Depth-camera-based control method for six-axis robotic arm for oil filling in nuclear power plant

Abstract

A depth-camera-based control method for a six-axis robotic arm for oil filling in a nuclear power plant. The depth-camera-based control method for a six-axis robotic arm for oil filling in a nuclear power plant comprises an environment sensing and modeling step, a target recognition and positioning step, a path planning and obstacle avoidance step, a motion control and execution step, and a real-time monitoring and feedback step. In the control method, depth-camera-based control for oil filling in a nuclear power plant is designed, so as to solve the problems in the prior art of the safety being low, the efficiency being low and the accuracy being insufficient, thereby enabling a precise oil filling operation of a robotic arm in a complex environment of a nuclear power plant.

Description

A control method for a six-axis robotic arm for nuclear power plant oil injection based on a depth camera Technical Field

[0001] This application belongs to the field of robot control technology, specifically relating to a control method for a six-axis robotic arm for nuclear power plant oil injection based on a depth camera. Background Technology

[0002] As a high-energy environment, the operational safety and reliability of equipment in nuclear power plants are paramount. Lubrication and oiling are crucial for ensuring normal operation and extending the lifespan of equipment. Traditional manual oiling methods suffer from high safety risks, low efficiency, and insufficient accuracy. Regarding high safety risks, the complex environment of nuclear power plants presents hazards such as radiation, high temperatures, and high pressures; manual operation could expose personnel to these dangers, posing serious safety risks. In terms of low efficiency, manual operation is limited by the skill level and workload of personnel, making it difficult to meet the high-efficiency maintenance requirements of nuclear power plants. Regarding insufficient accuracy, manual oiling may suffer from positioning errors and inaccurate oil volume, affecting the lubrication effect and operational reliability of the equipment.

[0003] Currently, some mechanical equipment has been applied to the maintenance work of nuclear power plants, such as bolt tension measurement, plug installation, and high-level radioactive waste recovery. However, it still has shortcomings in precise operation in complex environments and cannot completely replace manual labor.

[0004] For example, Patent 1 (publication number CN117911359A) discloses a vision-based 6D pose grasping method for a robotic arm. This method uses a depth camera to acquire target point cloud images, which are then recognized by a YOLOv5 network. The target pose is calculated using the SVD algorithm, and finally, the robotic arm is controlled to grasp the target through hand-eye calibration. This patent mainly focuses on vision-based 6D pose grasping and does not involve oil filling operations in the nuclear power field.

[0005] Patent 2 (publication number CN117124332A) discloses a robotic arm control method and system based on AI vision grasping. This system integrates radar and AI recognition technology to accurately locate the object to be grasped and plan the robotic arm's running route to avoid obstacles, thereby improving operational safety. This patent emphasizes the combination of AI vision and radar and is mainly used for grasping general objects; it is not specifically designed for nuclear power plant oil filling operations.

[0006] Patent 3 (publication number CN112936275A) discloses a robotic arm grasping system and control method based on a depth camera. This system acquires images through a depth camera, uses deep learning algorithms to calculate the optimal grasping point pose of the target object, and controls the robotic arm to grasp it. This patent focuses on grasping general objects and does not cover specific applications in the nuclear power field.

[0007] Patent 4 (CN111881772A) discloses a multi-robotic arm collaborative assembly method and system based on deep reinforcement learning: this method utilizes a multi-source heterogeneous sensor network, combined with deep reinforcement learning, to achieve collaborative assembly of multiple robotic arms. This patent focuses on the collaborative assembly of multiple robotic arms and does not involve the specific operation of nuclear power plant oil injection.

[0008] Patent 5 (CN114263840A) discloses an automatic oil injection device and a method for manufacturing an automatic oil injection system for the nuclear industry, and Patent 6 (CN106884923A) discloses a vacuum oil injection system and method for a hydraulic damper in a nuclear power plant. However, these patents mainly focus on the mechanical structure design of the oil injection device and the vacuum oil injection method, without addressing control methods based on depth cameras. Although the use of robots for operation is mentioned, the control method for a six-axis robotic arm, especially the control strategy based on vision sensors, is not described in detail. Summary of the Invention

[0009] In view of this, this application aims to provide a control method for a six-axis robotic arm for nuclear power plant oil injection based on a depth camera. By designing a depth camera-based control method for nuclear power plant oil injection, this method addresses the problems of low safety, low efficiency, and insufficient accuracy in existing technologies, and enables precise oil injection operations of the robotic arm in the complex environment of a nuclear power plant.

[0010] The first aspect of this application provides a control method for a six-axis robotic arm for nuclear power plant oil injection based on a depth camera. This method includes: an environmental perception and modeling step: using a radiation-resistant 3D laser depth camera mounted at the end of the robotic arm to acquire real-time 3D point cloud data of the robotic arm's working area; the control system preprocesses the data using voxel filtering and statistical filtering algorithms to construct a 3D environment model; a target recognition and localization step: the control system uses an improved PointNet++ deep learning network based on self-attention mechanism and multi-scale feature aggregation to classify and segment the preprocessed point cloud data; combined with the equipment's CAD model, an improved ICP algorithm is used for precise registration to obtain the precise position and attitude of the oil injection target; a path planning and obstacle avoidance step: based on the robotic arm's kinematic model and the environment model, the control system uses an improved RRT* algorithm combined with an artificial potential field method to plan the optimal obstacle avoidance path that satisfies the robotic arm's motion constraints; and a motion control and execution step: the control system uses a model predictive control algorithm to convert the planned path into joint motion commands for the robotic arm; combined with a force / position hybrid control strategy, the control arm executes the oil injection operation in real time. Real-time monitoring and feedback steps: Continuously acquire environmental data using a depth camera, detect environmental changes, dynamically update the 3D model and path planning, and trigger a redundant safety mechanism to automatically stop the robotic arm's movements when an anomaly or emergency is detected.

[0011] In one specific implementation of this application, a self-attention mechanism is introduced into the PointNet++ deep learning network to calculate the importance weight of each point in the point cloud and enhance the feature representation of key feature points.

[0012] In one specific embodiment of this application, the improved ICP algorithm introduces a feature-based weighted matching method, employing KD-trees and nearest neighbor search algorithms.

[0013] In one specific embodiment of this application, in the path planning and obstacle avoidance steps, the cost function comprehensively considers the robot arm's energy consumption, path length, smoothness, and obstacle avoidance requirements, and uses a dynamic window method to predict and avoid moving obstacles.

[0014] In one specific embodiment of this application, the motion control and execution step employs an adaptive control strategy based on force / position hybrid control, adjusting control parameters in real time according to force feedback information.

[0015] A second aspect of this application provides a computer device including a processor and a memory. The processor is used to execute a six-axis robotic arm control method for nuclear power plant oil injection based on a depth camera, as described in the first aspect of this application. The memory is used to store executable instructions from the processor.

[0016] A third aspect of this application provides a computer-readable storage medium storing executable instructions for a computer. When executed by a processor, the executable instructions implement a six-axis robotic arm control method for nuclear power plant oil injection based on a depth camera, as described in the first aspect of this application.

[0017] The fourth aspect of this application provides a computer program product, including a computer program / instructions, which, when executed by a processor, implements the six-axis robotic arm control method for nuclear power plant oil injection based on a depth camera, as described in the first aspect of this application.

[0018] The beneficial effects of this technical solution are as follows: By combining an improved PointNet++ network and the ICP algorithm, high-precision target recognition and positioning of the robotic arm in the complex environment of a nuclear power plant are achieved, enabling precise oil injection operations. The improved path planning and control algorithms allow the robotic arm to complete oil injection operations safely and efficiently. This depth camera-based six-axis robotic arm control method for nuclear power plant oil injection offers advantages in terms of improved safety, enhanced adaptability, increased efficiency, and technological advantages. Regarding improved safety, it reduces personnel operations in high-risk environments, lowering the risk of radiation exposure. In terms of enhanced adaptability, this depth camera-based six-axis robotic arm control method can perceive environmental changes in real time and dynamically adjust the path to adapt to the complex and ever-changing working environment of a nuclear power plant. Regarding improved efficiency, this depth camera-based six-axis robotic arm control method for nuclear power plant oil injection has a high degree of automation, reducing oil injection operation time by approximately 50% compared to manual methods, thus improving equipment maintenance efficiency. In terms of technological advantages, this depth camera-based six-axis robotic arm control method for nuclear power plant oil injection outperforms existing technologies in target recognition accuracy, path planning efficiency, and control accuracy, demonstrating significant technological advantages. Attached Figure Description

[0019] Figure 1 shows a schematic diagram of the structure of a nuclear power plant oil injection robot provided in an embodiment of this application.

[0020] Figure 2 is a simplified flowchart illustrating a control method for a six-axis robotic arm for nuclear power plant oil injection based on a depth camera, according to an embodiment of this application.

[0021] Figure 3 shows an improved PointNet++ network structure provided in an embodiment of this application.

[0022] Figure 4 shows an improved PointNet++ network structure provided in another embodiment of this application. Detailed Implementation

[0023] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0024] At least one embodiment of this application provides a control method for a six-axis robotic arm for nuclear power plant oil injection based on a depth camera. This control method can be implemented using a nuclear power plant oil injection robot. Referring to Figure 1, the nuclear power plant oil injection robot may include a depth camera, a control system, and a robotic arm. Referring to Figure 2, the control method for the six-axis robotic arm for nuclear power plant oil injection based on a depth camera includes the following steps.

[0025] Environmental perception and modeling steps: Real-time 3D point cloud data of the working area of ​​the robotic arm is acquired using a radiation-resistant 3D laser depth camera installed at the end of the robotic arm. The control system uses voxel filtering and statistical filtering algorithms to preprocess the data and construct a 3D environment model.

[0026] Target recognition and localization steps: The control system uses an improved PointNet++ deep learning network based on self-attention mechanism and multi-scale feature aggregation to classify and segment the preprocessed point cloud data. Combined with the equipment's CAD model, an improved ICP algorithm is used for precise registration to obtain the precise position and orientation of the oil injection target.

[0027] Path planning and obstacle avoidance steps: Based on the kinematic model of the robotic arm and the environmental model, the control system uses an improved RRT* (Fast Random Tree) algorithm combined with the artificial potential field method to plan the optimal obstacle avoidance path that satisfies the motion constraints of the robotic arm.

[0028] Motion control and execution steps: The control system adopts the model predictive control (MPC) algorithm to convert the planned path into joint motion commands of the robotic arm. Combined with the force / position hybrid control strategy, it controls the robotic arm to perform the oil injection operation in real time.

[0029] Real-time monitoring and feedback steps: Continuously acquire environmental data using a depth camera, detect environmental changes, dynamically update the 3D model and path planning, and trigger a redundant safety mechanism to automatically stop the robotic arm's movements when an anomaly or emergency is detected.

[0030] It should be noted that the 3D environment model can be a high-precision 3D environment model. A high-precision 3D laser depth camera can be used. The 3D environment model can include the position and shape information of equipment, obstacles, and oil injection targets.

[0031] According to the technical solution provided in this application, by combining an improved PointNet++ network and the ICP algorithm, high-precision target recognition and positioning of the robotic arm in the complex environment of a nuclear power plant is achieved, enabling precise oil injection operations. The improved path planning and control algorithms allow the robotic arm to complete oil injection operations safely and efficiently. This depth camera-based six-axis robotic arm control method for nuclear power plant oil injection has beneficial effects in terms of improved safety, enhanced adaptability, increased efficiency, and technological advantages. In terms of improved safety, it reduces personnel operations in high-risk environments, lowering the risk of radiation exposure. In terms of enhanced adaptability, this depth camera-based six-axis robotic arm control method for nuclear power plant oil injection can perceive environmental changes in real time and dynamically adjust the path to adapt to the complex and ever-changing working environment of a nuclear power plant. In terms of improved efficiency, this depth camera-based six-axis robotic arm control method for nuclear power plant oil injection has a high degree of automation, reducing oil injection operation time by approximately 50% compared to manual methods, thus improving equipment maintenance efficiency. In terms of technological advantages, this depth camera-based six-axis robotic arm control method for nuclear power plant oil injection outperforms existing technologies in target recognition accuracy, path planning efficiency, and control accuracy, demonstrating significant technological advantages.

[0032] It should be noted that an improved PointNet++ deep learning network is used to classify and segment the preprocessed point cloud data, as shown in Figures 3 and 4. Considering the characteristics of the nuclear power plant environment, the PointNet++ network was improved in the following ways: 1. Data Augmentation: CAD models of nuclear power equipment are used to generate diverse training samples, increasing the network's adaptability to complex shapes and materials. 2. Multi-Scale Feature Extraction: A multi-scale feature aggregation module is introduced to capture the local and global geometric features of the equipment, improving the ability to recognize complex structures. 3. Attention Mechanism: An attention mechanism is added to the network to strengthen the focus on key feature points and improve recognition accuracy.

[0033] Using CAD models of nuclear power plant equipment, an improved ICP (Iterative Nearest Point) algorithm was employed for accurate registration. The improved ICP algorithm includes: 1. Weighted Matching: Introducing point cloud feature weights, assigning higher weights to key feature points to reduce mismatches. 2. Dynamic Threshold Adjustment: Dynamically adjusting the distance threshold based on the matching error to filter out outliers and improve the robustness of registration. 3. Accelerated Convergence: Employing KD-trees and nearest neighbor search algorithms to improve computational efficiency and shorten convergence time.

[0034] The improvements to the RRT* (Fast Random Tree) algorithm are as follows: 1. Cost function optimization: Optimizing path quality by considering the robot arm's energy consumption, path smoothness, and obstacle avoidance requirements. 2. Dynamic obstacle avoidance: Introducing a dynamic window method to predict and avoid moving obstacles, ensuring the real-time performance and safety of the path. 3. Constraints: Comprehensively considering the robot arm's joint angle limitations, speed limits, and load capacity to ensure the feasibility of the planned path.

[0035] The control system employs a Model Predictive Control (MPC) algorithm to convert the planned path into joint motion commands for the robotic arm. Specifically, this includes: 1. Dynamics Modeling: Establishing a dynamic and kinematic model of the robotic arm, considering factors such as joint friction, inertia, and load variations. 2. Adaptive Control: Adjusting control parameters in real time based on force and visual feedback information to compensate for system errors. 3. Precise Lubrication: During lubrication, combining data from force sensors, controlling the lubrication device to complete the lubrication operation with appropriate force and position.

[0036] In at least one embodiment of this application, a self-attention mechanism is introduced into the PointNet++ deep learning network to calculate the importance weight of each point in the point cloud and enhance the feature representation of key feature points.

[0037] In at least one embodiment of this application, the improved ICP algorithm introduces a feature-based weighted matching method, employing KD-trees and nearest neighbor search algorithms. Thus, by introducing a feature-based weighted matching method, points with significant features are assigned higher matching weights. The use of KD-trees and nearest neighbor search algorithms improves computational efficiency.

[0038] In at least one embodiment of this application, in the path planning and obstacle avoidance steps, the cost function comprehensively considers the energy consumption, path length, smoothness and obstacle avoidance requirements of the robotic arm, and uses the dynamic window method to predict and avoid moving obstacles.

[0039] In at least one embodiment of this application, an adaptive control strategy based on force / position hybrid control is employed in the motion control and execution steps, adjusting control parameters in real time according to force feedback information. This ensures the accuracy of the oil injection operation by adjusting control parameters in real time based on force feedback information.

[0040] The technical solution of the present invention will be described in detail below with reference to specific embodiments.

[0041] 1. Experimental Environment

[0042] Equipment: Nuclear power plant electrical system

[0043] Robotic arm: Six-axis industrial robotic arm, load capacity 20kg, repeatability ±0.08mm

[0044] Depth Camera: An industrial-grade 3D laser depth camera with radiation-resistant design, offering a measurement accuracy of ±0.5mm.

[0045] Moving obstacles: Simulates mobile devices or personnel that may appear in a nuclear power plant.

[0046] 2. Experimental Procedure

[0047] (1) Environmental perception and modeling steps

[0048] The depth camera is activated to perform real-time scanning of the motor system and its surrounding environment, acquiring high-precision 3D point cloud data.

[0049] Voxel filtering and statistical filtering algorithms are used to preprocess point cloud data to remove noise and outliers.

[0050] Construct a high-precision three-dimensional environment model that includes pipes, valves, and support structures.

[0051] (2) Target identification and localization steps

[0052] By using an improved PointNet++ network, target classification and segmentation were performed on the preprocessed point cloud data, and the location of the valve that needed to be injected with oil was successfully identified.

[0053] By introducing data augmentation and attention mechanisms, the accuracy of target recognition in complex environments has been improved.

[0054] By combining the valve's CAD model, an improved ICP algorithm is used for precise registration, with a positioning error of less than ±1mm.

[0055] (3) Path planning and obstacle avoidance steps

[0056] Based on the kinematic model of the robotic arm, an improved RRT* algorithm is used to plan the optimal path from the initial position to the target valve.

[0057] By combining artificial potential field methods, avoid surrounding fixed obstacles, such as pipes and supporting structures.

[0058] Because there are moving obstacles in the environment, a dynamic window method is used to predict and avoid them, and the path planning is updated in real time.

[0059] (4) Motion control and execution steps

[0060] The MPC algorithm is used to convert the planned path into joint motion commands for the robotic arm.

[0061] During the movement, the force feedback information of the robotic arm is monitored in real time to perform error compensation and dynamic adjustment.

[0062] An adaptive control strategy based on force / position hybrid control is adopted to ensure the accuracy of the oil injection operation.

[0063] (5) Real-time monitoring and feedback steps

[0064] The depth camera continuously acquires environmental data, monitoring changes in the surrounding environment and the location of moving obstacles.

[0065] When a new obstacle or emergency is detected, the system immediately updates the environmental model and path planning.

[0066] The redundant safety mechanism is triggered, the robotic arm automatically stops its operation and issues an alarm to ensure safety.

[0067] 3. Experimental Results

[0068] Target recognition accuracy: In complex environments, the target recognition accuracy reaches over 98%.

[0069] Positioning accuracy: The positioning error of the oil injection target is controlled within ±1mm.

[0070] Oiling operation time: The time for a single oiling operation is reduced by about 60% compared to manual methods, which significantly improves efficiency.

[0071] Radiation safety: The oil injection process no longer requires human intervention.

[0072] At least one embodiment of this application also provides a computer device including a processor and a memory. The processor is used to execute a six-axis robotic arm control method for nuclear power plant oil injection based on a depth camera, as provided in any of the above embodiments of this application. The memory is used to store executable instructions of the processor, such as application programs. There can be one or more processors. The application programs stored in the memory can include one or more modules, each corresponding to a set of instructions. Furthermore, the processor is configured to execute instructions to perform the above-described six-axis robotic arm control method for nuclear power plant oil injection based on a depth camera.

[0073] The computer device may also include a power supply component configured for power management, a wired or wireless network interface configured to connect the computer device to a network, and an input / output (I / O) interface. The computer device can operate on an operating system stored in memory, such as Windows Server. TM Mac OSX TM Unix TM Linux TM FreeBSD TM Or similar.

[0074] At least one embodiment of this application also provides a computer-readable storage medium storing executable instructions for a computer. When executed by a processor, the executable instructions implement a six-axis robotic arm control method for nuclear power plant oil injection based on a depth camera, as provided in any of the above embodiments of this application.

[0075] A non-transitory computer-readable storage medium, when the instructions in the storage medium are executed by the processor of the computer device, enables the computer device to perform the aforementioned depth camera-based control method for a six-axis robotic arm used for nuclear power plant oil injection. This depth camera-based control method for a six-axis robotic arm used for nuclear power plant oil injection is executed by an agent program.

[0076] Those skilled in the art will recognize that the algorithmic steps of the various examples described in conjunction with the embodiments disclosed in this application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0077] At least one embodiment of this application also provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements a six-axis robotic arm control method for nuclear power plant oil injection based on a depth camera provided in any of the above embodiments of this application.

[0078] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a computer program product. This computer program product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the six-axis robotic arm control method for nuclear power plant oil injection based on a depth camera, as described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program verification codes, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0079] It should be noted that the combination of the technical features in the embodiments of this application is not limited to the combination methods described in the embodiments of this application or the combination methods described in specific embodiments. All technical features described in this application can be freely combined or combined in any way, unless they contradict each other.

[0080] As indicated in this application and claims, unless the context clearly indicates otherwise, the words "a," "an," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the term "comprising" only indicates that it includes the explicitly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0081] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.

[0082] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications or equivalent substitutions made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A control method for a six-axis robotic arm for nuclear power plant oil injection based on a depth camera, characterized in that, include: Environmental perception and modeling steps: Real-time 3D point cloud data of the working area of ​​the robotic arm is acquired using a radiation-resistant 3D laser depth camera installed at the end of the robotic arm. The control system uses voxel filtering and statistical filtering algorithms to preprocess the data and construct a 3D environment model. Target identification and localization steps: The control system adopts an improved PointNet++ deep learning network based on self-attention mechanism and multi-scale feature aggregation to classify and segment the preprocessed point cloud data. Combined with the CAD model of the nuclear power equipment, the improved ICP algorithm is used for accurate registration to obtain the precise position and attitude of the oil injection target. Path planning and obstacle avoidance steps: Based on the kinematic model of the robotic arm and the environmental model, the control system uses an improved RRT* algorithm combined with the artificial potential field method to plan the optimal obstacle avoidance path that satisfies the motion constraints of the robotic arm. Motion control and execution steps: The control system adopts a model predictive control algorithm to convert the planned path into joint motion commands of the robotic arm. Combined with a force / position hybrid control strategy, it controls the robotic arm to perform the oil injection operation in real time.

2. The control method for a six-axis robotic arm for nuclear power plant oil injection based on a depth camera according to claim 1, characterized in that, The PointNet++ deep learning network introduces a self-attention mechanism to calculate the importance weights of each point in the point cloud, thereby enhancing the feature representation of key feature points.

3. The control method for a six-axis robotic arm for nuclear power plant oil injection based on a depth camera according to claim 1, characterized in that, The improved ICP algorithm introduces a feature-based weighted matching method and employs KD-trees and nearest neighbor search algorithms.

4. The control method for a six-axis robotic arm for nuclear power plant oil injection based on a depth camera according to claim 1, characterized in that, In the path planning and obstacle avoidance steps, the cost function comprehensively considers the robot arm's energy consumption, path length, smoothness, and obstacle avoidance requirements, and uses the dynamic window method to predict and avoid moving obstacles.

5. A control method for a six-axis robotic arm for nuclear power plant oil injection based on a depth camera, as described in any one of claims 1 to 4, characterized in that, In the motion control and execution steps, an adaptive control strategy based on force / position hybrid control is adopted, and the control parameters are adjusted in real time according to the force feedback information.

6. A computer device, characterized in that, include: A processor for executing the nuclear power plant oil injection six-axis robotic arm control method based on a depth camera as described in any one of claims 1 to 5; as well as Memory for storing the executable instructions of the processor.

7. A computer-readable storage medium having executable instructions stored thereon, characterized in that, When the executable instructions are executed by the processor, they implement the control method for a six-axis robotic arm for nuclear power plant oil injection based on a depth camera, as described in any one of claims 1 to 5.

8. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the control method for a six-axis robotic arm for nuclear power plant oil injection based on a depth camera, as described in any one of claims 1 to 5.

Images