EP4487303A1 - Automatische herstellung eines digitalen zwillings - Google Patents
Automatische herstellung eines digitalen zwillingsInfo
- Publication number
- EP4487303A1 EP4487303A1 EP23704760.0A EP23704760A EP4487303A1 EP 4487303 A1 EP4487303 A1 EP 4487303A1 EP 23704760 A EP23704760 A EP 23704760A EP 4487303 A1 EP4487303 A1 EP 4487303A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- robot
- data
- environment
- processor
- object type
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/35—Categorising the entire scene, e.g. birthday party or wedding scene
- G06V20/36—Indoor scenes
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/06—Recognition of objects for industrial automation
Definitions
- the invention relates to a method for automatically producing a digital twin of at least one section of a building interior using a robot, a robot, and a data processing device for automatically producing a digital twin of at least one section of a building interior using a robot.
- mapping which means that existing sensors cannot be used.
- this can be due to a lack of options for merging different data sources or a lack of localization of the individual sensors, and on the other hand to a lack of distribution of the manufacturing processes of the map, for example due to large amounts of data and limited data transmission options.
- the use of 3D maps is also limited with conventional methods, since no semantic information and its localization can be contained in the 3D maps.
- the object of the present invention is to provide efficient generation of a digital twin of a robot environment of a robot. This object is solved by the features of the independent claims.
- the object of the invention is achieved by a method for automatically producing a digital twin of at least a section of a building interior using at least one robot, which is arranged in the building interior, the at least one robot having at least one sensor for detection a robot environment in the interior of the building, wherein at least one object is arranged in the robot environment, with at least one object type from a set of predetermined object types being assigned to the object, the method having the following features: detecting the robot environment by the at least one sensor of the robot to obtain captured environmental data; Assigning the at least one object type to the object in the robot environment using a neural network on the basis of the environment data, the neural network being set up to recognize object types, the neural network being executed by a processor; and associating the associated object type with position information indicating a position of the object to create the digital twin.
- the interior of the building can in particular be a warehouse, an assembly hall, an industrial area within a building or a sales area or a room used for industrial purposes.
- a room used for industrial purposes can be understood in particular as a room with an inner surface which can in particular have the properties of a warehouse, an assembly hall and/or an industrial area within a building or a sales area.
- At least one robot can preferably be understood to mean a single robot, two robots or a plurality of robots.
- At least one sensor can be understood to mean a single sensor, two sensors or a plurality of sensors or a sensor array.
- at least one object type can be understood to mean a single object type, two object types or a plurality of object types.
- the robot can be an industrial robot which is designed to take on additional tasks of an industrial robot, such as autonomous goods or parts transport, load handling and/or forklift truck functions.
- the robot can be a stationary robot, so the sensor captures the same environment to detect any changes.
- the robot is movable in translation and/or rotation.
- the robot is a device for generating or generating data, for example an autonomous vehicle, in particular an industrial truck, or a part of a vehicle, in particular an industrial truck, or a sensor arrangement which is attached, for example, to vehicles, conveyor belts or frames, or by people can be worn.
- an autonomous vehicle in particular an industrial truck
- a part of a vehicle in particular an industrial truck
- a sensor arrangement which is attached, for example, to vehicles, conveyor belts or frames, or by people can be worn.
- the processor is implemented in the robot, with the at least one associated object type being sent to a data processing device via a communication network, and with the data processing device linking the at least one associated object type with the position information.
- the robot sends the recorded environment data to a data processing device via a communication network, the processor being implemented in the data processing device, and the data processing device linking the at least one assigned object type to the position information.
- the data processing device is a server, for example a cloud server.
- an output of the neural network is a digital feature set that represents the associated object type.
- the position information is information about a position of the robot obtained from a global localizing system, or the position information is a position of the object, or the processor derives the position information from the recorded environmental data.
- Position information can be understood in particular as information with regard to the x-axis, the y-axis and the z-axis or a spatial axis or a plurality of spatial axes of a coordinate system. Particularly preferably, this can be understood as pose information which, in addition to the information regarding the x-axis, the y-axis and the z-axis, preferably includes information about a spatial angular position, in particular information about a rotation about the x-axis y-axis and/or the z-axis.
- the position information can be a GPS position of a robot.
- the object has an attribute that is detected by the sensor in the environment data, or the robot has another sensor for attribute detection, in particular a laser scanner, which outputs attribute data, the processor being designed to process the attribute to be detected in the environment data or the attribute data.
- the attribute is a geometric characteristic of the object, in particular a geometric shape or a geometric extent, or an object label, or an object orientation.
- the processor is designed to recognize the attribute on the basis of pattern recognition or on the basis of the neural network or on the basis of another neural network that is set up to recognize attributes.
- the attribute is linked to the associated object type with position information.
- the associated object type is linked to the position information by associating the position information with the object type or by entering the position information in a digital map.
- At least one additional object is arranged in the robot environment, with at least one additional object type of the at least one additional object being detected by executing the neural network on the processor, and with the localization information or additional localization information being linked to the at least one additional object type .
- the object type can preferably be an object type that is customary in the application, preferably a pallet, a robot, a wall, an aisle, a shelf, a door, or an information sign.
- the object type is a pallet, robot, wall, aisle, shelf, door, or information sign.
- the object of the invention is achieved by a robot, which is arranged in a building interior, with: at least one sensor for detecting a robot environment in the building interior, with at least one object being arranged in the robot environment, the object at least one object type from a set of predetermined object types is assigned; a processor which is designed to assign at least one object type to the object in the robot environment using a neural network on the basis of the environment data, the neural network being set up to recognize object types; and wherein the processor is further configured to link the at least one associated object type to position information indicating a position of the object in order to produce the digital twin.
- the object has an attribute that is detected by the sensor in the environment data, or the robot has a further sensor for attribute detection, in particular a laser scanner, which attribute data outputs, the processor being designed to detect the attribute in the environmental data or the attribute data.
- the object of the invention is achieved by a data processing device for automatically producing a digital twin of at least one section of a building interior using at least one robot, which is arranged in the building interior, the robot having at least one sensor for detecting a robot environment in the interior of the building, at least one object being arranged in the robot environment, at least one object type from a set of predetermined object types being assigned to the object, the data processing device having the following features: a communication interface for receiving environment data from the at least one robot via a communication network, wherein the captured environment data represents the captured robot environment; a processor which is designed to assign at least one object type to the object in the robot environment by executing a neural network on the basis of the environment data, wherein the neural network is set up to recognize object types, and the processor is also designed to associated object type with position information indicating a position of the object to link to produce the digital twin.
- the object according to the invention is achieved by a computer program for executing the method according to the first aspect when the computer program is executed using a processor.
- 1a is a flow chart illustrating steps of a method for automatically creating a digital twin of at least a portion of a building interior using a robot according to an embodiment
- FIG. 1b shows a schematic view of a robot according to an embodiment and a data processing device according to an embodiment in a communication network;
- FIG. 2 shows a schematic view of implementation steps by robots according to an embodiment and by a data processing device according to an embodiment
- FIG. 3 shows a schematic view of a system architecture of robots according to an embodiment, a data processing device according to an embodiment and a further data processing device according to an embodiment.
- FIG. 1a shows a flowchart which illustrates steps of a method 10 for automatically producing a digital twin of at least a section of a building interior using a robot according to one embodiment.
- the robot 101, 101' which is arranged in the interior of the building, has a sensor 105, 105' for detecting a robot environment in the interior of the building.
- At least one object is arranged in the robot environment, with an object type from a set of predetermined object types being assigned to the object.
- the method 10 has the following features: detection 11 of the robot's surroundings by the sensor of the robot 101, 101' in order to obtain detected surroundings data; Assigning 12 an object type to the object in the robot environment by means of a neural network on the basis of the environment data, the neural network being set up to recognize object types, the neural network being executed by a processor 103, 103', 113; and linking 15 the associated object type with position information which indicates a position of the object in order to produce the digital twin.
- Figure 1b shows a schematic view of a robot 101, 101' according to an embodiment and a data processing device 111 according to an embodiment in a communication network 100.
- a plurality of robots 101, 101' can be designed to communicate with a data processing device 111 via a communication network 100 in order to produce the digital twin (also referred to below as a map).
- the robots 101, 101' can each comprise corresponding first communication interfaces 109, 109' and the data processing device 111 can comprise a second communication interface 117 in order to send sensor data from the sensors 105, 105' of the robot 101, 101' via the communication network 100, for example wirelessly or wired.
- the sensor data can be preprocessed by corresponding first processors 103, 103' of the robots 101, 101 ' become.
- the robots 101, 101' can have corresponding first non-volatile memories 107, 107' and the data processing device 111 can have a second non-volatile memory 115.
- the data processing device 111 can include a second processor 113 for further processing of the pre-processed data and/or the sensor data 105, 105'.
- the non-volatile memories 107, 107', 115 can be designed to store data and respectively executable program code which, when executed by the corresponding processor 103, 103', 113, causes at least one of the processors 103, 103', 113 to perform the functions, operations, and procedures described below.
- the robots 101, 101' can include more than one sensor 105, 105'.
- the sensor 105, 105' can be a 3D sensor, for example a 3D lidar sensor, a 3D ToF camera, a radar sensor, an ultrasonic sensor or a stereo camera, and generate distance information, in particular angle-related distance information, of the objects.
- the sensors 105, 105' can include a sensor for attribute detection, for example a laser scanner, which is designed to output attribute data.
- the robots 101, 101' can include an internal measurement unit (IMU) or an odometry sensor system for detecting a movement and/or position of the sensors 105, 105'.
- IMU internal measurement unit
- odometry sensor system for detecting a movement and/or position of the sensors 105, 105'.
- the implementation steps for producing the digital twin or the map can be distributed to the first processors 103, 103' of the robots 101, 101' and to a second processor 113 of the data processing unit 111.
- Figures 1c-e show schematic views of robots according to embodiments.
- the robot 101, 101' can be an autonomous vehicle (AMR) and the robot 101, 101' can comprise a large number of sensors 105a-c, which can be detected by overlapping the fields of view of the individual sensors 105, 105' can open up a common field of vision.
- the robot 101, 101' can include 2D color cameras 105a as sensors 105, 105' and the robot 101, 101 ' can have a 3D lidar sensor 105b as an additional sensor 105, 105'.
- AMR autonomous vehicle
- the sensors 105, 105' for generating depth images can be 105c, which are each arranged on one side of the robot 101, 10T.
- at least one sensor preferably the sensors 105a-c, can also be arranged on a load-handling means, preferably a mast and/or a fork carrier and/or a fork tine.
- At least one sensor, preferably sensors 105a-c, can be arranged, for example, in such a way that they have a line of sight towards the hall floor. As shown in FIG.
- the robot 101, 10T can be a sensor arrangement with a 3D lidar sensor 105b as sensor 105, 105' and 2D color cameras 105a as additional sensors 105, 105'.
- the communication interface 109, 109' can be designed as a radio interface, as illustrated in FIGS. 1c-e.
- a large number of existing sensors can be used by the automated robots 101, 10T to produce the digital twin, such as fixed sensors or vehicle sensors from a number of vehicles and from a number of locations.
- FIGS. Figure 2 shows a schematic view of implementation steps by robots 101, 10T according to an embodiment and by a data processing device 111 according to an embodiment
- Figure 3 shows a schematic view of a system architecture of robots 101, 10T according to an embodiment, a data processing device 111 according to an embodiment and a further data processing device 310 according to an embodiment.
- the steps implemented by the second processor 113 can be distributed to the data processing device 111 and the further data processing device 310 in one embodiment.
- FIG. 2 shows the processing steps of the first processors 103, 103′ of two robots 101, 10T shown in FIG. 1b.
- more than two robots 101, 101' or only one robot 101, 10T are also possible for the automatic production of the digital twin.
- the robots 101, 10T can be designed differently with regard to the number and/or type of sensors 105, 105'.
- the respective first processors 103, 103' can be designed to read out information about update rates 203, which are described in more detail below.
- the update rates can be stored in a predefined manner in the corresponding first memories 107, 107' shown in FIG. 1b.
- the update rates 203 can be determined by the first processors 103, 103' based on an area of the map 211 in which the respective robots 101, 101' are located and/or depending on movement data, for example depending on speed data from the movement sensors 213, 213'. , determined and/or modified.
- the first processors 103, 103' can be designed, if the corresponding robot 101, 101' comprises more than one sensor 105, 105', to carry out a data fusion 201, 201' of the respective sensor data in one processing step, for example as shown in Figure 3, to a point cloud (also known as "point cloud" in English) by a point cloud generator 305.
- the sensors can be configured and based on information on sensor calibration 205, 205 'calibrated so that a common or at least a partial common field of vision is spanned by the corresponding sensors 105, 105' of the respective robot 101, 101'. If one of the sensors 105, 105' is a color sensor, for example a 2D color camera, a colored point cloud can be generated by the corresponding first processors 103, 103'.
- the respective first processors 103, 103' can be designed to implement a processing step 207, 207' for classifying and segmenting the sensor data.
- the sensor data can be classified with regard to a dynamic.
- Dynamic data can be assigned to vehicles or people, for example, and goods, for example, can be assigned to semi-dynamic data associated and static data may be associated with shelves or walls, for example.
- the second time interval can be longer than the first time interval.
- the module 207 can also be used, for example by pattern recognition, to recognize attributes or semantic information in the sensor data. Attributes or semantic information is understood here to mean information which types of an object, such as a pallet, vehicle, person or shelf, for example based on a geometric shape or extent of the object, and/or a numbering and/or labeling of the object can display . Furthermore, the semantic information or the attributes can include an object orientation.
- the respective first processor 103, 103' can be designed to define and/or modify the corresponding update rates 203 of the sensors based on the attributes or semantic information.
- the respective first processor 103, 103' can be designed to implement a corresponding first neural network 307, 307', which is designed for machine learning and/or computer vision .
- the respective neural network 307, 307' can include subnets 301, 301', which can be assigned specifically to individual sensors 105, 105' of the corresponding robot 101, 101'.
- the respective first neural network 307, 307' and the sub-networks 301, 301' can be trained using objects that typically occur in warehouses, for example sensor-specifically, and thus be designed to recognize objects in a warehouse.
- the module 207 can be designed to discard sensor data that does not correspond to a specific classification according to dynamics, which is predetermined class-specifically with the update rates 203, for example. The sensor data can thus be reduced by the module 207 .
- the subnets 301, 301' can also be designed prior to the data fusion 201 for the localization 303 to generate localization information based on the movement data of the movement sensors 213, 213 of the respective robot 101, 1011 .
- the localization 303 can alternatively and/or additionally be based on the attributes or semantic information.
- the corresponding first processor 103, 103' can also be designed to implement a processing step 209, in which the corresponding first processor 103, 103' is designed to determine a deviation of the sensor data from the map 211 of the environment, and only those areas of the Card 211 further processing, which have changed compared to the card 211.
- the corresponding first processor 103, 103' can also be designed to implement a further processing step 215.
- the information on the class and the attributes or semantic information from processing step 207 and data from motion sensors 213, 213' can be added to the sensor data.
- the corresponding first processor 103, 103' can be configured to send the sensor data supplemented in this way to the data processing device 111 using a predefined transmission protocol such as MQTT.
- the second processor 113 of the data processing device 111 can be designed to receive the sensor data preprocessed by the respective first processors 103, 103′ via the second communication interface 117 using the predefined transmission protocol of the data processing device 111.
- the data of the robots 101, 101' which are received at time intervals according to the current update rates 203 through the second communication interface 117, and depending on the type of the corresponding sensors 105, 105', preferably images and/or point clouds and/or semantic information and/or attributes, in particular from processing step 215, are stored individually.
- the data can be collected and stored in a data store, for example in a database 309, with a time stamp.
- the data collected can be regularly analyzed using a metric, for example on the amount of data, the distance moved by the robots 101, 101' after a time interval determined by the second processor 113 depending on the update data 203, the environment, a change assessment of the environment determined based on the collected data and/or the map areas of the map 211 for evaluation to the modules described below.
- the collected forwarding can be limited to a maximum of once per meter of movement of the robots 101, 101' and/or to a range of the time interval from 30 seconds to 5 minutes. These values can depend on the environment or areas of the map 211 . In surroundings or areas of the map 211 with a relatively large number of changes, evaluation can be carried out more frequently than in surroundings that hardly change or do not change at all.
- the processor 113 of the data processing device 211 can be designed to implement an online calibration module 315 for self-monitoring of the respective robots 101, 101'.
- Online calibration of the corresponding sensors 105, 105′ of the respective robots 101, 101′ can be achieved in a processing step 219 by the online calibration module 315 .
- the individual data from the sensors can be linked to one another based on the route taken.
- the online calibration module 315 can implement a suitable method, for example a simultaneous localization and mapping (SLAM) method, for each sensor 105, 105′. From the trajectories of the sensors 105, 105' and the information that the corresponding sensors of the respective robots 101, 101 ' are firmly coupled to one another, their movement must also be identical.
- SLAM simultaneous localization and mapping
- the second processor 113 can carry out corresponding difference calculations from the individual data of the relevant sensors 105, 105'.
- the calibration can be transmitted via the first and second communication interfaces 109, 109', 117 to the respective robot 101, 101' as a corresponding further sensor calibration 205, 205'.
- the further sensor calibration 205, 205' can then be compared with the previous, for example initial, sensor calibration 205, 205' by the respective first processors 103, 103'. If the deviation is clearly too large, the corresponding robot 101, 101' can be calibrated to the further sensor calibration 205, 205' or but determine the existence of a possible error and respond with a suitable system reaction, for example stop the service.
- the second processor 113 can also be designed in a processing step 221 to carry out data reductions.
- the second processor 113 can implement a point cloud mapping module 313 .
- the individual data from one of the robots 101, 101′ forwarded by the point cloud mapping module 313 can be combined to form an entire point cloud map. This can result in a unique amount of data.
- the individual data can represent excerpts from this entire point cloud map.
- the second processor 113 can be designed to carry out a change assessment of the entire point cloud map in comparison to the currently current map 211 and to decide based on the change assessment whether the entire point cloud is processed further.
- dynamic objects such as vehicles and people can be removed from the map or transferred to a separate map.
- the completed point cloud map can be written back to the database 309 and the items of data accumulated up to the creation of the point cloud map can be deleted. New individual data can then be merged together with the point cloud map into a new point cloud map in subsequent passes, based on the time-interval-controlled forwarding of the collected data.
- the second processor 113 can also implement a multi-point cloud matcher module 317 that operates similarly to the point cloud mapping module 313 .
- finished point clouds from different robots 101, 101' are brought together, whereas the point cloud mapping module 313 uses the data from one robot 101, 101'.
- the data from multiple robots 101, 101' can be brought together directly in the point cloud mapping module 313.
- the second processor 113 can implement a point cloud reducer module 311 for further data reduction.
- the task of the point cloud reducer module 311 is to reduce the amount of data in a point cloud as optimally as possible.
- a further check with regard to the dynamics of the objects can be carried out in order to filter out dynamic objects or static objects, for example.
- Another possibility for reduction is the use of AI algorithms using an encoder-decoder principle. The AI algorithms can be trained in such a way that objects are detected in their entirety.
- the amount of data in the encoder can be essentially reduced to features that are really needed by the following neural networks, for example deep neural networks (also known as “deep neural networks”), in order to find objects such as vehicles, pallets, etc. and to recognize. These features would be sufficient to create the map. Due to a possible loss of information due to the features from a "dense” (densely populated) to a “sparse” (sparsely populated) map, the feature reduction can also be applied in the reverse processing direction and the features can again be derived, for example, using the neural network and a Decoders the point cloud are extracted.
- deep neural networks also known as "deep neural networks”
- the feature reduction can also be applied in the reverse processing direction and the features can again be derived, for example, using the neural network and a Decoders the point cloud are extracted.
- the data processing device 111 can be connected to the further data processing device 310 via the second communication interface 117 for synchronization 323 .
- the data-reduced point clouds can be stored in a database 325 of the data processing device 111 .
- the map 211 generated by the data processing device 111 can be stored in a map memory 321 of the data processing device 111 and synchronized with a map memory 319 of the further data processing device 310 .
- the maps can be fed back to the point cloud reducer module 311 via the map memory 319 of the further data processing device 310 in order to enable a combination to form a new point cloud, as described above.
- the functionalities and components of the additional data processing device 310 can also be included in the data processing device 111, as illustrated in FIG. Due to the division between the data processing device 111 and the further data processing device 310, the individual data from the sensors 105, 105' can remain on the further data processing device 310, thus reducing the data traffic between the data processing device 111 and the further Data processing device 310, for example, especially in the case of a large number of other data processing devices 310, can be achieved.
- the second processor or the data processing device 111 can also be designed in a processing step 223 to bring about a merging of the attributes or semantic information. Instance designations, which were taken over from the individual data, can be cleaned up here. For example, a numbering 1 to 5 of palettes of first individual data and a numbering 1 to 5 of palettes of second individual data can be adjusted to a numbering 1 to 10 in the merged data. Furthermore, segmentation instances can be merged. For example, a left half of a shelf in first items and a right half of a shelf in second items may be referred to as an entire shelf in the merged data.
- a segmentation engine 327 based on a difference model between the map of the map 211 and the merged point cloud, objects that have already been segmented and recognized can be calculated from the point cloud and only the unknown objects can be passed on to a segmentation engine 327, thus separating the data volume into a segmented data volume and a non-segmented data volume -segmented amount of data can be achieved.
- the segmentation engine 327 can be configured to load the point cloud maps for segmentation.
- a segmentation not only takes place according to objects, but the individual objects can also be distinguished from one another. For example, if there are ten pallets next to each other, all objects can be given the label "Palette” for segmentation. However, the individual palettes can still be differentiated here, for example each palette can be given the label "Palette” but also a sequence number from 1 to 10. This information is used for further processing.
- the segmentation engine 327 can use a machine learning approach for segmentation and implement another neural network.
- the segmentation engine 327 can therefore post-segment the non-segmented data volume in which the class or the object type is not yet known.
- an independent object type can be assigned, for example, the floor can be anywhere or area-dependent in the Surroundings have the same object type or goods can be segmented into a set of points.
- the objects can be specifically created, for example manually, based on the current post-segmentation and/or a post-segmentation of an earlier run.
- An object type can be assigned for the post-segmentation data and a CAD model can be stored.
- the segmentation engine 327 can detect tags on goods and, based on this, track information from a goods management system (WMS) 227 or also use other data sources, such as the Internet 229 .
- WMS goods management system
- the segmentation engine 327 can be designed to query positions of goods via the WMS 227 in order to identify which goods are involved and to query existing map information, such as a building plan with a dedicated coordinate system, via the database 231 in order to optimize the map 211 to reach existing coordinate systems.
- the second processor 113 assigned to the further neural network of the segmentation engine 327 is more powerful than the respective first processors 103, 103', which means that finer segmentation and thus a higher number of classes can be achieved.
- the segmentation engine 327 can include a data labeler, which is designed to label special load carriers or goods that are to be segmented, in order to train the further neural network specifically for this data. Furthermore, the segmentation engine 327 can be linked to a CAD system of the customer for object recognition, so that the data for objects can be transferred directly to the map. Further information about goods can also be queried via the WMS 227, for example system information about the condition. Thus, for example, the product type can be searched for directly on the Internet 229 in order to obtain further training data and, on the basis of this, to quickly train the further neural network for new objects.
- the segmentation engine 327 can also be designed in a processing step 233 for segmentation using temporal information.
- the position of all objects or points that could not be assigned to any object can be tracked over time. Points/objects that do not move over a defined period of time can then be classified as static. This means that points caused by data artifacts can also be removed.
- Data that cannot be summarized by the segmentation engine 327, for example because noise from the sensors 105, 105' has resulted in isolated points still being present, can then be removed in a processing step 235.
- the second processor 113 can also be configured to implement a method step 237 for replacing known segments with 3D models.
- the data processing device 111 can include an object replacement module 331 for this purpose.
- Objects in a warehouse such as pallets, shelves or lattice boxes, can be replaced with a 3D representation, such as a CAD file.
- This allows mapping to the 3D map 211 from the point cloud.
- the map 211 can be stored in the map memory 321 of the data processing device 111 and, as described, can also be mirrored back to the further data processing device 310.
- the position and content of goods are known from the WMS 227, which means that this information can be simplified into models, for example CAD models, and can also be included in the card 211.
- the second processor 113 may further be configured to implement a processing step 239 for replacing unknown segments with geometry models.
- the data processing device 111 can include a point cloud meshing module 329 for this purpose.
- large areas of the point cloud can be combined as a polygon mesh (also referred to as "mesh"), for example to replace the ground with this polygon mesh.
- the polygon mesh itself can only be formed from a few vertices, for example as is known from gaming engines.
- other large areas, such as walls, ceilings, but also pallets, shelves, goods, provided that not yet replaced by the object replacement module 331, are shown on the map 211.
- the map 211 can be distributed again to the robot 101, 101' via a map API 333, and/or the map 211 can be used in a simulation via a card reader 335. Furthermore, the map 211 can be made available to other programs via a corresponding interface, such as CAD programs or goods management systems 227. In one embodiment, the map API 333 can also be integrated in the further data processing device 310 in order to use the robots 101, 101 'with to supply the map update of the map 211. Map API 333 may have interfaces and/or standardized protocols such as VDA5050 for map 211 distribution. The robots 101, 101' can be designed to locate themselves using the map 211, for example via SLAM.
- Visualization interfaces 337, 341 of the data processing device 111, 310 can be used to view the generated map 211, i.e. the 3D twin of the department store, via a defined interface 339 and thus enable the user to move virtually in his warehouse can.
- the user can be connected to the defined interface 339 via an Internet connection and user-specific access data.
- the view can take place on a device, for example via a tablet, mobile phone, PC, or by means of virtual reality (VR) and augmented reality (AR), for example in the form of an AR/VR device.
- VR virtual reality
- AR augmented reality
- the advantage of an AR device is that it can be worn directly in the warehouse and the map 211 and the real environment can thus be superimposed.
- the card 211 can be used to carry out a live inventory of the warehouse or a manual inventory, preferably supported by AR devices.
- the method steps described above for FIGS. 2 and 3 can be based on filtering static and semi-dynamic objects.
- the dynamic objects can then be shown or hidden in the updateable map 211
- the whole Work process can be automated and does not require human intervention or processing of data.
- the system can thus be encapsulated and several functions can be implemented simultaneously, such as live mapping of the environment and associated digital services, such as live inventory, localization and simulation of the real environment. In this way, costs can be reduced and processing times can be reduced at the same time, and data can also be collected that are absolutely necessary for advancing digitization using artificial intelligence.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| DE102022105079.3A DE102022105079A1 (de) | 2022-03-03 | 2022-03-03 | Automatische Herstellung eines digitalen Zwillings |
| PCT/EP2023/053206 WO2023165799A1 (de) | 2022-03-03 | 2023-02-09 | Automatische herstellung eines digitalen zwillings |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| EP4487303A1 true EP4487303A1 (de) | 2025-01-08 |
Family
ID=85225125
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| EP23704760.0A Pending EP4487303A1 (de) | 2022-03-03 | 2023-02-09 | Automatische herstellung eines digitalen zwillings |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US20250174016A1 (de) |
| EP (1) | EP4487303A1 (de) |
| DE (1) | DE102022105079A1 (de) |
| WO (1) | WO2023165799A1 (de) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102023125462A1 (de) | 2023-09-20 | 2025-03-20 | Still Gesellschaft Mit Beschränkter Haftung | Vorrichtung und Verfahren zum automatisierten Erkennen von Gefahrensituationen in einem Warenlager |
| US20250130572A1 (en) * | 2023-10-23 | 2025-04-24 | BrightAI Corporation | Systems and associated methods for multimodal feature detection of an environment |
| DE102024116308A1 (de) | 2024-06-11 | 2025-12-11 | Still Gesellschaft Mit Beschränkter Haftung | Vorrichtung, Verfahren und System zum Betreiben eines Flurförderzeugs in einem Warenlager |
| DE102024131005A1 (de) | 2024-10-24 | 2026-04-30 | Still Gesellschaft Mit Beschränkter Haftung | Ticketing-System für ein intralogistisches Umfeld mit Flurförderzeugen |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3680813B1 (de) * | 2019-01-14 | 2025-12-24 | Siemens Schweiz AG | Verfahren und system zum erfassen von in einem gebäude installierten objekten |
-
2022
- 2022-03-03 DE DE102022105079.3A patent/DE102022105079A1/de active Pending
-
2023
- 2023-02-09 US US18/843,173 patent/US20250174016A1/en active Pending
- 2023-02-09 EP EP23704760.0A patent/EP4487303A1/de active Pending
- 2023-02-09 WO PCT/EP2023/053206 patent/WO2023165799A1/de not_active Ceased
Also Published As
| Publication number | Publication date |
|---|---|
| WO2023165799A1 (de) | 2023-09-07 |
| US20250174016A1 (en) | 2025-05-29 |
| DE102022105079A1 (de) | 2023-09-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2023165799A1 (de) | Automatische herstellung eines digitalen zwillings | |
| DE102018006764B4 (de) | Verfahren und system(e) für das management von frachtfahrzeugen | |
| DE102018006765B4 (de) | Verfahren und system(e) für das management von frachtfahrzeugen | |
| EP4010766B1 (de) | Verfahren zur erstellung eines digitalen zwillings einer anlage oder vorrichtung | |
| EP2767925B1 (de) | Verfahren zur Erkennung von Objekten in einem Lager und/oder zur räumlichen Orientierung in einem Lager | |
| EP2854106B1 (de) | 3D-Kamera nach dem Stereoskopieprinzip und Verfahren zum Erfassen von Tiefenkarten | |
| DE102010018634B4 (de) | Verfahren zur Eingabe eines räumlichen Aufbaus von Fertigungseinrichtungen in ein rechnergestütztes Planungsprogramm und dessen Optimierung | |
| DE102018128531A1 (de) | System und Verfahren zum Analysieren einer durch eine Punktwolke dargestellten dreidimensionalen Umgebung durch tiefes Lernen | |
| DE112019006132T5 (de) | Verfahren, system und vorrichtung zur hilfsetikett-erkennung und -zuordnung | |
| EP3977225B1 (de) | Verfahren zur erstellung einer umgebungskarte für die verwendung bei der autonomen navigation eines mobilen roboters | |
| EP4064106A1 (de) | Verfahren zum erzeugen von trainingsdaten für ein ml-modell | |
| DE102017213601A1 (de) | Verfahren zum Erstellen einer Objektkarte für eine Fabrikumgebung | |
| EP4154219A1 (de) | Materialflusssteuerung mit virtuellen sensoren | |
| EP4239428B1 (de) | Verfahren und system zur navigation eines flurförderzeugs | |
| EP3812869A1 (de) | Verfahren zur erstellung einer umgebungskarte für ein sich selbsttätig fortbewegendes bodenbearbeitungsgerät, sowie system aus zwei sich selbsttätig fortbewegenden bodenbearbeitungsgeräten | |
| DE102019203623A1 (de) | Verfahren zur Bereitstellung einer Karte | |
| WO2022199994A1 (de) | Verfahren zum ermitteln von steuerungsdaten für eine greifeinrichtung zum greifen eines gegenstands | |
| DE102022201311A1 (de) | Überwachungsvorrichtung für einen Lagerbereich, Intralogistikanordnung mit der Überwachungsvorrichtung sowie Überwachungsverfahren | |
| DE102008008499B4 (de) | Verfahren zur rechnergestützten Berechnung der Bewegung eines Objekts aus Sensordaten | |
| DE112022002520T5 (de) | Verfahren zur automatischen Kalibrierung von Kameras und Erstellung von Karten | |
| DE102020209078B4 (de) | Automatisierte Prozessüberwachung | |
| EP3543901A2 (de) | Vorrichtung und verfahren zur robusten ermittlung der position, ausrichtung, identität und ausgewählter zustandsinformationen von objekten | |
| DE10013137B4 (de) | Verfahren zur bildgesteuerten Prüfung und Bearbeitung von Produkten | |
| DE69325194T2 (de) | Verfahren zur Erzeugung des Kennzeichens eines auf einem numerischen Bild dargestellten Objektes mit Bestimmung mindestens einer charakteristischen Grösse dieses Objektes und zugehöriges Verfahren zur Prüfung des Objektkennzeichens | |
| DE102019201633A1 (de) | Kalibrierung eines Sensors für ein Fahrzeug basierend auf objektseitigen und bildseitigen Identifikationsindizes eines Referenzobjektes |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: UNKNOWN |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
| PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
| 17P | Request for examination filed |
Effective date: 20240812 |
|
| AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC ME MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
| DAV | Request for validation of the european patent (deleted) | ||
| DAX | Request for extension of the european patent (deleted) | ||
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
| 17Q | First examination report despatched |
Effective date: 20260401 |