly of the robot arm when carrying a heavy object.

[0050] If the target object belongs to the second type, the specification information of the target object is obtained according to the image data analysis, and the weight information is calculated based on the specification information to determine the initial clamping force. If the target object belongs to the first type, it is determined whether the target object is damaged. If not, the preset clamping force corresponding to the type is queried to obtain the initial clamping force; if damaged, the specification information of the target object is obtained according to the image data analysis, and the weight information is calculated based on the specification information to determine the initial clamping force.

[0051] For example, when the target object is determined to be a certain type of nuclear power equipment, if the equipment is not damaged, the initial clamping force of the equipment of this type can be obtained by querying from the pre-stored clamping forces corresponding to different equipment. When the target object is determined to be a waste liquid barrel, the specifications of the waste liquid barrel are determined according to the size, etc., and then the initial clamping force of the waste liquid barrel is obtained by querying from the pre-stored clamping forces corresponding to different barrel specifications.

[0052] If nuclear power equipment or waste liquid barrels are damaged, their weight and size will change, and the preset clamping force will no longer apply. If the target object is a building fragment, it does not have a preset fixed specification such as volume and weight. Therefore, image processing is required to analyze the specification information of the target object and then evaluate its weight. The clamping force is affected by the weight of the object, so determining the weight information helps to clamp and move the object safely, stably and accurately.

[0053] The specification information includes volume information and material information. The material information is obtained by identifying the recognition model.

[0054] The volume information is obtained by obtaining image data of the target object at different angles and analyzing the image data using a binocular vision method to obtain the volume information. Images at different angles are obtained, and two suitable images are selected from the images and analyzed using a binocular vision method to obtain the volume information. Then, the weight information is calculated based on the volume information and the material information, and the initial clamping force of the target object is further calculated and determined. The method for calculating the initial clamping force based on the weight information can refer to the prior art.

[0055] In the prior art, a handling robot needs to first clamp the target object with a certain clamping force, and then try to pick up the target object. If it can be picked up, the object is directly carried. If it cannot be picked up, the clamping force needs to be increased and then tried again until the object can be picked up. If the certain clamping force is too small, a lot of adjustment time is required; if the certain clamping force is too large, some dangerous objects (such as waste liquid barrels) may be damaged, resulting in serious consequences.

[0056] The present invention can adapt to the characteristics of a nuclear accident site where the types of objects to be transported span a wide range and the weight range span is also very large. According to the different types of target objects, different methods are used to accurately and efficiently directly determine their initial clamping force without the need for high calculation complexity. When the target object belongs to the first type and is not damaged, the corresponding preset clamping force is directly queried, and the appropriate initial clamping force can be quickly and accurately determined for transportation. When the target object belongs to the first type and is damaged or belongs to the second type, its weight information is analyzed to calculate the initial clamping force, and the accurate clamping force can also be obtained to clamp the object. Among them, through image analysis and processing, as well as the use of machine learning, the weight and size of the object to be transported can be quickly identified, thereby improving the degree of automation. The present invention does not require the robot to attempt to transport multiple times, reduces the adjustment time for transportation, and can also reduce the risk of damaging fragile or dangerous items.

[0057] S3. Controlling the transport robot to transport the target object according to the initial clamping force.

[0058] Before controlling the gripping assembly to contact the target object, the target object is approached with a small constant gripping force. After controlling the position of the gripping assembly relative to the target object to be within the adaptive adjustment range, the gripping drive assembly is controlled to drive the gripping assembly to close, and then the gripping surface of the gripping assembly and the target object is adjusted to the maximum, thereby clamping the target object. After contacting the target object, that is, when the robot arm clamps the target object, the model predictive control algorithm is used to adjust the actual gripping force of the robot arm to increase to the initial gripping force to reduce the adverse effects of system delay, and finally the robot arm is controlled to achieve the specified initial gripping force with a lower overshoot. Then the robot arm moves the target from A to B according to the set trajectory.

[0059] Among them, the model predictive control algorithm is used to adjust the actual clamping force of the robot arm to reach the initial clamping force, including:

[0060] S31. According to the actual clamping force and the initial clamping force, the target pressure parameter of the clamping drive assembly is calculated based on the model predictive control algorithm (MPC). Specifically, the actual clamping force of the clamping assembly is detected by a clamping force sensor installed on the clamping assembly. When the actual clamping force does not reach the initial clamping force, the required target pressure parameter is calculated based on the difference between the actual clamping force and the initial clamping force using the model predictive control algorithm to adjust the clamping force to reach the target value.

[0061] S32, obtaining actual pressure parameters of the clamping drive assembly.

[0062] S33. According to the actual pressure parameter and the target pressure parameter, a PID algorithm is used to perform PID feedback adjustment on the clamping drive component to control the clamping component to reach the clamping force corresponding to the target pressure parameter.

[0063] The clamping drive component controls the clamping force of the clamping component on the target object according to the pressure parameter. The clamping drive component of this embodiment adopts a clamping cylinder, and the clamping component adopts a clamping jaw. The pressure parameter refers to the working pressure inside the clamping cylinder. The clamping cylinder performs linear motion under different pressures to drive the opening and closing of the clamping jaw. This embodiment uses a high-frequency response proportional valve to adjust the action of the clamping cylinder, thereby controlling the working pressure inside the controller. The actual pressure parameter value inside the cylinder is measured in real time by the cylinder pressure sensor. When the actual pressure parameter does not reach the target pressure parameter, the output value of the high-frequency response proportional valve is corrected based on the PID algorithm in real time to achieve the target pressure parameter. This scheme can achieve low overshoot clamping force control through a dual closed-loop force control mode of cylinder pressure inner loop control + clamping force outer loop control.

[0064] This solution reduces overshoot, improves control accuracy, and improves the working efficiency of the handling robot.

[0065] The present invention also provides an embodiment of a transport control system of a nuclear accident rescue transport robot. The transport control system of the nuclear accident rescue transport robot can be applied to the transport control method of the nuclear accident rescue transport robot disclosed in the embodiment of the present invention.

[0066] like Figure 2 As shown, the transport control system includes: a clamping force determination module 10 and a transport control module 20 .

[0067] The clamping force determination module 10 is used to obtain image data of the target object, identify the type of the target object, and determine the initial clamping force of the target object according to the type. The handling control module 20 is used to control the handling robot to handle the target object according to the initial clamping force.

[0068] In this embodiment, the clamping force determination module 10 includes: a target recognition module 101 and a clamping force classification determination module 102 .

[0069] The target recognition module 101 is used to use the trained recognition model to recognize the image data and obtain the type of the target object.

[0070] The clamping force classification determination module 102 is used to obtain the specification information of the target object according to the image data analysis when the type of the target object belongs to the first type, and calculate the weight information based on the specification information to determine the initial clamping force. And when the type of the target object belongs to the second type, it is judged whether the target object is damaged. If it is not damaged, the preset clamping force corresponding to the query type is obtained to obtain the initial clamping force; if it is damaged, the specification information of the target object is obtained according to the image data analysis, and the weight information is calculated based on the specification information to determine the initial clamping force. Among them, the clamping force classification determination module obtains image data of the target object at different angles, and uses a binocular vision method to analyze and obtain volume information. Then, the weight information is calculated based on the volume information and material information, and the initial clamping force of the target object is further calculated and determined.

[0071] In this embodiment, the transport control module 20 includes a pressure parameter adjustment module 202 and a clamping force adjustment module 201 .

[0072] The pressure parameter adjustment module 202 is used to calculate the target pressure parameter of the clamping drive assembly based on the model predictive control algorithm according to the actual clamping force and the initial clamping force.

[0073] The clamping force adjustment module 201 is used to obtain the actual pressure parameters of the clamping drive component; according to the actual pressure parameters and the target pressure parameters, the PID algorithm is used to perform PID feedback adjustment on the clamping drive component to control the clamping component to achieve the clamping force corresponding to the target pressure parameters.

[0074] The present invention also provides a handling robot. In one embodiment, the robot includes the handling control system of the nuclear accident rescue handling robot disclosed in any embodiment of the present invention. By setting the handling control system, the handling robot can quickly and accurately determine the appropriate initial clamping force for handling, without having to make multiple handling attempts on the target object, reducing overshoot, improving control accuracy, and further improving the working efficiency and rescue efficiency of the handling robot, so that other rescue equipment or personnel can enter the accident site in time.

[0075] The present invention also provides a handling robot system, comprising a handling robot and a server. The server comprises a clamping force determination module 10 in the handling control system of the nuclear accident rescue handling robot disclosed in any embodiment of the present invention. The handling robot comprises a handling control module 20 in the handling control system of the nuclear accident rescue handling robot disclosed in any embodiment of the present invention.

[0076] In a specific embodiment, the clamping drive assembly of the robot's mechanical arm adopts a clamping cylinder, and the clamping assembly adopts a clamping claw. The robot also includes a main controller, a digital controller, a proportional valve, a clamping force sensor, and a cylinder pressure sensor. The main controller is connected to the digital controller and the clamping force sensor, the digital controller is connected to the proportional valve and the cylinder pressure sensor, the proportional valve is connected to the clamping cylinder, and the clamping cylinder is connected to the clamping claw. The clamping force sensor is used to measure the actual clamping force of the clamping claw. The cylinder pressure sensor is used to measure the actual pressure inside the clamping cylinder. The pressure parameter adjustment module is set in the main controller, and the clamping force adjustment module is set in the digital controller.

[0077] After the server determines the initial gripping force of the target object, it sends it to the main controller of the handling robot. Figure 3 As shown, the main controller receives the initial clamping force and the actual clamping force fed back by the clamping force sensor in real time, calculates the desired cylinder pressure parameters (target pressure parameters), and sends them to the digital controller. The digital controller controls the high-frequency response proportional valve to prompt the clamping cylinder to push the clamping claw to clamp the target object. The cylinder pressure sensor feeds back the actual cylinder pressure to the digital controller in real time. The digital controller uses the PID algorithm to correct the output value of the high-frequency response proportional valve in real time according to the feedback information, thereby achieving the desired cylinder pressure parameters. This solution can achieve low overshoot clamping force control through the dual closed-loop force control mode of cylinder pressure inner loop control + clamping force outer loop control.

[0078] This solution sets the clamping force determination module 10 in the server, which can improve computing performance, more efficiently determine the initial clamping force of the target object, reduce the cost and weight of the transport robot, and help the transport robot work efficiently at the nuclear accident site.

[0079] It can be understood that the above embodiments only express the preferred implementation modes of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the patent scope of the present invention. It should be pointed out that, for ordinary technicians in this field, the above technical features can be freely combined without departing from the concept of the present invention, and several deformations and improvements can be made, which all belong to the protection scope of the present invention. Therefore, all equivalent changes and modifications made to the scope of the claims of the present invention should belong to the coverage of the claims of the present invention.

Claims

1. A method for controlling the transport of a nuclear accident rescue transport robot, characterized in that: The following steps are involved: Acquire image data of a target object and identify the type of the target object; Determine the initial clamping force of the target object according to the type; wherein, if the type of the target object belongs to the first type, determine whether the target object is damaged, and if not damaged, query the preset clamping force corresponding to the type to obtain the initial clamping force; The transport robot is controlled to transport the target object according to the initial clamping force.

2. The method for controlling the transport of a nuclear accident rescue transport robot according to claim 1, characterized in that: The type of the target object obtained by identification includes: The image data is identified using a trained recognition model to obtain the type of the target object.

3. The method for controlling the transport of a nuclear accident rescue transport robot according to claim 1, characterized in that: Determining the initial clamping force of the target object according to the type includes: If the type of the target object belongs to the second type, the specification information of the target object is obtained according to the image data analysis, and the weight information is calculated based on the specification information to determine the initial clamping force.

4. The method for controlling the transport of a nuclear accident rescue transport robot according to claim 1, characterized in that: After determining whether the target object is damaged, the method further includes: If damaged, the specification information of the target object is obtained according to the analysis of the image data, and the weight information is calculated based on the specification information to determine the initial clamping force.

5. The method for controlling the transport of a nuclear accident rescue transport robot according to claim 3 or 4, characterized in that: The specification information includes volume information, and the specification information of the target object obtained by analyzing the image data includes: Image data of the target object at different angles are acquired, and the volume information is obtained by analyzing the image data using a binocular vision method.

6. The method for controlling the transport of a nuclear accident rescue transport robot according to claim 1, characterized in that: The transport robot includes a mechanical arm, and controlling the transport robot to transport the target object according to the initial clamping force includes: After the robotic arm clamps the target object, a model predictive control algorithm is used to adjust the actual clamping force of the robotic arm to reach the initial clamping force.

7. The method for controlling the transport of a nuclear accident rescue transport robot according to claim 6, characterized in that: The mechanical arm comprises a clamping drive component and a clamping component, wherein the clamping drive component controls the clamping force of the clamping component on the target object according to a pressure parameter; and the method of using a model predictive control algorithm to adjust the actual clamping force of the mechanical arm to reach the initial clamping force comprises: According to the actual clamping force and the initial clamping force, a target pressure parameter of the clamping drive assembly is calculated based on a model predictive control algorithm; Acquiring actual pressure parameters of the clamping drive assembly; According to the actual pressure parameter and the target pressure parameter, a PID algorithm is used to perform PID feedback regulation on the clamping drive assembly to control the clamping assembly to achieve a clamping force corresponding to the target pressure parameter.

8. A handling control system for a nuclear accident rescue handling robot, applied to the handling control method for a nuclear accident rescue handling robot according to any one of claims 1 to 7, characterized in that: include: A clamping force determination module, used to obtain image data of a target object and identify the type of the target object; determining an initial gripping force of the target object according to the type; The clamping force determination module includes: a clamping force classification determination module, which is used to determine whether the target object is damaged when the type of the target object belongs to the first type, and if not damaged, query the preset clamping force corresponding to the type to obtain the initial clamping force; A transport control module is used to control the transport robot to transport the target object according to the initial clamping force.

9. The handling control system of the nuclear accident rescue handling robot according to claim 8, characterized in that: The clamping force determination module also includes: The target recognition module is used to use the trained recognition model to recognize the image data and obtain the type of the target object.

10. The handling control system of the nuclear accident rescue handling robot according to claim 9, characterized in that: The clamping force classification determination module is further configured to, when the type of the target object belongs to the second type, obtain specification information of the target object according to the image data analysis, calculate the weight information based on the specification information, and thereby determine the initial clamping force; And when the type of the target object belongs to the second type, it is determined whether the target object is damaged. If damaged, the specification information of the target object is obtained according to the image data analysis, and the weight information is calculated based on the specification information to determine the initial clamping force.

11. The handling control system of the nuclear accident rescue handling robot according to claim 8, characterized in that: The handling control module includes a pressure parameter adjustment module and a clamping force adjustment module; The pressure parameter adjustment module is used to calculate the target pressure parameter of the clamping drive assembly based on the model predictive control algorithm according to the actual clamping force and the initial clamping force; The clamping force adjustment module is used to obtain the actual pressure parameter of the clamping drive component; according to the actual pressure parameter and the target pressure parameter, a PID algorithm is used to perform PID feedback adjustment on the clamping drive component to control the clamping component to reach the clamping force corresponding to the target pressure parameter.

12. A transport robot, characterized in that: A transport control system comprising the nuclear accident rescue transport robot as described in any one of claims 8-11.

13. A handling robot system, characterized in that: Including handling robots and servers; The transport robot comprises a transport control module of a transport control system of a nuclear accident rescue transport robot according to any one of claims 8 to 11; The server comprises a clamping force determination module of the transport control system of the nuclear accident rescue transport robot as described in any one of claims 8-11.

Images