Method and system for predicting collision between components of a vehicle

Abstract

A system (210, figure 2) and a method 400 is used for predicting a collision between components of a vehicle. The method includes collecting, by a controller (208), data associated with at least two c

Description

[0001] The present disclosure relates to the field of collision management. In particular, the present disclosure provides a method and a system for predicting collision between components of a vehicle using a quantum circuit model. BACKGROUND

[0002] Generally, components of vehicles, or parts of vehicles may undergo multiple design changes in a parts system. During the design changes, a dimension of the parts or the components of the vehicle may also change multiple times. The parts or the components may have a high tendency to collide or intersect with each other, which is called as a collision. A process to identify whether or not there is a valid collision between a part pair or a component pair is called as collision management. In collision management, the collision may refer to an intersection of two or more parts or components. The intersection of two or more parts or components may occur due to non-compliance in alignment of the parts during design or when the parts are received from multiple vendors.

[0003] Conventionally, several collisions have been reported in the vehicle, and classification of collisions may be performed or evaluated by users, as shown in FIG. 1. The users may classify the collisions into relevant collisions and non-relevant collisions based on their experience and historical data. Manual classification may not evaluate or classify the collisions accurately. Every time the user may have to open data or collision three-dimensional (3D) matrix to provide their rating. Therefore, there is a need to recognize the collisions or interruptions between two or more parts or components in an early stage to increase a level of vehicle maturity in an early (digital) development phase and improve a quality of hardware prototypes.

[0004] Many techniques have been evolved to obviate the above-mentioned issues, for instance, Patent document JP2009086864A describes a component interference check device and method capable of performing an interference check of a necessary component without exception. The component interference check device has a database classifying components constituting a vehicle into a plurality of evaluation units, and storing component data related to the respective components. An extraction means extracts the component data related to a first component group and a second component group comprising the same components, and including all the components belonging to the designated evaluation unit from the database. An interference check means compares a shortest distance between the components and a prescribed reference distance aside from a combination between the same components and a combination between each component of the first component group and each component of the second component group to perform the interference check. A display means displays an interference check result by the interference means.

[0005] Patent document US20080065251A1 describes a method and a system for determining an interference between a first physical part and at least a second part in an assembly of manufactured parts. The method includes acquiring three-dimensional digital data representing the first physical part. The method includes forming a virtual representation of the first physical part using digital data. The method includes placing the virtual representation of the first physical part and a virtual representation of the second part in a common reference frame. The second part corresponds to one of a second physical part and a nominal part. The method includes determining the interference between the first physical part and the second part using the virtual representation of the first physical part and the virtual representation of the second part.

[0006] Though the cited documents disclose various techniques for determining interference between two or more parts, they do not focus on collision prediction between the two or more parts or components via a quantum circuit model. There is, therefore, still a scope for a solution that predicts the collision between the two or more pails or components of the vehicle in advance. OBJECTS OF THE PRESENT DISCLOSURE

[0007] A general object of the present disclosure is to provide an efficient and a reliable system and method that obviates the above-mentioned limitations of existing systems and methods and predicts a collision between two or more parts or components of a vehicle in advance.

[0008] An object of the present disclosure is to provide a system and a method for extracting features of two or more parts or components from data collected from a data system.

[0009] Another object of the present disclosure is to provide a system and a method that trains a quantum circuit model based on the features of the two or more parts or components.

[0010] Another object of the present disclosure is to provide a system and a method that predicts a collision between the two or more parts or components via a quantum circuit model.

[0011] Still another object of the present disclosure is to provide a system and a method that classifies a collision between the two or more parts or components into a relevant collision and a non-relevant collision based on historical data and predefined configurations. SUMMARY

[0012] Aspects of the present disclosure relates to the field of collision management. In particular, the present disclosure provides a method and a system for predicting collision between components of a vehicle using a quantum circuit model.

[0013] An aspect of the present disclosure pertains to a method for predicting collision between components of a vehicle. The method includes collecting, by a controller associated with a system, data associated with at least two components of the vehicle from a data system. The method includes extracting, by the controller, one or more features of the at least two components from the collected data. The method includes training, by the controller, a quantum circuit model based on the one or more features of the at least two components. The method includes predicting, by the controller, the collision between the at least two components via the quantum circuit model.

[0014] In an aspect, the one or more features may include at least one of a minimum distance between the at least two components, a Hausdorff distance between the at least two components, a coefficient of the collision between the at least two components, and a material of the at least two components.

[0015] In another aspect, the method may include determining, by the controller, a maximum thickness of the collision between the at least two components based on the Hausdorff distance between the at least two components.

[0016] In another aspect, training, by the controller, the quantum circuit model may include merging, by the controller, the features of the at least two components with a predefined coefficient, identifying, by the controller, one or more outliers based on the merged features of the at least two components, and scaling, by the controller, the collected data based on the one or more outliers.

[0017] In another aspect, the method may include determining, by the controller, quantum bits based on the scaled data. The method may include generating, by the controller, a quantum circuit in a grid lattice based on the quantum bits. The method may include transforming, by the controller, a tensor corresponding to the scaled data to a quantum tensor by passing the tensor corresponding to the scaled data into the quantum circuit. The method may include providing, by the controller, the quantum tensor as an input into a neural network. The method may include training, by the controller, the quantum circuit model based on the input.

[0018] In another aspect, the method may include classifying, by the controller, the collision between the at least two components into a relevant collision and a non-relevant collision based on historical data and predefined configurations.

[0019] Another aspect of the present disclosure pertains to a system for predicting a collision between components of a vehicle. The system includes a controller associated with a processor, and a memory operatively coupled with the processor. The memory includes one or more instructions which, when executed, cause the controller to collect data associated with at least two components of the vehicle from a data system, extract one or more features of the at least two components from the collected data, train a quantum circuit model based on the one or more features of the at least two components, and predict the collision between the at least two components via the quantum circuit model.

[0020] In an aspect, the memory includes one or more instructions which, when executed, may cause the controller to determine a maximum thickness of the collision between the at least two components based on a Hausdorff distance between the at least two components.

[0021] In an aspect, the controller may train the quantum circuit model by being configured to merge the features of the at least two components with a predefined coefficient, identify one or more outliers based on the merged features of the at least two components, and scale the collected data based on the one or more outliers.

[0022] In another aspect, the memory includes one or more instructions which, when executed, may cause the controller to determine quantum bits based on the scaled data, generate a quantum circuit in a grid lattice based on the quantum bits, transform a tensor corresponding to the scaled data to a quantum tensor by passing the tensor corresponding to the scaled data into the quantum circuit, provide the quantum tensor as an input into a neural network, and train the quantum circuit model based on the input.

[0023] Various objects, features, aspects and advantages of the inventive subject matter will become more apparent from the following detailed description of preferred embodiments, along with the accompanying drawing figures in which like numerals represent like components. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The accompanying drawings are included to provide a further understanding of the present disclosure, and are incorporated in and constitute a part of this specification. The drawings illustrate exemplary embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0025] FIG. 1 illustrates an example flow diagram for determining a collision between two or more components of a vehicle, in accordance with the prior arts.

[0026] FIG. 2 illustrates an exemplary block diagram of a system for predicting a collision between components of a vehicle, in accordance with an embodiment of the present disclosure.

[0027] FIG. 3 illustrates an exemplary representation for implementing a method for predicting a collision between components of a vehicle, in accordance with an embodiment of the present disclosure.

[0028] FIG. 4 illustrates a flow chart for implementing an example method for predicting a collision between components of a vehicle, in accordance with an embodiment of the present disclosure.

[0029] FIG. 5 illustrates an exemplary computer system in which or with which embodiments of the present disclosure may be implemented.

[0030] The foregoing shall be more apparent from the following more detailed description of the disclosure. DETAILED DESCRIPTION

[0031] The following is a detailed description of embodiments of the disclosure depicted in the accompanying drawings. The embodiments are in such details as to clearly communicate the disclosure. However, the amount of detail offered is not intended to limit the anticipated variations of embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the present disclosures as defined by the appended claims.

[0032] Embodiments explained herein relate to the field of collision management. In particular, the present disclosure provides a method and a system for predicting a collision between components of a vehicle using a quantum circuit model. Various embodiments of the present disclosure will be explained in detail with reference to FIGs. 2-5.

[0033] Referring to FIG. 2, an exemplary block diagram 200 of a proposed system (interchangeably referred to as a system 210, herein) may be implemented in a vehicle for predicting a collision between two or more components of the vehicle in an efficient manner.

[001] In an embodiment, the system 210 may include one or more processor(s) 202 implemented as one or more microprocessors, microcomputers, microcontrollers, edge or fog microcontrollers, digital signal processors, central processing units, logic circuitries, and / or any devices that process data based on operational instructions. Among other capabilities, the one or more processors) 202 may be configured to fetch and execute computer-readable instructions stored in a memory 204 of the system 210. The memory 204 may be configured to store one or more computer-readable instructions or routines in a non-transitory computer-readable storage medium, which may be fetched and executed to predict the collision between two or more components or parts. The memory 204 may comprise any non-transitory storage device including, for example, volatile memory such as Random-Access Memory (RAM), or non-volatile memory such as Erasable Programmable Read-Only Memory (EPROM), flash memory, and the like.

[0034] In an embodiment, the system 210 may include an interface(s) 206. The interface(s) 206 may include a variety of interfaces, for example, interfaces for data input and output devices, referred to as VO devices, storage devices, and the like. The interface(s) 206 may facilitate communication of the system 210. The interface(s) 206 may also provide a communication pathway for one or more components of the system 210. Examples of such components include, but not limited to, a controller 208 and a database 222. The database 222 may comprise data that may be either stored or generated as a result of functionalities implemented by any of the components of the processor(s) 202 or the controller 208 or the system 210.

[0035] According to an embodiment, the controller 208 may include a data collection engine 212, a feature extraction engine 214, a model training engine 216, a collision prediction engine 218, and other engine(s) 220. The other engine(s) 220 may implement functionalities that supplement applications / functions performed by the controller 208. The other engine(s) 220 may include one or more components selected from a classification engine, a detection engine, a monitoring engine, and the like.

[0036] In an embodiment, the controller 208 may be associated with the one or more processor(s) 202, and a memory 204 operatively coupled with the one or more processor(s) 202. The memory 204 may include one or more instructions which, when executed, cause the controller 208 to collect data associated with at least two components of the vehicle from a data system via the data collection engine 212.

[0037] In an embodiment, the controller 208 may extract, via the feature extraction engine 214, one or more features of the at least two components from the collected data. The one or more features may include, but not limited to, a minimum distance between the at least two components, a Hausdorff distance between the at least two components, a coefficient of collision between the at least two components, and a material of the at least two components.

[0038] In an embodiment, if the minimum distance between the at least two components is positive, the controller 208 may determine that there is no collision and the at least two components are in some distance with each other. In an embodiment, if the minimum distance between the at least two components is negative, the controller 208 may determine that there is a possibility of collision and the at least two components have intersection with each other.

[0039] In an embodiment, the controller 208 may determine the Hausdorff distance between the at least two components to determine a maximum thickness of intersection between the at least two components. The Hausdorff distance between the at least two components may be positive.

[0040] In an embodiment, the controller 208 may train, via the model training engine 216, a quantum circuit model based on the one or more features of the at least two components.

[0041] In another embodiment, the controller 208 may merge, via the model training engine 216, the one or more features of the at least two components with a predefined coefficient, for example., a Trafo coefficient. In another embodiment, the controller 208 may identify one or more outliers based on the one or more merged features of the at least two components. In another embodiment, the controller 208 may scale the collected data based on the one or more outliers.

[0042] In an embodiment, the controller 208 may determine, via the model training engine 216, quantum bits based on the scaled data. In another embodiment, the controller 208 may generate a quantum circuit in a grid lattice based on the quantum bits. In another embodiment, the controller 208 may transform a tensor corresponding to the scaled data to a quantum tensor by passing the tensor corresponding to the scaled data into the quantum circuit. In another embodiment, the controller 208 may provide the quantum tensor as an input into a neural network. In another embodiment, the controller 208 may train, via the model training engine 216, the quantum circuit model based on the input.

[0043] In an embodiment, the controller 208 may, via the collision prediction engine 218, predict the collision between the at least two components using the quantum circuit model. In an embodiment, the controller 208 may, via the classification engine (e.g., 220), classify the collision between the at least two components into a relevant collision and a non-relevant collision based on historical data and predefined configurations.

[0044] In an embodiment, the controller 208 may, determine a maximum thickness of collision between the at least two components based on the Hausdorff distance between the at least two components. The maximum thickness of collision between the at least two components may be determined to predict the collision between the at least two components.

[0045] FIG. 3 illustrates an exemplary representation 300 for implementing a method for predicting collision between components of a vehicle, in accordance with an embodiment of the present disclosure.

[0046] In classical computing, a bit may have a single state:O or 1. In quantum computing, a quantum bit (qubit) which is a fundamental unit of information in a quantum state may exist in a superposition of both states simultaneously. For an N-qubit circuit, there may be 2N possible combinations.

[0047] Computing platforms, for example., quantum computers may be utilized for training neural networks. Variation quantum circuits may be constructed or generated for a quantum deep learning on noisy intermediate scale quantum devices. A hybrid quantum-classical neural network architecture where each neuron is a variation quantum circuit may be utilized for performing collision prediction of at least two components of a vehicle. The performance of the hybrid quantum-classical neural network may be analyzed on a series of binary classification data sets using, for example, a simulated universal quantum computer.

[0048] Referring to FIG. 3, at step 310, one or more features of the at least two components may be extracted from data collected from a data system. The one or more features of the at least two components may be merged with a predefined coefficient, i.e., a Trafo coefficient. Outliers may be identified based on the merged features of the at least two components. The collected data may be scaled or pre-processed based on the one or more outliers.

[0049] At step 320, quantum bits may be determined based on the scaled data. A quantum circuit may be generated in a grid lattice based on the quantum bits. A tensor corresponding to the scaled data may be transformed to a quantum tensor by passing the tensor corresponding to the scaled data into the quantum circuit.

[0050] At step 330, the quantum tensor may be provided as an input into the neural network through classical layers to train the quantum circuit model based on the input. Therefore, the quantum circuit model may be a hybrid classical-quantum model. The hybrid classical-quantum model and the variational quantum circuit may be utilized in an efficient and fast model training. An output model may be then trained with the extracted features, thereby making the output model ready to classify the future collisions without any manual intervention.

[0051] FIG. 4 illustrates a flow chart for implementing an example method 400 for predicting collision between components of a vehicle, in accordance with an embodiment of the present disclosure.

[0052] Referring to FIG. 4, at step 410, the method 400 may include collecting data from a data system. The data collection may be performed by extracting required attributes of the components in a tabular format from a pair table or a look-up table.

[0053] At step 420, the method 400 may include extracting one or more features of the at least two components from the collected data. The one or more features may include, but not limited to, a minimum distance between the at least two components, a Hausdorff distance between the at least two components, a coefficient of collision between the at least two components, and a material of the at least two components.

[0054] At step 430, the method 400 may include preparation of data. The data may be prepared by merging the one or more features of the at least two components with a predefined coefficient, identifying outliers based on the merged features, and scaling and pre-processing the collected data based on the outliers.

[0055] At step 440, the method 400 may include initializing a Quantum Machine Learning (QML) with necessary quantum bits. The QML may be initialized based on a model type, a number of hidden layers, input tensor dimensions, and an optimizer type.

[0056] At step 450, the method 400 may include determining quantum bits based on the scaled data and generating a quantum circuit in a grid lattice based on the quantum bits. The method 400 may include transforming a tensor corresponding to the scaled data to a quantum tensor by passing the tensor corresponding to the scaled data into the quantum circuit. The method 400 may include providing the quantum tensor as an input into a neural network, and training the quantum circuit model based on the input to predict the collision between the at least two components.

[0057] At step 460, the method 400 may include predicting the collision between the at least two components. The method 400 may include classifying the collision between the at least two components into a relevant collision and a non-relev ant collision based on historical data and predefined configurations. In another embodiment, the method 400 may include determining the relevant collision and the non-relevant collision using the quantum circuit model.

[0058] FIG. 5 illustrates an exemplary computer system 500 in which or with which embodiments of the present disclosure may be implemented.

[0059] Referring to FIG. 5, the computer system 500 includes an external storage device 510, a bus 520, a main memory 530, a read only memory 540, a mass storage device 550, a communication port 560, and a processor 570. A person skilled in the art will appreciate that the computer system 500 may include more than one processor 570 and communication ports 560. The processor 570 may include various modules associated with embodiments of the present invention. The communication port 560 can be any of an RS-232 port for use with a modem-based dialup connection, a 10 / 100 Ethernet port, a Gigabit or 10 Gigabit port using copper or fiber, a serial port, a parallel port, or other existing or future ports. The communication port 560 may be chosen depending on a network, such a Local Area Network (LAN), Wide Area Network (WAN), or any network to which the computer system 500 connects.

[0060] In an embodiment, the memory 530 may be a Random Access Memory (RAM), or any other dynamic storage device commonly known in the art. The read only memory 540 may be any static storage device(s) e.g., but not limited to, a Programmable Read Only Memory (PROM) chips for storing static information e.g., start-up or BIOS instructions for processor 570. The mass storage device 560 may be any current or future mass storage solution, which may be used to store information and / or instructions. Exemplary mass storage solutions include, but are not limited to, Parallel Advanced Technology Attachment (PATA) or Serial Advanced Technology Attachment (SATA) hard disk drives or solid-state drives (internal or external, e.g., having Universal Serial Bus (USB) and / or Firewire interfaces), one or more optical discs, Redundant Array of Independent Disks (RAID) storage, e.g., an array of disks (e.g., SATA arrays).

[0061] In an embodiment, the bus 520 may communicatively couple the processor(s) 570 with the other memory, storage, and communication blocks. The bus 520 may be, e.g., a Peripheral Component Interconnect (PCI) / PCI Extended (PCI-X) bus, Small Computer System Interface (SCSI), USB, or the like, for connecting expansion cards, drives, and other subsystems as well as other buses, such a front side bus (FSB), which connects the processor 570 to a software system.

[0062] In another embodiment, operator and administrative interfaces, e.g., a display, keyboard, and a cursor control device, may also be coupled to the bus 520 to support direct operator interaction with the computer system 500. Other operator and administrative interfaces may be provided through network connections connected through the communication port 560. The external storage device 510 may be any kind of external hard-drives, floppy drives, Compact Disc -Read Only Memory (CD-ROM), Compact Disc - Re-Writable (CD-RW), Digital Video Disk - Read Only Memory (DVD-ROM). Components described above are meant only to exemplify various possibilities. In no way should the aforementioned exemplary computer system 500 limit the scope of the present disclosure.

[0063] While the foregoing describes various embodiments of the invention, other and further embodiments of the invention may be devised without departing from the basic scope thereof. The scope of the invention is determined by the claims that follow. The invention is not limited to the described embodiments, versions or examples, which are included to enable a person having ordinary skill in the art to make and use the invention when combined with information and knowledge available to the person having ordinary skill in the art. ADVANTAGES OF THE PRESENT DISCLOSURE

[0064] The present disclosure provides a system and a method for predicting a collision between two or more parts or components of a vehicle in an efficient manner.

[0065] The present disclosure provides a system and a method for extracting features of two or more parts or components from data collected from a data system.

[0066] The present disclosure provides a system and a method that trains a quantum circuit model based on the features of the two or more parts or components.

[0067] The present disclosure provides a system and a method that predicts a collision between the two or more parts or components via a quantum circuit model.

[0068] The present disclosure provides a system and a method that classifies a collision between the two or more parts or components into a relevant collision and a non-relevant collision based on historical data and predefined configurations.

Claims

1. A method (400) for predicting a collision between components of a vehicle, the method (400) comprising:collecting (410), by a controller (208) associated with a system (210), data associated with at least two components of the vehicle from a data system;extracting (420), by the controller (208), one or more features of the at least two components from the collected data;training (450), by the controller (208), a quantum circuit model based on the one or more features of the at least two components; andpredicting (460), by the controller (208), the collision between the at least two components via the quantum circuit model.

2. The method (400) as claimed in claim 1, wherein the one or more features comprise at least one of: a minimum distance between the at least two components, a Hausdorff distance between the at least two components, a coefficient of the collision between the at least two components, and a material of the at least two components.

3. The method (400) as claimed in claim 2, comprising determining, by the controller (208), a maximum thickness of the collision between the at least two components based on the Hausdorff distance between the at least two components.

4. The method as claimed in claim 1, wherein training (450), by the controller (208), the quantum circuit model comprises:merging (430), by the controller (208), the one or more features of the at least two components with a predefined coefficient;identifying, by the controller (208), one or more outliers based on the one or more merged features of the at least two components; andscaling, by the controller (208), the collected data based on the one or more outliers.

5. The method (400) as claimed in claim 4, comprising:determining (440), by the controller (208), quantum bits based on the scaled data;generating, by the controller (208), a quantum circuit in a grid lattice based on the quantum bits;transforming, by the controller (208), a tensor corresponding to the scaled data to a quantum tensor by passing the tensor corresponding to the scaled data into the quantum circuit;providing, by the controller (208), the quantum tensor as an input into a neural network; andtraining (450), by the controller (208), the quantum circuit model based on the input.

6. The method (400) as claimed in claim 1, comprising classifying, by the controller (208), the collision between the at least two components into a relevant collision and a non-relevant collision based on historical data and predefined configurations.

7. A system (210) for predicting a collision between components of a vehicle, the system (210) comprising:a controller (208) associated with a processor (202); anda memory (204) operatively coupled with the processor (202), wherein the memory (204) comprises one or more instructions which, when executed, cause the controller (208) to:collect data associated with at least two components of the vehicle from a data system;extract one or more features of the at least two components from the collected data;train a quantum circuit model based on the one or more features of the at least two components; andpredict the collision between the at least two components via the quantum circuit model.

8. The system (210) as claimed in claim 7, wherein the memory (204) comprises one or more instructions which, when executed, cause thecontroller (208) to determine a maximum thickness of the collision between the at least two components based on a Hausdorff distance between the at least two components.

9. The system (210) as claimed in claim 7, wherein the controller (208) is to train the quantum circuit model by being configured to:merge the one or more features of the at least two components with a predefined coefficient;identify one or more outliers based on the one or more merged features of the at least two components; andscale the collected data based on the one or more outliers.

10. The system (210) as claimed in claim 9, wherein the memory (204) comprises one or more instructions which, when executed, cause the controller (208) to:determine quantum bits based on the scaled data;generate a quantum circuit in a grid lattice based on the quantum bits;transform a tensor corresponding to the scaled data to a quantum tensor by passing the tensor corresponding to the scaled data into the quantum circuit;provide the quantum tensor as an input into a neural network; and train the quantum circuit model based on the input.

Images