Robot evaluation method, storage medium, electronic device and program product

Abstract

The invention provides a robot evaluation method, a storage medium, electronic equipment and a program product, and relates to the technical field of intelligent equipment. The robot evaluation method comprises the steps of determining a weight corresponding to the degree of freedom of motion of a robot based on a to-be-executed task of the robot; based on the upper limit of the movement speed of the target joint, the weight corresponding to the target joint is determined, and the target joint comprises joints related to the to-be-executed task; based on the weight corresponding to the motion freedom degree of the robot and the weight corresponding to the target joint, operability evaluation information of the robot under the current configuration is calculated, and the operability evaluation information represents the ability of the robot to complete the to-be-executed task with the current configuration.

Description

Technical Field

[0001] This application relates to the field of embodied intelligence technology, specifically to a robot evaluation method, storage medium, electronic device, and program product. Background Technology

[0002] While robot evaluation technology has made some progress, there are still many aspects that need improvement and refinement. For example, it does not fully meet the diverse task requirements, and there are shortcomings in the consideration of robot joint constraints. As a result, the existing robot evaluation technology still has a certain gap in its fit with practical applications, and further optimization and improvement are needed to better adapt to complex and ever-changing application scenarios. Summary of the Invention

[0003] In view of this, embodiments of this application provide a robot evaluation method, a storage medium, an electronic device, and a program product.

[0004] In a first aspect, one embodiment of this application provides a robot evaluation method comprising: determining the weights corresponding to the robot's degrees of freedom of motion based on the robot's task to be performed; determining the weights corresponding to the target joints based on the upper limit of the motion speed of the target joints, wherein the target joints include the joints involved in the task to be performed; and calculating the operability evaluation information of the robot in the current configuration based on the weights corresponding to the robot's degrees of freedom of motion and the weights corresponding to the target joints, wherein the operability evaluation information represents the robot's ability to complete the task to be performed in the current configuration.

[0005] In conjunction with the first aspect, in some implementations of the first aspect, the degrees of freedom of motion include translational degrees of freedom and rotational degrees of freedom. Based on the task to be performed by the robot, the weights corresponding to the robot's degrees of freedom of motion are determined, including: determining the task type of the task to be performed; and determining the respective weights of the robot's translational and rotational degrees of freedom based on the task type of the task to be performed.

[0006] In conjunction with the first aspect, in some implementations of the first aspect, the weights of the robot's translational and rotational degrees of freedom are determined based on the task type of the task to be performed, including: if the task type is a translation-dominant task, the weight of the translational degree of freedom is configured to be higher than the weight of the rotational degree of freedom; if the task type is a rotation-dominant task, the weight of the rotational degree of freedom is configured to be higher than the weight of the translational degree of freedom; if the task type is a composite task, the weight ratio of the translational and rotational degrees of freedom is adjusted based on the motion characteristics of the task to be performed.

[0007] In conjunction with the first aspect, in some implementations of the first aspect, the weight corresponding to the target joint is determined based on the upper limit of the target joint's motion velocity, including: determining the upper limit of the target joint's motion velocity as the weight corresponding to the target joint.

[0008] In conjunction with the first aspect, in some implementations of the first aspect, after calculating the operability evaluation information of the robot in the current configuration based on the weights corresponding to the robot's degrees of freedom and the weights corresponding to the target joint, the method further includes: if the operability evaluation information meets the lower operability limit requirement, adjusting the null space component of the motion velocity of the target joint until the operability evaluation information meets the upper operability requirement, wherein the lower operability limit requirement represents the minimum operability evaluation information value required for the robot to complete the task to be performed, and the upper operability limit requirement represents the maximum operability evaluation information value that the robot can achieve in the task to be performed.

[0009] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: determining the null component of the motion velocity of the target joint based on the product of the partial derivative of the angle of the target joint with the operability assessment information and the target scaling factor.

[0010] In conjunction with the first aspect, in some implementations of the first aspect, the operability assessment information of the robot in the current configuration is calculated based on the weights corresponding to the robot's degrees of freedom and the weights corresponding to the target joints. This includes: constructing a task weight matrix by assigning weights corresponding to the robot's degrees of freedom, wherein the task weight matrix is ​​a diagonal matrix and the values ​​of the elements on the diagonal of the diagonal matrix correspond one-to-one with the values ​​of the weights of each degree of freedom; constructing a joint weight vector by assigning weights corresponding to the target joints; and calculating the operability assessment information of the robot in the current configuration based on the task weight matrix, the Jacobian matrix corresponding to the task weight matrix, and the joint weight vector.

[0011] Secondly, one embodiment of this application provides a robot evaluation device, comprising: a first determining module, configured to determine the weights corresponding to the robot's degrees of freedom of motion based on the robot's task to be performed; a second determining module, configured to determine the weights corresponding to a target joint based on the upper limit of the motion speed of the target joint, the target joint including the joints involved in the task to be performed; and a calculation module, configured to calculate the operability evaluation information of the robot in the current configuration based on the weights corresponding to the robot's degrees of freedom of motion and the weights corresponding to the target joints, the operability evaluation information representing the robot's ability to complete the task to be performed in the current configuration.

[0012] Thirdly, one embodiment of this application provides a computer-readable storage medium storing a computer program for performing the robot evaluation method described in the first aspect.

[0013] Fourthly, one embodiment of this application provides an electronic device, the electronic device comprising: a processor; a memory for storing processor-executable instructions; the processor being configured to perform the robot evaluation method described in the first aspect.

[0014] Fifthly, one embodiment of this application provides a computer program product including instructions that, when executed on an electronic device, cause the electronic device to implement the robot evaluation method described in the first aspect.

[0015] In this application, the weights corresponding to the degrees of freedom of motion are determined by the robot's task to be performed, accurately integrating task requirements into the evaluation process. This fully considers the differences in the impact of different tasks on the robot's motion accuracy, speed, and path planning, ensuring that the evaluation results closely align with actual application scenarios and overcoming the problem of traditional methods being disconnected from real-world applications. Simultaneously, the weights are determined based on the upper limit of the target joint's motion speed, incorporating joint speed limitations to ensure that the evaluation results accurately reflect the robot's actual operational performance. In summary, this application's solution improves the accuracy and practicality of the evaluation by addressing both task requirements and joint physical characteristics. Attached Figure Description

[0016] The above and other objects, features, and advantages of this application will become more apparent from the more detailed description of the embodiments of this application in conjunction with the accompanying drawings. The drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the embodiments of this application to explain this application and do not constitute a limitation thereof. In the drawings, the same reference numerals generally represent the same components or steps.

[0017] Figure 1 The diagram shown is a flowchart of a robot evaluation method provided in an embodiment of this application.

[0018] Figure 2 The diagram shown is a structural schematic of a robot evaluation device provided in an embodiment of this application.

[0019] Figure 3 The diagram shown is a structural schematic of an electronic device provided in an embodiment of this application. Detailed Implementation

[0020] 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.

[0021] In the field of robot evaluation, the state of technological development exhibits certain limitations, as detailed below.

[0022] On the one hand, traditional evaluation methods have significant shortcomings in terms of task adaptability. For example, common operability assessments fail to effectively differentiate based on task requirements, leading to evaluation results that are often out of touch with actual application scenarios. In actual robot operation tasks, the requirements for robot motion accuracy, speed, and path planning vary, and traditional evaluation methods fail to fully consider these differences, resulting in biased evaluation results when guiding actual operations.

[0023] On the other hand, the upper limits of physical speeds differ significantly between different joints; for example, distal joints typically rotate at higher speeds. This difference directly impacts the robot's overall motion performance and task execution capabilities. However, relevant evaluation methods have not adequately considered this crucial factor, resulting in evaluation results that do not accurately reflect the robot's performance in actual operation.

[0024] Furthermore, in the field of teleoperated robots, operator behavioral preferences have a significant impact on the robot's operational efficiency and accuracy. However, current evaluation methods lack quantitative modeling of operator behavioral preferences. Taking wrist rotation agility as an example, some operators may be more adept at performing fine operations through wrist rotation, but traditional evaluation methods fail to take this individual difference into account, making it difficult to achieve true human-robot collaborative optimization.

[0025] In summary, relevant robot evaluation technologies urgently need improvement and refinement in terms of task adaptability, joint constraint considerations, and human-robot compatibility to meet the increasingly complex demands of robot applications. Therefore, this application is submitted, specifically... Figure 1 The diagram shown is a flowchart illustrating a robot evaluation method provided in an embodiment of this application. Figure 1 As shown, the method includes the following steps.

[0026] Step S110: Based on the robot's task to be performed, determine the weights corresponding to the robot's degrees of freedom of motion.

[0027] Degrees of freedom (DOF) refer to the number of joints or coordinate axes that a robot can move independently. For example, if a robot's arm has six joints that can rotate or extend, then its DDF is 6 (assuming each joint can move independently without other constraints). Furthermore, the weights corresponding to DDFs refer to the importance coefficients assigned to each DDF when evaluating the robot's ability to perform a specific task.

[0028] In some embodiments, first, the task to be performed by the robot is determined. Then, weights are assigned to each degree of freedom of motion based on the importance of the task to the individual degrees of freedom. For example, in tasks requiring high-precision position control, such as soldering tiny electronic components, the degrees of freedom controlling the position of the robot arm's end effector (e.g., translational degrees of freedom along the x, y, and z axes) will have higher weights because they directly affect the accuracy of the solder joints. As another example, in tasks requiring rapid object movement, the degrees of freedom related to velocity and acceleration (e.g., the rotational velocity of joints) have higher weights, as they determine the robot's ability to respond quickly and complete the task.

[0029] Step S120: Determine the weight corresponding to the target joint based on the upper limit of the target joint's motion velocity.

[0030] Target joints include the joints involved in the task to be performed, that is, those joints that need to move or adjust when completing the task. For example, in a robotic arm performing an object grasping task, the wrist joint and elbow joint are target joints.

[0031] The upper limit of motion speed refers to the maximum motion speed that the target joint can achieve under normal working conditions. This speed is limited by factors such as the motor power and mechanical structure strength of the joint.

[0032] In some embodiments, firstly, the target joints involved in the task to be performed by the robot are identified for targeted evaluation. Then, for each target joint, its upper limit of motion speed is obtained. Finally, the weights of each target joint are determined based on its upper limit of motion speed. Optionally, the weight of a target joint is positively correlated with its upper limit of motion speed. That is, target joints with higher upper limits of motion speed can respond and adjust more quickly during task execution and are therefore assigned higher weights; conversely, target joints with lower upper limits of motion speed have relatively lower weights.

[0033] Step S130: Based on the weights corresponding to the robot's degrees of freedom and the weights corresponding to the target joints, calculate the robot's operability assessment information in the current configuration.

[0034] The current configuration of a robot refers to the combined state of its joint positions, postures, and degrees of freedom of motion at a given moment. For example, after a robot's arm completes a movement, the angles and degrees of extension of its joints together constitute the robot's current configuration.

[0035] Operability assessment information indicates a robot's ability to complete a task in its current configuration. It comprehensively considers factors such as the weights of the robot's degrees of freedom and the weights of the target joints to determine the feasibility and efficiency of the robot completing the task in its current configuration.

[0036] In some embodiments, the weights corresponding to the degrees of freedom of motion and the weights corresponding to the target joints are calculated together to obtain the operability assessment information, which can be a specific numerical value or an assessment level. This information can intuitively reflect the robot's ability to complete the task to be performed in the current configuration.

[0037] For example, the weight of the target joint can be added to the weight of the corresponding degree of freedom, or the two weights can be combined through mathematical operations (such as multiplication). Specifically, for a particular degree of freedom, it already has an initial weight based on the task type, while the target joint corresponding to that degree of freedom has its own weight. Adding these two weights together yields a final weight that more comprehensively reflects both the task's requirements for the degree of freedom and the relevant characteristics of the target joint. This allows for a more comprehensive consideration of both factors when calculating operability assessment information, making the assessment results more aligned with actual task requirements and the robot's physical condition. When using multiplication to combine the weights of the target joint and the degree of freedom, the two weights are multiplied together. That is, the two weights influence and constrain each other. For example, if a degree of freedom has a high weight but the corresponding target joint has a low weight, the combined weight after multiplication will be at a relatively intermediate level. This method emphasizes the synergistic effect of the two; only when both weights are high will the combined weight be high, and vice versa. This is applicable to situations where it is necessary to more strictly meet the requirements of the task to be performed for the degrees of freedom of motion and the capability limitations of the target joint, so that the final operability assessment information can more accurately reflect the robot's ability to complete the task in the current configuration after comprehensively considering the task and joint characteristics.

[0038] In this embodiment, the weights corresponding to the degrees of freedom of motion are determined by the robot's task to be performed, accurately integrating task requirements into the evaluation process. This fully considers the differences in the impact of different tasks on the robot's motion accuracy, speed, and path planning, ensuring that the evaluation results closely align with actual application scenarios and overcoming the problem of traditional methods being disconnected from real-world applications. Simultaneously, the weights are determined based on the upper limit of the target joint's motion speed, incorporating joint speed limitations to ensure that the evaluation results accurately reflect the robot's actual operational performance. In summary, the solution in this application improves the accuracy and practicality of the evaluation by addressing both task requirements and joint physical characteristics.

[0039] To enable the robot evaluation scheme to more accurately match actual task requirements, this application further optimizes the weight determination mechanism. Specifically, the motion degrees of freedom include translational degrees of freedom and rotational degrees of freedom. Based on the robot's task to be performed, the weights corresponding to the robot's motion degrees of freedom are determined, including: determining the task type of the task to be performed; and determining the respective weights of the robot's translational and rotational degrees of freedom based on the task type.

[0040] Translational degrees of freedom refer to a robot's ability to move along a straight line in space. Specifically, it describes a robot's linear motion along three coordinate axes (x-axis, y-axis, and z-axis) in three-dimensional space. For example, a robot arm that can move up and down along the z-axis has one translational degree of freedom in that z-axis direction. Understandably, translational degrees of freedom are crucial in industrial production and logistics. For instance, robots on automotive production lines need to grip parts at different locations and assemble them onto the car body, requiring good translational degrees of freedom for precise position control.

[0041] Rotational degrees of freedom refer to a robot's ability to rotate around a fixed axis. It describes the robot's rotational motion in three-dimensional space around three coordinate axes (x-axis, y-axis, and z-axis). Rotational degrees of freedom enable robots to change their posture and orientation to adapt to different task requirements. For example, in the field of medical robotics, robots used for surgical procedures need to precisely control the angle and orientation of surgical instruments, which relies on their rotational degrees of freedom.

[0042] In some embodiments, translational and rotational degrees of freedom together determine the robot's mobility and flexibility in space. Translational degrees of freedom primarily involve changes in position, while rotational degrees of freedom primarily involve adjustments in posture. The two can work together to enable the robot to perform a variety of complex tasks.

[0043] Understandably, tasks vary widely, such as handling, welding, and assembly, each with its unique motion requirements. Taking handling tasks as an example, the robot's ability to move in space is emphasized, making translational degrees of freedom more critical. In welding tasks, to ensure welding quality, the robot needs precise control of the welding torch angle, highlighting the importance of rotational degrees of freedom. Therefore, it is necessary to determine the weights of translational and rotational degrees of freedom based on the different requirements of each task type.

[0044] In this embodiment, the robot can allocate the weights of translation and rotation degrees of freedom more reasonably according to specific task requirements, so as to accurately reflect the robot's ability to complete specific tasks in the current configuration in the subsequent operability assessment, ensuring that the robot can better perform its functions in actual operation and improve the efficiency and quality of task execution.

[0045] To make the operability assessment more aligned with the needs of different tasks, this application further refines the configuration rules for the weights of motion degrees of freedom. By distinguishing between translation-dominant, rotation-dominant, and composite tasks, the weight allocation is dynamically adjusted to achieve scenario-optimized assessment metrics. Specifically, if the task type is translation-dominant, the weight of the translation degree of freedom is configured to be higher than that of the rotation degree of freedom; if the task type is rotation-dominant, the weight of the rotation degree of freedom is configured to be higher than that of the translation degree of freedom; if the task type is composite, the weight ratio of the translation and rotation degrees of freedom is adjusted based on the motion characteristics of the task to be executed.

[0046] In translation-dominated tasks, the robot's primary objective is to move an object from one location to another, with relatively low requirements for the object's orientation. In this process, the robot needs precise control of its translational degrees of freedom to ensure the object accurately reaches the target position. In rotation-dominated tasks, the focus is primarily on the orientation adjustment of the robot's end effector. For example, in welding tasks, the robot needs to precisely control the angle of the welding torch to ensure welding quality. Composite tasks involve both translational and rotational motions, but the weighting ratio of these two motions is adjusted according to the specific characteristics of the task. For instance, the weighting ratio of translational and rotational degrees of freedom is dynamically adjusted based on the relative importance of positional accuracy and orientation accuracy.

[0047] In some embodiments, for translation-dominant tasks, the weight of translational degrees of freedom should be set higher than that of rotational degrees of freedom to ensure that the robot's translational performance meets the task requirements. Conversely, for rotation-dominant tasks, the key lies in the posture adjustment of the robot's end effector; therefore, rotational degrees of freedom should be given a higher weight, making the evaluation focus more on the accuracy and flexibility of rotational motion. For composite tasks, which involve both translation and rotation, the relative importance of each varies depending on the specific motion characteristics. In this case, the weight ratio of translational and rotational degrees of freedom should be dynamically adjusted according to the specific requirements of the task to be performed.

[0048] For example, for translation-dominant tasks, the weights of the three translation degrees of freedom and the three rotation degrees of freedom are (1 / 3, 1 / 3, 1 / 3, 0, 0, 0), which means that the weight of the rotation degree of freedom is set to 0 and the weights of each translation degree of freedom are equal. This is suitable for tasks that mainly focus on position movement and do not have high requirements for posture.

[0049] For rotation-dominated tasks, the weights for the three translational degrees of freedom and the three rotational degrees of freedom are (0, 0, 0, 1 / 3, 1 / 3, 1 / 3), which means that the weight of the translational degree of freedom is set to 0, and the weights of each rotational degree of freedom are equal. This is suitable for tasks that mainly focus on attitude adjustment and do not have high requirements for position.

[0050] For general tasks in complex tasks, the weights corresponding to the three translational degrees of freedom and the three rotational degrees of freedom are (1 / 6, 1 / 6, 1 / 6, 1 / 6, 1 / 6, 1 / 6), which means that the weights of all translational and rotational degrees of freedom are equal, and are suitable for tasks that require a relatively balanced translation and rotation.

[0051] For example, in the complex task of flipping meat while grilling, the weights for the three translational degrees of freedom and the three rotational degrees of freedom are (1 / 6, 1 / 6, 0, 1 / 6, 0, 1 / 2), that is, the weights of the translational degree of freedom in the z-direction and the rotational degree of freedom in the y-direction are set to 0 to accommodate the special requirements for position and posture when flipping meat. In the complex task of playing ping-pong, the weights for the three translational degrees of freedom and the three rotational degrees of freedom are (1 / 4, 1 / 4, 1 / 4, 0, 1 / 8, 1 / 8), to accommodate the dynamic requirements for position and posture in ping-pong.

[0052] In this embodiment, for translation-dominant tasks, a higher weight is assigned to the translational degrees of freedom to ensure the robot's accuracy and efficiency in positional movement, effectively meeting the stringent positional control requirements of such tasks. In rotation-dominant tasks, the weight of the rotational degrees of freedom is emphasized, enabling the robot to control its posture more precisely and ensuring task quality. For complex tasks, the weight ratio is flexibly adjusted based on the task's motion characteristics to balance the contributions of translation and rotation, allowing the robot to simultaneously meet the comprehensive requirements of position and posture when performing complex tasks. This flexible weighting mechanism makes robot evaluation more closely aligned with actual task needs, optimizes the robot's operational performance, and enhances its adaptability and reliability in diverse tasks.

[0053] To more accurately reflect the physical characteristics of the joints, this application further optimizes the method for determining the target joint weights. Specifically, determining the weights corresponding to the target joint based on the upper limit of the target joint's motion velocity includes: determining the upper limit of the target joint's motion velocity as the weights corresponding to the target joint.

[0054] Taking a 7-DOF robot as an example, assume that the upper limit of its hardware layer (such as motors, reducers, controllers, etc.) for the motion speed of target joints 1, 2, and 3 is 1.5708 rad / s, target joint 4 is 2.0944 rad / s, and target joints 5, 6, and 7 are 3.1416 rad / s. Based on these speed upper limits, the weights of target joints 1-7 can be set as (1.5708, 1.5708, 1.5708, 2.0944, 3.1416, 3.1416, 3.1416).

[0055] In this embodiment, the weight of the target joint reflects the speed limit of each joint, which allows for reasonable allocation and optimization of joint motion during task execution to avoid exceeding hardware limitations, thereby improving the safety and efficiency of robot operation.

[0056] To make the calculation of operability assessment information more accurate and efficient, embodiments of this application provide a matrix and vector-based calculation method to more accurately assess the robot's operational capabilities. Specifically, the weights corresponding to the robot's degrees of freedom are constructed into a task weight matrix; the weights corresponding to the target joints are constructed into joint weight vectors; and based on the task weight matrix, the Jacobian matrix corresponding to the task weight matrix, and the joint weight vectors, the robot's operability assessment information under the current configuration is calculated.

[0057] Specifically, the task weight matrix is ​​a diagonal matrix, with each element on the diagonal corresponding to a weight for each degree of freedom. For example, in a table tennis task, the weights for the three translational and three rotational degrees of freedom are (1 / 4, 1 / 4, 1 / 4, 0, 1 / 8, 1 / 8), and the task weight matrix can be represented as: diag([1 / 4, 1 / 4, 1 / 4, 0, 1 / 8, 1 / 8]). For instance, if the weights for target joints 1-7 are (1.5708, 1.5708, 1.5708, 2.0944, 3.1416, 3.1416, 3.1416), then the joint weight vector is [1.5708, 1.5708, 1.5708, 2.0944, 3.1416, 3.1416, 3.1416]. T .

[0058] Furthermore, the task weight matrix can be configured with either trunk space task weights or end-effector space task weights, depending on the ease of describing the actions relevant to the task at hand. When using trunk space to build the task weight matrix, the Jacobian matrix in trunk space must be selected. Similarly, when using end-effector space to build the task weight matrix, the Jacobian matrix in end-effector space must be selected.

[0059] It's important to note that trunk space and end effector space are two distinct reference coordinate system concepts. Trunk space, also known as base space or world coordinate system, is typically set at the robot's base or a fixed reference point. It serves as the reference frame for the robot's overall motion, describing the robot's position and orientation relative to its fixed base. For example, on an industrial production line, if a robot needs to pick up object B from a fixed location A and move it to another fixed location C, using trunk space to plan and control the robot's motion is appropriate.

[0060] The end-effector space, also known as the end-effector coordinate system, is a coordinate system attached to the robot's end-effector (such as the gripper of a robotic arm or a welding torch). It moves with the end-effector and is used to describe its surrounding environment and motion from the end-effector's own perspective. For example, when a robot performs precision assembly tasks, its motion needs to be adjusted according to the end-effector's posture and position to accurately screw screws into target holes. In this case, using the end-effector space to describe and control the end-effector's motion is more convenient.

[0061] For example, assuming the task weight matrix is ​​represented by D, the joint weight matrix by w, and the Jacobian matrix by J, then the operability assessment information = w T J T DJw.

[0062] In this embodiment, the weights corresponding to the degrees of freedom and the target joints are converted into matrix form, and calculations are performed using matrix multiplication. This efficiently handles the complex relationships between multiple degrees of freedom and joints involved in robot motion, avoiding tedious item-by-item calculations, simplifying the process and improving efficiency. Furthermore, when task requirements and joint physical characteristics change, only the corresponding element values ​​of the task weight matrix and joint weight matrix need to be adjusted, without large-scale model modifications, thus enabling rapid adaptation to new situations. Finally, this calculation method is easy to combine with other mathematical tools such as optimization algorithms and control theory. For example, operability assessment information can be incorporated into optimization objectives or constraints to achieve refined control and optimization of robot motion, improving overall performance and task execution effectiveness.

[0063] To make the robot evaluation method more practical, this application provides an optional solution: after calculating the operability evaluation information, if the operability evaluation information meets the lower limit of operability requirements, the null space component of the target joint's motion velocity is adjusted until the operability evaluation information meets the upper limit of operability requirements.

[0064] Specifically, the lower operability limit represents the minimum operability assessment information value required for the robot to complete the task. It is the minimum requirement to ensure the task can be completed. If the value is lower than this, the robot may not be able to complete the task effectively. The upper operability limit represents the maximum operability assessment information value that the robot can achieve in the task. It represents the robot's optimal performance level when completing the task. When the operability assessment information is close to or reaches this value, the robot can complete the task with high efficiency and capability.

[0065] In some embodiments, the lower and upper operability requirements define the range of capabilities required for the robot to complete the task. Then, operability assessment information for the robot's current configuration is calculated in real time. If the calculated operability assessment information meets the lower operability requirement, it indicates that the robot possesses the basic capability to complete the task. At this point, the null-space component of the target joint's motion velocity is adjusted; that is, the joint motion component generated under redundant degrees of freedom that does not change the actuator pose.

[0066] It can be seen that the adjustment of the null space component involves optimizing the allocation of joint velocities without affecting the robot's actuator motion task. By continuously adjusting the null space component, the robot's operability assessment information is gradually improved until it meets the upper limit of operability requirements. This process is equivalent to optimizing the robot's motion state while ensuring task completion, enabling it to complete the task with better performance.

[0067] The solution in this embodiment, while ensuring the robot completes its task, fully utilizes the additional degrees of freedom provided by the null component. This allows the robot's operability assessment information to be progressively improved from the lower limit to the upper limit, optimizing the robot's motion state and enhancing its efficiency and ability to complete tasks. Furthermore, this adjustment method does not affect the actuator's speed and trajectory, ensuring task accuracy and stability and avoiding task deviations or failures caused by adjusting joint speeds. Simultaneously, through real-time monitoring and adjustment of operability assessment information, dynamic optimization of the robot's motion can be achieved, enhancing its ability to adapt to complex tasks and environmental changes, and improving overall performance and reliability.

[0068] To more precisely control the null-space component of the motion velocity of a robot's target joint, and to effectively adjust the operability assessment information from meeting the lower limit requirements to meeting the upper limit requirements, embodiments of this application provide a method based on the product of partial derivatives and a scaling factor. Specifically, the null-space component of the motion velocity of the target joint is determined based on the product of the partial derivative of the operability assessment information with respect to the angle of the target joint and the target scaling factor.

[0069] For example, the null space component of the motion velocity of the target joint Where k represents the target scaling factor, WMoM (q*) This represents the operability assessment information, where q represents the angle of the target joint.

[0070] Total motion velocity of the target joint in, This indicates the movement speed of the target joint in order to complete the task.

[0071] For example, assuming that the operability assessment information (0.005) of a 7-DOF robotic arm during grasping is less than the lower operability limit requirement (0.01), then the calculation... It was found that elbow flexion improves operability. Furthermore, the zero-space components of the target joint's motion velocity were obtained, such as 0.1 rad / s for the shoulder joint and -0.2 rad / s for the elbow joint. Finally, the total motion velocity of the target joint was determined. While maintaining the actuator trajectory, elbow flexion increases WMoM to the upper limit of operability requirements (e.g., 0.015).

[0072] In this embodiment, partial derivatives accurately capture the sensitivity of operability assessment information to changes in the target joint's angle, providing a basis for adjusting the null space component and improving the efficiency and accuracy of the adjustment. Secondly, the introduction of a proportional coefficient allows for flexible control of the adjustment range according to actual needs, balancing adjustment speed and stability. Finally, this solution fully utilizes the null space component to optimize the robot's motion state without affecting the end effector's task, thereby improving performance.

[0073] The following section will use the example of a robot playing table tennis to illustrate the solutions in the above embodiments in detail.

[0074] The robot's end effector grips the ping-pong paddle in the following way: the robot's end effector's x-axis is perpendicular to the ping-pong paddle's striking plane and points in the direction of the ball, its y-axis is located within the ping-pong paddle's striking plane, and its z-axis is along the direction of the ping-pong paddle's handle towards the far end of the paddle.

[0075] Since it is more convenient to describe the expected movement of the ping-pong paddle in the end-effector space during the receiving and striking process, the task weight matrix D is described in the end-effector space. body During a shot, the racket needs to move a wide range of motion to receive balls landing at different points, so the omnidirectional, rapid translational capability of the racket configuration is of great concern. Therefore, D... body The first three vectors on the diagonal are assigned [1 / 4, 1 / 4, 1 / 4]. Meanwhile, regarding the shot, rotation around the x-axis, i.e., the racket's rotation within the hitting plane, is meaningless. Rotation in the other two directions can make minor adjustments to the racket's orientation; therefore, D... body The last three elements of the vector on the diagonal are set to [0, 1 / 8, 1 / 8].

[0076] Based on the actual hitting posture, the joint position q* of the ready-to-hit position is given. The corresponding task weight matrix D in the end-effector space is... body Calculate the Jacobian matrix J of the terminal space. body (q*). Set the joint weight vector w according to the physical velocity limit of the target joint.

[0077] Finally, the operability assessment information is calculated according to the given formula.

[0078] In addition, the scheme in this application was compared with traditional evaluation techniques. In the comparative experiment, the standard grasping task configuration before and after the wrist structure improvement was selected for operability measurement evaluation. The results are shown in Table 1.

[0079] Table 1

[0080] Evaluation indicators Before improvement Improved Performance changes Traditional operability assessment information 0.00888100 0.01567971 +76.5％ Rotation scale 9.9310 13.3674 +34.6％ Translational scale 0.9564 0.6568 -31.3％

[0081] As shown in Table 1, the rotational scalar value increased by 34.6%, demonstrating that the improved wrist structure is better suited for rotational tasks (such as screw tightening and posture adjustment). The translational scalar value decreased by 31.3%, indicating that the design optimization focused on rotational agility, sacrificing some translational capability. Although traditional operability assessment information improved by 76.5%, it could not distinguish the differences between rotational and translational performance, only outputting a single scalar value, thus masking the actual cost of the configuration improvement. Therefore, this application quantifies task adaptability by configuring a weight matrix in a targeted manner, separately assesses rotational and translational capabilities, and clearly reveals the trade-off between the improvement in rotation and the decrease in translation, which can further guide the optimization direction of robot configuration.

[0082] As described above, the solution presented in this application can be used for selecting robotic arm configurations. Specifically, when choosing between different wrist designs, a corresponding task weight matrix can be set according to the characteristics of different tasks. The joint weight vector is then determined by combining this with the physical speed limits of the robotic arm's joints. Finally, operability evaluation information is calculated. Furthermore, by comparing these values, the adaptability of different wrist designs to specific tasks can be quantitatively evaluated, thus providing a strong basis for selecting the most suitable robotic arm configuration.

[0083] Furthermore, it can also be used for teleoperation training. Specifically, firstly, a task weight matrix is ​​constructed based on the specific operation task, then the joint weight vector is determined based on the physical speed limit of the robot joints, and subsequently, operability assessment information is calculated in real time during operation. When the operability assessment information is detected to meet the operability threshold, the current operation posture is determined to be inefficient. At this time, the operator is notified of the situation in real time and prompted to make corrections, helping the operator optimize the operation posture and improve operation efficiency and accuracy.

[0084] Of course, it can also be used to optimize operational performance. Specifically, in teleoperation scenarios, when the operability assessment information shows a downward trend or falls below expectations, a better robotic arm configuration can be switched in a timely manner according to the actual situation. For autonomous robots, during task execution, based on the real-time calculated operability assessment information, the robot adjusts its posture according to the preset optimization strategy until it meets the upper limit of operability requirements, so that the robot always completes the task in a better posture and improves the overall operational performance.

[0085] The above text combined Figure 1 The embodiments of the robot evaluation method of this application are described in detail below, in conjunction with... Figure 2 This application provides a detailed description of embodiments of the robot evaluation apparatus. It should be understood that the descriptions of the robot evaluation method embodiments correspond to the descriptions of the robot evaluation apparatus embodiments; therefore, any parts not described in detail can be found in the preceding method embodiments.

[0086] Figure 2 The diagram shown is a structural schematic of a robot evaluation device provided in an embodiment of this application. Figure 2 As shown, the robot evaluation device 20 provided in this application embodiment includes:

[0087] The first determining module 210 is used to determine the weights corresponding to the robot's degrees of freedom of motion based on the robot's task to be performed.

[0088] The second determining module 220 is used to determine the weight of the target joint based on the upper limit of the movement speed of the target joint, wherein the target joint includes the joints involved in the task to be performed;

[0089] The calculation module 230 is used to calculate the operability evaluation information of the robot in the current configuration based on the weights corresponding to the robot's degrees of freedom and the weights corresponding to the target joints. The operability evaluation information represents the robot's ability to complete the task to be performed in the current configuration.

[0090] In one embodiment of this application, the motion degrees of freedom include translational degrees of freedom and rotational degrees of freedom; the first determining module 210 is further configured to determine the task type of the task to be performed; and based on the task type of the task to be performed, determine the respective weights of the robot's translational degrees of freedom and rotational degrees of freedom.

[0091] In one embodiment of this application, the first determining module 210 is further configured to: if the task type is a translation-dominant task, configure the weight of the translation degree of freedom to be higher than the weight of the rotation degree of freedom; if the task type is a rotation-dominant task, configure the weight of the rotation degree of freedom to be higher than the weight of the translation degree of freedom; if the task type is a composite task, adjust the weight ratio of the translation degree of freedom and the rotation degree of freedom based on the action characteristics of the task to be executed.

[0092] In one embodiment of this application, the second determining module 220 is further configured to determine the upper limit of the movement speed of the target joint as the weight corresponding to the target joint.

[0093] In one embodiment of this application, the calculation module 230 is further configured to: construct a task weight matrix by assigning weights corresponding to the robot's degrees of freedom of motion, wherein the task weight matrix is ​​a diagonal matrix and the values ​​of the elements on the diagonal of the diagonal matrix correspond one-to-one with the values ​​of the weights of each degree of freedom of motion; construct a joint weight vector by assigning weights corresponding to the target joints; and calculate the operability evaluation information of the robot in the current configuration based on the task weight matrix, the Jacobian matrix corresponding to the task weight matrix, and the joint weight vector.

[0094] In one embodiment of this application, the robot evaluation device 20 further includes an adjustment module, used to adjust the zero-space component of the motion velocity of the target joint when the operability evaluation information meets the lower operability requirement, until the operability evaluation information meets the upper operability requirement. The lower operability requirement represents the minimum operability evaluation information value required for the robot to complete the task to be performed, and the upper operability requirement represents the maximum operability evaluation information value that the robot can achieve in the task to be performed.

[0095] In one embodiment of this application, the adjustment module is further configured to determine the null component of the motion velocity of the target joint based on the product of the partial derivative of the target joint angle with the operability assessment information and the target scaling factor.

[0096] Below, for reference Figure 3 This describes an electronic device according to embodiments of the present application. Figure 3 The diagram shown is a structural schematic of an electronic device provided in an exemplary embodiment of this application.

[0097] like Figure 3 As shown, the electronic device 30 includes one or more processors 301 and memory 302.

[0098] The processor 301 may be a central processing unit (CPU) or other form of processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 30 to perform desired functions.

[0099] The memory 302 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 301 may execute the program instructions to implement the robot evaluation methods of the various embodiments of this application described above and / or other desired functions.

[0100] In one example, the electronic device 30 may also include an input device 303 and an output device 304, which are interconnected via a bus system and / or other forms of connection mechanism (not shown).

[0101] The input device 303 may include, for example, a keyboard, a mouse, etc.

[0102] The output device 304 can output various information to the outside. The output device 304 may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0103] Of course, for the sake of simplicity, Figure 3 Only some of the components of the electronic device 30 relevant to this application are shown in this illustration; components such as buses, input / output interfaces, etc., are omitted. In addition, the electronic device 30 may include any other suitable components depending on the specific application.

[0104] In addition to the methods and apparatus described above, embodiments of this application may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps in the robot evaluation methods according to various embodiments of this application as described above.

[0105] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0106] Furthermore, embodiments of this application may also be computer-readable storage media storing computer program instructions that, when executed by a processor, cause the processor to perform the steps in the robot evaluation methods according to various embodiments of this application described above.

[0107] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may, for example, include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0108] The basic principles of this application have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this application are merely examples and not limitations, and should not be considered as essential features of each embodiment of this application. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the application to the necessity of employing the aforementioned specific details for implementation.

[0109] The block diagrams of devices, apparatuses, devices, and systems involved in this application are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0110] It should also be noted that in the apparatus, equipment, and methods of this application, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions of this application.

[0111] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of this application. Therefore, this application is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0112] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this application to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A robot evaluation method, characterized in that, include: Based on the task to be performed by the robot, determine the weights corresponding to the robot's degrees of freedom of motion; Based on the upper limit of the movement speed of the target joint, the weight corresponding to the target joint is determined, and the target joint includes the joints involved in the task to be performed; Based on the weights corresponding to the robot's degrees of freedom and the weights corresponding to the target joints, the operability assessment information of the robot in the current configuration is calculated. The operability assessment information represents the robot's ability to complete the task to be performed in the current configuration.

2. The robot evaluation method according to claim 1, characterized in that, The degrees of freedom of motion include translational degrees of freedom and rotational degrees of freedom. The determination of the weights corresponding to the robot's degrees of freedom based on the robot's task to be performed includes: Determine the task type of the task to be executed; Based on the task type of the task to be performed, the weights of the robot's translational and rotational degrees of freedom are determined.

3. The robot evaluation method according to claim 2, characterized in that, The determination of the weights of the robot's translational and rotational degrees of freedom based on the task type of the task to be executed includes: If the task type is a translation-dominant task, then the weight of the translation degree of freedom is configured to be higher than the weight of the rotation degree of freedom; If the task type is a rotation-dominated task, then the weight of the rotation degree of freedom is configured to be higher than the weight of the translation degree of freedom; If the task type is a composite task, the weight ratio of the translational degree of freedom and the rotational degree of freedom is adjusted based on the action characteristics of the task to be executed.

4. The robot evaluation method according to claim 1, characterized in that, The determination of the weight corresponding to the target joint based on the upper limit of the target joint's motion velocity includes: The upper limit of the movement speed of the target joint is determined as the weight corresponding to the target joint.

5. The robot evaluation method according to any one of claims 1 to 4, characterized in that, After calculating the operability evaluation information of the robot in the current configuration based on the weights corresponding to the robot's degrees of freedom and the weights corresponding to the target joints, the method further includes: If the operability assessment information meets the lower operability requirement, the null-space component of the motion velocity of the target joint is adjusted until the operability assessment information meets the upper operability requirement. The lower operability requirement represents the minimum operability assessment information value required for the robot to complete the task to be performed, and the upper operability requirement represents the maximum operability assessment information value that the robot can achieve in the task to be performed.

6. The robot evaluation method according to claim 5, characterized in that, Also includes: Based on the product of the partial derivative of the angle of the target joint with the operability assessment information and the target scaling factor, the null space component of the motion velocity of the target joint is determined.

7. The robot evaluation method according to any one of claims 1 to 4, characterized in that, The calculation of the robot's operability assessment information in the current configuration, based on the weights corresponding to the robot's degrees of freedom and the weights corresponding to the target joints, includes: The weights corresponding to the robot's degrees of freedom of motion are constructed into a task weight matrix. The task weight matrix is ​​a diagonal matrix, and the element values ​​on the diagonal of the diagonal matrix correspond one-to-one with the values ​​of the weights of each degree of freedom of motion. The weights corresponding to the target joints are constructed into a joint weight vector; Based on the task weight matrix, the Jacobian matrix corresponding to the task weight matrix, and the joint weight vector, the operability evaluation information of the robot under the current configuration is calculated.

8. A computer-readable storage medium, characterized in that, The storage medium stores a computer program for executing the robot evaluation method according to any one of claims 1 to 7.

9. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is used to execute the robot evaluation method according to any one of claims 1 to 7.

10. A computer program product, characterized in that, The computer program product includes instructions that, when executed on an electronic device, cause the electronic device to implement the robot evaluation method according to any one of claims 1 to 7.

Images