Intelligent control method, device and equipment for heavy-load robot

Abstract

The present invention relates to an intelligent control method, device and equipment for a heavy-load robot, belonging to the field of heavy-load robots. The present invention calculates the torque information received by each lever arm in each operable posture according to the mass information of the goods and the operable posture data set of the heavy-load robot, and finally obtains the operating posture of the heavy-load robot in the process of picking and unloading goods according to the torque information received by each lever arm in the operable posture and the motion path of the position of the goods during the handling process, and controls the heavy-load robot according to the operating posture of the heavy-load robot in the process of picking and unloading goods. The present invention fully considers the change of the maximum load torque of each lever arm of the heavy-load robot under different operating postures, so that the heavy-load robot changes the operating posture according to the maximum load torque characteristics, which can increase the service life of the heavy-load robot, reduce the maintenance cost of the heavy-load robot, and make the control of the heavy-load robot more reasonable.

Description

Technical Field

[0001] The present invention relates to the technical field of heavy-load robots, and in particular to an intelligent control method, device and equipment for a heavy-load robot. Background Art

[0002] With the development of the economy, labor costs have increased. In the absence of population welfare, many companies are in urgent need of industrial upgrading. The use of industrial robots is an important means of industrial upgrading. The robots on the market are diverse in form and variety, and are widely applicable in a wide range of scenarios. They can be used in handling, grinding, welding, spraying, assembly, cutting, engraving and other tasks. You must clearly understand your own needs and the performance description and application scenarios of the robot before you can determine the load of the robot. In today's society, due to the high load capacity and high efficiency of robots, they are gradually replacing manual labor to perform some tasks that are highly repetitive, work-intensive, and in harsh working environments. Heavy-load robots that carry goods are one of them. Nowadays, since most heavy-load robots are composed of multiple levers, when carrying goods, after a certain number of years of use, the maximum torque that each heavy-load robot's lever can withstand will become smaller. For different heavy objects, the torques received in different operating postures will change, resulting in different torques acting on the corresponding levers. This problem is not considered in the prior art, resulting in the heavy-load robot's lever arms being scrapped in an instant or having a low service life when carrying heavy objects, resulting in excessively high maintenance costs for the heavy-load robots. Summary of the invention

[0003] The present invention overcomes the deficiencies of the prior art and provides an intelligent control method, device and equipment for a heavy-load robot.

[0004] To achieve the above object, the technical solution adopted by the present invention is:

[0005] A first aspect of the present invention provides an intelligent control method for a heavy-load robot, comprising the following steps:

[0006] Acquire the pickup position information and unloading position information of the heavy-load robot, and simulate the running posture of the heavy-load robot according to the pickup position information and unloading position information of the heavy-load robot to obtain an operational posture data set of the heavy-load robot;

[0007] Initialize the motion trajectory of the cargo position during the picking and unloading process according to the picking and unloading position information of the heavy-load robot, optimize the motion trajectory of the cargo position during the picking and unloading process, and obtain the motion path of the cargo position during the handling process;

[0008] Obtaining the mass information of the goods, and calculating the torque information of each lever arm in each operable posture according to the mass information of the goods and the operable posture data set of the heavy-load robot;

[0009] The operating posture of the heavy-load robot during the picking and unloading process is obtained according to the torque information of each lever in the operable posture and the motion path of the cargo during the handling process, and the heavy-load robot is controlled according to the operating posture of the heavy-load robot during the picking and unloading process.

[0010] Furthermore, in this method, the operation posture of the heavy-load robot is simulated according to the pickup position information and the unloading position information of the heavy-load robot to obtain an operable posture data set of the heavy-load robot, which specifically includes:

[0011] Obtain the working range area of ​​each arm of the heavy-load robot, and obtain the running posture range collection of each arm of the heavy-load robot according to the working range area of ​​each arm of the heavy-load robot, and count the running posture range collection of each arm of the heavy-load robot to obtain the running posture data set of the heavy-load robot;

[0012] Obtain obstacle information at the current position according to the cargo pickup position information of the heavy-load robot, perform feature extraction on the obstacle information at the current position, and obtain volume information and position information of the obstacle;

[0013] The running posture with obstacles is calculated according to the running posture data set of the heavy-load robot, the volume information and the position information of the obstacles, and the running posture with obstacles is counted to obtain the running posture data set with obstacles;

[0014] The running posture data set with obstacles is eliminated from the running posture data set of the heavy-load robot, the runnable posture data set of the heavy-load robot is obtained, and the runnable posture data set of the heavy-load robot is output.

[0015] Furthermore, in this method, the motion trajectory of the cargo position during the unloading movement is initialized according to the cargo pickup position information and the cargo unloading position information of the heavy-load robot, and the motion trajectory of the cargo position during the cargo pickup and unloading movement is optimized to obtain the motion path of the cargo position during the handling process, specifically including:

[0016] Obtaining the cargo pickup position information and cargo unloading position information of the heavy-load robot, and using the cargo pickup position information and cargo unloading position information of the heavy-load robot as the initial position and the final position of the cargo during the unloading movement;

[0017] Initialize the motion trajectory of the cargo position during the unloading movement according to the initial position and the terminal position of the cargo position during the unloading movement, and calculate the travel distance value of the motion trajectory of the cargo position during the unloading movement;

[0018] When the travel distance value of the motion trajectory of the location of the cargo during the unloading movement is lower than the preset travel distance value, the motion trajectory of the location of the cargo during the unloading movement is output, and the motion trajectory of the location of the cargo during the unloading movement is output as the motion path of the location of the cargo during the handling process;

[0019] When the travel distance value of the motion trajectory of the cargo position during the unloading movement is not less than the preset travel distance value, the motion trajectory of the cargo position during the unloading movement is adjusted until it is not less than the preset travel distance value.

[0020] Furthermore, in this method, the mass information of the goods is obtained, and the torque information of each lever arm in each operable posture is calculated according to the mass information of the goods and the operable posture data set of the heavy-load robot, specifically including:

[0021] Acquire the design element characteristic data of the heavy-load robot, and construct a model diagram of the heavy-load robot according to the design element characteristic data of the heavy-load robot, and at the same time, obtain the quality information of the goods;

[0022] According to the operable posture data set of the heavy-load robot and the model diagram of the heavy-load robot, an operation model diagram corresponding to each operation posture is obtained, and the gravity information of the cargo is calculated according to the mass information of the cargo;

[0023] According to the operation model diagram corresponding to the operation posture and the gravity information of the cargo, the force analysis of each arm of the heavy-load robot is performed to obtain the torque information of each arm, and the torque information of each arm is counted to obtain the torque information of each arm in each operable posture.

[0024] Furthermore, in this method, the operating posture of the heavy-load robot during the unloading process is obtained according to the torque information of each lever arm in the operable posture and the motion path of the position of the cargo during the handling process, which specifically includes:

[0025] A genetic algorithm is introduced, and the genetic algebra is set according to the genetic algorithm. The motion path of the cargo position during the handling process is divided into several sub-paths, and the set of operable postures of the heavy-load robot in each sub-path is obtained, and the combination of operating postures of each sub-path is configured in each sub-path.

[0026] Initialize each sub-path running posture combination according to the set of runnable postures of the heavy-load robot in each sub-path, and obtain the torque information of each lever arm in each running posture in each sub-path running posture combination according to the torque information of each lever arm in the runnable posture;

[0027] Obtain the maximum bearing torque information of each force arm in the heavy-load robot, and determine whether the torque information of each force arm in each running posture in each sub-path running posture combination is greater than the maximum bearing torque information of the relative stress arm;

[0028] If it is greater than, perform inheritance according to genetic algebra, adjust the running posture in each sub-path running posture combination until it is no greater than the maximum bearing torque information of the relative stress arm, output, output the running posture combination of each sub-path, and count the running posture combination of each sub-path to obtain the running posture of the heavy-load robot during the picking and unloading process.

[0029] Furthermore, in this method, the following steps are also included:

[0030] Obtaining historical service data information of the heavy-load robot, and building a performance degradation prediction model based on a deep neural network, inputting the historical service data information of the heavy-load robot into the performance degradation model for training, and obtaining a trained performance degradation prediction model;

[0031] Obtaining service data information of the heavy-load robot within a preset time, and inputting the service data information of the heavy-load robot within the preset time into a performance degradation prediction model for prediction, and obtaining performance characteristic data information within the current preset time;

[0032] The maximum bearing torque information of each arm of the heavy-load robot is updated according to the performance characteristic data information within the current preset time, and the updated maximum bearing torque information of each arm of the heavy-load robot is obtained;

[0033] The running posture of the heavy-load robot during the picking and unloading process is readjusted according to the updated maximum bearing torque information of each force arm in the heavy-load robot.

[0034] A second aspect of the present invention provides an intelligent control device for a heavy-load robot, the device comprising a memory and a processor, the memory comprising an intelligent control method program for the heavy-load robot, and when the intelligent control method program for the heavy-load robot is executed by the processor, the following steps are implemented:

[0035] Acquire the pickup position information and unloading position information of the heavy-load robot, and simulate the running posture of the heavy-load robot according to the pickup position information and unloading position information of the heavy-load robot to obtain an operational posture data set of the heavy-load robot;

[0036] Initialize the motion trajectory of the cargo position during the picking and unloading process according to the picking and unloading position information of the heavy-load robot, optimize the motion trajectory of the cargo position during the picking and unloading process, and obtain the motion path of the cargo position during the handling process;

[0037] Obtaining the mass information of the goods, and calculating the torque information of each lever arm in each operable posture according to the mass information of the goods and the operable posture data set of the heavy-load robot;

[0038] The operating posture of the heavy-load robot during the picking and unloading process is obtained according to the torque information of each lever in the operable posture and the motion path of the cargo during the handling process, and the heavy-load robot is controlled according to the operating posture of the heavy-load robot during the picking and unloading process.

[0039] A third aspect of the present invention provides an intelligent control device for a heavy-load robot, comprising:

[0040] An acquisition module is used to acquire the pickup position information and the unloading position information of the heavy-load robot, and simulate the running posture of the heavy-load robot according to the pickup position information and the unloading position information of the heavy-load robot to acquire an operable posture data set of the heavy-load robot;

[0041] The motion path calculation module initializes the motion trajectory of the cargo position during the picking and unloading process according to the picking and unloading position information of the heavy-load robot, optimizes the motion trajectory of the cargo position during the picking and unloading process, and obtains the motion path of the cargo position during the handling process;

[0042] The torque analysis module obtains the mass information of the goods and calculates the torque information of each lever arm in each operable posture according to the mass information of the goods and the operable posture data set of the heavy-load robot;

[0043] The operation posture generation module obtains the operation posture of the heavy-load robot during the picking and unloading process according to the torque information of each lever in the operable posture and the motion path of the cargo position during the handling process, and controls the heavy-load robot according to the operation posture of the heavy-load robot during the picking and unloading process.

[0044] The fourth aspect of the present invention provides a computer-readable storage medium, which includes a program for an intelligent control method for a heavy-load robot. When the program for the intelligent control method for a heavy-load robot is executed by a processor, any step of the intelligent control method for a heavy-load robot is implemented.

[0045] The present invention solves the defects existing in the background technology and has the following beneficial effects:

[0046] The present invention obtains the picking-up position information and the unloading position information of the heavy-load robot, and simulates the running posture of the heavy-load robot according to the picking-up position information and the unloading position information of the heavy-load robot, obtains the operable posture data set of the heavy-load robot, and then initializes the motion trajectory of the position of the goods during the unloading movement according to the picking-up position information and the unloading position information of the heavy-load robot, and optimizes the motion trajectory of the position of the goods during the picking-up and unloading movement to obtain the motion path of the position of the goods during the handling process, thereby obtaining the quality information of the goods, and calculating the torque information of each lever in each operable posture according to the quality information of the goods and the operable posture data set of the heavy-load robot, finally, according to the torque information of each lever in the operable posture and the motion path of the position of the goods during the handling process, the running posture of the heavy-load robot in the picking-up and unloading process is obtained, and the heavy-load robot is controlled according to the running posture of the heavy-load robot in the picking-up and unloading process. The present invention fully considers the changes in the maximum load torque of each lever arm of the heavy-load robot under different operating postures, so that the heavy-load robot changes its operating posture according to the maximum load torque characteristics, which can increase the service life of the heavy-load robot, reduce the maintenance cost of the heavy-load robot, and make the control of the heavy-load robot more reasonable. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, drawings of other embodiments can be obtained based on these drawings without paying creative work.

[0048] Figure 1 The overall method flow chart of the intelligent control method of the heavy-load robot is shown;

[0049] Figure 2 A first method flow chart of an intelligent control method for a heavy-load robot is shown;

[0050] Figure 3 A device block diagram of an intelligent control device for a heavy-load robot is shown;

[0051] Figure 4 A structural schematic diagram of an intelligent control device for a heavy-load robot is shown. DETAILED DESCRIPTION

[0052] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0053] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0054] like Figure 1 As shown, the first aspect of the present invention provides an intelligent control method for a heavy-load robot, comprising the following steps:

[0055] S102: Obtaining the pickup position information and the unloading position information of the heavy-load robot, and simulating the running posture of the heavy-load robot according to the pickup position information and the unloading position information of the heavy-load robot to obtain an operational posture data set of the heavy-load robot;

[0056] like Figure 2 As shown, it should be noted that, in this step, specifically including:

[0057] S202: Obtain the working range area of ​​each lever arm of the heavy-load robot, and obtain the running posture range collection of each lever arm of the heavy-load robot according to the working range area of ​​each lever arm of the heavy-load robot, and count the running posture range collection of each lever arm of the heavy-load robot to obtain the running posture data set of the heavy-load robot;

[0058] S204: Obtain obstacle information at the current position according to the cargo pickup position information of the heavy-load robot, and perform feature extraction on the obstacle information at the current position to obtain volume information and position information of the obstacle;

[0059] S206: Calculate the running posture with obstacles according to the running posture data set of the heavy-load robot, the volume information and the position information of the obstacles, and count the running posture with obstacles to obtain the running posture data set with obstacles;

[0060] S208: Eliminate the running posture data set with obstacles from the running posture data set of the heavy-load robot, obtain the operable posture data set of the heavy-load robot, and output the operable posture data set of the heavy-load robot.

[0061] It should be noted that, in fact, each force arm has a certain working range in three-dimensional space due to the influence of the designed length, width, height and other data, which leads to certain limitations in the working range of the heavy-load robot's running posture in three-dimensional space. The running posture of the heavy-load robot is simulated through virtual reality technology and three-dimensional modeling technology to form a data set. Among them, in the actual working environment, the heavy-load robot is affected by obstacles, and the heavy-load robot should avoid obstacles when setting the handling running posture, so as to obtain the operational posture data set of the heavy-load robot.

[0062] S104: Initializing the motion trajectory of the cargo position during the picking and unloading movement according to the picking and unloading position information of the heavy-load robot, and optimizing the motion trajectory of the cargo position during the picking and unloading movement to obtain the motion path of the cargo position during the handling process;

[0063] This step specifically includes:

[0064] Obtaining the cargo pickup position information and cargo unloading position information of the heavy-load robot, and using the cargo pickup position information and cargo unloading position information of the heavy-load robot as the initial position and the final position of the cargo during the unloading movement;

[0065] Initialize the motion trajectory of the cargo position during the unloading movement according to the initial position and the terminal position of the cargo position during the unloading movement, and calculate the travel distance value of the motion trajectory of the cargo position during the unloading movement;

[0066] When the travel distance value of the motion trajectory of the location of the cargo during the unloading movement is lower than the preset travel distance value, the motion trajectory of the location of the cargo during the unloading movement is output, and the motion trajectory of the location of the cargo during the unloading movement is output as the motion path of the location of the cargo during the handling process;

[0067] When the travel distance value of the motion trajectory of the cargo position during the unloading movement is not less than the preset travel distance value, the motion trajectory of the cargo position during the unloading movement is adjusted until it is not less than the preset travel distance value.

[0068] It should be noted that the motion trajectory of the cargo position during the unloading movement is initialized based on the heavy-load robot's picking position information, unloading position information, and the cargo position during the unloading movement, and a preset driving distance value is set. The motion trajectory of the cargo position during the unloading movement is optimized according to the preset driving distance value, so that the motion trajectory of the cargo position during the unloading movement is not greater than the preset driving distance value, making the motion trajectory of the heavy-load robot more reasonable.

[0069] S106: Obtaining the mass information of the goods, and calculating the torque information of each lever arm in each operable posture according to the mass information of the goods and the operable posture data set of the heavy-load robot;

[0070] This step specifically includes:

[0071] Acquire the design element characteristic data of the heavy-load robot, and construct a model diagram of the heavy-load robot according to the design element characteristic data of the heavy-load robot, and at the same time, obtain the quality information of the goods;

[0072] According to the operable posture data set of the heavy-load robot and the model diagram of the heavy-load robot, an operation model diagram corresponding to each operation posture is obtained, and the gravity information of the cargo is calculated according to the mass information of the cargo;

[0073] According to the operation model diagram corresponding to the operation posture and the gravity information of the cargo, the force analysis of each arm of the heavy-load robot is performed to obtain the torque information of each arm, and the torque information of each arm is counted to obtain the torque information of each arm in each operable posture.

[0074] It should be noted that a heavy-load robot model diagram is constructed by using 3D modeling software (such as SolidWorks, UG, Maya software, etc.), so as to perform force analysis on each lever of the heavy-load robot according to the gravity information of the cargo and the characteristic data of the design elements of the heavy-load robot, so as to obtain the torque information of each lever in each operable posture; wherein, the characteristic data of the design elements of the heavy-load robot include the length, width, height of the lever in the heavy-load robot, the rated load torque data of the motor, etc.

[0075] S108: Obtain the operating posture of the heavy-load robot during the picking and unloading process based on the torque information of each lever in the operable posture and the motion path of the cargo during the handling process, and control the heavy-load robot according to the operating posture of the heavy-load robot during the picking and unloading process.

[0076] Furthermore, in step S108 of the method, it specifically includes:

[0077] A genetic algorithm is introduced, and the genetic algebra is set according to the genetic algorithm. The motion path of the cargo position during the handling process is divided into several sub-paths, and the set of operable postures of the heavy-load robot in each sub-path is obtained, and the combination of operating postures of each sub-path is configured in each sub-path.

[0078] Initialize each sub-path running posture combination according to the set of runnable postures of the heavy-load robot in each sub-path, and obtain the torque information of each lever arm in each running posture in each sub-path running posture combination according to the torque information of each lever arm in the runnable posture;

[0079] Obtain the maximum bearing torque information of each force arm in the heavy-load robot, and determine whether the torque information of each force arm in each running posture in each sub-path running posture combination is greater than the maximum bearing torque information of the relative stress arm;

[0080] If it is greater than, perform inheritance according to genetic algebra, adjust the running posture in each sub-path running posture combination until it is no greater than the maximum bearing torque information of the relative stress arm, output, output the running posture combination of each sub-path, and count the running posture combination of each sub-path to obtain the running posture of the heavy-load robot during the picking and unloading process.

[0081] It should be noted that, if the heavy object is regarded as a point, the movement path of the cargo during the handling process is equivalent to the movement of a point of the heavy object. Since the heavy-load robot has multiple degrees of freedom, there may be multiple operating postures at each point, that is, keeping the position of the heavy object unchanged, the heavy-load robot has multiple movement postures. Due to different operating postures (the combination of the movement conditions of each force arm), the torques on the force arms of the heavy-load robot are different. The genetic algorithm is used to find the operating posture of the heavy-load robot in the process of picking and unloading, so that the torque information on each force arm in each operating posture in each sub-path operating posture combination is not greater than the maximum bearing torque information of the relative stress arm (such as the real-time torque information of the A force arm is lower than the maximum bearing torque information of the A force arm, and the real-time torque information of the B force arm is lower than the maximum bearing torque information of the B force arm), thereby improving the control rationality of the heavy-load robot.

[0082] Furthermore, in this method, the following steps are also included:

[0083] Obtaining historical service data information of the heavy-load robot, and building a performance degradation prediction model based on a deep neural network, inputting the historical service data information of the heavy-load robot into the performance degradation model for training, and obtaining a trained performance degradation prediction model;

[0084] Obtaining service data information of the heavy-load robot within a preset time, and inputting the service data information of the heavy-load robot within the preset time into a performance degradation prediction model for prediction, and obtaining performance characteristic data information within the current preset time;

[0085] The maximum bearing torque information of each arm of the heavy-load robot is updated according to the performance characteristic data information within the current preset time, and the updated maximum bearing torque information of each arm of the heavy-load robot is obtained;

[0086] The running posture of the heavy-load robot during the picking and unloading process is readjusted according to the updated maximum bearing torque information of each force arm in the heavy-load robot.

[0087] It should be noted that the historical service data information of the heavy-load robot is the characteristic data of the change of the maximum bearing torque. This method can predict the performance characteristic data information of the maximum bearing torque within a preset time, and adjust the operating posture in time, thereby improving the control rationality of the heavy-load robot.

[0088] In addition, the method may further comprise the following steps:

[0089] Obtaining the maximum bearing torque information of each force arm in each heavy-load robot in the current target area, and obtaining the maximum bearing torque information with the minimum value according to the maximum bearing torque information of each force arm in each heavy-load robot;

[0090] Obtaining order information of the current goods, obtaining weight information of the goods in the current order according to the order information of the goods, and calculating estimated torque information of each force arm in each operating posture of the heavy-load robot according to the weight information of the goods in the current order;

[0091] Obtaining the estimated torque information of the maximum value according to the estimated torque information received by each lever arm in the heavy-load robot in each operating posture, and determining whether the estimated torque information of the minimum value is greater than the maximum bearing torque information with the minimum value;

[0092] If the estimated torque information of the maximum value is not greater than the maximum bearing torque information of the minimum value, the corresponding heavy-load robot will be treated as a heavy-load robot working normally. If it is greater, the corresponding heavy-load robot will be treated as an abnormally working heavy-load robot, and the work of the heavy-load robot working normally will be assigned.

[0093] It should be noted that if the estimated torque information of the minimum value is not greater than the maximum bearing torque information with the minimum value, it means that the heavy-load robot is not suitable for carrying the current heavy object. This method can improve the rationality of the work allocation of the heavy-load robot.

[0094] In addition, the method may further comprise the following steps:

[0095] Obtaining order information of current goods, and extracting weight information of goods in the order according to the order information of current goods, and calculating estimated bearing moment information of each force arm of each normally working heavy-load robot under each operating posture according to the weight information of goods in the order;

[0096] Obtaining the maximum value of the estimated torque information in each lever arm under each operating posture of the normally working heavy-load robot, and predicting the predicted time threshold range within which the maximum torque of each lever arm is less than the maximum value of the estimated torque information in each lever arm under each operating posture of the normally working heavy-load robot through the performance degradation prediction model;

[0097] Acquire the handling efficiency information and workload of the heavy-load robot, and calculate the time point when the handling is completed according to the handling efficiency information and workload of the heavy-load robot;

[0098] When the time point of completion of the transportation falls within the predicted time threshold range where the maximum bearing torque of each force arm is less than the maximum value of the estimated bearing torque information of each force arm under each operating posture of the normally operating heavy-load robot, the workload of the heavy-load robot is readjusted.

[0099] It should be noted that when the time point of completion of the transportation falls within the predicted time threshold range where the maximum bearing torque of each force arm is less than the maximum value of the estimated bearing torque information of each force arm under each operating posture of the normally working heavy-load robot, it means that no matter how the operating posture of the heavy-load robot is adjusted, the heavy-load robot will cause abnormal operation. This method can further optimize the workload of the heavy-load robot and make the workload distribution more reasonable.

[0100] like Figure 3 As shown, the second aspect of the present invention provides an intelligent control device 4 for a heavy-load robot, the device 4 includes a memory 41 and a processor 42, the memory 41 includes an intelligent control method program for the heavy-load robot, and when the intelligent control method program for the heavy-load robot is executed by the processor 42, the following steps are implemented:

[0101] Acquire the pickup position information and unloading position information of the heavy-load robot, and simulate the running posture of the heavy-load robot according to the pickup position information and unloading position information of the heavy-load robot to obtain an operational posture data set of the heavy-load robot;

[0102] Initialize the motion trajectory of the cargo position during the picking and unloading process according to the picking and unloading position information of the heavy-load robot, optimize the motion trajectory of the cargo position during the picking and unloading process, and obtain the motion path of the cargo position during the handling process;

[0103] Obtaining the mass information of the goods, and calculating the torque information of each lever arm in each operable posture according to the mass information of the goods and the operable posture data set of the heavy-load robot;

[0104] The operating posture of the heavy-load robot during the picking and unloading process is obtained according to the torque information of each lever in the operable posture and the motion path of the cargo during the handling process, and the heavy-load robot is controlled according to the operating posture of the heavy-load robot during the picking and unloading process.

[0105] like Figure 4 As shown, the third aspect of the present invention provides an intelligent control device for a heavy-load robot, comprising:

[0106] An acquisition module 10 acquires the pickup position information and the unloading position information of the heavy-load robot, and simulates the running posture of the heavy-load robot according to the pickup position information and the unloading position information of the heavy-load robot to acquire an operable posture data set of the heavy-load robot;

[0107] The motion path calculation module 20 initializes the motion trajectory of the cargo position during the picking and unloading motion according to the picking and unloading position information of the heavy-load robot, optimizes the motion trajectory of the cargo position during the picking and unloading motion, and obtains the motion path of the cargo position during the handling process;

[0108] The torque analysis module 30 obtains the mass information of the goods, and calculates the torque information of each lever arm in each operable posture according to the mass information of the goods and the operable posture data set of the heavy-load robot;

[0109] The operation posture generation module 40 obtains the operation posture of the heavy-load robot during the picking and unloading process according to the torque information of each lever in the operable posture and the motion path of the cargo position during the handling process, and controls the heavy-load robot according to the operation posture of the heavy-load robot during the picking and unloading process.

[0110] The fourth aspect of the present invention provides a computer-readable storage medium, which includes a program for an intelligent control method for a heavy-load robot. When the program for the intelligent control method for a heavy-load robot is executed by a processor, any step of the intelligent control method for a heavy-load robot is implemented.

[0111] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0112] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0113] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0114] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0115] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0116] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An intelligent control method for a heavy-load robot, characterized in that: The following steps are involved: Acquire the cargo pickup position information and cargo unloading position information of the heavy-load robot, and simulate the operation posture of the heavy-load robot according to the cargo pickup position information and cargo unloading position information of the heavy-load robot to obtain an operable posture data set of the heavy-load robot; Initialize the motion trajectory of the cargo position during the picking and unloading movement according to the picking and unloading position information of the heavy-load robot, optimize the motion trajectory of the cargo position during the picking and unloading movement, and obtain the motion path of the cargo position during the handling process; Obtaining mass information of the cargo, and calculating the torque information of each lever arm in each operable posture according to the mass information of the cargo and an operable posture data set of the heavy-load robot; The operation posture of the heavy-load robot during the process of picking up and unloading goods is obtained according to the torque information of each lever arm in the operable posture and the motion path of the position of the goods during the handling process, and the heavy-load robot is controlled according to the operation posture of the heavy-load robot during the process of picking up and unloading goods; The operation posture of the heavy-load robot in the process of picking up and unloading is obtained according to the torque information of each lever arm in the operable posture and the motion path of the position of the cargo during the handling process, specifically including: A genetic algorithm is introduced, and a genetic algebra is set according to the genetic algorithm, so as to divide the motion path of the position of the cargo during the handling process into a plurality of sub-paths, and a set of operable postures of the heavy-load robot in each sub-path is obtained, and a combination of operating postures of each sub-path is configured in each sub-path; Initializing the operation posture combination of each sub-path according to the operable posture collection of the heavy-load robot in each sub-path, and obtaining the torque information of each lever arm in each operation posture in the operation posture combination of each sub-path according to the torque information of each lever arm in the operable posture; Obtaining the maximum bearing torque information of each force arm in the heavy-load robot, and determining whether the torque information received by each force arm in each running posture in each sub-path running posture combination is greater than the maximum bearing torque information of the relative stress arm; If it is greater than, perform inheritance according to the genetic algebra, adjust the running posture in each sub-path running posture combination until it is no greater than the maximum bearing torque information of the relative stress arm, output each sub-path running posture combination, and count each sub-path running posture combination to obtain the running posture of the heavy-load robot in the process of picking up and unloading; The following steps are also included: Acquire historical service data information of the heavy-load robot, and construct a performance degradation prediction model based on a deep neural network, input the historical service data information of the heavy-load robot into the performance degradation prediction model for training, and obtain a trained performance degradation prediction model; Obtaining service data information of the heavy-load robot within a preset time, and inputting the service data information of the heavy-load robot within the preset time into the performance degradation prediction model for prediction, and obtaining performance characteristic data information within the current preset time; Updating the maximum bearing torque information of each lever arm in the heavy-load robot according to the performance characteristic data information within the current preset time, and obtaining the updated maximum bearing torque information of each lever arm in the heavy-load robot; The running posture of the heavy-load robot during the picking and unloading process is readjusted according to the updated maximum bearing torque information of each force arm in the heavy-load robot.

2. The intelligent control method for a heavy-load robot according to claim 1, characterized in that: The operation posture of the heavy-load robot is simulated according to the pickup position information and the unloading position information of the heavy-load robot to obtain an operable posture data set of the heavy-load robot, specifically including: Obtaining the working range area of ​​each lever arm of the heavy-load robot, and obtaining the running posture range collection of each lever arm of the heavy-load robot according to the working range area of ​​each lever arm of the heavy-load robot, and counting the running posture range collection of each lever arm of the heavy-load robot to obtain the running posture data set of the heavy-load robot; Obtain obstacle information at the current position according to the cargo pickup position information of the heavy-load robot, and perform feature extraction on the obstacle information at the current position to obtain volume information and position information of the obstacle; Calculating the running posture with obstacles according to the running posture data set of the heavy-load robot, the volume information and the position information of the obstacles, and counting the running posture with obstacles to obtain the running posture data set with obstacles; The running posture data set with obstacles is removed from the running posture data set of the heavy-load robot, the operable posture data set of the heavy-load robot is obtained, and the operable posture data set of the heavy-load robot is output.

3. The intelligent control method for a heavy-load robot according to claim 1, characterized in that: Initializing the motion trajectory of the cargo position during the picking and unloading movement according to the picking and unloading position information of the heavy-load robot, and optimizing the motion trajectory of the cargo position during the picking and unloading movement to obtain the motion path of the cargo position during the handling process, specifically including: Acquire the cargo pickup position information and cargo unloading position information of the heavy-load robot, and use the cargo pickup position information and cargo unloading position information of the heavy-load robot as the initial position and the final position of the cargo during the unloading movement; Initializing the motion trajectory of the cargo position during the unloading movement according to the initial position and the final position of the cargo position during the unloading movement, and calculating the travel distance value of the motion trajectory of the cargo position during the unloading movement; When the travel distance value of the motion trajectory of the location of the cargo during the unloading movement is lower than the preset travel distance value, the motion trajectory of the location of the cargo during the unloading movement is output, and the motion trajectory of the location of the cargo during the unloading movement is output as the motion path of the location of the cargo during the handling process; When the travel distance value of the motion trajectory of the cargo position during the unloading movement is not less than the preset travel distance value, the motion trajectory of the cargo position during the unloading movement is adjusted until it is less than the preset travel distance value.

4. The intelligent control method for a heavy-load robot according to claim 1, characterized in that: Obtaining the mass information of the goods, and calculating the torque information of each lever arm in each operable posture according to the mass information of the goods and the operable posture data set of the heavy-load robot, specifically including: Acquire design element characteristic data of the heavy-load robot, and construct a model diagram of the heavy-load robot according to the design element characteristic data of the heavy-load robot, and at the same time, acquire quality information of the goods; Obtaining an operation model diagram corresponding to each operation posture according to the operable posture data set of the heavy-load robot and the model diagram of the heavy-load robot, and calculating the gravity information of the cargo according to the mass information of the cargo; According to the operation model diagram corresponding to the operation posture and the gravity information of the cargo, a force analysis is performed on each arm of the heavy-load robot to obtain the torque information of each arm, and the torque information of each arm is counted to obtain the torque information received by each arm in each operable posture.

5. An intelligent control device for a heavy-load robot, characterized in that: The device includes a memory and a processor, wherein the memory includes an intelligent control method program for a heavy-load robot, and when the intelligent control method program for the heavy-load robot is executed by the processor, the following steps are implemented: Acquire the cargo pickup position information and cargo unloading position information of the heavy-load robot, and simulate the operation posture of the heavy-load robot according to the cargo pickup position information and cargo unloading position information of the heavy-load robot to obtain an operable posture data set of the heavy-load robot; Initialize the motion trajectory of the cargo position during the picking and unloading movement according to the picking and unloading position information of the heavy-load robot, optimize the motion trajectory of the cargo position during the picking and unloading movement, and obtain the motion path of the cargo position during the handling process; Obtaining mass information of the cargo, and calculating the torque information of each lever arm in each operable posture according to the mass information of the cargo and an operable posture data set of the heavy-load robot; The operation posture of the heavy-load robot during the process of picking up and unloading goods is obtained according to the torque information of each lever arm in the operable posture and the motion path of the position of the goods during the handling process, and the heavy-load robot is controlled according to the operation posture of the heavy-load robot during the process of picking up and unloading goods; The operation posture of the heavy-load robot in the process of picking up and unloading is obtained according to the torque information of each lever arm in the operable posture and the motion path of the position of the cargo during the handling process, specifically including: A genetic algorithm is introduced, and a genetic algebra is set according to the genetic algorithm, so as to divide the motion path of the position of the cargo during the handling process into a plurality of sub-paths, and a set of operable postures of the heavy-load robot in each sub-path is obtained, and a combination of operating postures of each sub-path is configured in each sub-path; Initializing the operation posture combination of each sub-path according to the operable posture collection of the heavy-load robot in each sub-path, and obtaining the torque information of each lever arm in each operation posture in the operation posture combination of each sub-path according to the torque information of each lever arm in the operable posture; Obtaining the maximum bearing torque information of each force arm in the heavy-load robot, and determining whether the torque information received by each force arm in each running posture in each sub-path running posture combination is greater than the maximum bearing torque information of the relative stress arm; If it is greater than, perform inheritance according to the genetic algebra, adjust the running posture in each sub-path running posture combination until it is no greater than the maximum bearing torque information of the relative stress arm, output each sub-path running posture combination, and count each sub-path running posture combination to obtain the running posture of the heavy-load robot in the process of picking up and unloading; The following steps are also included: Acquire historical service data information of the heavy-load robot, and construct a performance degradation prediction model based on a deep neural network, input the historical service data information of the heavy-load robot into the performance degradation prediction model for training, and obtain a trained performance degradation prediction model; Obtaining service data information of the heavy-load robot within a preset time, and inputting the service data information of the heavy-load robot within the preset time into the performance degradation prediction model for prediction, and obtaining performance characteristic data information within the current preset time; Updating the maximum bearing torque information of each arm of the heavy-load robot according to the performance characteristic data information within the current preset time, and obtaining the updated maximum bearing torque information of each arm of the heavy-load robot; The running posture of the heavy-load robot during the picking and unloading process is readjusted according to the updated maximum bearing torque information of each force arm in the heavy-load robot.

6. An intelligent control device for a heavy-load robot, characterized in that: include: An acquisition module is used to acquire the pickup position information and the unloading position information of the heavy-load robot, and simulate the running posture of the heavy-load robot according to the pickup position information and the unloading position information of the heavy-load robot to acquire an operable posture data set of the heavy-load robot; A motion path calculation module initializes the motion trajectory of the cargo position during the picking and unloading motion according to the picking and unloading position information of the heavy-load robot, optimizes the motion trajectory of the cargo position during the picking and unloading motion, and obtains the motion path of the cargo position during the handling process; The torque analysis module obtains the mass information of the goods and calculates the torque information of each lever arm in each operable posture according to the mass information of the goods and the operable posture data set of the heavy-load robot; An operation posture generating module is used to obtain the operation posture of the heavy-load robot during the process of picking up and unloading goods according to the torque information of each lever arm in the operable posture and the motion path of the position of the goods during the handling process, and control the heavy-load robot according to the operation posture of the heavy-load robot during the process of picking up and unloading goods; The operation posture of the heavy-load robot in the process of picking up and unloading is obtained according to the torque information of each lever arm in the operable posture and the motion path of the position of the cargo during the handling process, specifically including: A genetic algorithm is introduced, and a genetic algebra is set according to the genetic algorithm, so as to divide the motion path of the position of the cargo during the handling process into a plurality of sub-paths, and a set of operable postures of the heavy-load robot in each sub-path is obtained, and a combination of operating postures of each sub-path is configured in each sub-path; Initializing the operation posture combination of each sub-path according to the operable posture collection of the heavy-load robot in each sub-path, and obtaining the torque information of each lever arm in each operation posture in the operation posture combination of each sub-path according to the torque information of each lever arm in the operable posture; Obtaining the maximum bearing torque information of each force arm in the heavy-load robot, and determining whether the torque information received by each force arm in each running posture in each sub-path running posture combination is greater than the maximum bearing torque information of the relative stress arm; If it is greater than, perform inheritance according to the genetic algebra, adjust the running posture in each sub-path running posture combination until it is no greater than the maximum bearing torque information of the relative stress arm, output each sub-path running posture combination, and count each sub-path running posture combination to obtain the running posture of the heavy-load robot in the process of picking up and unloading; The following steps are also included: Acquire historical service data information of the heavy-load robot, and construct a performance degradation prediction model based on a deep neural network, input the historical service data information of the heavy-load robot into the performance degradation prediction model for training, and obtain a trained performance degradation prediction model; Obtaining service data information of the heavy-load robot within a preset time, and inputting the service data information of the heavy-load robot within the preset time into the performance degradation prediction model for prediction, and obtaining performance characteristic data information within the current preset time; Updating the maximum bearing torque information of each lever arm in the heavy-load robot according to the performance characteristic data information within the current preset time, and obtaining the updated maximum bearing torque information of each lever arm in the heavy-load robot; The running posture of the heavy-load robot during the picking and unloading process is readjusted according to the updated maximum bearing torque information of each force arm in the heavy-load robot.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes an intelligent control method program for a heavy-load robot. When the intelligent control method program for a heavy-load robot is executed by a processor, the steps of the intelligent control method for a heavy-load robot as described in any one of claims 1 to 4 are implemented.

Images