Safety device for an industrial robot

Abstract

Safety device for an industrial robot, comprising - a detection device designed to detect a potential hazardous condition for a body part of a person who is in the vicinity of the industrial robot, caused by a component of the industrial robot or an object moved by the industrial robot, - a safety measure device designed to carry out a safety measure by which the hazardous condition is reduced or avoided, - a control device which is signal-coupled to the detection device and the safety measure device and is designed to carry out an assessment of a potential hazardous condition detected by the detection device on the basis of predetermined criteria and, depending on the assessment, to control the safety measure device to execute a first safety measure, characterized in that the detection device comprises an image detection device which is oriented to carry out an image detection in a hazard zone which comprises the industrial robot and a spatial section surrounding the industrial robot, and the control device is designed to carry out the assessment on the basis of a temporally successive sequence of images with image data captured by the image detection device, wherein the control device is programmed to - to recognize a body part of the user in each image of the sequence of images based on the image data, - to determine the position of the detected body part within a spatial reference system, - to calculate the direction and speed of movement of the detected body part by comparing the respective position of the detected body part in two or more consecutive images, - to determine the position, direction of movement and speed of a potentially injury-prone component of the industrial robot and, if applicable, of an object moved by the industrial robot, - by comparing the determined position and the calculated direction and speed of movement of the detected body part with the position, direction and speed of movement of the injury-risk component of the industrial robot, to calculate whether contact between the detected or another body part of the user and the injury-risk component of the industrial robot is to be expected within a predetermined or calculated period of time, and if so, to generate a first hazard signal and send it to the safety measure device, wherein the safety measure device is designed to execute the first safety measure upon receipt of the first hazard signal.

Description

[0001] The invention relates to a safety device for an industrial robot, comprising a detection device which is designed to detect a potential hazardous condition for a body part of a person who is in the vicinity of the industrial robot, by a component of the industrial robot or an object moved by the industrial robot, a safety measure device which is designed to carry out a safety measure by which the hazardous condition is reduced or avoided, a control device which is signal-coupled to the detection device and the safety measure device and is designed to carry out an evaluation of a potential hazardous condition detected by the detection device on the basis of predetermined criteria and, depending on the evaluation, to control the safety measure device to carry out a first safety measure.

[0002] Safety devices for industrial robots are designed to prevent collisions between the industrial robot and people, vehicles, or other objects. Due to the large range of motion that an industrial robot can cover and the often multiple axes of motion that an industrial robot has, the demands placed on such safety systems are high. It is generally known to design a safety system in such a way that one or more sensors detect whether a person is located within the entire range that the industrial robot can cover and in which there is therefore a risk of collision with the person. If such a potentially hazardous situation is detected by the sensors, the movement of the industrial robot can be stopped, thus preventing a collision between the industrial robot and the person.The disadvantage of this safety concept, however, is that a relatively large area covered by the industrial robot is monitored, and upon entering this area, the robot's safety stop is triggered, regardless of whether the industrial robot actually extends into the area where the person is located. This severely limits the possibilities for performing a human activity in interaction with a robot, as the safety system always requires a distance between people and the robot's potential range of movement.

[0003] US 2021 / 053227 A1 discloses a safety system that improves the ability of a person to work within the range of a robot. This safety system provides a plurality of sensors that capture images of a portion of a workspace and perform object recognition to detect a person and the robot. This object recognition is used to detect the person and the robot, as well as their movements, and thus to actually detect an approach of the person to the robot. In the event of such an approach, the robot's movement is stopped to maintain a safety distance between the robot and the person. A safety device functioning in a similar manner is also previously known from DE 10 2017 221 305 A1.While this type of safety device requires considerably greater computing power to monitor the dangerous proximity between a person and the robot in real time and to ensure that the robot's movement is shut down in a timely manner before contact occurs between the robot and the person, it has the advantage that a person can, in principle, enter the movement area covered by the robot without the robot's movement being immediately stopped, as long as the robot does not approach the person in a critical manner within this movement area. A disadvantage of this safety system, however, is that the person's interaction with the robot is only possible to a limited extent, because if the safety distance between the person and the robot is exceeded, the robot's movement is shut down.

[0004] The invention is based on the object of providing a safety system for industrial robots which enables interaction between the industrial robot and a person in a better way.

[0005] This object is achieved with a safety device of the type described above, in which the detection device comprises an image capture device which is oriented to carry out an image capture in a hazard zone comprising the industrial robot and a spatial section surrounding the industrial robot, and the control device is designed to carry out the assessment based on a temporally successive sequence of images captured by the image capture device with image data, wherein the control device is programmed to detect a body part of the user in each image of the sequence of images based on the image data, to determine the position of the detected body part within a spatial reference system,to calculate the direction of movement and the speed of movement of the detected body part by comparing the respective position of the detected body part in two or more consecutive images, to determine the position, direction of movement and speed of movement of a component of the industrial robot that may cause injury and, if applicable, of an object moved by the industrial robot, to calculate, by comparing the determined position and the calculated direction of movement and speed of movement of the detected body part with the position, direction of movement and speed of movement of the component of the industrial robot that may cause injury, whether contact between the detected or another body part of the user and the component of the industrial robot that may cause injury is to be expected within a predetermined or calculated period of time, and if so,to generate a first hazard signal and to send it to the safety measure device, wherein the safety measure device is designed to execute the first safety measure upon receipt of the first hazard signal.

[0006] The safety device according to the invention fundamentally comprises a detection device, a safety measure device, and a control device. The detection device serves to detect a potentially hazardous condition, which is understood to be a situation caused by the position, movement, and acceleration of a body part of a person or an entire person on the one hand, and a component of the industrial robot on the other, which can lead to injury to the person through contact with the component of the industrial robot. A component of the industrial robot is understood here to mean, on the one hand, the industrial robot and its structural components, i.e., typically housing-enclosed robot arms, joint arrangements, actuators, or the like, which constitute the actual industrial robot.Furthermore, such components of the industrial robot can also be understood as tools that the industrial robot guides or objects that the industrial robot grasps and which, due to the movements of the industrial robot, can come into proximity with the person and cause injury. In the safety device according to the invention, the detection device comprises an image detection device, which can be a device for capturing images in the visible light range, infrared, by means of actively transmitting and receiving electromagnetic radiation, or by passively receiving ambient radiation. The image detection device is designed, in particular, to continuously and in real time capture the danger zone.The image capture device may be formed by a single sensor that surveys the entire area; however, the image capture device preferably comprises multiple sensors that capture the hazard area from different positions and / or with different capture directions, wherein the areas captured by the individual sensors may partially or completely overlap for redundancy purposes, and by combining the multiple image capture areas, an overall image of the hazard area is obtained.

[0007] The safety measure device is a device that, when a condition occurs that would lead to an injury, takes a safety measure suitable for preventing that injury. The safety measure device can be implemented in a specific controller or in the programming of a controller of the industrial robot, which, for example, triggers a stop or deceleration of the movement of the industrial robot as a measure, thereby preventing a situation that could cause an injury.The safety measure device can also alternatively or additionally take further measures, for example emitting warning signals such as optical or acoustic signals that are perceptible to the user and warn him of the potential injury. Furthermore, alternatively or additionally, active protective measures can also be carried out by the safety measure device, for example shielding components that pose a risk of injury, such as sharp-edged tools, a partial stop of certain movements of individual components of the robot, for example rotating tools of the robot or crushing gripping elements of the robot.The safety measure device can also control an active movement of the robot as a safety measure, which moves one or more components of the robot in such a way that a hazardous situation is thereby avoided or eliminated. This can be done, for example, in control cooperation with the detection device in order to determine, on the basis of image data, a form of movement of the industrial robot or a specific component of the industrial robot that leads to the avoidance of the hazardous situation and then to control or execute this movement by the safety measure device.

[0008] The third fundamental component of the safety device according to the invention is a control device that is signal-coupled to the detection device and the safety measure device. This control device is designed to evaluate the data acquired by the image capture device and, in doing so, to detect a potential hazardous situation in real time. For this purpose, the control device can perform appropriate image evaluations and image recognition in order, on the one hand, to detect a person or body parts of a person and determine their position and direction of movement, and, on the other hand, to detect the industrial robot and its components, as well as any tools or objects guided by the industrial robot, and in turn, to determine their position and movement.

[0009] The control device is then designed to make a future-oriented assessment based on the person, body parts, the industrial robot, components of the industrial robot, objects, or tools detected in this way. This assessment uses the positions, directions of movement and speeds, and possibly also the directions and levels of acceleration, to determine whether contact between a component of the industrial robot and a body part of the person that could lead to injury is to be expected. The control device can further use this detected position and movement data of the person and the industrial robot to determine how much time is required to prevent this injury to the person through a suitable safety measure, and whether the time remaining from the time of detection until the expected time of injury is still sufficient to effectively implement the safety measure.This may, for example, include the control device being able to determine whether the movement of the industrial robot can still be slowed down to such an extent that the injury is thereby avoided, but may also include more sophisticated control methods, for example determining whether the injury can still be avoided by an evasive movement of the robot and in which direction and at what speed this evasive movement must be carried out.For the purpose of determining when the safety measure must be carried out in order to still effectively prevent the injury, the control device can access corresponding technical data characterizing the industrial robot, which can be stored accordingly, such as the mass and the position of the center of mass of individual components of the industrial robot, the acceleration capabilities of individual components of the industrial robot, such as in particular the forces and torques that can be generated by the actuators of the industrial robot and their effect on possible accelerations of the components of the industrial robot, latency times in the control of the industrial robot and other technical data relevant to the respective safety measure, which affect the time period in which a safety measure can be carried out.The control device sends out the first danger signal at the latest when the time period within which a contact potentially causing injury is to be expected corresponds to the time period within which the injury can be avoided by the safety measure or when this time period is longer than the time until the expected occurrence of the injury by a predetermined safety time period, and upon receipt of this first danger signal, the safety measure device triggers the corresponding safety measure.

[0010] This specific detection of an impending injury-risk situation, on the one hand, and the analysis performed by the control system, which considers both the movement of the industrial robot and that of the person in determining the hazardous condition and, in doing so, incorporates the time required to prevent the injury through a safety measure into the control for transmitting the hazard signal, enable differentiated control of the safety measures. For example, for slow movements that would lead to an injury situation, the hazard signal can be transmitted later than if the same movement occurs with a fast movement, which therefore requires a longer period for deceleration or evasive movement due to inertial forces.Furthermore, in the event of an expected, potentially harmful contact between a component section that exhibits a high mass inertia relative to the necessary change in movement, the hazard signal can be emitted earlier than if the potentially harmful contact is caused by a component section that exhibits a low mass inertia relative to the necessary change in movement to prevent the injury. This also allows the person to work closer to the industrial robot and avoids premature or unnecessary triggering of safety measures.

[0011] According to a first preferred embodiment, it is provided that the control device is programmed to calculate a severity of the expected contact between the detected or the other body part of the user and the injury-risk component of the industrial robot based on the calculated direction of movement and speed of movement and, if applicable, the direction of acceleration and acceleration of the detected body part and the direction of movement and speed of movement and, if applicable, the direction of acceleration and acceleration of the injury-risk component of the industrial robot, wherein the severity of the contact describes at least a level of the expected acceleration of the body part due to the contact, to compare the calculated severity of the expected contact with a predetermined first limit value, and if the calculated severity of the expected contact exceeds the first limit value,to generate the first hazard signal. According to this embodiment, the control device is designed to differentiate between an injury-risking and a non-injury-risking contact of the industrial robot with the person and to emit the hazard signal only when an injury-risking contact is to be expected. This differentiation is carried out by calculating a severity of the expected contact. This severity of the expected contact characterizes an expected acceleration of the body part of the person that comes into contact with the industrial robot due to this contact. The control device can take into account various properties of the body part and the industrial robot and parameters of the respective movement situation that leads to the contact. Thus, on the one hand, it can be taken into account which mass inertia, i.e. in particular which mass and which mass inertia point,the body part is subjected to an acceleration caused by the potentially injury-threatening contact. This allows a distinction to be made between contact with a limb that is remote from the joint and that is close to the joint, and contact far from the joint can be assessed differently due to the accelerating evasive reaction or rebound situation that can be brought about there with a lower force than contact close to the joint, where such an evasive movement could only be generated by a higher force and consequently a higher risk of injury. The control device can also take into account the anatomical nature of the body part, in particular its cushioning soft tissue thickness and structure. In this way, a distinction can be made between contact with a body part covered by soft tissue, such as a lower leg, thigh, forearm, or upper arm, and a body part not covered by relevant soft tissue, such as a person's head.differentiated, and contact with the head can be assessed as potentially causing injury at a lower degree of acceleration than contact with a soft-tissue-covered body part. The control device can further consider the injury sensitivity of certain body parts and, for example, classify contact with sensory organs or the person's head as potentially causing injury at lower accelerations and contact forces than similar contact with a person's extremities. Accordingly, the predetermined first limit value can vary based on these properties and parameters considered by the control device and can be individually predetermined for the respective contact situation and contact position in relation to the body part and the component.

[0012] This inventive design of the control device fundamentally avoids the need for a safety measure to be triggered whenever there is contact between the robot or an object guided by the robot and a person. Instead, it allows such contact to occur and the robot to continue its movement unchanged if the control device assesses the contact as not being of a severity that could cause injury.This allows, on the one hand, actions requiring contact between a person and the robot to be carried out while the safety device is continuously monitoring the safety, for example because the person is holding on to the robot, leaning on it, or something similar to perform certain actions, or because the person wants to guide robot components by applying force, for example as part of a training process, or the person wants to accept objects guided by the robot, wants to hand an object to the robot, or because the person has inadvertently caused contact with the robot which, however, has not reached a level of severity that could cause injury. In all of these situations, the differentiated assessment by the control device prevents any interruption or change in the robot movement and no safety measure is triggered.

[0013] It is further preferred that the control device is programmed to compare the calculated severity of the expected contact with a plurality of predetermined limit values, and if the calculated severity of the expected contact exceeds a first limit value of the plurality of predetermined limit values, to generate the first hazard signal and send it to the safety measure device, if the calculated severity of the expected contact exceeds a second limit value of the plurality of predetermined limit values, to generate a second hazard signal and send it to the safety measure device, wherein the safety measure device is designed to execute a second safety measure which is different from the first safety measure upon receipt of the second hazard signal.According to this embodiment, the control device is designed by electronic programming to differentiate between two different ranges of the severity of the contact on the basis of two different limit values ​​and, depending on the severity range in which the expected contact lies, to generate a first or a second hazard signal and consequently to trigger a first or a second safety measure that are different from one another.

[0014] The different degrees of severity can be caused, in particular, by different accelerations of one and the same body part. However, the different degrees of severity can also be caused by different contact points on a body part, different body parts that would come into contact, or different contact points on the industrial robot component. Other influencing factors can also play a role, such as the surface contour of the contact point on the industrial robot component, the elastic compliance of the contact points, and other influences.The different safety measures triggered by the various hazard signals can include, for example, issuing a warning signal perceptible to the user, slowing down the industrial robot, stopping the industrial robot, directing the industrial robot into a counter-movement or evasive movement suitable for contact avoidance, or other safety measures that reduce or prevent the hazard. It is fundamentally important to understand that the effectiveness of the safety measure to avoid the hazardous situation should be adapted to the severity of the contact; therefore, the more severe the contact, the more effective the safety measure should be.

[0015] Even further, it is preferred if the control device is programmed to compare the calculated severity of the expected contact for a first body part with the first limit value, and to compare the calculated severity of the expected contact for a second body part with a second limit value, and if the calculated severity of the expected contact of the first body part exceeds the first limit value, to generate the first hazard signal and send it to the safety measure device, if the calculated severity of the expected contact of the second body part exceeds the second limit value, to generate the first hazard signal and send it to the safety measure device, wherein the control device is further programmed not to generate the first hazard signal if the calculated severity of the expected contact of the second body part is between the first and second limit values.According to this preferred embodiment, the assessment of the risk of injury is differentiated according to at least two different body parts, the severity of the contact being assessed using two correspondingly different threshold values. This assessment and corresponding threshold determination can take into account, on the one hand, the sensitivity of the respective body part and, on the other hand, the soft tissue padding, which has a cushioning effect on contact. This allows an effective distinction to be made between contact with an operator's head, the severity of which is assessed using a lower threshold value, and contact with, for example, a user's forearm, which is assessed using a higher threshold value. A safety measure adapted to this can be implemented accordingly.

[0016] Even further, it is preferred if the control device is programmed to compare the calculated severity of the expected contact between the first body part and the first injury-risk component with the first limit value, and to compare the calculated severity of the expected contact between the first body part and a second injury-risk component with the first limit value, and if the calculated severity of the expected contact of the first body part with the first injury-risk component exceeds the first limit value, to generate the first hazard signal and send it to the safety measure device, if the calculated severity of the expected contact of the first body part with the second injury-risk component exceeds the first limit value, not to generate the first hazard signal.According to this embodiment, the control device is designed to differentiate between contact between two different components of the industrial robot and a body part of the user. In the event of contact with a first component, a safety measure is triggered; in the event of contact between the same body part and a second component of the industrial robot, this safety measure is not triggered. Consequently, either no safety measure can be triggered at all or a different safety measure can be triggered.This training is particularly advantageous when, on the one hand, particularly injury-prone components of the industrial robot are to be protected in such a way that they trigger a safety measure at a low threshold of the severity of the contact. For example, because these components have sharp edges, exert a movement of their own, such as rotation, shearing action, or the like, and therefore pose a particular risk of injury compared to other components that pose a low risk of injury as blunt or padded components. Such components with a low risk of injury may also be intentionally contacted by the user, and therefore such contact should not trigger a safety measure that impairs the operation of the industrial robot.

[0017] It is further preferred if the control device is programmed to recognize a second body part of the person that is different from the first and to calculate its position, speed of movement and direction of movement, and optionally acceleration and direction of acceleration. According to this further development, the control device is designed to recognize and calculate the movement of a second body part. This can be done, for example, by separately recognizing this body part via an image and calculating its movement; however, a dependent calculation can also be carried out on another body part, for example the first body part, if the first and second body parts are connected to one another by one or more body joints and the movement of the second body part therefore results from the movement of the first body part or is partially dependent on it.

[0018] According to a further preferred embodiment, the safety device is further developed by stationary markings in the movement range of the industrial robot, which can be optically detected by the image capture device, in particular markings formed on a floor support surface. The control device is characterized in that it is configured to recognize the markings and to enter the position of the body part and / or the industrial robot in a stationary coordinate system based on the markings and to evaluate it based on the stationary coordinate system. A fundamental problem with the safety monitoring of industrial robots using image capture is that a clear spatial assignment of the user's body parts to the components of the industrial robot must be established. This spatial assignment must take into account the three-dimensional spatial conditions.Safe assignment can be compromised by changes in the position of the industrial robot itself, but especially by changes in the positions or angular orientations of the sensors used for image acquisition, for example, if these are attached to moving components of the industrial robot. Equipping the safety device with detectable, stationary markings and their detection by image recognition of the control device achieves robust detection of hazardous conditions against such influences, since these stationary markings always allow for reliable determination of the relative positions based on the entries in a stationary coordinate system.

[0019] In this case, detectable, stationary markers can be markers that also serve as signaling functions for the user, for example, limit points of the robot's maximum range of motion. A number of markers can be used that meets or exceeds the minimum required number of three markers to clearly assign a space, in order to include redundant markers and, if necessary, compensate for obscured markers. Two-dimensional, i.e., flat elements such as stickers, colored markings, or the like can be used as markers, and three-dimensional markers such as spherical elements, cuboids, pyramids, or the like can be used.

[0020] It is further preferred if the control device is further programmed to calculate an acceleration direction and an acceleration of the detected body part, or to determine an acceleration direction and an acceleration of the injury-risk component of the industrial robot based on a comparison of the respective position of the detected body part and / or component in three or more consecutive images, and to calculate whether contact between the detected or the other body part of the user and the injury-risk component of the industrial robot is to be expected within the predetermined time period, also based on the acceleration direction and the acceleration of the detected body part and the acceleration direction and the acceleration of the injury-risk component of the industrial robot.In principle, to determine an impending contact and the severity of this contact, the positions, speeds, and directions of movement of the industrial robot component and the body part can be used alone. Based on this data, assuming constant movement, a prediction can be made as to whether contact is to be expected and, if so, what the severity of this contact will be. However, both the industrial robot components and the user's body parts can be accelerated in a direction of acceleration and consequently change the direction and magnitude of their speed. Taking this acceleration into account according to its direction and magnitude can therefore enable a more reliable and more proactive determination of an expected contact.In particular, this allows for the consideration of potential injury-preventing reactions of the user or potential reflexes that increase the risk of injury, and the appropriate safety measure to be selected based on these reactions in order to reliably prevent injury even at such accelerations. In principle, this can be determined directly based on three consecutive images; however, the corresponding algorithm can also indirectly access such three images, for example, by calculating the acceleration based on two sequentially determined speeds.

[0021] It is even further preferred if the control device is designed to detect an operational input variable of the industrial robot based on the image data of an image, in particular the provision of an object to be grasped by the robot, the provision of a deposit location for an object grasped by the robot, and that the control device has an interface to a controller of the industrial robot and is designed to transmit the detected operational input variable via this interface. According to this embodiment, the control device is additionally designed to detect operational input variables for controlling the industrial robot, such as, for example, detecting objects that the industrial robot is intended to grasp or detecting deposit locations at which the industrial robot is intended to deposit an object.Through a corresponding interface to the control system of the industrial robot or through a corresponding integration of the properties of the control device required for the safety device into the control system of the industrial robot, the knowledge gained from this image acquisition and evaluation by the control device can be directly integrated into the control of the movement sequence of the industrial robot.Through this additional function, the safety device according to the invention fulfills, on the one hand, an improved safety function in that such objects and storage locations or other input variables on the basis of which the industrial robot is controlled are taken into account when determining a possible hazardous state. On the other hand, the functionality of the safety device according to the invention is also used to improve the operational function of the industrial robot, for example by controlling access to objects and their storage in an improved manner.

[0022] According to a further preferred embodiment, it is provided that the first security measure and optionally the second security measure are selected from • a reduction in the movement speed of the industrial robot, • an emergency stop of the movement of the industrial robot, • an emergency stop of the movement of the industrial robot and a subsequent control of the industrial robot into a passive mobility, in which actuators of the industrial robot are controlled in such a way that weight forces are compensated by the components of the robot and, if applicable, by an object held by the robot and the components of the robot are movable by the action of external forces, • a change in the movement of the component of the industrial robot into an evasive movement, wherein the control device is programmed to calculate the direction of movement and preferably the speed of movement of the evasive movement based on the position, the calculated direction of movement and speed of movement and, if applicable, the direction of acceleration and acceleration of the detected body part and the position, direction of movement and speed of movement and, if applicable, the direction of acceleration and acceleration of the injury-risk component of the industrial robot in such a way that contact between the body part and the injury-risk component of the industrial robot is avoided by the evasive movement.

[0023] According to this embodiment, different reactions of the safety device are possible as the first and, if applicable, second safety measure. For example, the speed intended for the normal operation of the industrial robot can be reduced if a hazard involving potential contact with the user is expected, for example, to reduce the contact to a level that does not cause injury to the user. This means that the industrial robot can continue to perform its operation, albeit at a slower speed, and at the same time, the user is alerted to the hazardous situation they have caused by the perceptible slowdown in speed, and can also eliminate it through their own movements.An emergency stop of the movement of the industrial robot is also possible as a safety measure, which is particularly relevant if a contact of a severity that is immediately classified as potentially hazardous to life is to be expected and this can only be avoided by an appropriate emergency stop.

[0024] The emergency stop can then be followed by a blocking of the movement of the industrial robot in order to maintain the position reached by the industrial robot after the emergency stop. In a further variant of the safety measure, the emergency stop can also be followed by a control of the industrial robot's actuators, which only compensate for the weight forces of the individual components of the industrial robot, but allow movements generated by external forces acting on the components of the industrial robot. This control, which is also used for training processes on the industrial robot, enables a user to move out of a position on the industrial robot in which they are prevented from making their desired movement or being released by components of the industrial robot. For this purpose, they can also move components of the industrial robot by pushing them away, shifting them, pivoting them, or the like.Finally, the movement of the industrial robot component can also be changed into an evasive movement. This evasive movement may be necessary, for example, if an emergency stop can no longer reliably prevent the potentially injurious contact, but a change in the movement can still achieve this. Or even if an emergency stop can prevent potentially injurious contact, but the user is subsequently restricted or even trapped by the industrial robot, and the evasive movement can remove this restriction on the person's ability to escape.

[0025] It is further preferred if the control device is configured to determine the position, speed, and / or acceleration of the component of the industrial robot based on data processing with artificial intelligence used in the evaluation of the image data, or a marking on the component of the industrial robot that can be detected during the evaluation of the image data, or an operator input, or position data received from a transmitting device on the component. According to this embodiment, the position and movement data of the industrial robot are determined using specific data or data evaluations, thus achieving a reliable determination of the current position and movement data as well as a reliable forecast of the future position and movement data of the individual components of the industrial robot.On the one hand, this can be achieved by analyzing the image data captured by the image capture device, and using artificial intelligence in this image analysis. This type of analysis is particularly suitable because an industrial robot typically performs repetitive movement sequences. Therefore, with a sufficiently long observation phase, an analysis using artificial intelligence can initiate a learning process for the artificial intelligence. Subsequently, based on the learned data, a reliable prediction of future positions and movement data can be made if a pattern of the current position and movement pattern has been recognized by the image capture.

[0026] For reliable position detection of the industrial robot component, a marking can also be applied to the component, which can be captured by the image capture device. Such a marking eliminates the need for image analysis to identify a component and the associated computing power. It is therefore easier to identify and track, and allows for computer-assisted real-time image recognition and tracking of component movement with less computing power.

[0027] In principle, the control device can also have an interface for receiving control data from the industrial robot or have corresponding control data stored. Based on this control data, the position and movement data of the industrial robot for a specific point in time can be directly determined and predicted, enabling a reliable forecast of the position and movement data. The position of the industrial robot component and its movement data can also be recorded through an operator input, which can be made via a user interface on the control device, as is the case, for example, when programming the movement of the industrial robot and can be derived from such programming.Finally, a transmitting device can also be arranged on a component of the industrial robot and used to determine the position and movement data of the component, for example by determining the position based on the direction of the emitted transmission beams, a runtime measurement or the like.

[0028] It is even further preferred if the control device has pre-stored anatomical data and is programmed to calculate a position, movement speed and movement direction of the second body part or a third body part of the person based on the position, movement speed and movement direction of the detected first body part and an assignment of the first body part to a second body part different from the first, as defined in the anatomical data, and / or the control device is configured to determine calibration image data based on calibration image acquisition by capturing one or more body parts or an entire person and to carry out the evaluation based on the chronologically successive sequence of the images captured by the image capture device, in particular the calculation of the movement direction and speed of a body part taking into account the calibration image data.The basic problem is that when an image of a person is captured, some body parts can be easily identified through image analysis, but this is not the case for all body parts. This is due, on the one hand, to the different geometric characteristics of body parts, and, on the other hand, to the fact that body parts can be hidden and thus not be identified. According to this embodiment, this problem is overcome by either storing anatomical data for several adjacent body parts in the control device, thereby making it possible to determine the position and movement data of a neighboring body part from one of the captured body parts, whose position and movement data are available through image capture and analysis, using this stored anatomical data.This can be done, for example, depending on joint data of a joint connecting the two body parts, based on anatomical data describing the length of the first, second, and possibly third and further body parts, their envelope, and the like. Alternatively or additionally, the control device can also be configured to perform a calibration image acquisition in a step preceding the subsequent safety monitoring and to determine calibration image data from one or more body parts in this step.In this way, corresponding anatomical data in the form of this calibration image data is read into the control device, which ideally corresponds to the person who is to be monitored by the safety device and can be used in the same way as before to evaluate and recognize the body parts recorded in the calibration from image data of an image acquisition, if necessary to infer positions and movement data of neighboring body parts and consequently to determine position and movement data of the body parts quickly and reliably.

[0029] It is even further preferred if the control device is designed to determine the position, direction of movement, speed of movement and, if applicable, acceleration and direction of acceleration of the component of the industrial robot and / or of an object moved by the industrial robot from received program data of the industrial robot, and / or from an image capture of the industrial robot by means of the image capture device, wherein the image capture takes place in real time parallel to the image capture of the first body part of the person or the image capture takes place in a temporally preceding learning process in which the industrial robot executes a repetitive sequence of movements and the control device stores the individual positions, speeds of movement and directions of the injury-prone component of the industrial robot and preferably of other components of the industrial robot,in order to determine the positions, movement speeds, and movement directions of the component in a monitoring process following the learning process, wherein, preferably before the real-time image acquisition or in addition to the learning process, a calibration image acquisition is carried out to determine calibration image data by capturing one or more components of the industrial robot and / or an object to be moved by the industrial robot, and to determine the position, movement direction, movement speed, and, if applicable, acceleration and acceleration direction of the component of the industrial robot and / or the object, taking the calibration image data into account. According to this embodiment, the position and movement data of the industrial robot are determined from received program data of the industrial robot itself.which control the movement sequences of the industrial robot and therefore define the position and movement of the individual components of the industrial robot for each point in time and make them determinable and predictable, or from an image acquisition of the industrial robot, which determines the position and movement data of the components of the industrial robot by means of image acquisition and analysis and, as previously explained, can predict these, if necessary, using trained software with artificial intelligence. The image acquisition takes place in real time in parallel with the image acquisition of one or more body parts of the person, thus enabling real-time monitoring of any collisions that could cause injury. A training process can precede the image acquisition in order to use an image acquisition of the industrial robot while it is performing a repetitive sequence of movements,to store the position and movement data of the individual components of the industrial robot and, in a monitoring process taking place after the learning process, to determine and predict the position and movement data of the individual components of the industrial robot using this stored data. It is therefore particularly preferred to record the components of the industrial robot using image capture in a calibration process prior to the monitoring, and if necessary also to record objects or tools moved by the industrial robot and thereby determine calibration data, on the basis of which a reliable image evaluation and recognition as well as movement prediction of these components and objects is possible in the subsequent monitoring process. In particular, based on the calibration data, such evaluation and recognition is possible with a reduced computing effort because on the basis of distinctive,During the calibration of determined geometric properties, a detection that reduces the computing time is possible.

[0030] It is even further preferred if the control device is designed to calculate a future position and / or direction of movement and / or speed of movement and / or acceleration and / or direction of acceleration of the component of the industrial robot on the basis of a position, direction of movement, speed of movement and, if applicable, acceleration and direction of acceleration of the component of the industrial robot detected in real time and to include this in the comparison as to whether contact between the detected or another body part of the user and the injury-risk component of the industrial robot is to be expected, and / or to calculate a future position and / or direction of movement and / or speed of movement and / or acceleration and / or direction of acceleration of the component of the industrial robot on the basis of a position, direction of movement,Movement speed and, if applicable, acceleration and acceleration direction of the user's body part, to calculate a future position and / or movement direction and / or movement speed and / or acceleration and / or acceleration direction of the body part and to include this in the comparison as to whether contact between the detected or another body part of the user and the injury-risk component of the industrial robot is to be expected. According to this embodiment, a possible future collision between the component and the body part is determined from the position and movement data of the component of the industrial robot and / or the user's body part recorded in real time, and at least the position and movement data are used to predict the future position of the component or body part, ideally both the component and the body part.This enables the advance calculation of movements and positions necessary for an adequate safety measure and can be used, in particular, to initiate a safety measure in a timely manner, to issue a warning signal, and, in particular, to undertake an emergency safety measure that does not necessarily completely interrupt the workflow of the industrial robot.

[0031] It is even further preferred if the control device is designed to determine an orientation of a longitudinal axis of the body part based on the image data of an image and to determine a future, expected direction of movement of the body part based on a comparison with pre-stored correlation data in which the orientation of the longitudinal axis is correlated with the future direction of movement of the body part and to include in the comparison whether contact between the detected or another body part of the user and the injury-risk component of the industrial robot is to be expected, and / or to determine an orientation of the component of the industrial robot and / or of an object moved by the industrial robot and to determine an orientation of the component of the industrial robot and to compare it with pre-stored correlation data in which the orientation is correlated with the future direction of movement of the component and / or the object,to determine a future expected direction of movement of the component and / or object and to include it in the comparison as to whether contact between the detected or another body part of the user and the injury-risk component of the industrial robot and / or object is to be expected. According to this embodiment, by determining the orientation of a body part or component of the industrial robot and based on data that correlate such an orientation in space with an expected direction of movement of the corresponding body part or component in space,a prediction of a future movement and the resulting position of the body part or component is calculated based on this determined longitudinal alignment. This embodiment therefore uses a probability of certain movement patterns, which often results from the integration of such body parts and components into articulated arrangements with corresponding movement restrictions and which must or are likely to result from an alignment of the longitudinal axis, in order to make a prediction for the future position and movement data of the body part or component. It should be understood that this embodiment can be used according to the invention alone or in addition to other calculation methods for such a prediction, and the control device can be designed in particular to determine the prediction of the position and movement data of a body part or component based on several calculation methods and probabilities.to weight individual calculation methods and to make a best estimate if different forecasts with error probabilities occur.

[0032] According to a further preferred embodiment, it is provided that the detection device comprises data glasses with an image detection device which is aligned to carry out an image detection in the field of vision of the wearer of the data glasses. In the sense of the invention, data glasses are understood as a head holder for attachment to the head of the user and therefore do not necessarily have to have a transparent area in front of the eyes of the user in the sense of a spectacle lens in the sense of glasses.Such an arrangement of the image capture device on a head mount is particularly well suited to carrying out safety monitoring on an industrial robot, since it allows the numerous different perspectives resulting from the accessibility of the industrial robot from several sides and the numerous different hazard locations resulting from the high mobility of the industrial robot to be well captured in the area in which the user interacts with the industrial robot and which the user therefore typically also has in his field of vision.

[0033] The control device can control a single safety measure or, from several different safety measures, select and control a safety measure appropriate for the detected potential hazard state. This selection of a suitable safety measure can also be based on predetermined criteria.

[0034] According to the invention, the detection device comprises a headgear for attachment to the user's head and an image capture device attached to the headgear, which is aligned to capture an image in the field of vision of the user wearing the headgear. The detection device is therefore designed to detect a potential hazardous condition by means of image capture, and the image capture device required for this purpose is arranged on a headgear worn by the user. The image capture device is aligned to capture an image in the user's field of vision, i.e., typically, an image capture device is attached to the headgear, aligned in a straight-ahead line of sight of the user, and has an image capture area that corresponds at least to that which a user perceives with their eyes when looking straight ahead.The image capture device can also be aligned and designed to capture a larger area than the area captured by the user in the straight-ahead line of sight, in order to be able to determine a potential hazardous condition based on the capture of components or body parts that are potentially hazardous and are outside the user's actual line of sight.

[0035] The headgear can, for example, be a pair of glasses to which one or two cameras are attached as an image capture device, for example, on the sides of the glasses. Such glasses then serve to capture images in the direction of the face orientation of the wearer of the data glasses. In other embodiments, the headgear can also be designed as a helmet, headband, cap, or the like, which is worn on the head by the user and to which the image capture device is attached. This can again be one or two cameras, for example, two video cameras attached to the side of the helmet or headband.In principle, the detection device designed in this way has the advantage that it carries out the image capture in the user's field of vision, i.e. it carries out the head movements and head swivels of the user and is therefore, on the one hand, favorably aligned with a danger zone that the user observes with his eyes, and on the other hand, it allows a conclusion to be drawn about the user's line of sight, thus also making it possible to detect if the user turns his head away from the danger zone in a potentially dangerous manner.

[0036] The control device in the safety device according to the invention is designed to carry out the assessment of whether a potential hazardous condition exists due to the situation detected by the detection device, on the basis of the images that are captured by the image capture device on the data glasses

[0037] It is preferred if the control device is designed to determine an image section of the captured image which corresponds to a predetermined field of view or section of the field of view, in particular a section corresponding to the fovea of ​​the field of view, of a user wearing the data glasses, and the control device is designed to determine by means of an image evaluation whether the component is located within the image section and to take into account as a further parameter when generating the first hazard signal whether the component is located inside or outside the image section.

[0038] The predetermined field of view can correspond to the user's field of vision or their field of view, or can correspond to a section thereof. According to this embodiment, the image capture device or the control device captures an image area that corresponds to a predetermined field of vision or section of the user's field of vision. In particular, the fovea of ​​the field of vision, i.e. the area that a user has approximately in the center of their field of vision and which they can monitor with concentration, can correspond. The image capture device is therefore aimed at or encompasses precisely such an image area that can also be reliably captured by the user when observing with their eyes. Based on image analysis, it can then be determined whether the hazardous component is located within this image section.In this case, it is ensured that when the component is detected in the image section, the user also has the component within their concentrated, monitored field of vision, and a decision can then be made as to whether a potentially hazardous situation exists or not. However, if the component is not detected within the image section, the situation must be assessed as meaning that the user is also not safely monitoring the component. In this case, according to this training, the control device is trained to trigger a safety measure.

[0039] It can preferably further be provided that the data glasses have a device for eye tracking, and that the image section is determined depending on the user's line of sight determined by means of eye tracking. By tracking the user's eyes, it can also be determined in which direction the user's eye is currently looking, i.e. whether, for example, the user is not looking straight ahead but to the side. This makes it possible to determine whether the user, although their head is positioned so that the central, straight-ahead line of sight is directed towards the hazardous component, deviates from this main axis due to their viewing angle and therefore does not have the component in their line of sight, which in turn would indicate a potential hazardous condition and trigger a safety measure.

[0040] It is even more preferred if the control device is arranged on the headgear, and the headgear further comprises a signal transmission unit for wireless signal transmission and is signal-coupled to the safety measure device by means of this signal transmission unit. With such a signal transmission unit, the headgear can be comfortably worn by the user, and the data determined by the control device on the headgear, and in particular the data content for triggering a safety measure, can be transmitted to the safety measure device.

[0041] Alternatively, it is provided that the control device is arranged on the industrial robot, and the head mount further comprises a signal transmission unit for wireless signal transmission and is signal-coupled to the control device by means of this signal transmission unit. According to this embodiment, the control device is not arranged on the head mount, but rather on the industrial robot, and in this case, the data acquired by the image capture device on the head mount is transmitted to the control device via the signal transmission unit.

[0042] In addition to these two possibilities for arranging the control device on the head mount or on the industrial robot, another configuration is also advantageous in certain embodiments, in which the control device - a first control unit arranged on the headrest and - comprises a second control unit arranged on the industrial robot, and the headgear further comprises a signal transmission unit for wireless signal transmission, and by means of this signal transmission unit, the first and second control units are signal-coupled, wherein the first control unit is designed to carry out a first part of the assessment and to transmit a result determined therefrom to the second control unit, and the second control unit is designed to carry out a second part of the assessment on the basis of this determined result and, depending on the assessment, to control the safety measure device to carry out a safety measure. Here, the assessment of the situation captured by the image capture device for a potential hazardous state is carried out by a first control unit of a headgear and a second control unit on the industrial robot.Such a division of the assessment makes it possible for those parts of the assessment to be carried out at the headgear, which leads to a reduction in the amount of data to be transmitted, in order to be able to carry out an efficient assessment in real time.

[0043] It is even further preferred if the headgear further comprises an image output device for outputting image and text information to one or both eyes of the user wearing the headgear, in particular by means of - Display of image and text information on a screen, or - Projection of image and text information onto the retina of one or both eyes of the user.

[0044] According to this type of training, the headgear is also equipped to output an image that can be seen by the user, for example, via a screen mounted on the headgear or via a corresponding projection onto the retinas of both eyes. This allows, on the one hand, simple or differentiated warning signals to be output to the user via the headgear. On the other hand, additional information not related to a hazardous situation can be displayed to the user via the image output device.

[0045] It is particularly preferred if the head support has a data interface for data transmission, in particular a data transmission unit for wireless data transmission, and is designed to receive image and / or text information via the data interface and to display it on the image output device, which - a sequence of predetermined work processes for machining a workpiece - a representation of predetermined orientations and / or movements of a tool or workpiece to perform a machining step - a designation of machined workpieces before and / or after machining, wherein the image or text information is preferably reproduced on the basis of the image capture with the image capture device and an image analysis carried out therefrom to determine the position of the tool or the workpiece in an area which is assigned to the tool or the workpiece in the user's field of vision.This embodiment also uses the head mount for the targeted, location-specific output of information to the user that is helpful for processing a workpiece. For example, a workpiece on which several processing steps must be performed with the industrial robot can be displayed to the user via the image output device on the head mount with regard to the necessary alignments and movements of the workpiece or tool, and a sequence of the processing steps to be carried out one after the other can be displayed as predetermined work processes. Furthermore, workpieces that are created in this way can be labeled accordingly to the user via the image output device on the head mount, for example as finished parts that the user should specifically deposit, or as intermediate finished parts that still require further processing, or as offcuts.

[0046] This information can be provided in image or text form, with the image or text information preferably being displayed to the user in such a way that they can see it in the respective workpiece in the manner of augmented reality, allowing them to clearly identify it for processing. It should be understood that in an alternative embodiment, these spatially resolved display functions of the image output device on the head mount can also be implemented without the image capture device arranged on the head mount.

[0047] According to a further preferred embodiment, the control device is signal-coupled to an electronic storage device and continuously transmits the acquired image data to the electronic storage device, which is designed to store the image data and, upon reaching a capacity limit of the storage device, to overwrite the oldest image data with the most recently transmitted image data. According to this further development, the image data are stored in the storage device, and thus image data are electronically stored for a specific period of time in such a way that they are accessible for later evaluation. The storage period can be one hour, several hours, but also one or more days or weeks.This allows the stored image data to be used for further training of artificial intelligence, thus increasing analysis accuracy and reducing the probability of errors. Furthermore, the image data enables an assessment of security measures or security incidents that occurred during the period in which the image data was stored.

[0048] It is even more preferred if the control device is configured to distinguish between a low and a higher hazard level and to execute a first safety measure, in particular a warning signal, at the low hazard level and to execute a second safety measure, which is different from the first safety measure, at the higher hazard level. According to this embodiment, at least two different hazard levels are differentiated and trigger different safety measures.The two or more different hazard levels can be differentiated from one another by different properties, for example by different distances between body part and component, by different approach speeds, by different predicted times until contact between body part and component, by different injury susceptibilities of individual body parts stored in the control device or by different injury risks from different components of the industrial robot stored in the control device.The differentiated triggering of different safety measures helps to interrupt the operation of the industrial robot only in situations where there is a serious risk, but at the same time to be able to trigger safety measures preventively in the case of minor risks. These measures help to avoid the occurrence of a serious risk by warning before the occurrence of a serious risk and thus enable the user to react in a way that prevents the occurrence of a serious risk.

[0049] It is even further preferred if the image capture device is designed to capture images with depth information, in particular by - the image capture device is designed to capture runtime information on image content or - the image capture device is designed to determine depth information from two images captured at a different time and with different recording directions based on an image evaluation of the position of detected objects relative to each other or by - the image capture device comprises a first and a second image capture unit which are arranged at a distance from one another, for example fastened to the head mount on the left and right sides of the user's head, and is designed to determine depth information from a stereoscopic image evaluation of simultaneously captured images of the first and second image evaluation unit.

[0050] According to this embodiment, the image capture device is designed such that it captures depth information about the objects captured in an image, thereby making it possible to determine the distance of these objects from the image capture device. This depth information can be provided point by point for each captured pixel or object by object. In principle, various configurations for capturing depth information of this type are possible, for example based on propagation time information of the signal from an object to the image capture device, or by capturing two images offset in time with a single image capture device and thereby determining depth information based on a comparison of objects that were captured in both images but which have a different position due to a movement of the image capture device between the two offset images.Furthermore, stereoscopic depth information can also be determined if two spaced-apart image acquisition units are arranged on the head mount, which have an at least partially overlapping image acquisition area and form the image acquisition device. Based on an object that is simultaneously captured by both image acquisition units, depth information can then be stereoscopically calculated from the angular position of the object in each of the two image acquisition areas.

[0051] A further aspect of the invention is an industrial robot comprising a safety device of the type described above.

[0052] A further aspect of the invention is data glasses for a safety device of the type described above, which are characterized by an image capture device which is aligned to carry out an image capture in the viewing direction of the wearer of the data glasses, and preferably further comprising a control device which is coupled to the image capture device in terms of signals and is designed to carry out an assessment of a potential hazardous state detected by the image capture device on the basis of predetermined criteria, wherein further preferably the data glasses have a data interface, in particular a wireless data transmission device and are designed to control the safety measure device to carry out a safety measure as a function of the assessment via the data interface.

[0053] The data glasses can be further developed in particular according to the features of the data glasses described above.

[0054] A further aspect of the invention relates to a method for preventing injuries on machine tools, such as industrial robots, comprising • Teaching a control device by reading in data in which several different situations in which contact between a body part of a user and a component of the machine tool is to be expected are depicted in image data and • Assigning situations to hazardous situations, • Identifying relationships between the image data and the associated hazard situation using a neural network, and • Saving these relationships in the control device, in which • the learning status of the control device is evaluated after passing through positions a) to c) and is compared with a predetermined triggering safety level, which describes a probability with which the control device triggers a safety measure when hazardous situations occur, and • in which, if the comparison shows that the learning status reaches the predetermined triggering safety level, the relationships are finally saved in the control device and the control device is subsequently operated with this learning status without any further changes to the learning status.

[0055] According to this aspect of the invention, the control device of the safety device according to the invention is programmed through a learning process that uses artificial intelligence to assign image data recorded with the detection device, which represent different situations in which a hazardous situation to a body part occurs due to a component of the industrial robot, to a hazardous situation. The control device thereby acquires a programmed learning status that can be improved by various influences, e.g., by reading in more image data, reading in further data describing the different situations, reading in data and image data describing further situations, and defining the correlation between these read-in data, image data, and situations to hazardous situations.This continuously improved learning status is compared with a triggering safety level, which describes whether there is already a sufficient probability, for operational safety, that the control device will correctly and timely detect a hazardous situation to prevent an injury through a safety measure. The triggering safety level can also include additional criteria, such as an error probability with which the control device detects a hazardous situation even though one does not exist. According to the invention, a learning status that has reached or exceeded the predetermined triggering safety level is then stored and used to control the control device.It is crucial that this learning status of the control device is not further changed during the operation of the industrial robot, especially not by additional data acquired during operation. This ensures that a positively determined operational reliability of the control device is not altered by subsequent changes, such as those regularly encountered in the context of the use of artificial intelligence, and that this could potentially adversely affect the safety of the system.

[0056] The programming and installation of such a control device of a safety device is usually carried out with the aim of achieving product approval or acceptance, i.e., to approve the control device based on a test regulated by laws, ordinances, or regulations, and thereby establish and document consumer safety. For this approval process, it is advantageous if the control device is immutable with regard to its safety-relevant functions. However, to achieve a high level of safety, it is advantageous to use artificial intelligence in a progressive and iterative learning process to program the control device. This is achieved by the method according to the invention.The method according to the invention does not preclude the control device from being re-trained in a subsequent step outside of the control device's operation using a type of update process, and then a re-trained status that forms the basis for the control device's operation is frozen and saved. However, the decisive factor for the method according to the invention is that it only serves to achieve a trained status, which is then saved, and that this trained status is no longer changed during the operational operation of the control device when used by the consumer.

[0057] Another aspect of the invention is a method for preventing injuries to industrial robots, comprising: • Detecting a potential hazard for a user’s body part caused by an injury-prone component of the industrial robot by means of a detection device, • Carrying out a safety measure by which a hazardous situation for the user of the machine tool caused by a component of the machine tool is reduced or avoided by means of a safety measure device, • Evaluating a potential hazard condition detected by the detection device based on predetermined criteria by means of a control device that is signal-linked to the detection device and the safety measure device, and • Controlling the safety measure device to execute a safety measure depending on the evaluation, in which • the detection of the potential hazardous condition is carried out by means of an image capture device, in particular an image capture device arranged on data glasses, and • the evaluation is carried out based on images captured by the image capture device of the data glasses, with the following steps: ◯ Detecting a body part of the user in each image of the sequence of images based on the image data, ◯ Determining the position of the detected body part within a spatial reference system, ◯ Calculating the direction and speed of movement of the detected body part based on a comparison of the respective position of the detected body part in two or more consecutive images, ◯ Determining the position, direction of movement and speed of a potentially injury-prone component of the industrial robot, ◯ Calculating whether contact between the detected or another body part of the user and the injury-risk component of the industrial robot is to be expected within a predetermined period of time by comparing the determined position and the calculated direction and speed of movement of the detected body part with the position, direction and speed of movement of the injury-risk component of the industrial robot and ◯ Sending a first hazard signal to the safety measure device when contact is expected, ◯ Execution of a first safety measure by the safety measure device upon receipt of the first hazard signal.

[0058] This aspect of the invention relates to a method for preventing injuries to industrial robots, which can be carried out in particular with the previously explained safety device, a suitably equipped industrial robot and / or suitably equipped data glasses and which in particular carries out an assessment of the potential hazard state by means of a control device which has been programmed with the previously described methods for preventing injuries to industrial robots.It should be understood that the aspects and advantages previously described with regard to the safety device, the industrial robot, the data glasses, and the method for preventing injury are applicable and usable for this method in a corresponding manner, and the method is further developed accordingly with method steps that correspond to the device properties and method properties of the previously described safety device, the industrial robot, the data glasses, and the method for teaching the control device. In particular, the assessment of whether a hazardous condition exists that would trigger a safety measure can be carried out by determining the severity of the expected contact, thus achieving an appropriate safety response, as described above.

[0059] Preferred embodiments of the invention are described in more detail with reference to the accompanying figures.

[0060] Preferred embodiments of the invention are described in more detail with reference to the accompanying figures. They show: Fig. 1 a schematic perspective view of a first embodiment of a safety device according to the invention for an industrial robot. Fig. 2 a schematic, perspective view of a second embodiment of a safety device for an industrial robot. Fig. 3 a look-up table for assessing the severity of contact between body parts and components of the industrial robot.

[0061] Referring first to the Fig. 1 and Fig. 2, an industrial robot shown as an example has mobility about four axes 11, 21, 31, and 41, which connect a base 10 with an intermediate arm 20, an end arm 30, and a gripping element 40. The industrial robot can thereby move and pivot the gripping element 40 coupled to the end of the end arm 30 in a three-dimensional space and perform a gripping movement with the gripping element 40.

[0062] At the Fig. In the embodiment shown in Figure 1, a plurality of video cameras 50a-d are arranged on a frame 50 arranged above the industrial robot. These cameras are connected to a control device 60 via signal lines. The video cameras 51a-d are arranged at the four corners of the square frame 50 and each monitor a conical area below the frame. The combined areas cover the movement range of the industrial robot. The individual areas monitored by the video cameras 51a-d partially overlap and therefore provide image recognition redundancy in sub-areas of the space covered by the industrial robot.

[0063] Markings 20a, 30a are applied to the intermediate arm and the end arm of the industrial robot. These markings are designed as QR codes and are captured by the video cameras 51a-d. The QR codes can be recognized and evaluated from the image data of the video cameras by the control device 60, thereby enabling a clear assignment of the position of the components of the industrial robot.

[0064] In the floor area around the industrial robot, markers 70a-d are arranged. These markers are designed as tetrahedrons and are also detected by the video cameras. This makes it possible to reliably assign the position of a user 100 in relation to the industrial robot and the position of its components.

[0065] The control device 60 is connected by means of a signal connection 61, which in the embodiment in Fig. 1 is wired, connected to a controller 80 of the industrial robot.

[0066] The video cameras 51 ad continuously monitor the space in which the industrial robot moves. If a person 100 enters this space and, based on the evaluation of the image data by the control device 60, it is recognized that contact between a body part and a component is imminent due to the position, movement speed and direction as well as the acceleration of the individual components of the industrial robot and the body parts of the user, the severity of the contact is determined based on the movement data of the user and the industrial robot. This severity is determined using a Fig. 3 shown table and can be used in the example according to Fig. 3 Differentiation is made according to contact with the user's head, a user's arm, or the user's torso, as symbolically represented. Further differentiation is made according to the component of the industrial robot, which can be one of the two arms of the industrial robot, the gripping element arranged at the end of the arm, or a milling head that can be mounted instead of the gripping element. It should be understood that this differentiation can include further elements, subdivisions of the body parts and components.

[0067] Contact between a body part and a component can be classified according to severity levels A and B, although it should be understood that further subdivisions are possible. For a mild level of severity A, a safety measure I, II, III, or IV is implemented depending on the affected body part and component, as is the case for a severe level of B contact.

[0068] As from Fig. 3, different safety measures are taken depending on the body part and component involved and the degree of severity. For example, in the event of contact with the user's head, safety measure III must always be implemented in the case of a low degree of severity and IV in the case of a high degree of severity in order to reliably prevent injuries. If the milling head comes into contact with any part of the user's body, an appropriately effective safety measure IV must always be implemented in order to prevent any injuries caused by this sharp-edged component. In other cases, however, particularly when contact must be enabled, such as contact between the hand and one of the arms of the industrial robot, only a minor safety measure I is implemented.

[0069] A safety measure I can, for example, consist of a warning tone, a safety measure IV can consist of a complete stop of all movements of the industrial robot and a safety measure II or III can, for example, consist of a slight or strong slowing down of the movement of the industrial robot.

[0070] In Fig. 2 shows a second embodiment of the safety device according to the invention. The industrial robot in this embodiment is designed in the same way as in the embodiment according to Fig. 1. Deviating from the embodiment according to Fig. 1, this embodiment provides an image capture device that is arranged on data glasses worn by the user and that captures a monitoring area that includes and extends beyond the user's field of vision. The image capture device comprises two video cameras 151a, b arranged laterally on the temples of the data glasses, which capture and continuously monitor a stereoscopic image of the surroundings within the user's field of vision. Furthermore, a control device 160 is arranged on the head mount of the data glasses and is connected to the controller 80 of the industrial robot via a wireless signal connection.

[0071] In the same way as previously explained, the two video cameras 151a,b of the image capture device monitor the movement range of the industrial robot when the person is working in its area and the image capture is accordingly directed at the industrial robot. Based on the markings 20a, 30a arranged on the components of the industrial robot and the floor markings 70a-d, the control device can determine the position, speeds, and accelerations of these components in space and relative to the user's body parts, which are also captured in the field of view of the image capture device. In the same way as previously described, if a risk of contact between a body part and a component is detected, safety measures can be taken. These measures can be selected in the same way as previously explained using a table according to body part, component, and severity.

[0072] Basically, it should be understood that the Fig. 1 and Fig. The arrangements of the image capture device shown in Figure 2, on the one hand, on a frame arranged above the industrial robot and on a head mount of the user, can also be combined with each other, and a corresponding signal connection can be implemented between the video cameras of these image capture devices and the control device 60 or 160, or both. In this way, a monitoring area captured by both stationary video cameras and video cameras that move with the user can be used to secure and prevent injuries. QUOTES CONTAINED IN THE DESCRIPTION

[0000] This list of documents submitted by the applicant was generated automatically and is included solely for the convenience of the reader. This list is not part of the German patent or utility model application. The DPMA assumes no liability for any errors or omissions. Cited patent literature

[0000] US 2021 / 053227 A1

[0003] DE 10 2017 221 305 A1

[0003]

Claims

[1] Safety device for an industrial robot, comprising - a detection device designed to detect a potential hazardous condition for a body part of a person who is in the vicinity of the industrial robot, caused by a component of the industrial robot or an object moved by the industrial robot, - a safety measure device designed to carry out a safety measure by which the hazardous condition is reduced or avoided, - a control device which is signal-coupled to the detection device and the safety measure device and is designed to carry out an assessment of a potential hazardous condition detected by the detection device on the basis of predetermined criteria and, depending on the assessment, to control the safety measure device to execute a first safety measure, characterized by , that the detection device comprises an image detection device which is oriented to carry out an image detection in a hazard zone which comprises the industrial robot and a spatial section surrounding the industrial robot, and the control device is designed to carry out the assessment on the basis of a temporally successive sequence of images with image data captured by the image detection device, wherein the control device is programmed to - to recognize a body part of the user in each image of the sequence of images based on the image data, - to determine the position of the detected body part within a spatial reference system, - to calculate the direction and speed of movement of the detected body part by comparing the respective position of the detected body part in two or more consecutive images, - to determine the position, direction of movement and speed of a potentially injury-prone component of the industrial robot and, if applicable, of an object moved by the industrial robot, - by comparing the determined position and the calculated direction and speed of movement of the detected body part with the position, direction and speed of movement of the injury-risk component of the industrial robot, to calculate whether contact between the detected or another body part of the user and the injury-risk component of the industrial robot is to be expected within a predetermined or calculated period of time, and if so, to generate a first hazard signal and send it to the safety measure device, wherein the safety measure device is designed to execute the first safety measure upon receipt of the first hazard signal. [2] Safety device according to claim 1, characterized by that the control device is programmed to use the calculated direction of movement and speed of movement and, if applicable, the direction of acceleration and acceleration of the detected body part and the direction of movement and speed of movement and, if applicable, the direction of acceleration and acceleration of the injury-risk component of the industrial robot, wherein the severity of the contact describes at least a level of the expected acceleration of the body part due to the contact, - to compare the calculated severity of the expected contact with a predetermined first limit, and - if the calculated severity of the expected contact exceeds the first limit, to generate the first hazard signal. [3] Safety device according to claim 2, characterized bythat the control device is programmed to compare the calculated severity of the expected contact with a plurality of predetermined limit values, and o if the calculated severity of the expected contact exceeds a first limit of the plurality of predetermined limits, to generate the first hazard signal and send it to the safety measure device, ◯ if the calculated severity of the expected contact exceeds a second limit of the plurality of predetermined limits, to generate and send a second hazard signal to the safety measure device, - wherein the safety measure device is designed to execute a second safety measure which is different from the first safety measure upon receipt of the second hazard signal. [4] Safety device according to claim 3, characterized by that the control device is programmed to - compare the calculated severity of the expected contact for a first body part with the first limit value, and - to compare the calculated severity of the expected contact for a second body part with a second limit value, and ◯ if the calculated severity of the expected contact of the first body part exceeds the first limit value, to generate the first hazard signal and send it to the safety measure device, ◯ if the calculated severity of the expected contact of the second body part exceeds the second limit value, to generate the first hazard signal and send it to the safety measure device, - wherein the control device is further programmed not to generate the first hazard signal if the calculated severity of the expected contact of the second body part is between the first and second threshold values. [5] Safety device according to claim 4, characterized by that the control device is programmed to - compare the calculated severity of the expected contact between the first body part and the first injury-risk component with the first limit value, and - compare the calculated severity of the expected contact between the first body part and a second injury-risk component with the first limit value, and ◯ if the calculated severity of the expected contact of the first body part with the first injury-risk component exceeds the first limit value, to generate the first hazard signal and send it to the safety measure device, ◯ if the calculated severity of the expected contact of the first body part with the second injury-risk component exceeds the first limit value, not to generate the first hazard signal. [6] Safety device according to one of the preceding claims, characterized by that the control device is programmed to detect a second body part of the person which is different from the first and to calculate its position, speed and direction of movement and, if applicable, acceleration and direction of acceleration. [7] Safety device according to one of the preceding claims, characterized by stationary markings in the movement area of ​​the industrial robot, in particular markings formed on a floor surface, which can be optically detected by the image capture device, and characterized by that the control device is designed to recognize the markings and to enter the position of the body part and / or the industrial robot on the basis of the markings in a fixed coordinate system and to evaluate it on the basis of the fixed coordinate system. [8] Safety device according to one of the preceding claims, characterized by that the control device is still programmed to - to calculate an acceleration direction and an acceleration of the detected body part based on a comparison of the respective position of the detected body part in three or more consecutive images, - to determine the direction of acceleration and the acceleration of the component of the industrial robot that is at risk of injury, - to calculate whether contact between the detected or other body part of the user and the injury-risk component of the industrial robot is to be expected within the predetermined time period, also on the basis of the direction of acceleration and the acceleration of the detected body part and the direction of acceleration and the acceleration of the injury-risk component of the industrial robot. [9] Safety device according to one of the preceding claims, characterized by that the control device is designed to detect an operative input variable of the industrial robot based on the image data of an image, in particular • provision of an object to be grasped by the robot, • providing a storage location for an object gripped by the robot, and that the control device has an interface to a control device of the industrial robot and is designed to transmit the detected operational input variable via this interface. [10] Safety device according to one of the preceding claims, characterized by that the first security measure and, where applicable, the second security measure is selected from - a reduction in the movement speed of the industrial robot, - an emergency stop of the movement of the industrial robot, - an emergency stop of the movement of the industrial robot and a subsequent control of the industrial robot into a passive mobility, in which actuators of the industrial robot are controlled in such a way that weight forces are compensated by the components of the robot and, if applicable, by an object held by the robot and the components of the robot are movable by the action of external forces, - a change in the movement of the component of the industrial robot into an evasive movement, wherein the control device is programmed to calculate the direction of movement and preferably the speed of movement of the evasive movement based on the position, the calculated direction of movement and speed of movement and, if applicable, the direction of acceleration and acceleration of the detected body part and the position, direction of movement and speed of movement and, if applicable, the direction of acceleration and acceleration of the injury-risk component of the industrial robot in such a way that contact between the body part and the injury-risk component of the industrial robot is avoided by the evasive movement. [11] Safety device according to one of the preceding claims, characterized bythat the control device is designed to determine the position, speed and / or acceleration of the component of the industrial robot based on - data processing using artificial intelligence used to evaluate the image data, or - a marking on the component of the industrial robot that can be detected during the evaluation of the image data, or - an input from the operator, or - to determine the position data received from a transmitting device on the component. [12] Safety device according to one of the preceding claims, characterized bythat the control device has pre-stored anatomical data and is programmed to calculate a position, movement speed and movement direction of the second body part or a third body part of the person on the basis of the position, movement speed and movement direction of the detected first body part and an assignment of the first body part to a second body part different from the first, as defined in the anatomical data, and / or the control device is set up to determine calibration image data on the basis of a calibration image acquisition by capturing one or more body parts or an entire person and to carry out the evaluation on the basis of the chronologically successive sequence of the images captured by the image capture device, in particular the calculation of the movement direction and speed of a body part taking into account the calibration image data. [13] Safety device according to one of the preceding claims, characterized by that the control device is designed to determine the position, direction of movement, speed of movement and, if applicable, acceleration and direction of acceleration of the component of the industrial robot and / or of an object moved by the industrial robot - to determine from received program data of the industrial robot, and / or - from an image capture of the industrial robot by means of the image capture device, whereby ◯ the image capture is carried out in real time in parallel with the image capture of the first body part of the person or ◯ the image capture takes place in a prior learning process in which the industrial robot performs a repetitive sequence of movements and the control device stores the individual positions, movement speeds and directions of the injury-risk component of the industrial robot and preferably of other components of the industrial robot in order to determine the positions, movement speeds and directions of the component in a monitoring process following the learning process, ◯ wherein, preferably before the real-time image acquisition or in addition to the teaching process, a calibration image acquisition is carried out to determine calibration image data by capturing one or more components of the industrial robot and / or an object to be moved by the industrial robot and to determine the position, direction of movement, speed of movement and, if applicable, acceleration and direction of acceleration of the component of the industrial robot and / or the object, taking into account the calibration image data. [14] Safety device according to one of the preceding claims, characterized by that the control device is designed to • to calculate a future position and / or direction of movement and / or speed of movement and / or acceleration and / or direction of acceleration of the component based on a position, direction of movement, speed of movement and, if applicable, acceleration and direction of acceleration of the component of the industrial robot recorded in real time and to include this in the comparison as to whether contact between the detected or another body part of the user and the injury-risk component of the industrial robot is to be expected, and / or • to calculate a future position and / or direction of movement and / or speed of movement and / or acceleration and / or direction of acceleration of the body part based on a position, direction of movement, speed of movement and, if applicable, acceleration and direction of acceleration of the body part detected in real time and to include this in the comparison as to whether contact between the detected or another body part of the user and the injury-risk component of the industrial robot is to be expected. [15] Safety device according to one of the preceding claims, characterized by that the control device is designed to use the image data of an image • to determine an alignment of a longitudinal axis of the body part and, based on a comparison with pre-stored correlation data in which the alignment of the longitudinal axis is correlated with the future direction of movement of the body part, to determine a future, expected direction of movement of the body part and to include in the comparison whether contact between the detected or another body part of the user with the injury-risk component of the industrial robot is to be expected, and / or • to determine an orientation of the component of the industrial robot and / or an object moved by the industrial robot and, based on a comparison with pre-stored correlation data in which the orientation is correlated with the future direction of movement of the component and / or the object, to determine a future expected direction of movement of the component and / or the object and to include in the comparison whether contact between the detected or another body part of the user and the injury-risk component of the industrial robot and / or object is to be expected. [16] Safety device according to one of the preceding claims, characterized by that the detection device comprises data glasses with an image detection device which is aligned to perform image detection in the field of vision of the wearer of the data glasses. [17] Safety device according to claim 16, characterized bythat the control device is designed to determine an image section of the captured image which corresponds to a predetermined field of view or section of the field of view, in particular a section corresponding to the fovea of ​​the field of view, of a user wearing the data glasses and the control device is designed to determine by means of an image evaluation whether the component is located within the image section and to take into account as a further parameter when generating the first hazard signal whether the component is located inside or outside the image section. [18] Safety device according to claim 16 or 17, characterized by that the data glasses have a device for eye tracking and that the image section is determined depending on the user's gaze direction determined by means of eye tracking. [19] Safety device according to one of the preceding claims 16-18, characterized by that the control device is arranged on the data glasses and the data glasses further have a signal transmission unit for wireless signal transmission and are signal-coupled to the safety measure device for real-time data transmission by means of this signal transmission unit. [20] Safety device according to one of the preceding claims 16-18, characterized by that the control device is arranged on the machine tool and the data glasses further have a signal transmission unit for wireless signal transmission and are signal-coupled to the control device by means of this signal transmission unit. [21] Safety device according to one of the preceding claims 16-20, characterized by that the control device - a first control unit arranged on the data glasses and - comprises a second control unit arranged on the machine tool, and the data glasses further comprise a signal transmission unit for wireless signal transmission and by means of this signal transmission unit the first and the second control unit are signal-coupled, where - the first control unit is designed to carry out a first part of the evaluation and to transmit a result determined therefrom to the second control unit, and - the second control unit is designed to carry out a second part of the evaluation on the basis of this determined result and, depending on the evaluation, to control the safety measure device to carry out a safety measure. [22] Safety device according to one of the preceding claims 16-21, characterized bythat the data glasses further comprise an image output device for outputting image and text information to one or both eyes of the user wearing the data glasses, in particular by means of - Display of image and text information on a screen, or - Projection of image and text information onto the retina of one or both eyes of the user. [23] Safety device according to the preceding claim, characterized by that the data glasses have a data interface for data transmission, in particular a data transmission unit for wireless data transmission, and are designed to receive image and / or text information via the data interface and to display it on the image output device, which - A sequence of predetermined work processes for handling a workpiece by the industrial robot, - A representation of predetermined orientations and / or movements of a tool or a workpiece during the handling of the workpiece by the industrial robot - A designation of the workpieces handled by the industrial robot, wherein preferably the image or text information is reproduced on the basis of the image capture with the image capture device and an image analysis carried out therefrom to determine the position of the component of the industrial robot or the workpiece in an area which is assigned to the component of the industrial robot or the workpiece in the field of vision of the user. [24] Safety device according to one of the preceding claims, characterized bythat the control device is signal-coupled to an electronic storage device and continuously transmits the captured image data to the electronic storage device, which is designed to store the image data and, when a capacity limit of the storage device is reached, to overwrite the oldest image data with the most recently transmitted image data. [25] Safety device according to one of the preceding claims, characterized by that the control device is designed to distinguish between a low and a higher hazard level and to carry out a first safety measure, in particular a warning signal, at the low hazard level and to carry out a second safety measure, which is different from the first safety measure, at the higher hazard level. [26] Safety device according to one of the preceding claims, characterized bythat the image capture device is designed to capture images with depth information, in particular by - the image capture device is designed to capture runtime information on image content or - the image capture device is designed to determine depth information from two images captured at a different time and with different recording directions based on an image evaluation of the position of detected objects relative to each other or by - the image capture device comprises a first and a second image capture unit which are arranged at a distance from one another, for example fastened to the left and right temples of data glasses, and is designed to determine depth information from a stereoscopic image evaluation of simultaneously captured images of the first and second image evaluation unit. [27] Industrial robot comprising a safety device according to any one of the preceding claims. [28] Data glasses for a security device according to one of the preceding claims, characterized by an image capture device which is aligned to carry out an image capture in the viewing direction of the wearer of the data glasses, and preferably further comprising a control device which is signal-coupled to the image capture device and is designed to carry out an assessment of a potential hazardous state detected by the image capture device on the basis of predetermined criteria, wherein further preferably the data glasses have a data interface, in particular a wireless data transmission device and are designed to control the safety measure device to carry out a safety measure as a function of the assessment via the data interface. [29] Data glasses according to claim 28, characterized by that the data glasses are developed according to the features of the data glasses according to the safety device according to one of the preceding claims 16-23.

Images