Humanoid robot welding method, apparatus, and humanoid robot

Abstract

The present application relates to the technical field of robot control, and provides a humanoid robot welding method, device and humanoid robot, the method comprising: in the process of walking and welding of the humanoid robot, determining walking parameters of the humanoid robot at the next moment based on the center of gravity variation of the humanoid robot at the current moment; in the process of walking and welding of the humanoid robot, determining the pose of the welding robot arm at the next moment based on the welding trajectory deviation of the welding robot arm at the current moment, the walking parameters at the next moment, the pose of the welding robot arm at the current moment and the preset welding trajectory; and controlling the welding of the welding robot arm based on the pose at the next moment. The present application can realize accurate control of the welding trajectory, ensure that the welding arc is always located on the center line of the weld, improve the welding quality, and further ensure the precision, continuity and welding quality of the humanoid robot in welding long welds.

Description

Technical Field

[0001] The present invention relates to the field of robot control technology, and in particular to a humanoid robot welding method, device and humanoid robot. Background Art

[0002] Humanoid robot welding refers to the process of applying humanoid robots to welding operations, utilizing their flexibility and autonomy to complete welding tasks in complex environments.

[0003] Although humanoid robots can imitate human movements and have certain autonomous navigation and path planning capabilities, during the welding process, due to the complexity of their own movements and interference from the external environment, the actual welding trajectory of humanoid robots can easily deviate from the target weld, thereby causing quality problems such as discontinuous weld joints, poor weld formation, or uneven weld strength. Summary of the Invention

[0004] The present invention provides a humanoid robot welding method, device and humanoid robot, which are used to solve the defects in the prior art.

[0005] The present invention provides a humanoid robot welding method, comprising the following steps:

[0006] During the walking welding process of the humanoid robot, the walking parameters of the humanoid robot at the next moment are determined based on the center of gravity change of the humanoid robot at the current moment, where the center of gravity change at the current moment refers to the deviation between the center of gravity position at the current moment and the center of gravity position at the previous moment;

[0007] During the walking welding process of the humanoid robot, the posture of the welding robot arm at the next moment is determined based on the welding trajectory deviation of the welding robot arm at the current moment, the walking parameters at the next moment, the posture of the welding robot arm at the current moment, and the preset welding trajectory. The welding trajectory deviation at the current moment refers to the deviation between the actual welding trajectory of the welding robot arm at the current moment and the center line of the target weld;

[0008] Based on the posture at the next moment, the welding robot arm is controlled to weld.

[0009] According to a humanoid robot welding method provided by the present invention, determining the walking parameters of the humanoid robot at the next moment based on the change in the center of gravity of the humanoid robot at the current moment includes:

[0010] Obtaining the current motion state of the humanoid robot;

[0011] Inputting the motion state at the current moment and the center of gravity change at the current moment into a reinforcement learning model to obtain the walking parameters at the next moment output by the reinforcement learning model;

[0012] The reinforcement learning model is trained with the goal of minimizing a reward value, and the reward value is determined based on a change in the center of gravity of the humanoid robot.

[0013] According to a humanoid robot welding method provided by the present invention, the method determines the posture of the welding robot arm at the next moment based on the welding trajectory deviation of the welding robot arm at the current moment, the walking parameters at the next moment, the posture of the welding robot arm at the current moment, and the preset welding trajectory, including:

[0014] Based on the preset welding trajectory, a dynamic model of the humanoid robot during walking is constructed, wherein the dynamic model is used to describe the motion relationship and force conditions between various components of the humanoid robot during walking, as well as the kinematic constraints of the welding robot arm;

[0015] Determining an optimal adjustment path and posture compensation amount of the welding robot arm based on the dynamic model, the welding trajectory deviation at the current moment, the walking parameters at the next moment, and the posture of the welding robot arm at the current moment;

[0016] Based on the optimal adjustment path and the posture compensation amount, the posture of the welding robot arm at the next moment is determined.

[0017] According to a humanoid robot welding method provided by the present invention, the steps of acquiring the motion state and the posture at the current moment are as follows:

[0018] Collecting the initial motion state and initial posture at the current moment through sensors;

[0019] Filtering the initial motion state at the current moment to obtain the motion state at the current moment;

[0020] The initial posture at the current moment is filtered to obtain the posture at the current moment.

[0021] A humanoid robot welding method according to the present invention further includes:

[0022] When the change in the center of gravity at the current moment is greater than a first threshold, and / or the welding trajectory deviation at the current moment is greater than a second threshold, an early warning prompt is issued.

[0023] The present invention also provides a humanoid robot welding device, comprising the following modules:

[0024] a first determining unit configured to determine, during the walking welding process of the humanoid robot, walking parameters of the humanoid robot at a next moment based on a center of gravity change of the humanoid robot at a current moment, wherein the center of gravity change at the current moment refers to a deviation between the center of gravity position at the current moment and the center of gravity position at a previous moment;

[0025] a second determining unit, configured to determine, during the walking welding process of the humanoid robot, a posture of the welding robot arm at a next moment based on a welding trajectory deviation of the welding robot arm at a current moment, walking parameters at the next moment, a posture of the welding robot arm at a current moment, and a preset welding trajectory, wherein the welding trajectory deviation at the current moment refers to a deviation between an actual welding trajectory of the welding robot arm at the current moment and a center line of a target weld;

[0026] The welding unit is used to control the welding robot arm to weld based on the posture at the next moment.

[0027] The present invention also provides a humanoid robot, comprising: a robot body, a welding robot arm installed on the robot body, and the humanoid robot welding device as described above.

[0028] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, any one of the above-described humanoid robot welding methods is implemented.

[0029] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described humanoid robot welding methods.

[0030] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any one of the above-described humanoid robot welding methods.

[0031] The humanoid robot welding method, device, and robot provided by the present invention achieve balance control during the walking process of the humanoid robot by monitoring the change in the humanoid robot's center of gravity in real time and dynamically adjusting its walking parameters, ensuring that the humanoid robot remains stable during walking and providing a reliable platform for welding operations. Furthermore, by comprehensively considering welding trajectory deviation, walking parameters, the current position of the welding robot arm, and the preset welding trajectory, the present invention precisely controls the position of the welding robot arm at the next moment, achieving precise control of the welding trajectory, ensuring that the welding arc is always located on the centerline of the weld, improving welding quality, and thereby ensuring the accuracy, continuity, and quality of the humanoid robot's welding of long welds. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort on the basis of these drawings.

[0033] Figure 1 is a flowchart of the welding method of the humanoid robot provided by the present application.

[0034] Figure 2 is a flowchart of the gravity control of the humanoid robot provided by the present application.

[0035] Figure 3 is a flowchart of the pose adjustment of the welding robot arm provided by the present application.

[0036] Figure 4 is a structural diagram of the welding device of the humanoid robot provided by the present application.

[0037] Figure 5 is a structural diagram of the electronic device provided by the present application. DETAILED DESCRIPTION

[0038] In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely below in combination with the drawings in the present application. Obviously, the described embodiments are some embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without any creative effort belong to the protection scope of the present application.

[0039] At present, in the long-welding seam welding operation, the humanoid robot is difficult to meet the requirement of welding while walking. The main problems are as follows: (1) dynamic balance problem: the position of the gravity center of the robot changes continuously during walking, which is easy to cause vibration, tilting or instability, etc., and further causes the welding seam to deviate during the welding process, thereby affecting the welding quality. (2) It is difficult to accurately maintain the welding trajectory: when the robot is walking, the welding robot arm needs to be synchronized to maintain a relatively stable posture with the welding seam. However, there are deficiencies in accurately maintaining the welding trajectory during walking at present, which is easy to cause the welding joint to be discontinuous or the welding quality to be uneven, etc.

[0040] In view of this, the present application provides a humanoid robot welding method, which solves the problems of difficult to maintain dynamic balance and difficult to accurately maintain welding trajectory during the walking welding process of the humanoid robot.

[0041] wherein, Figure 1 is a flowchart of the welding method of the humanoid robot provided by the present application, as Figure 1As shown, the method includes step 110 , step 120 and step 130 .

[0042] Step 110: During the walking welding process of the humanoid robot, the walking parameters of the humanoid robot at the next moment are determined based on the center of gravity change of the humanoid robot at the current moment. The center of gravity change at the current moment refers to the deviation between the center of gravity position at the current moment and the center of gravity position at the previous moment.

[0043] Here, the center of gravity change at the current moment refers to the vector difference between the humanoid robot's center of gravity position at the current moment and its previous moment, and is used to measure the humanoid robot's balance state and movement trend. The greater the center of gravity change at the current moment, the more unstable the humanoid robot's current balance state is, and there is a risk of tipping over or experiencing large vibrations. In this case, the walking parameters need to be adjusted to quickly restore the balance state and reduce the center of gravity shift. The center of gravity change at the current moment can be directly measured using an inertial measurement unit (IMU) installed on the robot, or it can be calculated by calculating the kinematic data of each joint of the robot. For example, based on the kinematic data, the center of mass position of each component of the humanoid robot can be calculated using the forward kinematics formula. The center of gravity position at the current moment is then weighted averaged to obtain the difference between the current position and the previous moment.

[0044] The next-moment walking parameters refer to the set of instructions that control the humanoid robot's motion state at the next moment. This instruction set can include parameters such as step length, pace, gait cycle, stance phase duration, swing phase trajectory, hip joint height, and ankle joint angle. The walking parameters are determined based on the current center of gravity change. In other words, they are set to offset or reduce the current center of gravity change trend and maintain the robot's balance.

[0045] As an optional embodiment, the step length and speed of the next step can be adjusted based on the size of the change in the center of gravity at the current moment. When the change in the center of gravity is large, the step length and speed can be reduced, and the support time of the supporting leg can be increased to improve stability; when the change in the center of gravity is small, the step length and speed can be increased to improve walking efficiency.

[0046] Since the embodiment of the present invention takes the center of gravity change into consideration when determining the walking parameters, it can ensure that the humanoid robot can adjust its movement posture in a timely manner during walking, maintain balance, avoid tipping over, and ensure the dynamic balance of the humanoid robot during walking welding.

[0047] Step 120. During the walking welding process of the humanoid robot, the posture of the welding robot arm at the next moment is determined based on the welding trajectory deviation of the welding robot arm at the current moment, the walking parameters at the next moment, the posture of the welding robot arm at the current moment, and the preset welding trajectory. The welding trajectory deviation at the current moment refers to the deviation between the actual welding trajectory of the welding robot arm at the current moment and the center line of the target weld.

[0048] Specifically, the actual welding trajectory at the current moment refers to the path that the welding arc or the end of the welding gun on the welding robot arm actually moves on the surface of the welding workpiece during the welding process. The target weld center line refers to the pre-set center line of the weld, which is usually an ideal welding path determined in advance based on the geometric shape of the welding workpiece and the welding requirements. The greater the deviation between the two, the worse the welding quality, the more likely welding defects will occur, and even welding failure may occur.

[0049] A welding robot arm is a robotic arm mounted on a humanoid robot and used to perform welding tasks. The current pose refers to the position and posture of the end effector (usually a welding gun) of the welding robot arm in three-dimensional space, including position coordinates (X, Y, Z) and posture angles (such as Euler angles or quaternions). A preset welding trajectory refers to a pre-planned welding path based on the geometric shape of the welding workpiece and the welding process requirements, usually in the form of a series of ordered three-dimensional space points or curves.

[0050] Taking into account the changes in center of gravity and motion disturbances of the humanoid robot during walking, the motion accuracy of the welding robot arm is affected by the movement of the humanoid robot. There may be interference from the external environment during the welding process, such as wind force, temperature changes, etc., and the welding trajectory deviation at the current moment reflects the error of the current welding process and is an important basis for adjusting the posture of the robot arm. The walking parameters at the next moment affect the overall motion trend of the humanoid robot and have a constraining effect on the posture adjustment of the welding robot arm. The posture of the welding robot arm at the current moment is the basis for calculating the posture at the next moment and provides the current spatial state information of the robot arm. The preset welding trajectory gives an ideal welding path and is the target reference for posture adjustment. Therefore, the embodiment of the present invention determines the posture of the welding robot arm at the next moment based on the welding trajectory deviation at the current moment, the walking parameters at the next moment, the posture of the welding robot arm at the current moment, and the preset welding trajectory, so as to ensure that the actual welding trajectory of the welding robot arm coincides with the target weld as much as possible, reduce welding deviation, and thus ensure efficient and stable long weld mobile welding operations in complex working environments, thereby improving the quality of welds.

[0051] Step 130: Based on the posture at the next moment, control the welding robot arm to weld.

[0052] Specifically, the next-moment pose refers to the position and posture that the welding robot's end effector (welding gun) should reach during the next control cycle, and is used to guide the movement of the welding robot. Because the next-moment pose is determined based on the current welding trajectory deviation, the next-moment walking parameters, the welding robot's current pose, and the preset welding trajectory, it ensures that the welding robot minimizes welding trajectory deviation during movement, adheres to the preset welding trajectory, and coordinates with the walking motion of the humanoid robot. Therefore, when controlling the welding robot to perform welding based on the next-moment pose, precise welding trajectory control can be achieved, ensuring welding quality and improving welding efficiency.

[0053] As an optional embodiment, a PID controller or other motion control algorithm can be used to calculate the control instructions for each joint of the welding robot arm according to the posture at the next moment, drive the motor to move, and make the welding gun accurately reach the target position and posture.

[0054] The humanoid robot welding method provided by an embodiment of the present invention achieves balance control during the humanoid robot's walking process by monitoring the changes in the humanoid robot's center of gravity in real time and dynamically adjusting its walking parameters. This ensures the robot remains stable during walking and provides a reliable platform for welding operations. Furthermore, by comprehensively considering welding trajectory deviations, walking parameters, the welding robot's current position, and a preset welding trajectory, the embodiment of the present invention precisely controls the welding robot's position at the next moment, achieving precise control of the welding trajectory. This ensures that the welding arc remains centered on the weld seam, improving welding quality and, consequently, ensuring the accuracy, continuity, and quality of long welds made by the humanoid robot.

[0055] Based on the above embodiment, determining the walking parameters of the humanoid robot at the next moment based on the change in the center of gravity of the humanoid robot at the current moment includes:

[0056] Get the current motion state of the humanoid robot;

[0057] The current motion state and the center of gravity change at the current moment are input into the reinforcement learning model to obtain the walking parameters at the next moment output by the reinforcement learning model;

[0058] The reinforcement learning model is trained with the goal of minimizing the reward value, which is determined based on the change in the center of gravity of the humanoid robot.

[0059] Specifically, the motion state at the current moment refers to a set of information describing the current motion posture and speed of the humanoid robot, which can include parameters such as the angles, angular velocities, angular accelerations, postures of the trunk, linear velocities, angular velocities, center of gravity positions and speeds of each joint. Among them, the motion state at the current moment can be directly measured by sensors (such as encoders, gyroscopes, accelerometers, etc.) installed on the humanoid robot, or can be obtained by calculating the kinematics data of each joint of the robot, and the embodiments of the present application do not make specific limitations.

[0060] In addition, the reinforcement learning model refers to an intelligent decision-making model based on trial-and-error learning, which continuously learns and optimizes the strategy through interaction with the environment to achieve the set goal, which is trained to minimize the reward value, and the reward value is determined based on the center of gravity change amount of the humanoid robot, that is, the goal of the reinforcement learning model is to learn a walking strategy to make the humanoid robot maintain balance as much as possible during walking, reduce the center of gravity deviation, and thus obtain a higher reward.

[0061] Among them, the reinforcement learning model can be trained and optimized using algorithms such as proximal policy optimization (PPO), deep deterministic policy gradient (DDPG), etc., so that it can output appropriate walking parameters at the next moment according to the motion state at the current moment and the center of gravity change amount.

[0062] For example, a state space and an action space can be designed, where the state space includes parameters such as the current posture of the humanoid robot, the center of gravity position, the speed, the acceleration, etc., and the action space is the control instruction of each drive motor; the deep reinforcement learning algorithm (such as DDPG, PPO, etc.) is used to train the center of gravity control strategy during the walking process of the robot online, so that the humanoid robot can maintain stable motion of the center of gravity in a complex dynamic environment; a reward function is introduced during the training process, which comprehensively considers multiple indicators such as the balance of the robot (for example, the degree of deviation of the center of gravity from the center position of the weld seam), energy consumption, motion smoothness and welding trajectory stability. Among them, the design of the reward function needs to be adjusted according to the actual application scene, so that the humanoid robot can achieve adaptive center of gravity balance control during walking and achieve the best balance control effect.

[0063] Figure 2 is a schematic diagram of the center of gravity control process of the humanoid robot provided by the present application, as Figure 2As shown in the figure, sensors first collect the humanoid robot's current welding posture, including information such as welding position, center of gravity, and speed, in real time. Welding process parameters (voltage, current, speed, and swing) are also collected as input data. Next, the current state (S) is input into the policy (Actor) network. The policy network outputs the corresponding action (A) based on the current state, adjusting the humanoid robot's walking parameters to optimize the welding posture and maintain balance. The current state (S) includes the humanoid robot's current welding posture and welding process parameters.

[0064] At the same time, the target state (S') is input into the policy (Actor) target network to obtain the target action (A'). Furthermore, the current state (S) is processed with noise (noise) and then enters the value (critic) target network for the next step of network training. Meanwhile, the value (critic) network (consisting of value network 1 and value network 2) receives the current state (S) and action (A). Value network 1 calculates the current value 1 (Q1) based on the current state (S) and action (A), and value network 2 calculates the current value 2 (Q2) based on the current state (S) and action (A). Q1 and Q2 are used to evaluate the quality of the current policy. Next, the error 1 (such as the temporal difference error TD-error) is calculated to guide the parameter update of value network 1, and the error 2 (such as the temporal difference error TD-error) is calculated to guide the parameter update of value network 2, thereby improving the accuracy of value estimation.

[0065] Then, value target network 1 and value target network 2 calculate the target value (Q') based on the target state (S') and target action (A'), compare it with the current value Q (Q1 and Q2), and further optimize the network. This process forms a closed-loop Actor-Critic reinforcement learning framework. Through continuous iterative training, the policy network can output better walking parameters, ensuring that the humanoid robot can effectively adjust the center of gravity changes and maintain dynamic balance during the walking welding process.

[0066] Finally, the walking parameters output by the trained policy network are used to control the humanoid robot, enabling real-time adjustments to its motion, ensuring welding posture stability and improving welding quality. The entire process, informed by center of gravity feedback, continuously optimizes the robot's walking strategy, achieving efficient and stable welding operations.

[0067] Based on any of the above embodiments, the position and posture of the welding robot arm at the next moment are determined based on the welding trajectory deviation of the welding robot arm at the current moment, the walking parameters at the next moment, the position and posture of the welding robot arm at the current moment, and the preset welding trajectory, including:

[0068] Based on the preset welding trajectory, a dynamic model of the humanoid robot during walking is constructed. The dynamic model is used to describe the motion relationship and force conditions between the various components of the humanoid robot during walking, as well as the kinematic constraints of the welding robot arm.

[0069] Determine the optimal adjustment path and posture compensation of the welding robot arm based on the dynamic model, the current welding trajectory deviation, the walking parameters at the next moment, and the current posture of the welding robot arm;

[0070] Based on the optimal adjustment path and posture compensation, the posture of the welding robot arm at the next moment is determined.

[0071] Specifically, a dynamic model is a mathematical model that describes the rigid-body dynamics, joint moments of inertia, mass distribution, mechanical constraints, and kinematic chain relationships of the humanoid robot and its welding manipulator. It is used to simulate the dynamic response of the system under force and motion conditions. As an optional embodiment, the desired trajectory of each robot joint can be discretized into a series of reference position and velocity data at time steps based on a preset welding trajectory. Combined with the robot's configuration and physical parameters, the dynamic equations can be established using the Lagrangian or Newton-Euler method to form a complete model of motion constraints and force relationships.

[0072] The optimal adjustment path refers to the continuous and smooth welding trajectory adjustment plan planned by the welding robot arm under the current state and the influence of external disturbances to minimize the welding trajectory deviation and meet the kinematic and dynamic constraints. The posture compensation amount refers to the displacement and posture rotation compensation value required by the welding robot arm relative to the preset trajectory at the next moment to correct the trajectory deviation.

[0073] Taking into account that the humanoid robot will experience changes in center of gravity and dynamic disturbances during walking, the accuracy of the welding robot arm is easily affected. The dynamic model accurately describes the motion and force characteristics of each component of the robot. The welding trajectory deviation at the current moment reflects the error between the actual trajectory and the target trajectory. The walking parameters at the next moment reflect the overall motion trend of the robot. The posture of the welding robot arm at the current moment provides the current spatial state information. Therefore, the embodiment of the present invention determines the optimal adjustment path and posture compensation amount of the welding robot arm based on the dynamic model, the welding trajectory deviation at the current moment, the walking parameters at the next moment, and the posture of the welding robot arm at the current moment, so as to effectively compensate for the welding trajectory error, ensure the continuity and accuracy of the welding robot arm movement, and improve the overall quality and stability of the weld.

[0074] After determining the optimal adjustment path and posture compensation amount, the compensated target posture can be converted into control instructions for each joint of the robot arm through motion control algorithms (such as model predictive control MPC or inverse kinematics solution), and the posture of the welding robot arm at the next moment can be determined to achieve accurate welding trajectory tracking.

[0075] Figure 3 This is a flow chart of the welding robot arm posture adjustment process provided by the present invention, as shown in FIG. Figure 3 As shown in the figure, the humanoid robot's motion target and current position (including the position of the end effector, posture parameters, and the angles of each robot joint) are first obtained through the state machine. The motion target, current posture, and the posture of the welding robot obtained using forward kinematics are input into the trajectory planning module to obtain the expected trajectory planning parameters. Simultaneously, the motion target and current posture are input into the model predictive control (IS-MPC) module to obtain the optimized trajectory control variables. Forward kinematics refers to the posture of the welding robot calculated based on the humanoid robot's joint parameters.

[0076] The expected trajectory parameters output by the trajectory planning module and the trajectory control variables output by the model predictive control module are input into the trajectory processing module to obtain a smooth and constraint-compliant final trajectory control command. The control command output by the trajectory processing module is then input into the kinematic controller to obtain the target angles for each robot joint. Based on these target angles, the motion of each joint of the humanoid robot is controlled to achieve precise position adjustment of the welding robot arm.

[0077] In addition, the status of the humanoid robot is detected in real time, and the posture of the welding robot arm is obtained in real time through the information acquisition module. After processing by the Kalman filter, the current posture of the humanoid robot is obtained using inverse kinematics calculation. Based on the difference between the current posture of the humanoid robot and the expected posture, the posture of the humanoid robot is adjusted to ensure stable welding of the robot in a dynamic environment.

[0078] It can be seen that the embodiment of the present invention realizes high-precision active adjustment and trajectory maintenance of the posture of the humanoid robot welding arm through trajectory planning and dynamic trajectory adjustment based on model predictive control, combined with real-time posture feedback control of sensor acquisition and inverse kinematics, thereby improving the stability of the welding process and the quality of the weld.

[0079] Based on any of the above embodiments, the steps for obtaining the motion state and the posture at the current moment are as follows:

[0080] The initial motion state and initial posture at the current moment are collected through sensors;

[0081] Filter the initial motion state at the current moment to obtain the motion state at the current moment;

[0082] The initial pose at the current moment is filtered to obtain the pose at the current moment.

[0083] Specifically, the initial motion state and initial posture at the current moment collected by sensors may be subject to significant signal noise, vibration interference, and measurement errors due to the humanoid robot's walking, resulting in unstable or abnormal data fluctuations. To address this issue, embodiments of the present invention filter the initial motion state and initial posture at the current moment to obtain the current motion state and posture, ensuring smoother and more accurate data and improving the stability and reliability of subsequent control algorithms.

[0084] Based on any of the above embodiments, the method further includes:

[0085] When the change in the center of gravity at the current moment is greater than a first threshold, and / or the welding trajectory deviation at the current moment is greater than a second threshold, an early warning prompt is issued.

[0086] Specifically, if the center of gravity change at the current moment is greater than the first threshold, it indicates that the humanoid robot may be at risk of imbalance or tipping over. In order to ensure the safety of the robot's walking and the continuity of welding, an early warning prompt can be issued.

[0087] If the welding trajectory deviation at the current moment is greater than the second threshold, it indicates that the actual welding trajectory of the welding robot arm deviates significantly from the target weld, which may lead to a decrease in weld quality. In order to ensure welding quality and process stability, an early warning prompt can be issued.

[0088] It can be seen that the embodiment of the present invention realizes dual monitoring and risk prevention of the robot's walking balance and welding posture by real-time monitoring of the robot's center of gravity change and welding trajectory deviation, and combines threshold judgment to realize an early warning mechanism, thereby ensuring the safe and stable operation of the humanoid robot in welding operations and reliable guarantee of welding quality.

[0089] The humanoid robot welding device provided by the present invention is described below. The humanoid robot welding device described below and the humanoid robot welding method described above can be referenced to each other.

[0090] Based on any of the above embodiments, Figure 4 Schematic diagram of the structure of the humanoid robot welding device provided by the present invention, such as Figure 4 As shown, the device includes:

[0091] A first determining unit 410 is configured to determine walking parameters of the humanoid robot at a next moment based on a center of gravity change of the humanoid robot at a current moment during the walking welding process of the humanoid robot, where the center of gravity change at a current moment refers to a deviation between the center of gravity position at a current moment and the center of gravity position at a previous moment;

[0092] A second determining unit 420 is configured to determine the posture of the welding robot arm at a next moment during the walking welding process of the humanoid robot based on the welding trajectory deviation of the welding robot arm at a current moment, the walking parameters at a next moment, the posture of the welding robot arm at a current moment, and a preset welding trajectory, wherein the welding trajectory deviation at a current moment refers to the deviation between the actual welding trajectory of the welding robot arm at a current moment and the center line of the target weld;

[0093] The welding unit 430 is used to control the welding robot arm to weld based on the posture at the next moment.

[0094] Based on any of the above embodiments, determining the walking parameters of the humanoid robot at the next moment based on the change in the center of gravity of the humanoid robot at the current moment includes:

[0095] Get the current motion state of the humanoid robot;

[0096] The current motion state and the center of gravity change at the current moment are input into the reinforcement learning model to obtain the walking parameters at the next moment output by the reinforcement learning model;

[0097] The reinforcement learning model is trained with the goal of minimizing the reward value, which is determined based on the change in the center of gravity of the humanoid robot.

[0098] Based on any of the above embodiments, the position and posture of the welding robot arm at the next moment are determined based on the welding trajectory deviation of the welding robot arm at the current moment, the walking parameters at the next moment, the position and posture of the welding robot arm at the current moment, and the preset welding trajectory, including:

[0099] Based on the preset welding trajectory, a dynamic model of the humanoid robot during walking is constructed. The dynamic model is used to describe the motion relationship and force conditions between the various components of the humanoid robot during walking, as well as the kinematic constraints of the welding robot arm.

[0100] Determine the optimal adjustment path and posture compensation of the welding robot arm based on the dynamic model, the current welding trajectory deviation, the walking parameters at the next moment, and the current posture of the welding robot arm;

[0101] Based on the optimal adjustment path and posture compensation, the posture of the welding robot arm at the next moment is determined.

[0102] Based on any of the above embodiments, the steps for obtaining the motion state and the posture at the current moment are as follows:

[0103] The initial motion state and initial posture at the current moment are collected through sensors;

[0104] Filter the initial motion state at the current moment to obtain the motion state at the current moment;

[0105] The initial pose at the current moment is filtered to obtain the pose at the current moment.

[0106] Based on any of the above embodiments, the further comprising:

[0107] When the change in the center of gravity at the current moment is greater than a first threshold, and / or the welding trajectory deviation at the current moment is greater than a second threshold, an early warning prompt is issued.

[0108] Based on any of the above embodiments, the present invention further provides a humanoid robot, comprising:

[0109] A robot body, a welding robot arm mounted on the robot body, and a humanoid robot welding device as described in any of the above embodiments.

[0110] Humanoid robots can be designed with multi-legged or bipedal walking structures and adaptive gait adjustment capabilities. The robot chassis is equipped with high-performance servo motors, drive systems, and multi-degree-of-freedom sensors (including gyroscopes, accelerometers, and laser ranging sensors) to monitor posture changes and center-of-gravity shifts during walking. The robot chassis' motion control system and central processing unit enable high-speed data transmission and control command interaction, enabling real-time adjustment of joint angles during walking to maintain robot stability.

[0111] The welding arm, mounted on top of the robot, features multi-joint, multi-degree-of-freedom motion. A welding torch and welding fixture are mounted on the front of the arm, enabling it to perform various welding operations. To achieve high-precision tracking of the welding trajectory, the arm utilizes a high-precision servo drive system and feedback sensors, enabling real-time fine-tuning of its position under closed-loop control. Furthermore, the arm incorporates high-resolution vision and laser sensors to detect real-time deviations in the welding trajectory.

[0112] Based on any of the above embodiments, the present invention further provides a humanoid robot welding system, which includes: a humanoid robot, a data acquisition and processing module, a communication interface, and a fault self-diagnosis module.

[0113] Among them, the data acquisition and processing module includes a multi-channel sensor signal acquisition circuit, an A / D converter, and a signal filtering and processing unit. This module integrates the sensor data collected from the robot chassis and various components of the welding robotic arm in real time, eliminates noise and interference through Kalman filtering and multi-sensor data fusion algorithms, and transmits the processed data to the humanoid robot welding device in the humanoid robot, providing an accurate basis for subsequent control decisions.

[0114] The humanoid welding device in the humanoid robot uses a deep reinforcement learning algorithm (such as DDPG) to train the optimal center of gravity control strategy for the humanoid robot under different motion states. The system first simulates the humanoid robot offline to build state-space and action-space models. It then uses a reward function to comprehensively evaluate the robot's balance state, energy consumption, and motion smoothness. During online operation, the humanoid robot inputs real-time state data into the reinforcement learning module to obtain corresponding control actions, and then uses the servo drive to issue commands to adjust the humanoid robot's motion. Secondly, a model-predictive control (MPC)-based method is used for the welding robot arm. During each sampling cycle, this module calculates the optimal position adjustment for the robot arm over a period of time based on the welding trajectory deviation, robot travel speed, current position of the robot arm, and the preset welding trajectory. It then feeds compensation commands back to the robot arm actuator, thereby achieving continuous correction of the welding trajectory.

[0115] The communication interface features a built-in high-speed data communication bus, enabling data exchange between modules. The fault self-diagnosis module monitors the robot's sensor data, actuator status, and communication signals in real time. When an anomaly is detected, it automatically triggers an alarm and implements pre-set safety measures (such as stopping welding operations and switching to a backup control strategy) to ensure safe and reliable system operation.

[0116] Figure 5 Schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 5 As shown, the electronic device may include: a processor (processor) 510, a communication interface (Communications Interface) 520, a memory (memory) 530 and a communication bus 540, wherein the processor 510, the communication interface 520, and the memory 530 communicate with each other through the communication bus 540. The processor 510 can call the logic instructions in the memory 530 to execute the humanoid robot welding method, which includes: during the walking welding process of the humanoid robot, based on the change in the center of gravity of the humanoid robot at the current moment, determining the walking parameters of the humanoid robot at the next moment, the center of gravity change at the current moment refers to the deviation between the center of gravity position at the current moment and the center of gravity position at the previous moment; during the walking welding process of the humanoid robot, based on the welding trajectory deviation of the welding robot arm at the current moment, the walking parameters at the next moment, the posture of the welding robot arm at the current moment and the preset welding trajectory, determining the posture of the welding robot arm at the next moment, the welding trajectory deviation at the current moment refers to the deviation between the actual welding trajectory of the welding robot arm at the current moment and the center line of the target weld; based on the posture at the next moment, controlling the welding of the welding robot arm.

[0117] Furthermore, the logic instructions in the aforementioned memory 530 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0118] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the humanoid robot welding method provided by the above methods, which includes: during the walking welding process of the humanoid robot, based on the center of gravity change of the humanoid robot at the current moment, determining the walking parameters of the humanoid robot at the next moment, the center of gravity change at the current moment refers to the deviation between the center of gravity position at the current moment and the center of gravity position at the previous moment; during the walking welding process of the humanoid robot, based on the welding trajectory deviation of the welding robot arm at the current moment, the walking parameters at the next moment, the posture of the welding robot arm at the current moment and the preset welding trajectory, determining the posture of the welding robot arm at the next moment, the welding trajectory deviation at the current moment refers to the deviation between the actual welding trajectory of the welding robot arm at the current moment and the center line of the target weld; based on the posture at the next moment, controlling the welding of the welding robot arm.

[0119] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the humanoid robot welding method provided by the above-mentioned methods, the method comprising: during the walking welding process of the humanoid robot, based on the change in the center of gravity of the humanoid robot at the current moment, determining the walking parameters of the humanoid robot at the next moment, the center of gravity change at the current moment referring to the deviation between the center of gravity position at the current moment and the center of gravity position at the previous moment; during the walking welding process of the humanoid robot, based on the welding trajectory deviation of the welding robot arm at the current moment, the walking parameters at the next moment, the posture of the welding robot arm at the current moment and the preset welding trajectory, determining the posture of the welding robot arm at the next moment, the welding trajectory deviation at the current moment referring to the deviation between the actual welding trajectory of the welding robot arm at the current moment and the center line of the target weld; based on the posture at the next moment, controlling the welding of the welding robot arm.

[0120] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0121] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0122] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A humanoid robot welding method, characterized in that: include: During the walking welding process of the humanoid robot, the step length and pace of the next step are adjusted based on the center of gravity change of the humanoid robot at the current moment, and the walking parameters of the humanoid robot at the next moment are determined. The center of gravity change at the current moment refers to the deviation between the center of gravity position at the current moment and the center of gravity position at the previous moment; the walking parameters at the next moment refer to the instruction set that controls the motion state of the humanoid robot at the next moment; wherein, when the center of gravity change at the current moment is large, the step length and pace of the next step are reduced; when the center of gravity change at the current moment is small, the step length and pace of the next step are increased; During the walking welding process of the humanoid robot, the posture of the welding robot arm at the next moment is determined based on the welding trajectory deviation of the welding robot arm at the current moment, the walking parameters at the next moment, the posture of the welding robot arm at the current moment, and the preset welding trajectory. The welding trajectory deviation at the current moment refers to the deviation between the actual welding trajectory of the welding robot arm at the current moment and the center line of the target weld; the actual welding trajectory at the current moment refers to the path that the welding arc or the end of the welding gun on the welding robot arm actually moves on the surface of the welding workpiece during the welding process; Based on the posture at the next moment, the welding robot arm is controlled to weld.

2. The humanoid robot welding method according to claim 1, characterized in that: The step of determining the walking parameters of the humanoid robot at the next moment based on the change in the center of gravity of the humanoid robot at the current moment includes: Obtaining the current motion state of the humanoid robot; Inputting the motion state at the current moment and the center of gravity change at the current moment into a reinforcement learning model to obtain the walking parameters at the next moment output by the reinforcement learning model; The reinforcement learning model is trained with the goal of minimizing a reward value, and the reward value is determined based on a change in the center of gravity of the humanoid robot.

3. The humanoid robot welding method according to claim 2, characterized in that: The method of determining the posture of the welding robot arm at the next moment based on the welding trajectory deviation of the welding robot arm at the current moment, the walking parameters at the next moment, the posture of the welding robot arm at the current moment, and the preset welding trajectory includes: Based on the preset welding trajectory, a dynamic model of the humanoid robot during walking is constructed, wherein the dynamic model is used to describe the motion relationship and force conditions between various components of the humanoid robot during walking, as well as the kinematic constraints of the welding robot arm; Determining an optimal adjustment path and posture compensation amount of the welding robot arm based on the dynamic model, the welding trajectory deviation at the current moment, the walking parameters at the next moment, and the posture of the welding robot arm at the current moment; Based on the optimal adjustment path and the posture compensation amount, the posture of the welding robot arm at the next moment is determined.

4. The humanoid robot welding method according to claim 2, characterized in that: The steps for obtaining the motion state and the posture at the current moment are as follows: Collecting the initial motion state and initial posture at the current moment through sensors; Filtering the initial motion state at the current moment to obtain the motion state at the current moment; The initial posture at the current moment is filtered to obtain the posture at the current moment.

5. The humanoid robot welding method according to any one of claims 1 to 4, characterized in that: The method further comprises: When the change in the center of gravity at the current moment is greater than a first threshold, and / or the welding trajectory deviation at the current moment is greater than a second threshold, an early warning prompt is issued.

6. A humanoid robot welding device, characterized in that: include: a first determining unit configured to adjust a step length and a pace of the next step based on a current center of gravity change of the humanoid robot during walking welding, and determine walking parameters of the humanoid robot at the next moment, wherein the current center of gravity change refers to a deviation between the center of gravity position at the current moment and the center of gravity position at the previous moment; and the walking parameters at the next moment refer to a set of instructions for controlling the motion state of the humanoid robot at the next moment; wherein, when the current center of gravity change is large, the step length and pace of the next step are reduced; and when the current center of gravity change is small, the step length and pace of the next step are increased; a second determining unit, configured to determine, during the walking welding process of the humanoid robot, a position and posture of the welding robot arm at a next moment based on a welding trajectory deviation of the welding robot arm at a current moment, the walking parameters at the next moment, the position and posture of the welding robot arm at a current moment, and a preset welding trajectory, wherein the welding trajectory deviation at a current moment refers to a deviation between an actual welding trajectory of the welding robot arm at a current moment and a center line of a target weld; and the actual welding trajectory at a current moment refers to a path that a welding arc or a welding gun end on the welding robot arm actually moves on a surface of a welding workpiece during the welding process; The welding unit is used to control the welding robot arm to weld based on the posture at the next moment.

7. A humanoid robot, characterized in that: include: A robot body, a welding robot arm mounted on the robot body, and a humanoid robot welding device as claimed in claim 6.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the humanoid robot welding method according to any one of claims 1 to 5 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the humanoid robot welding method according to any one of claims 1 to 5 is implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the humanoid robot welding method according to any one of claims 1 to 5 is implemented.

Images