Robert Bosch GmbH patent applications on March 27th, 2025
Patent Applications by Robert Bosch GmbH on March 27th, 2025
Robert Bosch GmbH: 50 patent applications
Robert Bosch GmbH has applied for patents in the areas of G06V10/764 (4), G06N3/098 (3), B60W50/00 (3), G06N3/0464 (3), H04L9/40 (3) G06N3/098 (3), G06N3/082 (2), H04L63/1491 (2), G06N5/022 (2), G06N3/08 (2)
With keywords such as: data, device, based, learning, map, software, generating, image, machine, and brake in patent application abstracts.
Patent Applications by Robert Bosch GmbH
Inventor(s): Shabnam GHAFFARZADEGAN of Livermore CA US for robert bosch gmbh, Samarjit DAS of Wexford PA US for robert bosch gmbh, Luca BONDI of Pittsburgh PA US for robert bosch gmbh, Ho-Hsiang WU of Morrisville NC US for robert bosch gmbh, Joseph Aracri of Pittsburgh PA US for robert bosch gmbh, Kelly J. SHIELDS of Pittsburgh PA US for robert bosch gmbh, Sirajum MUNIR of Pittsburgh PA US for robert bosch gmbh
IPC Code(s): A61B7/00, A61B5/08, A61B7/04
CPC Code(s): A61B7/003
Abstract: methods and systems for training an audio-based machine learning model to predict a health condition based on biological sounds emitted by a person. audio data corresponding to biological sounds produced by the person is generated from a microphone. the audio data is segmented into a plurality of segments, each segment associated with a respective sound event. an audio-based machine learning model is executed on the plurality of segments. the audio-based machine learning model is configured to output, for each segment, a label of a medical condition and an associated a confidence score. the model is trained via active learning, in which a subset of the plurality of segments are selected based on their confidence score being below a threshold, and provided to a human for annotation.
20250099979. TIRE PARTICULATE COLLECTION SYSTEM_simplified_abstract_(robert bosch gmbh)
Inventor(s): Nicola MOLINARI of Cambridge MA US for robert bosch gmbh, Mordechai KORNBLUTH of Brighton MA US for robert bosch gmbh, Daniil KITCHAEV of Brookline MA US for robert bosch gmbh, Karim GADELRAB of Boston MA US for robert bosch gmbh, Charles TUFFILE of Swansea MA US for robert bosch gmbh
IPC Code(s): B03C7/02, B07B1/04
CPC Code(s): B03C7/02
Abstract: the present disclosure is directed to a tire particulate collection device for a motor vehicle. a tire particulate collection device is disclosed having at least a first chamber which includes a first grate and, a first collection compartment where tire particulate or other debris are collected. the device also comprises a last chamber having a collection plate. the last chamber also has a last collection compartment that allows entry of tire particulate matter into the last collection compartment. during vehicle operation, the tire particulate matter is accelerated through the device due to an applied electric field induced by providing an electrical charge to at least the first grate and collection plate. the tire particulate is then collected within the device.
Inventor(s): Augustine D. Saravanos of Atlanta GA US for robert bosch gmbh, Filipe J. CABRITA CONDESSA of Pittsburgh PA US for robert bosch gmbh, Wan-Yi LIN of Wexford PA US for robert bosch gmbh, Zhenzhen Li of Gibsonia PA US for robert bosch gmbh, Madan RAVI GANESH of Pittsburgh PA US for robert bosch gmbh
IPC Code(s): B25J9/16
CPC Code(s): B25J9/163
Abstract: methods and systems of training neural networks with federated learning. a portion of a server-maintained machine learning (ml) model is sent from a server to clients, whereupon local ml models are trained with locally-stored data, including determining cross entropy loss for each local ml model. the updated weights are evaluated on a common data set to obtain activation outputs for each layer of the local ml model, which are transferred to the server whereupon they are permuted to match a dimension of the selected client to obtain a matrix, which is sent to the clients. at each client, the local ml model is permuted based on the matrix to obtain permuted weights which are transferred to the server and aggregated. the aggregated permuted weights are transferred to the clients so that the local ml models are updated with the aggregated permuted weights.
Inventor(s): Matthias Greiner of Simmozheim DE for robert bosch gmbh
IPC Code(s): B60T13/68, B60T13/74
CPC Code(s): B60T13/686
Abstract: a wheel-specific brake unit for a vehicle. the wheel-specific brake unit including a single wheel brake cylinder, a motorized piston-cylinder device with an electric motor and at least one piston adjustable by means of an operation of the electric motor, and at least one hydraulic line via which the wheel brake cylinder is hydraulically connected to the motorized piston-cylinder device in such a way that brake fluid is transferable between the motorized piston-cylinder device and the wheel brake cylinder by means of the at least one adjusted piston of the motorized piston-cylinder device. a brake system for a vehicle, and a method for mounting a wheel-specific brake unit are also described.
Inventor(s): Andrej Gardt of Abstatt DE for robert bosch gmbh, Dietmar Kratzer of Tamm DE for robert bosch gmbh, Mark Boehm of Lehrensteinsfeld DE for robert bosch gmbh, Martin Winkler of Sonthofen DE for robert bosch gmbh
IPC Code(s): B60T17/22, B60T13/74, F16D65/18, F16D66/00, F16D66/02, F16D121/24
CPC Code(s): B60T17/22
Abstract: a method for ascertaining a wear value of an electromechanical wheel brake unit for a motor vehicle. the wheel brake unit includes a displaceable actuator element which is movable by a controllable actuator against a brake disk to generate a braking force. the actuator includes an electric motor with a rotor rotatably mounted and operatively connected to the actuator element. in the method, depending on the displacement of the actuator element, the wear value of the wheel brake unit is determined. for ascertaining the wear value, the actuator element is first displaced against an end stop. the actuator element is subsequently moved against the brake disk. when the actuator element is moved from the end stop against the brake disk, the number of revolutions of the rotor is monitored. depending on the sensed number of revolutions, the wear value of the wheel brake unit is ascertained.
20250100560. Unknown_simplified_abstract_(robert bosch gmbh)
Inventor(s): Daniel Groezinger of Stuttgart DE for robert bosch gmbh, Joerg Gebers of Hemmingen DE for robert bosch gmbh, Norbert Mueller of Tel Aviv IL for robert bosch gmbh, Peter Feuerstack of Ludwigsburg DE for robert bosch gmbh
IPC Code(s): B60W50/00
CPC Code(s): B60W50/0098
Abstract: the present invention creates a method for controlling a control unit network of a plurality of electronic control units of an electric vehicle and a corresponding control unit network. the method comprises the steps of identifying (s s) a current parking condition of a motor vehicle, in which an active motor vehicle operating function is in place comprising at least one control unit that can be deactivated, identifying (s s) one or more operating parameters of the parking condition, identifying (s s) a geographic location of the parking condition, evaluating (s s) the identified geographic location of the parking condition and the identified operating parameters of the parking condition, creating (s s) an operating plan of the unit network with respect to deactivation of one or more deactivatable control units of the unit network, based on the identified geographic location of the parking condition and the identified operating parameters of the parking condition and corresponding saved criteria for the geographic location and the operating parameters of the parking condition, and executing (s s) the created operating plan by automatically deactivating the deactivatable control units of the unit network, based on the created operating plan.
Inventor(s): Johannes Christian Mueller of Stuttgart DE for robert bosch gmbh, Martin Stoll of Renningen DE for robert bosch gmbh, Maxim Dolgov of Renningen DE for robert bosch gmbh, Ralf Kohlhaas of Calw DE for robert bosch gmbh, Stefan Ruppin of Grafenau DE for robert bosch gmbh
IPC Code(s): B60W60/00, B60W50/00
CPC Code(s): B60W60/001
Abstract: a hierarchical system for controlling an automated vehicle. the system includes: a first hardware-based layer designed to receive a first control signal and to carry out a conversion in terms of control technology of the first received control signal, or another base layer, and: a second reflex-based layer, hierarchically superordinate to the first hardware layer; and/or a third motion-based layer hierarchically superordinate to the second reflex-based layer; and/or a fourth intent-based layer; and/or a fifth context-based layer.
Inventor(s): Daniel Grimm of Karlsruhe DE for robert bosch gmbh, Alexander Naumann of Karlsruhe DE for robert bosch gmbh, Felix Hertlein of Karlsruhe DE for robert bosch gmbh, Juergen Luettin of Renningen DE for robert bosch gmbh, Maximilian Zipfl of Karlsruhe DE for robert bosch gmbh, Achim Rettinger of Trier DE for robert bosch gmbh, Lavdim Halilaj of Leonberg DE for robert bosch gmbh, Marius Zoellner of Karlsruhe DE for robert bosch gmbh, Stefan Schmid of Waiblingen DE for robert bosch gmbh, Steffen Thoma of Karlsruhe DE for robert bosch gmbh
IPC Code(s): B60W60/00, B60W50/00, G06N3/02
CPC Code(s): B60W60/00274
Abstract: a computer-implemented method for trajectory prediction. the method includes: receiving trajectory data of motion trajectories of road users arranged in a surrounding area of the ego vehicle by a prediction module, wherein the trajectory data are arranged in a graph representation; receiving map data of a map representation mapping the surrounding area of the ego vehicle by the prediction module; generating an interaction graph representation for the plurality of road users based on the trajectory data of the road users and roadway location information of the map representation by the prediction module; and predicting a future motion trajectory to be executed for at least one other road user based on the trajectory data, the map data, and the interaction graph representation of the road users by the prediction module.
Inventor(s): Kazuki Chiba of Kanagawa JP for robert bosch gmbh
IPC Code(s): B62J45/00, B60T13/66, B62L3/02
CPC Code(s): B62J45/00
Abstract: the present invention obtains a brake hydraulic pressure control apparatus that is mounted to a straddle-type vehicle and can improve an anti-vibration property when compared to the related art.
Inventor(s): Kazuki Chiba of Kanagawa JP for robert bosch gmbh
IPC Code(s): B62J45/00, B60T13/66, B62L3/02
CPC Code(s): B62J45/00
Abstract: the brake hydraulic pressure control apparatus according to the present invention includes: a base body formed with a channel for a brake fluid; a control board of a hydraulic pressure control mechanism for the brake fluid provided to the channel; a housing accommodating the control board and connected to the base body; and a connector provided to the housing and electrically connected to the control board, and is mounted to the straddle-type vehicle. the brake hydraulic pressure control apparatus includes a holding section that holds a cable connected to the connector.
20250101966. INTEGRATED ELECTRO-HYDRAULIC UNIT_simplified_abstract_(robert bosch gmbh)
Inventor(s): Enrique Busquets of Greer SC US for robert bosch gmbh, Andreas Guender of Lohr Am Main DE for robert bosch gmbh
IPC Code(s): F04B1/20, F04B1/128, F04B17/03
CPC Code(s): F04B1/20
Abstract: an integrated electro-hydraulic unit including an electric machine having a stator and a rotor. the integrated electro-hydraulic unit includes a hydraulic machine having a shaft configured to rotate around a central axis and a cylinder block coupled to the shaft. the cylinder block includes a plurality of bores receiving a plurality of pistons. the cylinder block is configured to rotate about the central axis to generate reciprocating movement of the plurality of pistons within the plurality of bores. the cylinder block and the shaft are coupled for rotation via a joint that accommodates bending of the shaft while maintaining a parallel orientation of the cylinder block with respect to the central axis. the joint is defined by a barrel-shaped portion of the shaft and a corresponding interior receiving portion of the cylinder block.
20250102031. Radial Piston Machine with Multi-Disc Brake_simplified_abstract_(robert bosch gmbh)
Inventor(s): Evangelos Rompogiannakis of Glasgow GB for robert bosch gmbh
IPC Code(s): F16D65/18, F16D55/00, F16D121/06, F16D125/06
CPC Code(s): F16D65/183
Abstract: a radial piston machine includes a multi-disc brake, a brake disc assembly of which interacts with a first annular section on a drive shaft and a second annular section on a housing. the brake disc assembly is disposed within a brake chamber. the first annular section and the second annular section each delimit the brake chamber in sections. a disc section, a spring, a brake piston, and the brake disc assembly are disposed next to one another in a specified sequence along an axis of rotation in such a way that a force of the spring is transmitted to the brake disc assembly.
Inventor(s): Andre Wagner of Hannover DE for robert bosch gmbh, Hans-Georg Raumer of Hildesheim DE for robert bosch gmbh, Max Kirstein of Hohenhameln - Ot Bruendeln, DE for robert bosch gmbh, Thomas Wenzel of Hamburg DE for robert bosch gmbh, Thorben Funke of Sarstedt DE for robert bosch gmbh
IPC Code(s): G01C21/00
CPC Code(s): G01C21/387
Abstract: a method for aligning a first map section of a digital road map with a second map section of the digital road map that at least partially overlaps the first map section. the method includes: determining that a first relative rotation between the two map sections cannot be unambiguously ascertained; ascertaining a second relative rotation between a third map section of the digital road map and a fourth map section of the digital road map that at least partially overlaps the third map section, wherein the third map section and the fourth map section are adjacent to the first map section and to the second map section; aligning the first map section with the second map section; wherein the alignment includes ascertaining a relative rotation between the first map section and the second map section based on the ascertained second relative rotation.
Inventor(s): Ferenc Lukacs of Budapest HU for robert bosch gmbh, Volkmar Senz of Metzingen DE for robert bosch gmbh
IPC Code(s): G01L9/00
CPC Code(s): G01L9/0072
Abstract: a pressure sensor. the pressure sensor has a diaphragm that stretches over a cavity. a first electrode is provided in or on the diaphragm in a central region. a second electrode is provided on the cavity base so as to lie opposite the central region of the diaphragm or the first electrode. the second electrode is arranged in a fixed and rigid manner. the first electrode in or on the diaphragm is designed so as to be able to be flexibly deflected together with the diaphragm and move toward the second electrode when a pressure is applied to the diaphragm. together, the first and second diaphragm form a first measuring capacitor, using which a pressure can be detected up to a pressure threshold. a second measuring capacitor is provided in the lateral region of the diaphragm.
Inventor(s): Michael Sturm of Milford MI US for robert bosch gmbh, Kevin Wienen of Farmington Hills MI US for robert bosch gmbh, Michael Yankonis of Whitmore Lake MI US for robert bosch gmbh
IPC Code(s): G01M7/02, G01M7/06, G01M17/06
CPC Code(s): G01M7/027
Abstract: system and methods for characterizing a response of a structure-under-test to applied excitation forces using a test fixture. the fixture is selectively coupleable to the structure-under-test and is configured to hold the structure-under-test at a known position and in a known orientation relative to the fixture. a plurality of excitation devices and response sensors are coupled to the fixture. excitation forces applied to the fixture by the excitation devices are conveyed by the fixture to the structure-under-test and each response sensor measures a dynamic response indicative of a response of the structure-under-test and the fixture to the applied excitation force. a controller receives response sensor data and applies a mathematical coordinate transformation to project the forces and moments corresponding to the applied excitation and the measured dynamic responses to a target point of the structure-under-test and to calculate a system response function based at least in part on the projection.
Inventor(s): Moritz Michael Knorr of Hildesheim DE for robert bosch gmbh
IPC Code(s): G01S5/16, G01S3/782, G06V10/24
CPC Code(s): G01S5/163
Abstract: a marking for position determination. the marking includes an indicator surface which is arranged at least partially in a first plane and on which a large number of different indicators is arranged, and a viewing area which is arranged in a second plane located in front of the first plane in an intended viewing direction and which is configured in such a way that it defines a viewing point through which the indicator surface in the first plane is to be viewed in order to read an indicator from the large number of different indicators. an associated camera system and an associated positioning system are also described.
[[20250102625. DEVICE AND COMPUTER-IMPLEMENTED METHOD FOR TRAINING A FIRST ENCODER FOR MAPPING RADAR SPECTRA TO ENCODINGS, IN PARTICULAR ENCODINGS FOR TRAINING, TESTING, VALIDATING, OR VERIFYING A FIRST MODEL THAT IS CONFIGURED FOR OBJECT DETECTION, FOR EVENT RECOGNITION, OR FOR SEGMENTATION_simplified_abstract_(robert bosch gmbh)]]
Inventor(s): Csaba Domokos of Simmozheim DE for robert bosch gmbh, Kilian Rambach of Stuttgart DE for robert bosch gmbh, Mariia Pushkareva of Haifa IL for robert bosch gmbh, Yuri Feldman of Haifa IL for robert bosch gmbh, Asaf Gendler of Haifa IL for robert bosch gmbh
IPC Code(s): G01S7/41, G01S13/89
CPC Code(s): G01S7/411
Abstract: a device and a computer-implemented method for training a first encoder for mapping radar spectra to encodings. the method includes providing the first encoder which is configured to map a radar spectrum to an encoding of the radar spectrum in a first feature space; providing a second encoder which is configured to map a digital image to an encoding of the digital image in the first features space; providing a first radar spectrum, and a first digital image, wherein the first radar spectrum and the first digital image represent the same or essentially the same real world scene; mapping the first radar spectrum with the first encoder to a first encoding; mapping the first digital image with the second encoder to a second encoding; and training the first encoder and/or the second encoder depending on a distance between the first encoding and the second encoding.
Inventor(s): Juergen Schmidt of Sindelfingen DE for robert bosch gmbh, Lena Bendfeld of Stuttgart DE for robert bosch gmbh, Michael Tchorzewski of Boeblingen DE for robert bosch gmbh, Tobias Wingert of Leonberg DE for robert bosch gmbh, Tom Reimann of Bissingen An Der Teck DE for robert bosch gmbh
IPC Code(s): G01S7/539, G01S15/66, G01S15/87, G01S15/931
CPC Code(s): G01S7/539
Abstract: a method for fusion of classification results of a plurality of classification models to classify environment objects using ultrasonic sensor devices in a mobile device. the method includes: detecting sensor signals of ultrasonic transducers of the ultrasonic sensor devices; tracking a position of detected environment objects by the ultrasonic sensor devices and classifying an object type of the detected environment objects by one of classification models associated with each of the ultrasonic sensor devices to obtain a classification result; in the event that it is determined that a specific environment object has entered a detection region of one of the ultrasonic sensor devices and was previously located in a detection region of a further of the ultrasonic sensor devices, selecting one of the classification results for the specific environment object depending on a classification quality based on the classification model and depending on the newness of the classification result.
Inventor(s): Daniel Schindler of Korntal-MĂźnchingen DE for robert bosch gmbh, Tobias Schmid of Fluorn-Winzeln DE for robert bosch gmbh, Benedikt Loesch of Stuttgart DE for robert bosch gmbh, Johannes Fink of Karlsruhe DE for robert bosch gmbh, Werner Soergel of Pforzheim DE for robert bosch gmbh
IPC Code(s): G01S13/87, G01S7/40
CPC Code(s): G01S13/878
Abstract: a computer device and a method for examining a radar system equipped with at least two transmitting and receiving units which each include at least one respective antenna element. the method includes: defining at least one probability distribution for at least one object with respect to a probable position of the respective object in an angular spectrum based on radar signals transmitted by the at least two transmitting and receiving units, reflected on the at least one object and received by the transmitting and receiving units, determining an average width of the probability distributions in the angular spectrum defined within a given time interval and within a given angular range of the angular spectrum, and defining position information relating to a displacement of at least one of the transmitting and receiving units out of its respective target position taking into account the determined average width.
Inventor(s): Simon Schrade of Baindt DE for robert bosch gmbh, Volker Mehl of Bruchsal-Untergrombach DE for robert bosch gmbh
IPC Code(s): G05B9/03, B60W50/02, B60W50/04
CPC Code(s): G05B9/03
Abstract: a method for operating an actuator arrangement for a motor vehicle. the actuator arrangement includes at least two controllable actuators and a control system with at least two control devices, which are each assigned to one of the actuators and a central control device, in each case connected to the control devices by means of communication technology by communication links. the control devices are controlled in a fault-free normal operating mode of the actuator arrangement by the central control device for controlling the relevant actuators. the control system is monitored for the occurrence of a malfunction in that an operating state of the relevant actuator is monitored. if a malfunction of the control system affecting one of the actuators is recognized, the affected actuator is controlled directly by the control device assigned to it depending on the operating state of the other actuator detected by the monitoring.
Inventor(s): Christoph Gladisch of Renningen DE for robert bosch gmbh, Falko Matern of Erlangen DE for robert bosch gmbh
IPC Code(s): G06F16/215
CPC Code(s): G06F16/215
Abstract: a method for ensuring a quality of synthetic data for at least one perception function using a distributed system includes (i) providing at least one interface of the distributed system in order as to provide access from at least two instances of the distributed system to an evaluation component of the distributed system by the at least one interface, (ii) determining an application for the synthetic data by one of the at least two instances of the distributed system, wherein the application includes at least the at least one perception function, a description of the synthetic data, and at least one metric for evaluating the quality of the synthetic data, (iii) generating the synthetic data based on the described application by the one or another of the at least two instances of the distributed system, and (iv) evaluating the synthetic data with respect to reference data using the at least one metric by the evaluation component of the distributed system to ensure the quality of the synthetic data. also disclosed is a computer program, a device and a storage medium for this purpose.
20250103712. SOFTWARE SECURITY CHECKING DEVICE_simplified_abstract_(robert bosch gmbh)
Inventor(s): Dominik Germek of Berlin DE for robert bosch gmbh, Maria Irina Nicolae of Stuttgart DE for robert bosch gmbh
IPC Code(s): G06F21/56
CPC Code(s): G06F21/56
Abstract: a software security checking device. the device includes: a rule database with rules, each associated with at least one of a plurality of software types and contains a criterion in terms of software feature(s), the rule stating that a piece of software that fulfills the criterion is malicious; an input interface configured to receive a specification of a piece of software; processor(s) configured to ascertain one or more software types of the plurality of software types that the software possesses, to ascertain which of the software features the software possesses, ascertain, for each of the rules associated with at least one of the one or more ascertained software types, whether the criterion that the rule contains is fulfilled, and determine that the software is malicious in response to it being ascertained, for at least one rule, that the criterion it contains is fulfilled.
20250103717. SOFTWARE VERIFICATION DEVICE_simplified_abstract_(robert bosch gmbh)
Inventor(s): Dominik Germek of Berlin DE for robert bosch gmbh, Maria Irina Nicolae of Stuttgart DE for robert bosch gmbh
IPC Code(s): G06F21/56
CPC Code(s): G06F21/566
Abstract: a software verification device. the device includes: a rule database having a plurality of rules, each rule containing a criterion regarding one or more software features and a software property, the rule stating that software that satisfies the criterion has the software property, an input interface configured to receive a specification (e.g., source code) of a software, and one or more processors configured to ascertain which of the software features the software has, and to ascertain, on the basis of which software features the software has been ascertained to have, which of the rules contain criteria that are satisfied, and to ascertain, according to the rules that contain criteria that are satisfied, which of the software properties the software has, and to ascertain whether the software properties that the software has been ascertained to have satisfy one or more predetermined requirements.
Inventor(s): MOHAMMAD SADEGH NOROUZZADEH of PITTSBURGH PA US for robert bosch gmbh, SHAHBAZ REZAEI of DAVIS CA US for robert bosch gmbh
IPC Code(s): G06N3/0464
CPC Code(s): G06N3/0464
Abstract: a method for neural network computations. the method includes receiving a codebook having a plurality of entries, multiplying a respective input of a layer of a neural network by each entry of the plurality of entries of the codebook, and determining, for the respective input of the layer of the neural network, an intermediate value based on a sum of each result of multiplying the respective layer of the neural network by each entry of the plurality of entries of the codebook. the method also includes storing the intermediate value associated with the respective input of the layer of the neural network in a lookup table, the lookup table including a plurality of intermediate values corresponding to other inputs of the layer of the neural network. the method also includes determining each output of the layer of the neural network using the lookup table.
Inventor(s): Xi Wang of Amherst MA US for robert bosch gmbh, Maja Rudolph of Madison WI US for robert bosch gmbh
IPC Code(s): G06N3/08, G06N3/0455
CPC Code(s): G06N3/08
Abstract: fine-tuning a base large language model (llm) is provided. a fine tuning of a base llm having pre-trained model weights is performed using a plurality of lora components each defining a trainable low-rank matrix, such that the low-rank matrices are trained to perform the fine tuning while the pre-trained model weights remain fixed. an ensemble is constructed using the plurality of lora components. one or more regularization techniques are performed to the lora components to counter overconfidence in the ensemble of lora components. the ensemble of lora components, as regularized, are utilized as a fine-tuned model of the base llm.
Inventor(s): Gonca Guersun of Stuttgart DE for robert bosch gmbh, Barbara Rakitsch of Stuttgart DE for robert bosch gmbh, Eitan Kosman of Haifa IL for robert bosch gmbh, Joerg Wagner of Renningen DE for robert bosch gmbh, Michael Herman of Sindelfingen DE for robert bosch gmbh, Yu Yao of Herzogenrath DE for robert bosch gmbh
IPC Code(s): G06N3/08
CPC Code(s): G06N3/08
Abstract: a computer-implemented method of predicting dynamics of objects in a surrounding of a vehicle is disclosed. the method starts with a step of receiving a first data sets characterizing dynamics of the objects respectively. then, each of the first data sets is propagated through an encoder outputting a latent representation for each of the first data sets. then, a graph based on the latent representations is generated. then, the graph is propagated through a graph neural network outputting an updated graph. based on the updated graph a decoder outputs a predicted dynamic for selected object for a subsequent time step.
Inventor(s): Mohammad Sadegh NOROUZZADEH of Pittsburgh PA US for robert bosch gmbh, Shahbaz REZAEI of Davis CA US for robert bosch gmbh
IPC Code(s): G06N3/082, G06N3/0464, G06N3/10
CPC Code(s): G06N3/082
Abstract: in some implementations, the device may include receiving a training dataset. in addition, the device may include training a neural model with the training dataset to generate a first layer having weighted parameters. the device may include dividing the first layer into a first predetermined number of segments based on the first layer being a first type of layer. moreover, the device may include generating a codebook by replacing the weighted parameters in each segment of the first layer with a codeword based on finding a representative vector which most closely relates to the weighted parameters of each segment in a vectorization dictionary, where the codebook includes a number of codewords equal to the first predetermined number of segments and each codeword includes the representative vector. also, the device may include in response to updating the neural model with the codebook, outputting a trained neural model that includes the codebook which replaces the first layer.
Inventor(s): Lukas Meiner of Weissach DE for robert bosch gmbh, Alexandru Paul Condurache of Renningen DE for robert bosch gmbh, Jens Eric Markus Mehnert of Malmsheim DE for robert bosch gmbh
IPC Code(s): G06N3/082, G06N3/0464
CPC Code(s): G06N3/082
Abstract: a computer-implemented method for a computer-implemented method of efficiently calculating convolution operations. the method includes receiving a tensor of input data to be proceeded and at least one filter and initializing a locality-sensitive hashing function. then, repeating the following steps for each patch in the tensor: slicing the current receptive field into a series of matrices. applying the locality-sensitive hashing to each of said matrices to determine a hash representation for each matrix. merging the matrixes with essentially the same hash representation to a new matrix. creating a reduced tensor by arrange the merged matrices in a series. merging the filter coefficients in the same order as the matrices have been merged and convolving the merged on the reduced sub-tensor with the merged filter.
Inventor(s): XIN LI of Sunnyvale CA US for robert bosch gmbh, SIMA BEHPOUR of Sunnyvale CA US for robert bosch gmbh, THANG DOAN of San Francisco CA US for robert bosch gmbh, WENBIN HE of Sunnyvale CA US for robert bosch gmbh, LIANG GOU of San Jose CA US for robert bosch gmbh, LIU REN of Saratoga CA US for robert bosch gmbh
IPC Code(s): G06N3/088, G06F40/40, G06V10/44, G06V10/762, G06V10/774, G06V10/776, G06V20/70
CPC Code(s): G06N3/088
Abstract: a method of performing data pre-selection for an object detection system includes receiving a first dataset that includes unlabeled data corresponding to one or more images, providing the first dataset and a plurality of learnable prompt vectors to a pre-training model. the learnable prompt vectors include text inputs. the method further includes generating, using the pre-training model, an unsupervised learning prompt based on the first dataset and the plurality of learnable prompt vectors. the unsupervised learning prompt corresponds to a multi-modal feature of the one or more images of the first dataset. the method further includes extracting features from either of the first dataset and a second dataset based on the unsupervised learning prompt, selecting and labeling a subset of instances of the extracted features, and generating and outputting a labeled dataset based on the labeled subset of instances.
Inventor(s): Orly Avner of Haifa IL for robert bosch gmbh, Dotan Di Castro of Haifa IL for robert bosch gmbh, Ori Linial of Haifa IL for robert bosch gmbh
IPC Code(s): G06N3/092, G06N3/0455
CPC Code(s): G06N3/092
Abstract: a computer-implemented method of training an agent for generating a diverse dataset of ordinary differential equations. the agent includes a neural network. the agent selects actions from an action space based on outputs of the neural network to sequentially generate a set of ordinary differential equations, wherein the agent performs the selected actions, thereby consecutively building up the ordinary differential equations by concatenating mathematical operators and/or variables to form equations and wherein the agent receives a reward based on the selected actions after a complete set of ordinary differential equations is generated.
Inventor(s): Xidong WU of Pittsburgh PA US for robert bosch gmbh, Filipe J. CABRITA CONDESSA of Pittsburgh PA US for robert bosch gmbh, Wan-Yi LIN of Wexford PA US for robert bosch gmbh, Devin T. WILLMOTT of Pittsburgh PA US for robert bosch gmbh, Zhenzhen LI of Gibsonia PA US for robert bosch gmbh, Madan Ravi GANESH of Pittsburgh PA US for robert bosch gmbh
IPC Code(s): G06N3/098, G06N3/045
CPC Code(s): G06N3/098
Abstract: methods and systems of training neural networks with federated learning. server-maintained machine learning models are sent from a server to clients, yielding local machine learning models. at each client, the models are trained with local data to determine a respective cross entropy loss and a distillation loss based on foundation models. respective weights are updated at each client for each of the local machine learning model based on the losses. the updated weights are transferred to the server without transferring the locally-stored data, whereupon they are aggregated and transferred back to the clients. at each client, the local machine learning model is updated with the aggregated updated weights.
Inventor(s): Xidong WU of Pittsburgh PA US for robert bosch gmbh, Filipe J. CABRITA CONDESSA of Pittsburgh PA US for robert bosch gmbh, Wan-Yi LIN of Wexford PA US for robert bosch gmbh, Devin T. WILLMOTT of Pittsburgh PA US for robert bosch gmbh, Zhenzhen LI of Gibsonia PA US for robert bosch gmbh, Madan Ravi GANESH of Pittsburgh PA US for robert bosch gmbh
IPC Code(s): G06N3/098, G06N3/045
CPC Code(s): G06N3/098
Abstract: methods and systems of training neural networks with federated learning. machine learning models are sent from a server to clients, yielding local machine learning models. at each client, the models are trained with locally-stored data, including determining a respective cross entropy loss for each of the plurality of local machine learning models. weights for each local model are updated, and transferred to the server without transferring locally-stored data. the transferred weights are aggregated at the server to obtain an aggregated server-maintained machine learning model. at the server, a distillation loss based on a foundation model is generated. the aggregated server-maintained machine learning is updated to obtain aggregated respective weights, which are transferred to the clients for updating in the local models.
Inventor(s): Augustine D. Saravanos of Atlanta GA US for robert bosch gmbh, Filipe J. CABRITA CONDESSA of Pittsburgh PA US for robert bosch gmbh, Wan-Yi LIN of Wexford PA US for robert bosch gmbh, Zhenzhen Li of Gibsonia PA US for robert bosch gmbh, Madan RAVI GANESH of Pittsburgh PA US for robert bosch gmbh
IPC Code(s): G06N3/098
CPC Code(s): G06N3/098
Abstract: methods and systems for training neural networks with federated learning. respective weights are transferred from each client to a respective neighboring client without transferring the locally-stored data of the clients. all models are permuted according to the respective weights to match the respectively updated weights to obtain permuted weights. the permuted weights are aggregated at the clients. at each client, local machine learning models are trained with locally-stored data, wherein the training includes determining a respective cross entropy loss for each of the plurality of local machine learning models and a loss computed based on a distance of the local mlm to the aggregated permuted weights. respective weights of each local machine learning models are updated based on the determined cross entropy loss and the loss.
Inventor(s): Mona Schirmer of Amsterdam NL for robert bosch gmbh, Dan Zhang of Leonberg DE for robert bosch gmbh, Eric Nalisnick of Ellicott City MD US for robert bosch gmbh
IPC Code(s): G06N5/022
CPC Code(s): G06N5/022
Abstract: a method for predicting the performance of a given classifier with respect to one or more given samples of input data. the method includes: providing further classifiers that, together with the given classifier f*, form a set f of classifiers f; computing, for the x, using each classifier f from the set f, classification scores f(x) with respect to all available classes k=1, . . . , k covered by the classifiers; determining, for pairs (f,fâ˛) of classifiers f and fⲠfrom the set f, divergences of the classification scores f(x) and fâ˛(x) for all k=1, . . . , k as pairwise divergences dis(f,fâ˛,x) of the classifiers f and fⲠwith respect to the one or more samples x; and determining the performance p(f*,x) of the classifier f* with respect to the one or more samples x based at least in part on pairwise divergences dis(f*,fâ˛,x) between the classifier f* and other classifiers fâ˛.
Inventor(s): Alexander Timans of Amsterdam NL for robert bosch gmbh, Christoph-Nikolas Straehle of Weil Der Stadt DE for robert bosch gmbh, Kaspar Sakmann of Stuttgart DE for robert bosch gmbh, Eric Nalisnick of Amsterdam NL for robert bosch gmbh
IPC Code(s): G06N5/022
CPC Code(s): G06N5/022
Abstract: device and computer-implemented methods for determining a multi-dimensional quantity that characterizes an object in an environment of a technical system, or a technical system, for operating a technical system, and for providing a quantity prediction system. the method includes providing at least one quantity that characterizes the technical system, or an environment of the technical system, predicting, depending on the at least one quantity, a first prediction of the multi-dimensional quantity, providing a multi-dimensional parameter that defines a prediction interval, determining a second prediction of the multi-dimensional quantity depending on the first prediction of the multi-dimensional quantity and the multi-dimensional parameter, wherein the second multi-dimensional prediction determines the multi-dimensional quantity.
Inventor(s): Kushagra Pandey of Irvine CA US for robert bosch gmbh, Maja Rudolph of Madison WI US for robert bosch gmbh
IPC Code(s): G06N7/08, G06N20/00
CPC Code(s): G06N7/08
Abstract: splitting integrators are provided for fast sampling from a diffusion generative model. a stochastic differential equation (sde) for the diffusion generative model is split into multiple terms, the multiple terms including deterministic components and random components. each of the multiple terms is solved to perform a time-reversed noise process using a splitting integrator such that each of the multiple terms is solved separately. alternating is performed between taking integration steps according to each of the multiple terms. the solving is repeated a desired quantity of steps to complete the time-reversed noise process.
20250103958. METHODS FOR GENEREATING A HONEYPOT_simplified_abstract_(robert bosch gmbh)
Inventor(s): Dominik Germek of Berlin DE for robert bosch gmbh, Niclas Ilg of Ammerbuch DE for robert bosch gmbh
IPC Code(s): G06N20/00, H04L9/40
CPC Code(s): G06N20/00
Abstract: a method for generating a honeypot for a target system. the method includes training a machine learning model to output, in response to an input (i.e., an input on which the machine learning model is trained) that includes a textual target system specification, a honeypot configuration matching the input (i.e., for a textually specified target system to be imitated by a honeypot, to output a suitable configuration for such a honeypot), receiving a textual specification of the target system, feeding the received textual specification to the trained machine learning model and generating a honeypot according to the configuration that the machine learning model outputs in response to the feed of the received textual specification.
Inventor(s): ASHER TROCKMAN of Pittsburgh PA US for robert bosch gmbh, DEVIN T. WILLMOTT of Pittsburgh PA US for robert bosch gmbh
IPC Code(s): G06T5/60, G06T5/20
CPC Code(s): G06T5/60
Abstract: a method of initializing and training a neural network having a plurality of layers includes defining a first function configured to generate a filter based on a plurality of variance values associated with respective pairs of parameters of the plurality of layers, calculating the plurality of variance values based on depths of respective layers of the plurality of layers such that the variance values increase as the depths increase, calculating a covariance matrix using the first function, the covariance matrix having a block structure and each block of the covariance matrix corresponding to a covariance between a respective parameter and other parameters of the plurality of layers, providing, as input, the covariance matrix to the neural network to initialize the neural network for training, and generating, using the neural network, an output based on the covariance matrix.
Inventor(s): Christopher MONACO of Sunnyvale CA US for robert bosch gmbh, Arun DAS of San Jose CA US for robert bosch gmbh, Maximilian MUFFERT of Belmont CA US for robert bosch gmbh, Ryan SOUSSAN of San Francisco CA US for robert bosch gmbh
IPC Code(s): G06T7/73, G01C21/30, G06V10/764, G06V20/56
CPC Code(s): G06T7/73
Abstract: the invention relates to a method for correcting a pose () of a motor vehicle () in the surroundings () of the motor vehicle () by an assistance system () of the motor vehicle (), the method comprising the steps of receiving first data () of semantic contour image measurements by an electronic computing device () of the assistance system (), receiving second data () of an initial pose estimate by the electronic computing device (), receiving third data () of semantically labeled map elements by the electronic computing device (), generating a score image () and/or an error image () and its image derivatives based on the first data () by the electronic computing device (), generating expected three-dimensional points () of the map elements at the initial pose estimate based on the second data () and third data () by the electronic computing device (), comparing the expected three-dimensional points () of the map elements with the score image () and/or the error image () and its image derivatives to perform model-to-image alignment by the electronic computing device (), based at least in part on projecting the expected three- dimensional points () into the score image () and/or the error image () and using the score image () and/or the error image () and its image derivative to perform an iterative optimization () by the electronic computing device (), and transmitting the alignment's resulting pose correction () and pose correction uncertainty () to the assistance system (). furthermore, the invention relates to a computer program product as well as an assistance system ().
Inventor(s): CHEN QIU of Pittsburgh PA US for robert bosch gmbh, XINGYU LI of New Orleans LA US for robert bosch gmbh, CHAITHANYA KUMAR MUMMADI of Pittsburgh PA US for robert bosch gmbh, MADAN RAVI GANESH of Pittsburgh PA US for robert bosch gmbh, ZHENZHEN LI of Gibsonia PA US for robert bosch gmbh, WAN-YI LIN of Wexford PA US for robert bosch gmbh, SABRINA SCHMEDDING of Tiefenbronn DE for robert bosch gmbh
IPC Code(s): G06V10/764, G06F40/284
CPC Code(s): G06V10/764
Abstract: a method of generating text-driven prompts and class prediction probabilities using a vision-language model (vlm) includes receiving candidate class names associated with a plurality of candidate classes for images, generating class text tokens based on a text description of the candidate class names, and generating a plurality of context prompt vectors using a prompt generator. the context prompt vectors define context information associated with an image classification task to be performed by the vlm. the method further includes generating prompts for each of the plurality of candidate classes by appending respective class text tokens to the context prompt vectors for each of the plurality of candidate classes, and, using the vlm, generating and outputting a class prediction probability for a sample image based on the plurality of context prompt vectors.
Inventor(s): XIN LI of Sunnyvale CA US for robert bosch gmbh, LIANG GOU of San Jose CA US for robert bosch gmbh, LIU REN of Saratoga CA US for robert bosch gmbh
IPC Code(s): G06V10/776, G06V10/764, G06V10/774, G06V10/82
CPC Code(s): G06V10/776
Abstract: a method of obtaining an uncertainty attribution of a prediction of objects in an input image includes receiving an input image, generating a prediction of objects in the input image, estimating an uncertainty associated with the prediction of the objects in the input image, calculating an uncertainty attribution that represents regions of the input image that cause the estimated uncertainty, including generating a plurality of adversarial gradients each corresponding to a modification of the input image configured to change the estimated uncertainty, and generating an output indicative of the calculated uncertainty attribution.
Inventor(s): Jan Hendrik Metzen of Boeblingen DE for robert bosch gmbh
IPC Code(s): G06V10/82, G06V10/74, G06V10/778
CPC Code(s): G06V10/82
Abstract: a computer-implemented method of classifying a sensor signal by a sensor signal encoder and a text encoder. the encoders are configured to encoder their inputs into a latent representation. the method includes: encoding the sensor signal to a first latent representation by the sensor signal encoder; generating a plurality of text prompts, wherein for each class several text prompts characterizing the corresponding class are instantiated; encoding the generated text prompts into second latent representations by the text encoder; determining a class query for each class by weighted averaging over the second representations corresponding to the same class; computing a similarity between the first latent representation and each of the class queries; assigning the sensor signal to the class with the highest similarity.
Inventor(s): Timo Bosch of Renningen DE for robert bosch gmbh, Tobias Falkenau of Esslingen DE for robert bosch gmbh
IPC Code(s): H01M8/04119, H01M8/04089, H01M8/04537, H01M8/04746, H01M8/04828
CPC Code(s): H01M8/04179
Abstract: the invention relates to a method for operating a fuel cell system, wherein hydrogen from a tank and recirculated hydrogen are fed as anode gas to at least one fuel cell via an anode circuit (), and water () contained in the anode gas is separated by means of a water separator () integrated into the anode circuit (), is collected in a container (), and is removed from the system by intermittently opening a drain valve (). according to the invention, the following steps are carried out to detect whether the container () is full:
Inventor(s): Timo Bosch of Renningen DE for robert bosch gmbh, Tobias Falkenau of Esslingen DE for robert bosch gmbh
IPC Code(s): H01M8/04119, H01M8/04089, H01M8/04537, H01M8/04746, H01M8/04828
CPC Code(s): H01M8/04179
Abstract: the invention further relates to a control device for carrying out the method or individual method steps.
20250105374. BATTERY_simplified_abstract_(robert bosch gmbh)
Inventor(s): Joachim Joos of Gerlingen DE for robert bosch gmbh, Walter Von Emden of Eningen Unter Achalm DE for robert bosch gmbh
IPC Code(s): H01M10/42, H01M10/48, H01M50/204, H01M50/51, H02J7/00
CPC Code(s): H01M10/425
Abstract: a battery. the battery includes: a first battery-cell assembly and a second battery-cell assembly, which each have a battery cell, a first switch and a second switch; and at least one analysis unit. in each battery-cell assembly, the first switch is connected in series with the battery cell, and the second switch is connected in parallel with the series connection consisting of the battery cell and its associated first switch. the battery-cell assemblies are connected in series. the analysis unit is configured to control, at a first predefined point in time, the first switch so that it opens and the second switch so that it closes, to electrically disconnect the battery-cell assembly from each of the other battery-cell assemblies of the battery and to bypass the battery-cell assembly.
Inventor(s): Dennis Mehlo of Reutlingen DE for robert bosch gmbh, Dennis Ehard of Eningen Unter Achalm DE for robert bosch gmbh, Peter Kunert of Lichtenstein DE for robert bosch gmbh, Simon Buck of St. Johann DE for robert bosch gmbh, Thilo Koeder of Gerlingen DE for robert bosch gmbh
IPC Code(s): H01M50/514, B62J43/13, B62J43/28, B62M6/55, H01M50/213, H01M50/249, H01M50/262, H01M50/291
CPC Code(s): H01M50/514
Abstract: an energy storage unit for a vehicle driven by an electric motor, in particular for a one-wheeler or two-wheeler driven by an electric motor, has a sub-housing, in which at least two cell stacks are housed for receiving at least two electrochemical energy storage cells in each case, which are configured as round cells. each energy storage cell comprises two electrical cell poles and the electrical cell poles of at least two energy storage cells are electrically conductively connected to each other in a series and/or parallel connection via at least one cell connector. the at least two cell stacks are arranged adjacent to each other, such that a compression device of the energy storage unit connects the cell connectors to the electrical cell poles of the energy storage cells in the assembled state of the energy storage unit in a non-positive force-fit manner.
20250106252. METHOD FOR GENERATING A HONEYPOT_simplified_abstract_(robert bosch gmbh)
Inventor(s): Dominik Germek of Berlin DE for robert bosch gmbh, Niclas Ilg of Ammerbuch DE for robert bosch gmbh
IPC Code(s): H04L9/40
CPC Code(s): H04L63/1491
Abstract: a method for generating a honeypot for a target system. the method includes ascertaining services provided and protocols supported by a target system to be imitated via a network interface by sending queries to the target system for a plurality of services, ascertaining a honeypot type and a configuration for the selected honeypot type that, if configured with the selected configuration, can provide the ascertained services and support the ascertained protocols, and generating a honeypot from the ascertained honeypot type with the ascertained configuration.
20250106253. METHOD FOR GENERATING A HONEYPOT_simplified_abstract_(robert bosch gmbh)
Inventor(s): Dominik Germek of Berlin DE for robert bosch gmbh, Niclas Ilg of Ammerbuch DE for robert bosch gmbh
IPC Code(s): H04L9/40
CPC Code(s): H04L63/1491
Abstract: a method for generating a honeypot for a target system. the method includes ascertaining, by means of a honeypot generating device, which is granted access to the target system, the directory tree of a file system of the target system, operating system shell commands supported by the operating system and processes running on the target system by accessing the target system and generating, by means of the honeypot generating device, a honeypot, which contains a file system with a copy of the ascertained directory tree, imitates the ascertained shell commands and imitates the execution of the ascertained processes.
Inventor(s): Basti Anil Shenoy of Hemmingen DE for robert bosch gmbh, Benedikt Arthur Maximilian Mansbart of Kista SE for robert bosch gmbh, Daniel Selig of Leonberg DE for robert bosch gmbh, Hongyan Zhang of Stuttgart DE for robert bosch gmbh, Joshua Rambo of Wixom MI US for robert bosch gmbh, Mikkel Liisberg of Stuttgart DE for robert bosch gmbh, Samir Hamzaoui of Stuttgart DE for robert bosch gmbh, Scott Chemello of Northville MI US for robert bosch gmbh, Stephan Rittler of Urbach DE for robert bosch gmbh, Ulrich Stech of Neckarsulm DE for robert bosch gmbh
IPC Code(s): H04L67/12, G06F8/35, G06F8/41, H04L12/40
CPC Code(s): H04L67/12
Abstract: a method for forwarding data in a communication system of a vehicle. the communication system includes at least a first bus system and at least one further bus system. the data can be exchanged between the bus systems, with at least one first domain as an independent execution instance, in particular an autosar domain. application programs, in particular vehicle functions, can be executed in the first domain. the first domain includes at least standardized interfaces, in particular autosar real-time environment, to the application programs. via a further domain as further execution instance independent of the first domain, data are exchanged between the communication system and the first domain by only the further domain accessing the physical interface of the communication system. data received in the further domain via the physical interface of the communication system are processed at least with regard to forwarding.
20250106608. METHODS AND DEVICES FOR RADIO COMMUNICATION_simplified_abstract_(robert bosch gmbh)
Inventor(s): Frank Hofmann of Hildesheim DE for robert bosch gmbh, Khaled Shawky Hassan of Laatzen DE for robert bosch gmbh
IPC Code(s): H04W4/90, H04L43/10, H04W4/46, H04W24/10
CPC Code(s): H04W4/90
Abstract: a method for an apparatus operating in a wireless communication network. the method includes transmitting a plurality of functional safety containers offset in time along with at least one associated functional safety indicator that indicates a relevance according to at least one safety integrity level, wherein at least one of the plurality of functional safety containers comprises data, especially v2x data that comprises at least one of a vehicle operating parameter and a roadway event, or industrial data that comprises a machine operating parameter, or building technology data that comprises building operational data.
Inventor(s): Khaled Shawky Hassan of Laatzen DE for robert bosch gmbh, Klaus Sambale of Oberhausen DE for robert bosch gmbh, Nadia Brahmi of Hildesheim DE for robert bosch gmbh
IPC Code(s): H04W72/20, H04W28/16
CPC Code(s): H04W72/20
Abstract: an apparatus (ue ue) comprising at least one processor, at least one memory including computer program code, and at least one communication module. the at least one memory and computer program code are configured, with the at least one processor, and the at least one communication module, to cause the apparatus (ue ue) to receive () a plurality of radio signal (s s) or at least one resource conflict indicator (rci). the at least one resource conflict indicator (rci) indicates at least one radio resource (rr) that has a potential risk of a resource conflict.
- Robert Bosch GmbH
- A61B7/00
- A61B5/08
- A61B7/04
- CPC A61B7/003
- Robert bosch gmbh
- B03C7/02
- B07B1/04
- CPC B03C7/02
- B25J9/16
- CPC B25J9/163
- B60T13/68
- B60T13/74
- CPC B60T13/686
- B60T17/22
- F16D65/18
- F16D66/00
- F16D66/02
- F16D121/24
- CPC B60T17/22
- B60W50/00
- CPC B60W50/0098
- B60W60/00
- CPC B60W60/001
- G06N3/02
- CPC B60W60/00274
- B62J45/00
- B60T13/66
- B62L3/02
- CPC B62J45/00
- F04B1/20
- F04B1/128
- F04B17/03
- CPC F04B1/20
- F16D55/00
- F16D121/06
- F16D125/06
- CPC F16D65/183
- G01C21/00
- CPC G01C21/387
- G01L9/00
- CPC G01L9/0072
- G01M7/02
- G01M7/06
- G01M17/06
- CPC G01M7/027
- G01S5/16
- G01S3/782
- G06V10/24
- CPC G01S5/163
- G01S7/41
- G01S13/89
- CPC G01S7/411
- G01S7/539
- G01S15/66
- G01S15/87
- G01S15/931
- CPC G01S7/539
- G01S13/87
- G01S7/40
- CPC G01S13/878
- G05B9/03
- B60W50/02
- B60W50/04
- CPC G05B9/03
- G06F16/215
- CPC G06F16/215
- G06F21/56
- CPC G06F21/56
- CPC G06F21/566
- G06N3/0464
- CPC G06N3/0464
- G06N3/08
- G06N3/0455
- CPC G06N3/08
- G06N3/082
- G06N3/10
- CPC G06N3/082
- G06N3/088
- G06F40/40
- G06V10/44
- G06V10/762
- G06V10/774
- G06V10/776
- G06V20/70
- CPC G06N3/088
- G06N3/092
- CPC G06N3/092
- G06N3/098
- G06N3/045
- CPC G06N3/098
- G06N5/022
- CPC G06N5/022
- G06N7/08
- G06N20/00
- CPC G06N7/08
- H04L9/40
- CPC G06N20/00
- G06T5/60
- G06T5/20
- CPC G06T5/60
- G06T7/73
- G01C21/30
- G06V10/764
- G06V20/56
- CPC G06T7/73
- G06F40/284
- CPC G06V10/764
- G06V10/82
- CPC G06V10/776
- G06V10/74
- G06V10/778
- CPC G06V10/82
- H01M8/04119
- H01M8/04089
- H01M8/04537
- H01M8/04746
- H01M8/04828
- CPC H01M8/04179
- H01M10/42
- H01M10/48
- H01M50/204
- H01M50/51
- H02J7/00
- CPC H01M10/425
- H01M50/514
- B62J43/13
- B62J43/28
- B62M6/55
- H01M50/213
- H01M50/249
- H01M50/262
- H01M50/291
- CPC H01M50/514
- CPC H04L63/1491
- H04L67/12
- G06F8/35
- G06F8/41
- H04L12/40
- CPC H04L67/12
- H04W4/90
- H04L43/10
- H04W4/46
- H04W24/10
- CPC H04W4/90
- H04W72/20
- H04W28/16
- CPC H04W72/20