Patent Application
20220237424
This application claims priority from European patent application No. 21305094.1, filed on Jan. 26, 2021, the contents of which are hereby incorporated herein in their entirety by this reference.
The present disclosure relates to computer-implemented methods for digitization of papercraft folding for creation of a papercraft model, and to papercraft digitization systems configured to perform such methods.
Papercraft is an artform (e.g. the artform of origami) based on the folding, i.e. papercraft folding, of two-dimensional (2D) paper or card, in general terms a sheet, to create three-dimensional (3D) designs, i.e. a papercraft model.
Digitization of papercraft is currently limited, with some artificial intelligence (AI) systems existing which take a digital 3D file as an input to generate a fold list which need to occur in order to create that 3D shape with real paper, but there is a lack of approaches centered on doing the reverse: digitizing analogue creations.
The object of the present disclosure is to provide an alternative method to obtain a fold list of folds which need to be performed on a sheet to create a papercraft model. Another object of the present disclosure is to provide a method of monitoring and supporting a user during the creation of a papercraft model at each folding step.
The present disclosure relates to a computer-implemented method as defined in claim 1 and a papercraft digitization system as defined in claim 15. The dependent configurations depict embodiments of the present disclosure.
The computer-implemented method for digitization of papercraft folding for creation of a papercraft model comprises:
In some aspects, the monitoring may comprise:
In a first embodiment, the computer-implemented method may further comprise:
In a second embodiment, the computer-implemented method may further comprise:
In a first refinement which is combinable with any one of the preceding aspects and embodiments, determining the occurrence of a fold performed on the sheet may comprise applying a tag proximity algorithm configured to:
In one aspect of the first refinement, analyzing the return signals may comprise:
In another aspect which is combinable with the preceding aspect, determining return signal properties may comprise determining a relative change of return signal strength of a received return signal. The change of return signal strength of a received return signal may be determined by a comparison with return signal strength of a previously received return signal of the same RFID tag. Comparing return signal properties may comprise comparing a relative change, specifically a decrease, of return signal strength of received return signals. A proximity between two RFID tags may be determined if one or both of the following conditions are met:
Alternatively, a binary-type proximity link may be used which assumes the value of 1 if the threshold condition is met.
Alternatively or additionally to the preceding aspect, determining return signal properties may comprise calculating a phase shift between a received return signal and the emitted signal. Comparing return signal properties may comprise comparing phase shifts of the received return signals. A proximity between two RFID tags may be determined if their respective phase shifts are substantially equal. Alternatively or additionally, a proximity between two RFID tags may be determined if their respective phase shifts are substantially equal within a relative tolerance interval of −15% to +15%, more specifically within −10% to +10%, and in examples within −5% to +5% or within −2.5% to +2.5%. The proximity link may include a proximity value which is calculated from a deviation of phase shifts of the RFID tags proximity was determined for. Alternatively a binary-type proximity link may be used which assumes the value of 1 if the phase shifts correlate within the tolerance interval.
In another aspect which is combinable with any one of the preceding aspects, the generation of a proximity link may be triggered upon determining proximity between two RFID tags.
In another aspect which is combinable with any one of the preceding aspects, outputting a proximity link may comprise storing it on a tag database and relating it to the tag IDs of the RFID tags proximity was determined for.
In another aspect which is combinable with any one of the preceding aspects, the tag proximity algorithm may be further configured to:
In a second refinement which is combinable with any one of the preceding aspects, refinements and embodiments, determining the fold properties of an occurred fold may comprise applying a papercraft digitization algorithm configured to:
The tag data may include for each RFID tag one or more of a tag ID, predefined tag coordinates with respect to the sheet, a tag resonance frequency, a proximity link, if present. In examples, the tag data may include all of the previously mentioned information. The tag data may be stored on a tag database.
In one aspect of the second refinement, calculating the fold properties may comprise retrieving tag data from the tag database. Additionally, calculating the fold properties may comprise determining a mid-point of the occurred fold by averaging x-coordinates and y-coordinates of the RFID tags being correlated by a proximity link. Additionally, calculating the fold properties may comprise determining x- and y-coordinates of a fold line through which the occurred fold is estimated to run through based on the mid-point and/or the x-coordinates and y-coordinates of the RFID tags. Additionally, calculating the fold properties may comprise determining a folding angle of the occurred fold with respect to a datum, such as a specific edge of the sheet having a length L, using trigonometry and the x- and y-coordinates of the previously calculated fold line. Additionally, if proximity values are present, calculating the fold properties may comprise determining a closing angle of the occurred fold based on a change rate of proximity values of RFID tags distanced further away from the fold line in a normal direction. The closing angle may be determined by assessing a series of proximity values of RFID tags arranged along a normal direction with respect to the fold line and in an increasing distance from the fold line, and then applying a conversion factor to the series of proximity values to obtain the closing angle.
In a third refinement which is combinable with any one of the preceding aspects, refinements and embodiments, the computer-implemented method may be executed in real-time during the creation process of folding. The emitter signal may be repeatedly sent at specific time intervals. The time interval between two emitter signals may be selected to secure that a maximum of one fold is performed during the time interval. Additionally, the time interval may be determined by a sampling rate. Additionally, the sampling rate may have a frequency of at least 0.1 Hz, specifically at least 1 Hz, more specifically at least 5 Hz and most specifically at least 10 Hz. A set of return signals may repeatedly be received at each time interval. The set of return signals may contain a return signal received from each of the RFID tags. The repeatedly received sets of return signals may form a time series of sets of return signals. Each set of return signals of the time series may be analyzed. Additionally, each set of return signals of the time series may be analyzed by comparing a newly received set of return signals with a set of return signals received at a previous, specifically immediately previous, time interval. Alternatively or additionally, a set of proximity links may be generated at each time interval, if proximity is determined. Additionally, fold properties may be determined for each set of proximity links. Alternatively or additionally, for each set of proximity links the fold properties may be added as a new fold dataset in the fold list.
In another aspect which is combinable with any one of the preceding aspects, refinements and embodiments, the sheet may be repeatedly monitored at regular time intervals. Additionally, a time series of sets of return signals may be received from the RFID tags and analyzed. Additionally, return signals may be compared within the set of return signals received at the same time interval and/or with one or more sets of return signals over previous time intervals. Additionally, based on the comparison, fold properties of occurred folds may be calculated which must have taken place in order to receive the present set of return signals.
In a fourth refinement which is combinable with any one of the preceding aspects, refinements and embodiments, the computer-implemented method may be executed after the creation process of folding is completed. The emitter signal may be sent at least once to receive at least one set of return signals. Additionally, determining the fold properties of an occurred fold may comprise applying a papercraft digitization algorithm configured to reverse-generate a fold list including the fold datasets of folds which must have occurred based on the present set of proximity links determined from the at least one set of return signals. Additionally, the reverse-generating may include:
In a fifth refinement which is combinable with any one of the preceding aspects, refinements and embodiments, the computer-implemented method may further comprise:
In one aspect of the fifth refinement, applying the fold list to a virtual representation of the sheet may include applying a fold render algorithm configured to:
Additionally, the fold render algorithm may be further configured to store the mesh model at different stages of the application of fold datasets as a virtual representation of the sheet representing the sheet in a folded state. Alternatively or additionally, the fold render algorithm may be further configured to store the mesh model after the application of all fold datasets as a virtual representation of the sheet representing the sheet in a completely folded state. Alternatively or additionally, the user-interface may be configured to allow a user to view, move and/or edit the virtual representation. The user-interface may be a smartphone, a display or any other device capable of depicting the virtual representation.
In a sixth refinement which is combinable with any one of the preceding aspects, refinements and embodiments, the computer-implemented method may further comprise:
In one aspect of the sixth refinement, generating a set of folding instructions may include applying an instructions generation algorithm configured to:
In a seventh refinement which is combinable with any one of the preceding aspects and refinements of the second embodiment, wherein assessing the adherence of the updating fold list to an existing fold list may include applying a fold monitoring algorithm configured to:
Alternatively or additionally, generating a user output may include applying a fold advice algorithm configured to:
Additionally, the prompt or advice may comprise visual or audio information notifying the user of a fold discrepancy. Alternatively or additionally, the prompt or advice may comprise a notification informing the user of changes the user needs to make in order to adhere to the selected folding instructions.
In another aspect of the seventh refinement which is combinable with any one of the preceding aspects and refinements of the second embodiment, the user-interface may be a smartphone, a display and/or a sound emitting device.
In another aspect of the seventh refinement which is combinable with any one of the preceding aspects and refinements of the second embodiment, wherein the computer-implemented method may be executed during a user is performing papercraft folding.
The present disclosure further relates to a papercraft digitization system. The papercraft digitization system comprises a sheet provided with an array of RFID tags, an RFID reader and a processing module. The RFID reader is configured to monitor the RFID tags. The processing module is configured to determine the occurrence and fold properties of a fold based on RFID reader output provided by the RFID reader. The processing module is further configured to generate a fold list by storing the fold properties of each occurred fold as a fold dataset.
In one aspect, the papercraft digitization system may be configured to perform the computer-implemented method of any one of the preceding aspects.
In another aspect which is combinable with the preceding aspect, each RFID tag may comprises a transponder circuit and an integrated circuit such as a microchip
In another aspect which is combinable with any one of the preceding aspects, each RFID tag may contain an individual tag ID. Alternatively or additionally, each RFID tag may contain an individual resonance frequency. Additionally, the individual tag ID and/or the individual resonance frequency may be stored on a tag database.
In another aspect which is combinable with any one of the preceding aspects, the array of RFID tags may comprise passive RFID tags.
In another aspect which is combinable with any one of the preceding aspects, the RFID tags may be distributed on the sheet at specific individual tag coordinates. The tag coordinates may comprise x-coordinates and y-coordinates. Additionally, the tag coordinates may be stored on a tag database. Alternatively or additionally, the tag coordinates may be linked with a tag ID of the respective RFID tag.
In another aspect which is combinable with any one of the preceding aspects, the RFID tags may be arranged in a predefined pattern on the sheet.
In another aspect which is combinable with any one of the preceding aspects, predefined fold lines may be applied to the sheet according to an existing fold list. In examples, predefined fold lines may be printed onto the sheet according to an existing fold list. Additionally, the RFID tags may be arranged on the sheet in a pattern corresponding to the predefined fold lines. Alternatively or additionally, at least a subset of RFID tags may be arranged laterally on both sides of the respective predefined fold line. Additionally, the RFID rags of a subset which corresponds to a fold line may be arranged laterally from the fold line at similar or substantially the same distances. Alternatively or additionally, the RFID tags of a subset which corresponds to a specific predefined fold line may have the same resonance frequencies. Additionally, the RFID tags of a subset which corresponds to a specific predefined fold line may have resonance frequencies differing from the resonance frequencies of RFID tags of a subset which corresponds to another predefined fold line.
In another aspect which is combinable with any one of the preceding aspects, the array of RFID tags may comprise at least two, more specifically at least 9, most specifically at least 81 RFID tags.
In another aspect which is combinable with any one of the preceding aspects, the RFID tags may be applied on a surface of the sheet. Alternatively or additionally, the RFID tags may be applied into the sheet. Alternatively or additionally, the RFID tags may be printed onto or in the sheet. The RFID tags may be printed by screen printing, by ink jet printing or any other suitable method of application.
In another aspect which is combinable with any one of the preceding aspects, the RFID reader may be configured to send an emitter signal at one or more emission frequencies. The RFID reader may further be configured to receive a return signal at an individual tag resonance frequency from each RFID tag which was stimulated at its resonance frequency. In other words, the RFID may be configured to monitor all or only a subgroup of RFID tags of the array of RFID tags provided on the sheet.
In another aspect which is combinable with any one of the preceding aspects, the RFID reader may be configured to control the emission frequency to preferentially probe the tag resonance frequency of particular RFID tags.
In another aspect which is combinable with any one of the preceding aspects, the RFID reader may be located in a non-portable or portable device, such as a smartphone, internet router.
In another aspect which is combinable with any one of the preceding aspects, the processing module comprises one or more of:
The present disclosure further relates to a fold database containing fold lists which are generated according to the computer-implemented method of any one of the preceding aspects.
The present disclosure further relates to a computer-implemented method for generating a set of folding instructions for creation of a papercraft model comprising:
Additionally, the fold list may be obtained from a fold database according to any one of the preceding aspects. Alternatively or additionally, generating a set of folding instructions may include applying an instructions generation algorithm configured to:
It has been found that papercraft folding can be easily digitized by combining papercraft folding with radio frequency identification (RFID) technology. This is implemented by providing a sheet with an array of RFID tags for papercraft folding and monitoring the sheet via an RFID reader. Based on this combined approach an analogue creation of a papercraft model can be digitized. More specifically, the folds (including fold properties) which need to occur on the sheet to create a desired papercraft model can be determined by analyzing information gathered by the RFID reader, i.e. RFID reader output (e.g. return signals of the tags). Thereby, the present disclosure makes use of two basic principles which may be used separately or in a combined approach:
Inductive effects between two RFID tags may lead to a reduction in return signal strength (RSS). The closer two RFID tags come to each other, the stronger the reduction in RSS will be. Thus, if two RFID tags have a similar decrease in RSS, this may indicate that these two RFID tags are brought in close proximity to each other. There may be used predefined threshold values of decrease in RSS which define how close these two RFID tags must be to trigger a “proximity”. Based on the fractional decrease of RSS a proximity value may be determined which indicates a distance between two RFID tags. Analogously to the RSS approach, two RFID tags are estimated to be at the same point in space (i.e. contacting or almost contacting each other) when their return signals exhibit the same phase shift with respect to the emitter signal.
Thus, when performing papercraft folding, different combinations of RFID tags may be brought into measurable proximity at each folding step. The proximity between two RFID tags may be determined by a similar decrease in RSS and/or a similar phase shift. For each combination the system and method may calculate fold properties by evaluating the coordinates of the RFID tags which are brought in measurable proximity. It is to be understood that the coordinates of each RFID tag are known to the system (and method). In that, an occurred fold and its properties which was performed may on the one hand be captured and digitized to be stored for follow-on applications (e.g., to generate folding instructions or to generate a 3D-visualization) in a fold list. On the other hand, a user can be monitored and supported during performing papercraft folding by determining an occurred fold performed by the user and comparing its properties with predefined fold properties.
Apart from real-time monitoring the occurred folds, the present disclosure also enables to digitize a papercraft model which is already completed. Based on the given RSS pattern and/or phase shift pattern, it is known which RFID tags are in proximity on the completed papercraft model. By applying a specific algorithm those folding steps which need to have occurred to result in the current RSS pattern and/or phase shift pattern are calculated reversely.
Following from the above, a user-friendly method for digitizing papercraft creations, such that they can then benefit from the use of digital (e.g. easy sharing, etc.), while retaining the physical product (e.g. working with hands, creating physical art for placement in the home, etc.) can be provided. In detail, an easy method to digitize an analogue papercraft creation with simple consumer hardware and low user-input can be provided (i.e. user just presses a button on the user interface of whatever device reads the RFID tags rather than having 3D cameras, scanning equipment). Furthermore, the present disclosure enables easy sharing of a digital representation of an analogue papercraft design on digital services such as social media. Based on the fold list, the presently disclosed method may create a visual virtual version of the papercraft (3D-visualization). Based on the fold list, the present disclosure further provides a simple method to generate digital instruction sets for the recreation of the analogue papercraft. This allows, for example, automatic creation of instruction sets, or the re-use of the same papercraft materials without fear of losing the creation (i.e. it can be remade easily as steps were recorded). Additionally, a method of direct and personalized feedback to aid in the creation of papercraft can be provided. Finally methods are disclosed which allow for a standardized format for sharing virtual copies of digital papercraft creations. To share their creations, the user needs only to transmit the fold list, which can then be recreated in a virtual form by software at the side of the recipient. This means the sharing of the model is very low bandwidth and data (compared to sharing a 3D model).
Other characteristics will be apparent from the accompanying drawings, which form a part of this disclosure. The drawings are intended to further explain the present disclosure and to enable a person skilled in the art to practice it. However, the drawings are intended as non-limiting examples. Common reference numerals on different figures indicate like or similar features.
Embodiments of the computer-implemented method and the papercraft digitization system according to the disclosure will be described with reference to the figures as follows.
In the present disclosure, the term “RFID” is an acronym for radio frequency identification which is a known communication technology in the art and functions on the basis of sending a signal from a reader (also referred to as RFID reader) and receiving an answer signal from a transponder (also referred to as RFID transponder or RFID tag).
In the present disclosure, the term “RFID reader” describes a receiver transmitter unit. The RFID reader is capable of sending an emitter signal over various frequencies which may be preselected. The RFID reader may also be capable of receiving return signals over various frequencies.
In the present disclosure, the term “RFID tag” may be used as a synonym for “RFID transponder” which is a device comprising a transponder circuit (e.g., an antenna) and an integrated circuit (e.g., a microchip). When being stimulated by an emitter signal, the RFID tag is configured to send a return signal. The return signal is characterized by the resonance frequency of the RFID tag which again is determined by the design of its transponder circuit. In other words the resonance frequency of one RFID tag can be distinct from the resonance frequency of another RFID tag based on the specifics of the design of the transponder circuit. For instance, each tag may have a resonance frequency distinct from all other resonance frequencies. In some embodiments, one or more groups of two or more RFID tags may exhibit the same resonance frequency. Thus, by adjusting the frequencies of the emitter signal, the RFID reader is capable of receiving one or more return signals from the RFID tags. For instance, when monitoring the sheet, the RFID reader may only emit frequencies which conform to some of the resonance frequencies of the RFID tags. Then, the RFID reader will also only receive return signals from those RFID tags of the array which were stimulated by their respective resonance frequency. RFID tags may be active (i.e. having a proprietary energy supply) or passive (i.e. having no proprietary energy supply).
In the present disclosure, the term “sheet” is to be understood as a general term for the basis material of a papercraft model in different stages of its creation, i.e. it can circumscribe the papercraft model before the folding process, also referred to as two-dimensional sheet, unfolded sheet or flat sheet, or it can circumscribe the papercraft model at any stage during the folding process or upon the folding process is finished (creation of papercraft model is completed), also referred to as three-dimensional sheet or folded sheet.
With regard to
The sheet 10 is made of a foldable material such as paper material. In other configurations, the sheet 10 may be made of any other suitable foldable material such as plastic material. In
In the example of
Each RFID tag 12 comprises a transponder circuit (e.g. antenna) and an integrated circuit such as a microchip. In examples, the array of RFID tags 12 comprises only passive RFID tags. However, in some configurations the array may also comprise one or more active RFID tags.
Each RFID tag 12 contains an individual tag ID, an individual resonance frequency and individual tag coordinates (e.g. x-coordinates and y-coordinates) with respect to the sheet 10. This information may also be referred to as “tag data” and may be stored on a tag database. Thereby, the tag data may be retrieved during various processes of the system and method. The tag data may additionally comprise so-called proximity links which will be explained in more detail further below. Each return signal comprises the individual tag ID which enables to distinguish each return signal from every other return signal. The tag coordinates are linked with the tag ID. The tag resonance frequency is linked with the tag ID.
The array of RFID tags 12 may be arranged in a predefined pattern on the sheet 10. Alternatively, the RFID tags 12 may be arranged randomly (i.e. no regular pattern) on the sheet 10 (e.g. but with known coordinates). In general, any geometric pattern of arrangement is possible. For instance, a matrix pattern, in particular a rectangular matrix pattern, as shown in
In another configuration, the RFID tags 12 may be arranged on the sheet 10 in a pattern which corresponds to predefined fold lines. In this regard,
The RFID tags 12 are distributed on the sheet 10 at specific individual tag coordinates. The tag coordinates comprise x-coordinates and y-coordinates with respect to a datum of the sheet 10 (see, e.g.,
The RFID reader 20 is configured to send an emitter signal at one or more emission frequencies. The RFID reader 20 is further configured to receive a return signal at an individual tag resonance frequency from each RFID tag 12 which was stimulated at its resonance frequency. In other words, the RFID reader 20 may be configured to monitor all or only a subgroup of RFID tags 12 of the array of RFID tags 12 provided on the sheet 10. If different emission frequencies are used, the RFID reader 20 may be configured to control the emission frequencies to preferentially probe the tag resonance frequency of particular RFID tags 12. Thereby, the monitoring field can be restricted to specific task and/or areas which are likely to take place. In some embodiments, the RFID reader 20 may be located in a non-portable or portable device, such as a smartphone, internet router or any other suitable device. In other embodiments, the RFID reader 20 may be a solitary device independent from other devices.
The processing module 30 comprises a tag database, a fold database (not depicted) and one or more processors (not depicted) for performing a tag proximity algorithm and a papercraft digitization algorithm. In other embodiments, the tag database and/or the fold database may be comprised in separate devices or may be provided separately. The tag database is configured for storing tag data including tag IDs, tag coordinates with respect to the sheet, tag resonance frequencies and proximity links (if present). The fold database is configured for storing one or more fold lists and/or one or more folding instructions and/or one or more virtual representations of papercraft models. The one or more processors may be further configured for performing a fold render algorithm, an instruction generation algorithm, a fold monitoring algorithm and/or a fold advice algorithm.
The papercraft digitization system may further comprise a user-interface for displaying a graphical representation of the fold list and/or for providing information and/or notifications to a user. The user-interface may be located in a non-portable or portable device, such as a smartphone, a RFID reader 20 or any other suitable device. In other embodiments, the user-interface may be a solitary device independent from other devices.
The papercraft digitization system 1 is configured to perform the computer-implemented method for digitization of papercraft folding for creation of a papercraft model which will be described in more detail in the following.
As already explained above, the computer-implemented method for digitization of papercraft folding for creation of a papercraft model comprises monitoring the sheet by sending an emitter signal and receiving one or more return signals from the RFID tags. In
In the next step, the RFID reader output is used to determine the occurrence of a fold (i.e. an occurred fold). In other words, the RFID reader output is obtained and analyzed. That means, the return signals are analyzed to determine the presence of an occurred fold (i.e. to determine the occurrence of a fold).
The principle which is applied here, may be called RFID tag mutual identification. Based on this principle a proximity of two or more RFID tags, specifically passive (i.e. unpowered) RFID tags, may be detected at distance by an RFID reader. This principle utilizes the independent recognition of two properties of the signal returned to the RFID reader: return signal strength (RSS) and phase difference. Due to the inductive effects between two proximate RFID tags, when two tags are brought close together (i.e. touching or almost touching), there is a significant and measurable decrease in the RSS from both RFID tags. Therefore, it is possible to identify that any single RFID tag is proximate to another RFID tag. The stronger the decrease in RSS, the closer the RFID tags are. In other words, the closer the RFID tags, the more mutual inductance will occur, so the RSS from both RFID tags will be weaker the closer the tags are. Using phase difference, relies on measurement of the phase shift of the returned signal with respect to the emitter signal. Phase shift increases with distance between RFID tag and RFID reader. If two RFID tags are in the exact same point in space, they should have identical phase shifts in their returned signals when read by the same RFID reader. For any two RFID tags which are at the same point in space (i.e. they are in contact, or almost in contact), the phase shift of their return signals should be equal. Therefore, individual RFID tag pairings may be identified. The closer the phase shifts are (i.e. the smaller the difference in phase shift), the closer the RFID tags are. Both properties may independently or in combination be used to determine a proximity between the RFID tags. The present disclosure makes use of this principle by concluding from a determined proximity between two or more RFID tags the occurrence of a fold which must have taken place to bring these two or more RFID tags in contact or proximity. From the known geometric arrangement of the RFID tags (i.e. tag coordinates) also the fold properties can be concluded.
Therefore, the computer-implemented method applies a tag proximity algorithm to determine the occurrence of a fold. In other words, the tag proximity algorithm analyzes the return signals to evaluate a proximity between two or more RFID tags. If a proximity is determined, the tag proximity algorithm generates a proximity link between the RFID tags proximity is determined for. The proximity link includes tag IDs of the RFID tags proximity was determined for. The proximity link may be binary or may include a proximity value. The proximity value takes into account a magnitude of proximity, i.e. a change of relative distance between the RFID tags proximity was determined for. In examples, the proximity value is calculated from a magnitude of correlating RSS reduction (specifically, for the return signal strength approach). Alternatively, the proximity value is calculated from a size of the differences in phase shift (specifically, for the phase shift method). In some examples, the proximity value is calculated from a combination of both, i.e. magnitude of correlating RSS reduction and a size of the differences in phase shift. Eventually, by outputting one or more proximity links, the occurrence of a fold is determined by the tag proximity algorithm. The one or more proximity links may then be stored on the tag database relating them to the tag IDs of the RFID tags proximity was determined for. In some embodiments, the tag proximity algorithm may be further configured to initiate a papercraft digitization algorithm upon recognition of a new proximity link.
The term “proximity” is to be understood as a relative term which is determined by the tag proximity algorithm if a predefined threshold condition is met. Only if the threshold condition is met the generation of a proximity link is triggered and the proximity link is stored on the tag database. Hence, the tag proximity algorithm determines return signal properties (RSS and/or phase shift) of each received return signal. The tag proximity algorithm then compares the return signal properties (RSS and/or phase shift) of a received return signal of each RFID tag with the return signal properties (RSS and/or phase shift) of a received return signal of every other RFID tag. If the compared return signal properties (RSS and/or phase shift) correlate within the predefined threshold a proximity between the respective RFID tags is determined and a proximity link is generated and stored. In other words, if the compared return signal properties (RSS and/or phase shift) correlate within the predefined threshold the occurrence of a fold is concluded.
As mentioned above, analyzing the return signals comprises analyzing one or more of the return signal properties. In detail analyzing the return signals comprises analyzing RSS and/or phase shift of a received return signal.
Analyzing RSS comprises determining a change, in particular a relative change, of return signal strength of a received return signal with respect to a reference value. The relative change of return signal strength of a received return signal is determined by a comparison with the return signal strength of a previously received return signal of the same RFID tag. Alternatively the change of return signal strength of a received return signal is determined by a comparison with a known standard value of return signal strength of the same RFID tag. This is done for each received return signal (i.e. for the return signal of each RFID tag) such that for each received return signal a relative change of RSS is determined. It is noted that unitary reference values are to be chosen, i.e. either respective standard values or respective previously received values.
Furthermore, it is noted that the relative change of RSS may be expressed as a percentage value (e.g. 10%) or as a decimal value (e.g. 0.1). Then the relative changes of RSS of the different RFID tags are compared with each other. A proximity between two or more RFID tags is determined if two conditions are met:
The correlation-condition is fulfilled if the changes of RSS are the same within a tolerance interval of at most +/−10%, particularly at most +/−5%, and more particularly at most +/−1%. These tolerance intervals may merely represent exemplary values and may be determined (e.g. experimentally) individually for each type of papercraft model. The threshold-condition is fulfilled if the changes of RSS is ≤−15%, particularly ≤−25%, more particularly ≤−50%, and most particularly ≤−80%. In other words, the threshold-condition is fulfilled if a decrease of RSS is at least 15%, particularly at least 25%, more particularly at least 50%, and most particularly at least 80%. If both conditions are met, the generation of a proximity link comprising the respective tag IDs is triggered. The proximity link reflects that proximity between two or more RFID tags is determined within the predefined conditions/thresholds (binary proximity link which assumes value of 1 if conditions are met). In examples, the proximity link further includes a proximity value which reflects the magnitude of proximity. The proximity value may be translated from an averaged change of RSS of the respective RFID tags. For instance, if the return signals of two RFID tags have a decrease of RSS of 84% and 86%, respectively (i.e. a change of RSS of −84% and −86%, respectively), the proximity value may be 0.85. Analogously, if the return signals of two RFID tags both have a decrease of RSS of 95% (i.e. a change of RSS of −95%), the proximity value may be 0.95. In the following step of determining fold properties, the proximity values may, for instance, be used to determine the closing angle of the fold. The decrease of RSS correlates with the distance between the RFID tags. For instance, two RFID tags being 2 mm apart may both see an 80% RSS reduction, and two RFID tags being 5 mm apart may both see a 50% RSS reduction. These values should be understood as merely exemplary values and may depend on the specifics (structure, frequency, standard signal strength, etc.) of the RFID reader and the RFID tags.
Analyzing phase shift comprises calculating a phase shift between a received return signal and the emitter signal. This is done for each received return signal such that for each received return signal a phase shift is determined. Then the phase shifts of the different RFID tags are compared with each other. A proximity between two or more RFID tags is determined if their respective phase shifts are substantially equal within a tolerance interval. A proximity between two RFID tags is determined if their respective phase shifts are substantially equal within a predefined tolerance interval of −15% to +15%, particularly within −10% to +10%, more particularly within −5% to +5% and most particularly within −2.5% to +2.5%. The proximity link includes a proximity value which is calculated from a deviation of phase shifts of the RFID tags proximity was determined for. Alternatively a binary-type proximity link may be used which assumes the value of 1 if the phase shifts correlate within the predefined tolerance interval.
In the next step, after determining the occurrence of a fold by generating one or more proximity links, the one or more proximity links are used to determine the fold properties of an occurred fold. Therefore, the computer-implemented method applies a papercraft digitization algorithm to calculate fold properties of each fold based on tag data of the RFID tags. The tag data includes for each RFID tag a tag ID, predefined tag coordinates with respect to the sheet, a tag resonance frequency, a proximity link, if present. The tag data is stored on a tag database (see, e.g.
The papercraft digitization algorithm retrieves the tag data from the tag database. Then, the papercraft digitization algorithm calculates the fold properties including a mid-point of the of the occurred fold, a folding angle of the occurred fold with respect to a datum of the sheet and, e.g. if proximity values are present, a closing angle of the occurred fold. The calculation of the fold properties of the occurred fold will be described in the following with respect to an exemplary fold line depicted in
When the fold properties are calculated, they are stored as a fold dataset. In other words, the mid-point, the folding angle, in examples the function or vector of the fold line including intersection points, and/or the closing angle are accumulated in a fold dataset. The term “fold dataset” describes a set of fold properties of one occurred fold. The fold dataset may be added to a fold list.
With respect to
In an alternative variation of the first example method, the computer-implemented method is executed in real-time during the creation process of folding. The emitter signal is repeatedly sent at specific time intervals. The time interval between two emitter signals may be selected to secure that a maximum of one fold is performed during the time interval. The time interval may be determined by a sampling rate which may have a frequency of at least 0.1 Hz, particularly at least 1 Hz, specifically at least 5 Hz and more particularly at least 10 Hz. A set of return signals is repeatedly received at each time interval. The set of return signals contains a return signal received from each of the RFID tags. It is noted that the set of return signals only contains a respective return signal from those RFID tags which have been probed with their resonance frequency. The repeatedly received sets of return signals forms a time series of sets of return signals. Each set of return signals of the time series is analyzed by applying the tag proximity algorithm. Each set of return signals of the time series may be analyzed by comparing a newly received set of return signals with a set of return signals received at a previous, specifically immediately previous, time interval. A set of new proximity links is generated at each time interval if proximity is determined. Fold properties are determined for each new set of proximity links. Thereby, fold properties of a fold which must have occurred in the new set of proximity links are calculated. For each set of new proximity links the fold properties are added as a new fold dataset in the fold list. In other words, a sequence of fold datasets is generated which represents the fold list. Thereby an order of folds can be created according to the position of the respective time interval in the time series. When the folding process is finished, i.e. when the papercraft model is complete, the fold list may be used further follow-on applications (e.g. 3D visualization, generation of folding instructions, etc.).
In a further alternative variation of the first example method, the sheet is repeatedly monitored at regular time intervals. A time series of sets of return signals is received from the RFID tags and analyzed. Return signals are compared within the set of return signals received at the same time interval and/or with one or more sets of return signals over previous time intervals. Based on the comparison, fold properties of occurred folds are calculated which must have taken place in order to receive the present set of return signals. The fold properties are stored as fold datasets.
With respect to
In an alternative variation of the second example method, the computer-implemented method is executed after the creation process of folding is completed. The emitter signal is sent at least once to receive at least one set of return signals. Determining the fold properties of an occurred fold comprises applying a papercraft digitization algorithm configured to reverse-generate a fold list including the fold datasets of folds which must have occurred based on the present set of proximity links determined from the at least one set of return signals. The reverse-generating includes virtually unfolding the sheet to reach a state of zero proximity links, generating possible lists of unfolds resulting in a completely unfolded sheet, ranking the generated lists of unfolds, selecting one list of unfolds based on given parameters, such as a number of fewest unfolds, and reversing the selected list of unfolds to obtain a fold list.
The computer-implemented method according to the present disclosure further includes various follow-on application steps which are performed after the fold properties of an occurred fold have been determined and the fold properties have been stored as a fold dataset.
The computer-implemented method further comprises generating a fold list by aggregating the respective fold datasets of occurred folds (see,
In a first application, the computer-implemented method further comprises applying the fold list to a virtual representation of the sheet and displaying the virtual representation via a user-interface. Applying the fold list to a virtual representation of the sheet includes applying a fold render algorithm. The fold render algorithm creates a three-dimensional mesh model of the sheet in an unfolded state. Then the fold render algorithm applies the fold datasets from the fold list, specifically one at a time. And finally, the fold render algorithm recalculates the mesh model with each application of a fold dataset. The fold render algorithm is configured to store the mesh model after the application of all fold datasets as a virtual representation of the sheet representing the sheet in a completely folded state. The fold render algorithm may be further configured to store the mesh model at different stages of the application of fold datasets as a virtual representation of the sheet representing the sheet in a folded state. The user-interface is configured to allow a user to view, move and/or edit the virtual representation. The user-interface may be a smartphone, a display or any other device capable of visualizing and/or manipulating the virtual representation.
In a second application, the computer-implemented method further comprises generating a set of folding instructions in natural language using the fold list. Generating a set of folding instructions includes applying an instructions generation algorithm. The instructions generation algorithm selects and obtains for each fold dataset of the fold list an instruction template from a set of predefined instruction templates based on the fold properties of the fold dataset. Then the instructions generation algorithm populates each obtained instruction template with the fold properties contained in the respective fold dataset and assigns a number to each obtained instruction template based on the position of the respective fold dataset in the fold list. When each instruction template has been populated and numbered, the instructions generation algorithm collates the obtained instruction templates into a single document and outputs the document as folding instructions.
In a third application, the computer-implemented method further comprises generating a fold list by aggregating the respective fold datasets of occurred folds (see,
One or more implementations disclosed herein include and/or may be implemented using a machine learning model. For example, one or more of the tag proximity algorithm, papercraft digitization algorithm, fold render algorithm, instructions generation algorithm, fold monitoring algorithm, and/or fold advice algorithm, may be implemented using a machine learning model and/or may be used to train a machine learning model. A given machine learning model may be trained using the data flow 910 of
The training data 912 and a training algorithm 920 (e.g., tag proximity algorithm, papercraft digitization algorithm, fold render algorithm, instructions generation algorithm, fold monitoring algorithm, and/or fold advice algorithm may be implemented using a machine learning model and/or may be used to train a machine learning model) may be provided to a training component 930 that may apply the training data 912 to the training algorithm 920 to generate a machine learning model. According to an implementation, the training component 930 may be provided comparison results 916 that compare a previous output of the corresponding machine learning model to apply the previous result to re-train the machine learning model. The comparison results 916 may be used by the training component 930 to update the corresponding machine learning model. The training algorithm 920 may utilize machine learning networks and/or models including, but not limited to a deep learning network such as Deep Neural Networks (DNN), Convolutional Neural Networks (CNN), Fully Convolutional Networks (FCN) and Recurrent Neural Networks (RCN), probabilistic models such as Bayesian Networks and Graphical Models, and/or discriminative models such as Decision Forests and maximum margin methods, or the like.
A machine learning model used herein may be trained and/or used by adjusting one or more weights and/or one or more layers of the machine learning model. For example, during training, a given weight may be adjusted (e.g., increased, decreased, removed) based on training data or input data. Similarly, a layer may be updated, added, or removed based on training data/and or input data. The resulting outputs may be adjusted based on the adjusted weights and/or layers.
In general, any process or operation discussed in this disclosure that is understood to be computer-implementable, such as the process illustrated in
A computer system, such as a system or device implementing a process or operation in the examples above, may include one or more computing devices. One or more processors of a computer system may be included in a single computing device or distributed among a plurality of computing devices. One or more processors of a computer system may be connected to a data storage device. A memory of the computer system may include the respective memory of each computing device of the plurality of computing devices.
In various embodiments, one or more portions of methods 600, 700, and 800 may be implemented in, for instance, a chip set including a processor and a memory as shown in
Unless specifically stated otherwise, as apparent from the following discussions, it is appreciated that throughout the specification, discussions utilizing terms such as “processing,” “computing,” “determining”, “analyzing” or the like, refer to the action and/or processes of a computer or computing system, or similar electronic computing device, that manipulate and/or transform data represented as physical, such as electronic, quantities into other data similarly represented as physical quantities.
In a similar manner, the term “processor” may refer to any device or portion of a device that processes electronic data, e.g., from registers and/or memory to transform that electronic data into other electronic data that, e.g., may be stored in registers and/or memory. A “computer,” a “computing machine,” a “computing platform,” a “computing device,” or a “server” may include one or more processors
In a networked deployment, the computer system 1000 may operate in the capacity of a server or as a client user computer in a server-client user network environment, or as a peer computer system in a peer-to-peer (or distributed) network environment. The computer system 1000 can also be implemented as or incorporated into various devices, such as a personal computer (PC), a tablet PC, a personal digital assistant (PDA), a mobile device, a palmtop computer, a laptop computer, a desktop computer, a communications device, a wireless telephone, a land-line telephone, a control system, a camera, a scanner, a facsimile machine, a personal trusted device, a web appliance, a network router, switch or bridge, or any other machine capable of executing a set of instructions (sequential or otherwise) that specify actions to be taken by that machine. In a particular implementation, the computer system 1000 can be implemented using electronic devices that provide voice, video, or data communication. Further, while a computer system 1000 is illustrated as a single system, the term “system” shall also be taken to include any collection of systems or sub-systems that individually or jointly execute a set, or multiple sets, of instructions to perform one or more computer functions.
As illustrated in
The computer system 1000 may include a memory 1004 that can communicate via a bus 1008. The memory 1004 may be a main memory, a static memory, or a dynamic memory. The memory 1004 may include, but is not limited to computer readable storage media such as various types of volatile and non-volatile storage media, including but not limited to random access memory, read-only memory, programmable read-only memory, electrically programmable read-only memory, electrically erasable read-only memory, flash memory, magnetic tape or disk, optical media and the like. In one implementation, the memory 1004 includes a cache or random-access memory for the processor 1002. In alternative implementations, the memory 1004 is separate from the processor 1002, such as a cache memory of a processor, the system memory, or other memory. The memory 1004 may be an external storage device or database for storing data. Examples include a hard drive, compact disc (“CD”), digital video disc (“DVD”), memory card, memory stick, floppy disc, universal serial bus (“USB”) memory device, or any other device operative to store data. The memory 1004 is operable to store instructions executable by the processor 1002. The functions, acts or tasks illustrated in the figures or described herein may be performed by the processor 1002 executing the instructions stored in the memory 1004. The functions, acts or tasks are independent of the particular type of instructions set, storage media, processor or processing strategy and may be performed by software, hardware, integrated circuits, firm-ware, micro-code and the like, operating alone or in combination. Likewise, processing strategies may include multiprocessing, multitasking, parallel processing and the like. As shown, the computer system 1000 may further include a display 1010, such as a liquid crystal display (LCD), an organic light emitting diode (OLED), a flat panel display, a solid-state display, a cathode ray tube (CRT), a projector, a printer or other now known or later developed display device for outputting determined information. The display 1010 may act as an interface for the user to see the functioning of the processor 1002, or specifically as an interface with the software stored in the memory 1004 or in the drive unit 1006.
Additionally or alternatively, the computer system 1000 may include an input/output device 1012 configured to allow a user to interact with any of the components of computer system 1000. The input/output device 1012 may be a number pad, a keyboard, or a cursor control device, such as a mouse, or a joystick, touch screen display, remote control, or any other device operative to interact with the computer system 1000.
The computer system 1000 may also or alternatively include drive unit 1006 implemented as a disk or optical drive. The drive unit 1006 may include a computer-readable medium 1022 in which one or more sets of instructions 1024, e.g. software, can be embedded. Further, instructions 1024 may embody one or more of the methods or logic as described herein. The instructions 1024 may reside completely or partially within the memory 1004 and/or within the processor 1002 during execution by the computer system 1000. The memory 1004 and the processor 1002 also may include computer-readable media as discussed above.
In some systems, a computer-readable medium 1022 includes instructions 1024 or receives and executes instructions 1024 responsive to a propagated signal so that a device connected to a network 1070 can communicate voice, video, audio, images, or any other data over the network 1070. Further, the instructions 1024 may be transmitted or received over the network 1070 via a communication port or interface 1020, and/or using a bus 1008. The communication port or interface 1020 may be a part of the processor 1002 or may be a separate component. The communication port or interface 1020 may be created in software or may be a physical connection in hardware. The communication port or interface 1020 may be configured to connect with a network 1070, external media, the display 1010, or any other components in computer system 1000, or combinations thereof. The connection with the network 1070 may be a physical connection, such as a wired Ethernet connection or may be established wirelessly as discussed below. Likewise, the additional connections with other components of the computer system 1000 may be physical connections or may be established wirelessly. The network 1070 may alternatively be directly connected to a bus 1008.
While the computer-readable medium 1022 is shown to be a single medium, the term “computer-readable medium” may include a single medium or multiple media, such as a centralized or distributed database, and/or associated caches and servers that store one or more sets of instructions. The term “computer-readable medium” may also include any medium that is capable of storing, encoding, or carrying a set of instructions for execution by a processor or that cause a computer system to perform any one or more of the methods or operations disclosed herein. The computer-readable medium 1022 may be non-transitory, and may be tangible.
The computer-readable medium 1022 can include a solid-state memory such as a memory card or other package that houses one or more non-volatile read-only memories. The computer-readable medium 1022 can be a random-access memory or other volatile re-writable memory. Additionally or alternatively, the computer-readable medium 1022 can include a magneto-optical or optical medium, such as a disk or tapes or other storage device to capture carrier wave signals such as a signal communicated over a transmission medium. A digital file attachment to an e-mail or other self-contained information archive or set of archives may be considered a distribution medium that is a tangible storage medium. Accordingly, the disclosure is considered to include any one or more of a computer-readable medium or a distribution medium and other equivalents and successor media, in which data or instructions may be stored.
In an alternative implementation, dedicated hardware implementations, such as application specific integrated circuits, programmable logic arrays and other hardware devices, can be constructed to implement one or more of the methods described herein. Applications that may include the apparatus and systems of various implementations can broadly include a variety of electronic and computer systems. One or more implementations described herein may implement functions using two or more specific interconnected hardware modules or devices with related control and data signals that can be communicated between and through the modules, or as portions of an application-specific integrated circuit. Accordingly, the present system encompasses software, firmware, and hardware implementations.
The computer system 1000 may be connected to a network 1070. The network 1070 may define one or more networks including wired or wireless networks. The wireless network may be a cellular telephone network, an 802.11, 802.16, 802.20, or WiMAX network. Further, such networks may include a public network, such as the Internet, a private network, such as an intranet, or combinations thereof, and may utilize a variety of networking protocols now available or later developed including, but not limited to TCP/IP based networking protocols. The network 1070 may include wide area networks (WAN), such as the Internet, local area networks (LAN), campus area networks, metropolitan area networks, a direct connection such as through a Universal Serial Bus (USB) port, or any other networks that may allow for data communication. The network 1070 may be configured to couple one computing device to another computing device to enable communication of data between the devices. The network 1070 may generally be enabled to employ any form of machine-readable media for communicating information from one device to another. The network 1070 may include communication methods by which information may travel between computing devices. The network 1070 may be divided into sub-networks. The sub-networks may allow access to all of the other components connected thereto or the sub-networks may restrict access between the components. The network 1070 may be regarded as a public or private network connection and may include, for example, a virtual private network or an encryption or other security mechanism employed over the public Internet, or the like.
In accordance with various implementations of the present disclosure, the methods described herein may be implemented by software programs executable by a computer system. Further, in an exemplary, non-limited implementation, implementations can include distributed processing, component/object distributed processing, and parallel processing. Alternatively, virtual computer system processing can be constructed to implement one or more of the methods or functionality as described herein.
It should be understood that the present invention can also (alternatively) be defined in accordance with the following configurations:
| Number | Date | Country | Kind |
|---|---|---|---|
| 21305094.1 | Jan 2021 | EP | regional |
