WO2024008232A1

WO2024008232A1 - Method for the dynamic detection of ratcheting in a collaborative robot by means of artifical intelligence and dynamic compensation of the trajectories

Info

Publication number: WO2024008232A1
Application number: PCT/DE2023/100476
Authority: WO
Inventors: Kazuaki Kaneko
Original assignee: Schaeffler Technologies AG & Co. KG
Priority date: 2022-07-07
Filing date: 2023-06-23
Publication date: 2024-01-11
Also published as: DE102022116969A1

Abstract

The invention relates to a method for the detection of ratcheting during operation of a robot, in particular a collaborative robot, in relation to at least one joint of the robot, in particular of the collaborative robot, on the basis of operating data of the robot by means of artificial intelligence comprising the following steps: providing of operating data, in particular current flow data, in relation to a time behaviour of a motor, in particular a servomotor, of a robot; detecting of ratcheting of a joint of the robot, in particular in the case of a strain wave gear mechanism, a harmonic drive and/or ellipto-centric gear mechanism, by evaluation of the operating data as indirect or direct input data for an artificial intelligence system yielding output data, wherein the output data of the artificial intelligence system comprise an indicator which indicates whether ratcheting has occurred in relation to the joint, in particular the gear mechanism.

Description

Method for dynamic detection of ratcheting in a collaborative robot using artificial intelligence and dynamic compensation of trajectories

TECHNICAL FIELD

The present invention relates generally to the technical field of robotics, autonomous mobile robots (AMRs) and in particular collaborative robots (cobots) and safety and precision technology in the workplace and in assembly plants.

BACKGROUND

Cobot systems have been used in more and more facilities in recent years. This has led to human workers increasingly sharing the same space with cobot systems. Such robots are designed to be particularly collaborative. For example, movements should initially be stopped if objects or workers are in the way in order to prevent damage and injuries. So-called voltage wave gears (harmonic drive I harmonic gear box) are often used as transmissions. Here, particularly in collision-stopped movements, a process that is often referred to as ratcheting can occur. In this case, an internal toothing of a transmission can slip or be displaced relative to one another by, for example, one tooth, but also by several teeth.

It has always been difficult to correctly determine this ratcheting, both in quantitative and qualitative terms. For example, if ratcheting is not taken into account or ratcheting that has occurred remains unobserved, it can happen, among other things, that a robot - and thus also the end effector - stops in the wrong end positions, etc.

It is therefore an object of the present invention to further develop collaborative robot systems in such a way that they can fulfill their tasks very reliably and in a robust manner, especially in shared work environments with people.

US7439693B2 discloses a method for detecting anomalies and a

Engine control device. The procedure for detecting anomalies in a linear

Movement device, wherein a motor control device of a motor having a driving a movable body of a linear motion device includes the following steps: detecting a position or a speed of the movable body; performing feedback control to supply current or voltage to the motor based on the detection result; and detecting an abnormality of the linear motion device based on an abnormal signal component included in a waveform of the supply current or the supply voltage.

Here, a control unit of a motor driver performs feedback control to power a linear motor based on a detection value of a linear encoder. An anomaly detection unit monitors the supply current to the linear motor, and the anomaly detection unit detects an abnormality of a linear motion device based on a waveform of the supply current. When an anomaly is detected, the user is alerted using a lamp, buzzer, email, or similar. Therefore, the abnormality of the linear motion device can be detected early and accurately.

SUMMARY OF REVELATION

The present invention provides a method according to claim 1. Accordingly, a method is provided for detecting ratcheting in the operation of a robot, in particular a cobot, in relation to at least one joint of the robot, in particular of the cobot, based on operating data of the robot using artificial intelligence, comprising the following steps: providing operating data, in particular current flow data, in relation to a time behavior of a motor, in particular a servo motor, of a robot, detecting a ratcheting of a joint of the robot, in particular in the case of a voltage wave gear, wave gear and/or sliding wedge gear, by evaluating the operating data as indirect or direct input data of an artificial intelligence with receipt of output data, the output data of the artificial intelligence comprising an indicator which indicates whether ratcheting has occurred in relation to the joint, in particular the gear.

The artificial intelligence determines particularly precisely whether ratcheting has occurred. The precision is higher than with conventional methods.

For example, the time behavior of a current flow is described by data, which can serve as input data for artificial intelligence. In this way, the plaintiff can classify whether ratcheting occurred during the relevant period of time or not. For example, ratcheting can also be quantified. For example, in the case of a tension shaft gear, for example, it can be determined how many teeth were skipped during ratcheting.

The Kl also takes on this task with greater precision than is the case with other or known methods.

The invention further creates a cobot according to claim 5. Accordingly, a cobot is provided, comprising a robotic device, in particular a robot arm and / or an assembly system, wherein the robotic device has one or more joints which can be moved by motors, in particular servo motors or several motor control units for controlling the motors, the cobot also being set up to use artificial intelligence to detect ratcheting of a joint, in particular in the case of a tension wave gear, wave gear and/or sliding wedge gear, by evaluating operating data as indirect or direct input data of the artificial intelligence, wherein the operating data includes data, in particular current flow data, relating to a time behavior of a motor of the robot.

The invention also creates artificial intelligence and a suitable training procedure. According to the invention, an artificial intelligence, in particular linear and/or non-linear regression, fast Fourier transformation and/or support vector machine and/or an artificial neural network, in particular recurrent neural network, is provided, which is set up to determine Presence or absence of ratcheting of a transmission, in particular in a cobot, and/or a determination of a number of teeth which were skipped in a transmission during ratcheting, comprising one or more input neurons for recording input data comprising data based on operating data, in particular current flow data , in relation to a time behavior of a motor, in particular a servo motor.

According to a further development, the artificial intelligence is set up to provide output data which includes an indicator which indicates whether ratcheting has occurred in relation to the joint, in particular the gearbox.

In this way, the appropriately trained AI can immediately and reliably produce labels that describe the presence or absence of ratcheting.

For example, such labels can be expressed by “0” and “1”, where “1” is describes ratcheting that has occurred. Corresponding technical corrective actions are reliably made possible.

According to a further development, output data further indicates an extent of ratcheting that has occurred, if such ratcheting has occurred, in particular a number of teeth that were skipped in a gearbox during ratcheting and/or an angle skipped by the ratcheting.

In this way, the appropriately trained AI can immediately and reliably produce labels that quantify ratcheting. For example, such labels can be expressed by “0”, “1”, “2”, “3” etc., where the number indicates how many teeth were skipped. This labeling of the Kl is a more precise determination than that based on traditional methods. Corresponding technical corrective actions are reliably made possible.

According to a further development, the cobot is further set up to calculate a corrected trajectory and/or corrected control instruction, in particular based on the number of teeth that were skipped during ratcheting and/or based on the angle skipped through ratcheting.

For example, a value for a current angle is corrected in the control so that after ratcheting occurs, it again corresponds to the angle actually present on the robot.

In this way, the determination of the Kl can be used for improved dynamic behavior of the robotic device.

According to a further development, the cobot comprises a central control unit and at least one motor control unit, wherein the central control unit and the motor control unit can communicate with one another via a bus, in particular an Ethernet bus, in particular a determination of whether ratcheting has occurred in relation to a joint assigned engine control unit, in particular a determination of a number of teeth that were skipped in a gearbox during ratcheting takes place in an assigned engine control unit, in particular a calculation of a corrected trajectory and / or corrected control instruction taking place in the central control unit. This division of work and communication between the central control unit and engine control units is particularly resource-saving, which enables effective ratcheting detection and dynamic correction in real time. BRIEF DESCRIPTION OF THE DRAWINGS

Preferred embodiments of the present disclosure are described below with reference to the following figures:

Fig. 1: a flowchart (in the form of a repeat loop) for a central control unit for detecting ratcheting according to embodiments of the invention, including compensation.

Fig. 2: a flowchart (in the form of a repeat loop) for a motor control unit for detecting ratcheting according to embodiments of the invention, including quantitative determination of the skipped teeth.

DETAILED DESCRIPTION

Figure 1 shows a flowchart (in the form of a repeat loop) for a central control unit for detecting ratcheting according to embodiments of the invention, including compensation.

At step 101, it is checked whether a ratcheting error (ratcheting occurrence) has been received by a joint (or its motor control unit).

If this is the case, a value for a currently occupied angle is corrected in step 102. It is corrected by the angle caused by the ratcheting. For example, this depends on a number of skipped teeth and/or on one or more total numbers of teeth that are present in the corresponding gear.

For example, a special mode is adopted by the central control unit, which is only adopted if ratcheting has been observed.

At step 103, corresponding variables for current end effector positions of the cobot are updated. In one example, this is a calculation based on the result from step 102. In step 104, a trajectory that the joint should traverse in the future is recalculated or updated. For example, this is calculated so that the robot can achieve a configuration that would have occurred if the ratcheting had not taken place. But there are also other behaviors possible. For example, an LS PB method (linear segments with parabolic blends) is used to calculate the trajectory.

In step 105, the central control unit returns to a normal mode. This is the mode normally used unless revenge occurs. This is the mode in which the central control unit was at the beginning 101 of the flowchart.

The flowchart is ended by the end 110.

Figure 2 shows a flowchart (in the form of a repeat loop) for a motor control unit for detecting ratcheting according to embodiments of the invention, including quantitative determination of the skipped teeth.

In step 201, timing data, for example a motor current flow of an articulated motor, is loaded into a calculation buffer. In step 202, Kl according to the invention is used to determine whether ratcheting has occurred at the joint (and, if necessary, quantified). If ratcheting is positively detected at branch 203, a corresponding ratcheting error code is output to a communications bus. This way the central control unit can find out about the error/ratcheting. For example, the error code contains information about how many teeth were skipped.

The flowchart is ended by the end 210.

The embodiments described schematically here can be further developed by numerous details of the invention, in particular those already described above.

Although some aspects have been described in the context of a device, it is clear that these aspects also represent a description of the corresponding method, where a block or a device corresponds to a method step or a function of a method step. Analogously, aspects that are described as part of a method step also represent a description of a corresponding block or element or a property of a corresponding device.

Embodiments of the invention can be implemented in a computer system. The computing system may be a local computing device (e.g., personal computer, laptop, tablet computer, or cell phone) with one or more processors and one or more storage devices, or may be a distributed computing system (e.g., a Cloud computing system with one or more processors or one or more storage devices distributed in different locations, for example at a local client and / or one or more remote server farms and / or data centers). The computer system may include any circuit or combination of circuits. In one embodiment, the computer system may include one or more processors, which may be of any type. As used herein, processor may mean any type of computing circuit such as, but not limited to, a microprocessor, a microcontroller, a complex instruction set microprocessor (CISC), a reduced instruction set microprocessor (RISC), a very long instruction word processor. (Very Long Instruction Word; VLIW) microprocessor, a graphics processor, a digital signal processor (DSP), a multi-core processor, a field programmable gate array (FPGA), or any other type of processor or processing circuit. Other types of circuits that may be included in the computer system may include a custom-built circuit, an application-specific integrated circuit (ASIC), or the like, such as one or more circuits (e.g., a communications circuit) for use with wireless devices such as . B. cell phones, tablet computers, laptop computers, walkie-talkies and similar electronic systems. The computer system may include one or more storage devices, which may include one or more storage elements suitable for the particular application, such as a main memory in the form of a random access memory (RAM), one or more hard drives, and/or a or multiple drives that handle removable media such as CDs, flash memory cards, DVDs and the like. The computer system may also include a display device, one or more speakers, and a keyboard and/or controller, which may include a mouse, trackball, touch screen, voice recognition device, or any other device that allows a system user to enter information into the computer system and information to receive from the same.

Some or all of the method steps may be performed by (or using) a hardware device, such as a processor, a microprocessor, a programmable computer, or an electronic circuit. In some embodiments, one or more of the key method steps may be performed by such a device. Depending on particular implementation requirements, embodiments of the invention may be implemented in hardware or software. The implementation may be performed with a non-volatile storage medium such as a digital storage medium such as a floppy disk, a DVD, a Blu-Ray, a CD, a ROM, a PROM and EPROM, an EEPROM or a FLASH memory in which electronically readable control signals are stored, which interact (or can interact) with a programmable computer system in such a way that the respective method is carried out. Therefore, the digital storage medium can be computer readable.

Some embodiments according to the invention include a data carrier with electronically readable control signals that can interact with a programmable computer system to perform one of the methods described herein.

In general, embodiments of the present invention may be implemented as a computer program product with program code, the program code being effective for executing one of the methods when the computer program product is running on a computer. The program code can, for example, be stored on a machine-readable medium.

Further exemplary embodiments include the computer program for carrying out one of the methods described herein, which is stored on a machine-readable medium.

In other words, an embodiment of the present invention is therefore a computer program having program code for carrying out one of the methods described herein when the computer program runs on a computer.

Therefore, another embodiment of the present invention is a storage medium (or a data carrier or a computer-readable medium) that includes, stored thereon, a computer program for carrying out one of the methods described herein when executed by a processor. The data carrier, digital storage medium or recorded medium is usually tangible and/or non-seamless. Another embodiment of the present invention is an apparatus as described herein that includes a processor and the storage medium. A further exemplary embodiment of the invention is therefore a data stream or a signal sequence that represents the computer program for carrying out one of the methods described herein. The data stream or the signal sequence can, for example, be configured so that they are transmitted via a data communication connection, for example via the Internet.

Another embodiment includes a processing means, for example a computer or a programmable logic device, configured or adapted to carry out any of the methods described herein.

Another embodiment includes a computer on which the computer program for executing one of the methods described herein is installed.

Another embodiment according to the invention includes an apparatus or system configured to transmit (e.g., electronically or optically) to a receiver a computer program for carrying out one of the methods described herein. The receiver may be, for example, a computer, a mobile device, a storage device, or the like. The device or system may, for example, include a file server for transmitting the computer program to the recipient.

In some embodiments, a programmable logic device (e.g., a field programmable gate array, FPGA) may be used to perform some or all of the functionality of the methods described herein. In some embodiments, a field programmable gate array may cooperate with a microprocessor to perform any of the methods described herein. In general, the methods are preferably performed by each hardware device.

Embodiments may be based on using a machine learning model and/or machine learning algorithm (so-called artificial intelligence). Machine learning can refer to algorithms and statistical models that computer systems can use to perform a specific task without using explicit instructions, rather than relying on models and inference. In machine learning, for example, instead of a rule-based transformation of data, a transformation of data can be used that can be derived from an analysis of historical and/or training data. For example, the content of images under Analyzed using a machine learning model or using a machine learning algorithm. In order for the machine learning model to analyze the content of an image, the machine learning model can be trained using training images as input and training content information as output. By training the machine learning model with a large number of training images and/or training sequences (e.g. words or sentences) and associated training content information (e.g. labels or annotations), the machine learning model “learns” the content of the images recognize so that the content of images not included in the training data can be recognized using the machine learning model. The same principle can be used for other types of sensor data as well: By training a machine learning model using training sensor data and a desired output, the machine learning model "learns" a transformation between the sensor data and the output, which can be used to create a Provide output based on non-training sensor data provided to the machine learning model. The provided data (e.g. sensor data, metadata and/or image data) can be preprocessed to obtain a feature vector, which is used as input for the machine learning model.

Machine learning models can be trained using training input data. The examples above use a training method called “supervised learning.” In supervised learning, the machine learning model is trained using a plurality of training samples, where each sample represents a plurality of input data values and a plurality of desired output values, i.e. H. Each training sample is assigned a desired output value, which can include. By specifying both training samples and desired output values, the machine learning model “learns” what output value to provide based on an input sample that is similar to the samples provided during training. In addition to supervised learning, semi-supervised learning can also be used. In semi-supervised learning, some of the training samples lack a desired output value. Supervised learning can be based on a supervised learning algorithm (e.g. a classification algorithm, a regression algorithm, or a similarity learning algorithm).

Classification algorithms can be used when the outputs are restricted to a limited set of values (categorical variables), i.e. the input is classified as one from the limited set of values. Regression algorithms can be used when the outputs are of any numerical value (within a range) identify. Similarity learning algorithms can be similar to both classification and regression algorithms, but are based on learning from examples using a similarity function that measures how similar or related two objects are. In addition to supervised learning or semi-supervised learning, unsupervised learning can be used to train the machine learning model. In unsupervised learning, input data may be provided (only) and an unsupervised learning algorithm may be used to find structure in the input data (e.g. by grouping or clustering the input data, finding commonalities in the data). Clustering is the assignment of input data comprising a plurality of input values into subsets (clusters) such that input values within the same cluster are similar according to one or more (predefined) similarity criteria, while they are dissimilar to input values comprised in other clusters.

Reinforcement learning is a third group of machine learning algorithms. In other words, reinforcement learning can be used to train the machine learning model. Reinforcement learning involves training one or more software actors (so-called “software agents”) to perform actions in an environment. Based on the actions taken, a reward is calculated. Reinforcement learning is based on training the one or more software agents to select the actions in such a way that the cumulative reward is increased, resulting in software agents that become better at the task they are given (as by increasing rewards proven).

Furthermore, some techniques can be applied to some of the machine learning algorithms. For example, feature learning can be used. In other words, the machine learning model may be at least partially trained using feature learning and/or the machine learning algorithm may include a feature learning component. Feature learning algorithms, called representation learning algorithms, can preserve the information in their input but transform it in a way that makes it useful, often as a preprocessing stage before performing classification or prediction. For example, feature learning can be based on principal component analysis or cluster analysis.

In some examples, anomaly detection (i.e., outlier detection) may be used, which aims to provide identification of input values that raise suspicion because they differ significantly from the majority of input and training data differentiate. In other words, the machine learning model may be at least partially trained using anomaly detection, and/or the machine learning algorithm may include an anomaly detection component.

In some examples, the machine learning algorithm may use a decision tree as a prediction model. In other words, the machine learning model can be based on a decision tree. In a decision tree, the observations about an item (e.g., a set of input values) can be represented by the branches of the decision tree, and an output value corresponding to the item can be represented by the leaves of the decision tree. Decision trees can support both discrete values and continuous values as output values. When discrete values are used, the decision tree can be called a classification tree; when continuous values are used, the decision tree can be called a regression tree.

Association rules are another technique that can be used in machine learning algorithms. In other words, the machine learning model can be based on one or more association rules. Association rules are created by identifying relationships between variables in large sets of data. The machine learning algorithm may identify and/or use one or more ratio rules that represent the knowledge derived from the data. The rules can e.g. B. be used to store, manipulate or apply knowledge.

Machine learning algorithms are usually based on a machine learning model. In other words, the term “machine learning algorithm” can mean a set of instructions that can be used to create, train, or use a machine learning model. The term “machine learning model” may mean a data structure and/or a set of rules that represents the learned knowledge (e.g. based on the training performed by the machine learning algorithm). In embodiments, the use of a machine learning algorithm may imply the use of an underlying machine learning model (or a plurality of underlying machine learning models). The use of a machine learning model may imply that the machine learning model and/or the data structure/set of rules that is/are the machine learning model is trained by a machine learning algorithm. For example, the machine learning model can be an artificial neural network (ANN). ANNs are systems inspired by biological neural networks such as those found in a retina or brain. ANNs include a plurality of interconnected nodes and a plurality of connections, called edges, between the nodes. There are usually three types of nodes, input nodes that receive input values, hidden nodes that are (only) connected to other nodes, and output nodes that provide output values. Each node can represent an artificial neuron. Each edge can send information from one node to another. The output of a node can be defined as a (nonlinear) function of the inputs (e.g. the sum of its inputs). A node's inputs can be used in the function based on a "weight" of the edge or node providing the input. The weight of nodes and/or edges can be adjusted in the learning process. In other words, training an artificial neural network may include adjusting the weights of the nodes and/or edges of the artificial neural network, ie, to achieve a desired output for a particular input.

Alternatively, the machine learning model can be a support vector machine, a random forest model or a gradient boosting model. Support Vector Machines are supervised learning models with associated learning algorithms that can be used to analyze data (e.g. in a classification or regression analysis). Support vector machines can be trained by providing input with a plurality of training input values belonging to one of two categories. The support vector machine can be trained to assign a new input value to either category. Alternatively, the machine learning model may be a Bayesian network, which is a probabilistic directed acyclic graphical model. A Bayesian network can represent a set of random variables and their conditional dependencies using a directed acyclic graph. Alternatively, the machine learning model may be based on a genetic algorithm, which is a search algorithm and heuristic technique that mimics the process of natural selection.

Claims

EXPECTATIONS

1 . Method for detecting ratcheting in the operation of a robot, in particular a cobot, in relation to at least one joint of the robot, in particular of the cobot, based on operating data of the robot using artificial intelligence, comprising the following steps:

Providing operating data, in particular current flow data, in relation to a time behavior of a motor, in particular a servo motor, of a robot,

Detecting a ratcheting of a joint of the robot, in particular in the case of a tension shaft gear, wave gear and/or sliding wedge gear, by evaluating the operating data as indirect or direct input data of an artificial intelligence to obtain output data, the output data of the artificial intelligence comprising an indicator which indicates whether Ratcheting has occurred in relation to the joint, especially the gearbox.

2. The method according to claim 1, wherein the artificial intelligence uses a technique of supervised or semi-supervised learning, in particular linear and / or non-linear regression, fast Fourier transformation and / or support vector machine and / or a Artificial neural network, especially recurrent neural network.

3. The method according to claim 1 or 2, wherein the output data further indicates an extent of ratcheting that has occurred, if such has occurred, in particular a number of teeth that were skipped in a gearbox during ratcheting and / or one that was skipped by the ratcheting Angle.

4. The method according to claim 3, further comprising a step of calculating a corrected trajectory and/or corrected control instruction, in particular based on the number of teeth that were skipped during ratcheting and/or based on the angle skipped by the ratcheting.

5. Cobot, comprising: a robotic device, in particular a robot arm and/or an assembly system, wherein the robotic device has one or more joints which can be moved by motors, in particular servo motors, one or more motor control units for controlling the motors, the cobot also being set up to do so by means of Artificial intelligence recognizes a ratcheting of a joint, in particular in the case of a voltage shaft gear, wave gear and / or sliding wedge gear, by evaluating operating data as indirect or direct input data of the artificial intelligence, the operating data being data, in particular current flow data, in relation to a time behavior of a motor of the robot include.

6. Cobot according to claim 5, wherein the artificial intelligence is set up to provide output data which includes an indicator which indicates whether ratcheting has occurred in relation to the joint, in particular the transmission.

7. Cobot according to claim 5 or 6, wherein output data further indicates an extent of ratcheting that has occurred, if such has occurred, in particular a number of teeth that were skipped in a gear during ratcheting, and / or an angle skipped by the ratcheting .

8. Cobot according to one of claims 5 - 7, further set up to calculate a corrected trajectory and / or corrected control instruction, in particular based on the number of teeth that were skipped during ratcheting and / or based on the number of teeth skipped by ratcheting angle.

9. Cobot according to one of claims 5 - 8, comprising a central control unit and at least one motor control unit, wherein the central control unit and the engine control unit can communicate with one another via a bus, in particular an Ethernet bus, in particular a determination of whether ratcheting has occurred in relation to a joint takes place in an assigned engine control unit, in particular a determination of a number of teeth, which were skipped in a transmission during ratcheting, takes place in an assigned engine control unit, in particular a calculation of a corrected trajectory and / or corrected control instruction taking place in the central control unit. Computer, computer system or computer network which are set up to locally or non-locally effect the method according to one of claims 1 - 4. Artificial intelligence, in particular machine learning model, in particular linear and/or non-linear regression, fast Fourier transformation and/or support vector machine and/or an artificial neural network, in particular recurrent neural network, set up to determine presence or absence a ratcheting of a transmission, in particular in a cobot, and/or a determination of a number of teeth which were skipped in a transmission during ratcheting, comprising one or more input neurons for recording input data comprising data based on o operating data, in particular current flow data, in Reference to the time behavior of a motor, especially a servo motor. Method for training an artificial intelligence according to claim 11, in particular through supervised or semi-supervised learning, using the following data sets as input data:

Data sets comprising data relating to a time behavior of a motor, in particular current flow data, which are provided with classifying labels as to whether the data correspond to ratcheting that has occurred or not. The method of claim 12, wherein the labels further index a number of teeth that were skipped in ratcheting corresponding to the data.

A computer program comprising instructions which, when executed by a computer, cause the computer to carry out the method according to any one of claims 1-4, 12 or 13.