Robert Bosch GmbH patent applications on April 3rd, 2025
Patent Applications by Robert Bosch GmbH on April 3rd, 2025
Robert Bosch GmbH: 23 patent applications
Robert Bosch GmbH has applied for patents in the areas of G06V10/774 (2), G06V10/764 (2), H04L9/40 (2), B60T7/06 (1), B33Y80/00 (1) H04L63/1491 (2), G06V10/764 (2), B60T7/06 (1), G06N3/098 (1), H01M8/04156 (1)
With keywords such as: image, sensor, data, vehicle, signal, source, based, input, target, and embedding in patent application abstracts.
Patent Applications by Robert Bosch GmbH
Inventor(s): Andreas Weh of Sulzberg DE for robert bosch gmbh, Joji Naka of Immenstadt DE for robert bosch gmbh
IPC Code(s): B60T7/06, G05G1/46
CPC Code(s): B60T7/06
Abstract: a functional system arrangement for a vehicle brake system in an associated vehicle on a vehicle wall. the functional system includes a component of a functional system of the vehicle brake system to be fastened to the vehicle wall, and a push rod coupled to the component. the component has a length extending along an x-axis and a height extending along a z-axis perpendicular to the x-axis, and a component-push-rod unit is formed with the component and the push rod, the component-push-rod unit running with its longitudinal extension along the x-axis, the component-push-rod unit is to be arranged on the vehicle wall rotated by an angle about the z-axis.
Inventor(s): Debayan Pradhan of Bengaluru IN for robert bosch gmbh, Jatavalaba Vijay Kumar Srikanth of Canton MI US for robert bosch gmbh, Faizan Mohammed of Belgavi IN for robert bosch gmbh
IPC Code(s): B60W50/029, B60W50/02, B60W50/14
CPC Code(s): B60W50/029
Abstract: systems and methods for detecting component faults for a straddle-type vehicle using sensed vibrations. one example system includes a vibration sensor positioned at a first position on the straddle-type vehicle and configured to sense vibrations of the straddle-type vehicle and an electronic processor communicatively coupled to the vibration sensor. the electronic processor is configured to receive, from the vibration sensor, sensor information, determine, based on the sensor information, whether a vibration is present at a predetermined frequency range, and determine, in response to determining that the vibration is present at the predetermined frequency range, whether a characteristic of the vibration exceeds a predetermined threshold. the electronic processor is further configured to, in response to determining that the characteristic exceeds the predetermined threshold, identify a fault with a component of the straddle-type vehicle corresponding to the predetermined threshold and execute a mitigation action based on the fault.
Inventor(s): Mohamed El-Gammal of Windsor CA for robert bosch gmbh, Juergen Zybell of Novi MI US for robert bosch gmbh
IPC Code(s): B61K9/12, B61L15/00, B61L23/04
CPC Code(s): B61K9/12
Abstract: systems and methods for predicting anomalies in a wheel system of a railway vehicle and a track. one example method includes determining a speed of the railway vehicle and whether the speed exceeds a speed threshold. the method includes obtaining, in response to the speed exceeding the threshold, a vibration measurement from a vibration sensor and determining, from the measurement, a classified vibration level and determining whether the classified vibration level is indicative of an anomaly, and deriving, in response to the classified vibration level being indicative of the anomaly, a dominant vibration frequency of the measurement. the method includes performing a comparison between the dominant vibration frequency and a predetermined frequency threshold, and identifying, based on the comparison and a reference classified vibration level, the anomaly existing within either or both of the railway vehicle wheel system and the track and performing a mitigation action.
Inventor(s): Richard Fix of Weil Im Schoenbuch DE for robert bosch gmbh, Susanne Wicker of Reutlingen DE for robert bosch gmbh
IPC Code(s): B81C1/00, B81B7/00
CPC Code(s): B81C1/00793
Abstract: a production method for a micromechanical sensor component and a corresponding micromechanical sensor component. the production method includes: providing a sensor wafer with a plurality of micromechanical sensor chips, which include one or more relevant sensor regions; forming an access wafer with one or a corresponding plurality of access chips, which in each case include one or more access regions to the sensor regions, which form relevant media access regions for the sensor regions; attaching the access wafer to the sensor wafer, so that the access regions are arranged above the corresponding sensor region(s); and separating the sensor chips with the access chips glued thereon, in order to obtain a plurality of sensor component chips.
Inventor(s): Adam Pawlowski of Stuttgart DE for robert bosch gmbh, Sonny Tran of Stuttgart DE for robert bosch gmbh
IPC Code(s): F17C13/02
CPC Code(s): F17C13/025
Abstract: a method () for detecting any throttling losses () in a hydrogen tank system (),
20250110223. Method for Controlling a Laser Rangefinder_simplified_abstract_(robert bosch gmbh)
Inventor(s): Kevin Bergmann of Uhingen DE for robert bosch gmbh, Gaetan Moren of Stuttgart DE for robert bosch gmbh, Joerg Stierle of Waldenbuch DE for robert bosch gmbh, Michael Holzaepfel of Essingen DE for robert bosch gmbh, Pia Rank of Schorndorf-Weiler DE for robert bosch gmbh, Sandra Hagmayer of Ebersbach DE for robert bosch gmbh
IPC Code(s): G01S7/4911, G01S7/481, G01S7/51
CPC Code(s): G01S7/4911
Abstract: a method for controlling a laser rangefinder having a control unit for carrying out the method is disclosed. the method includes (i) acquiring an actuation of a setting element of the laser rangefinder, (ii) providing an animated measurement mode visualization, and (iii) displaying the animated measurement mode visualization on a display unit of the laser rangefinder.
Inventor(s): Michael T. White of Livonia MI US for robert bosch gmbh, Paul J. Connor of Belleville MI US for robert bosch gmbh, Majed J. Sabbagh of Northville Township MI US for robert bosch gmbh
IPC Code(s): G01S7/52, G01S15/931
CPC Code(s): G01S7/52004
Abstract: systems and methods for ice removal system for an ultrasonic sensor. one example system includes the ultrasonic sensor including a transducer and an electronic processor. the electronic processor is configured to output, at the transducer, a chirp signal. the electronic processor is configured to determine, based on the chirp signal, whether a mechanical impedance is present at the transducer. the electronic processor is configured to, in response to determining that the mechanical impedance is present, output, at the transducer, a frequency sweep signal. the electronic processor is configured to receive, at the transducer, a reflected frequency sweep signal. the electronic processor is configured to determine, based on the reflected frequency sweep signal, a resonant frequency. the electronic processor is configured to output, at the transducer, an output signal according to the resonant frequency.
Inventor(s): Daniel Lopez Cuenca of Stuttgart DE for robert bosch gmbh, Julio Alberto Gonzalez Marin of Stuttgart DE for robert bosch gmbh, Thomas Anker of Reutlingen DE for robert bosch gmbh
IPC Code(s): G05B19/418
CPC Code(s): G05B19/41875
Abstract: a method for detecting a production error of an assembly in a manufacturing facility includes (i) providing sensor data having at least two dimensions, wherein a respective dimension of the sensor data comprises measurement data with respect to the assembly, (ii) performing a dimensional reduction of the sensor data, wherein at least one feature is extracted based on the at least two dimensions of the sensor data, (iii) reconstructing the dimension-reduced sensor data based on the at least one extracted feature to provide reconstructed sensor data, (iv) determining a reconstruction error based on a comparison of the sensor data with the reconstructed sensor data, and (v) detecting the production error of the assembly based on the determined reconstruction error. also disclosed is a computer program, a device, and a storage medium for this purpose.
Inventor(s): Jesko Hecking-Harbusch of Leonberg DE for robert bosch gmbh, Jochen Quante of Ludwigsburg DE for robert bosch gmbh, Matthias Woehrle of Bietigheim-Bissingen DE for robert bosch gmbh, Maximilian Schlund of Stuttgart DE for robert bosch gmbh, Sebastian Ernesto Sierra Loaiza of Stuttgart DE for robert bosch gmbh
IPC Code(s): G06F8/35, G06F11/3604
CPC Code(s): G06F8/35
Abstract: a computer-implemented method for the automated generation of a model of computation. the method includes generating, via a machine learning model, at least one model of computation based at least on a specification that the at least one model of computation is to fulfill, and a prompt; and evaluating the at least one model of computation, resulting in an evaluation result. a computer-implemented method for further training a machine learning model, wherein the machine learning model is designed to generate at least one model of computation is also described. the method includes adapting the machine learning model at least based on at least one model of computation and at least one evaluation result, wherein the at least one evaluation result results from evaluating the at least one model of computation.
Inventor(s): Lilly Wu of Shanghai CN for robert bosch gmbh, Yifan Du of Shanghai CN for robert bosch gmbh, Rui Zhang of Shanghai CN for robert bosch gmbh, Xiangyu Wu of Shanghai CN for robert bosch gmbh
IPC Code(s): G06F9/50
CPC Code(s): G06F9/5027
Abstract: a system and method for offloading autonomous driving tasks is disclosed. the system includes a plurality of computing nodes comprising one or a plurality of computing nodes located on a vehicle, one or a plurality of computing nodes located on edge devices, and one or a plurality of computing nodes located on cloud devices. the system further includes a modeling module configured to create a system model that comprises a communication latency between each pair of computing nodes among the plurality of computing nodes. the system also includes an allocation module configured to allocate a plurality of autonomous driving tasks of an autonomous driving service based on the system model in order to offload each autonomous driving task to one of the plurality of computing nodes, wherein the allocation is performed such that the end-to-end latency of the autonomous driving service is minimized.
Inventor(s): Jesko Hecking-Harbusch of Leonberg DE for robert bosch gmbh, Jochen Quante of Ludwigsburg DE for robert bosch gmbh, Matthias Woehrle of Bietigheim-Bissingen DE for robert bosch gmbh, Maximilian Schlund of Stuttgart DE for robert bosch gmbh, Sebastian Ernesto Sierra Loaiza of Leipzig DE for robert bosch gmbh
IPC Code(s): G06F11/36, G06F8/51, G06F8/77
CPC Code(s): G06F11/3616
Abstract: a method for automatically translating program code from a source language to a target language. the method includes: translating a source program code in a source language into a target program code in a target language by means of a language model; repeating the translation with changed conditions, such as changing one or more hyperparameters such as a temperature parameter of the language model, transformations in the source program code, and/or changes in the input to the language model; comparing the source program code and the target program code or codes with a test harness, wherein the test harness is generated automatically; and evaluating the target program code based on code quality metrics, test quality metrics and/or the number of tests.
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. a portion of a server-maintained machine-learning model is transferred from a server to clients, yielding a plurality of local machine-learning models. at each client, the local models are trained with locally-stored data, including determining a respective cross entropy loss for each local models. weights are updated for each local model, and evaluated based on a common dataset to obtain activation outputs for each layer. these are transferred to the server without transferring the locally-stored data of the clients, whereupon they are permuted according to the one respective updated weight to match a dimension of the selected client to obtain a matrix, which is sent to each client for permuting the local models based on the matrix. the permuted weights are sent to the server, whereupon they are aggregated and transferred back to the clients for updating of the local models.
Inventor(s): THANG DOAN of San Francisco CA US for robert bosch gmbh, XIN LI of Sunnyvale CA US for robert bosch gmbh, SIMA BEHPOUR of Sunnyvale 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): G06V10/764, G06V10/74, G06V10/774, G06V10/82, G06V20/56
CPC Code(s): G06V10/764
Abstract: a method of performing open world object detection includes receiving object data, that includes embeddings data corresponding to a plurality of embeddings for known objects in a first input image, projecting the embeddings into a hyperbolic embedding space that includes embeddings in a plurality of categories of objects each including one or more classes of objects, regularizing the projected embeddings within the hyperbolic embedding space by moving each of the projected embeddings closer to embeddings in a same category of the plurality of categories and further away from embeddings in different categories of the plurality of categories, receiving an unmatched query corresponding to an object in a second input image, and generating, based on the hyperbolic embedding space including the regularized embeddings, an output signal that indicates whether the object in the second input image corresponds to an unknown object in one of the classes of objects.
Inventor(s): Chen Qiu of Pittsburgh PA US for robert bosch gmbh, Clement Fung of Pittsburgh PA US for robert bosch gmbh, Maja Rudolph of Madison WI US for robert bosch gmbh
IPC Code(s): G06V10/764
CPC Code(s): G06V10/764
Abstract: a computer-implemented system and method relate to anomaly detection. a first source image is obtained from a first image set and a second source image is obtained from a second image set of an in-distribution image dataset. a diffusion model generates a modified image using the first source image and the second source image. a non-anomalous label is automatically generated for the first source image. the non-anomalous label is also generated for the second source image. an anomalous label is generated for the modified image. a training dataset is created. the training dataset includes at least the first source image with the non-anomalous label, the second source image with the non-anomalous label, and the modified image with the anomalous label. a machine learning model is trained or fine-tuned using the training dataset. the machine learning model being configured to perform a task of anomaly detection.
Inventor(s): Chen Qiu of Pittsburgh PA US for robert bosch gmbh, Clement Fung of Pittsburgh PA US for robert bosch gmbh, Maja Rudolph of Madison WI US for robert bosch gmbh
IPC Code(s): G06V10/774, G06V10/776, G06V40/40, H04N19/46
CPC Code(s): G06V10/774
Abstract: a computer-implemented system and method relate to anomaly detection. latent code of a source image is obtained. the latent code is designated as a target image. source embedding data is generated form the source image. text data, which is of a different domain than that of the source image, is obtained. text embedding data is generated from the text data. additional embedding data is generated using the source embedding data and the text embedding data. the additional embedding data provides guidance for modifying the source image. a modified image is generated via an iterative process that includes at least one iteration, where each iteration includes at least (i) encoding the target image to generate target embedding data, (ii) generating updated embedding data by combining the target embedding data and the additional embedding data, (iii) decoding the updated embedding data to generate a new image, and (iv) assigning the new image as the target image and the modified image. a non-anomalous label is generated for the source image and an anomalous label is generated for the modified image. a machine learning model is trained or fine-tuned using a dataset, which includes at least the source image with the non-anomalous label and the modified image with the anomalous label.
Inventor(s): William Harris Beluch of Stuttgart DE for robert bosch gmbh, Kanil Patel of Berlin DE for robert bosch gmbh
IPC Code(s): G06V10/778, G06V10/96, G06V20/70
CPC Code(s): G06V10/778
Abstract: device and computer-implemented method for active learning from multimodal input, wherein the method comprises providing () the input and learning () a model depending on the input, wherein the input comprises input of different modes, and wherein learning () the model comprises determining (-) an input of a mode from the input of different modes depending on an acquisition function that comprises a measure for a cost for labelling the input of the mode, labelling (-) the input of the mode with a label, and learning (-) the model depending on the label. technical system comprising the device.
20250111715. SIGNAL EXPECTED RANGE FOR A VEHICLE_simplified_abstract_(robert bosch gmbh)
Inventor(s): Adrien Cossa of Stuttgart DE for robert bosch gmbh, Sebastian Gropper of Donzdorf DE for robert bosch gmbh, Klaus Merkle of Oberriexingen DE for robert bosch gmbh, Victor Lemmel of Sersheim DE for robert bosch gmbh, Andres Murube Lindahl of Stuttgart DE for robert bosch gmbh, Matheus Duempelmann of Stuttgart DE for robert bosch gmbh, Timo Basile of Forst DE for robert bosch gmbh, Tushar Parulekar of Farmington Hills MI US for robert bosch gmbh, Sanjiv Lancy of Farmington Hills MI US for robert bosch gmbh
IPC Code(s): G07C5/08, B60L58/30, F02D41/22, F02M26/49, G07C5/10
CPC Code(s): G07C5/0816
Abstract: a system and method for indicating failure of a vehicle component of a vehicle by determining anomalies for a vehicle signal of a vehicle is provided that includes a model that is trained with training data resulting in a trained artificial intelligence model. the trained model is executed by an electronic processor configured to: receive a plurality of input signals correlated with the vehicle signal; analyze the input signals; determine a predicted vehicle signal from the input signals; determine a tolerance band from the input signals; and when the model is valid, generate a model valid signal. a comparison device is configured to: receive the predicted vehicle signal, the tolerance band, and the model valid signal; receive the measured vehicle signal; and determine whether the measured vehicle signal is an anomaly based on the measured vehicle signal, the predicted vehicle signal, the tolerance band, and the model valid signal.
Inventor(s): Long HUANG of Baton Rouge LA US for robert bosch gmbh, Pongtep ANGKITITRAKUL of Dublin CA US for robert bosch gmbh, Samarjit DAS of Wexford PA US for robert bosch gmbh
IPC Code(s): G10L21/18
CPC Code(s): G10L21/18
Abstract: systems and methods for converting a primary one-dimensional signal into a secondary one-dimensional signal of another modality. the primary signal is spliced into a plurality of consecutive frames. a first linear transformation transforms the frames into corresponding vectors. positional encodings are provided on the vectors to encode relative positional information associated with each sample within each frame. a multi-head self-attention machine-learning model compares relative importance of the samples within each vector to each other in that vector to yield high-level representation vectors. a second linear transformation transforms the high-level representation vectors into corresponding secondary signal frames. the secondary signal frames are concatenated into a reconstructed one-dimensional secondary signal having a different modality than the primary signal.
Inventor(s): Markus Feigl of Markgroeningen DE for robert bosch gmbh, Alexander Siegert of Kornwestheim DE for robert bosch gmbh, Jan Tremel of Erlangen DE for robert bosch gmbh
IPC Code(s): H01M8/0267, B33Y80/00, H01M8/0202, H01M8/04007
CPC Code(s): H01M8/0267
Abstract: the invention relates to a power distribution unit () for a fuel cell system, comprising a housing () which has a housing part () that forms a cooling duct (), to which a cooling medium can be applied, and at least one cooling tower (), extending substantially perpendicularly to the cooling duct (), for receiving a current-conducting component (), in particular a bus bar, wherein a cavity () is formed in the cooling tower () and is connected to the cooling duct () such that the cooling medium can also be applied to the cavity ().
Inventor(s): Markus Feigl of Markgroeningen DE for robert bosch gmbh, Alexander Siegert of Kornwestheim DE for robert bosch gmbh, Jan Tremel of Erlangen DE for robert bosch gmbh
IPC Code(s): H01M8/0267, B33Y80/00, H01M8/0202, H01M8/04007
CPC Code(s): H01M8/0267
Abstract: the invention also relates to a method for producing a power distribution unit ().
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, H01M8/0444, H01M8/04492, H01M8/04828, H01M8/10
CPC Code(s): H01M8/04156
Abstract: the invention relates to a method for operating a fuel cell system, wherein hydrogen-containing anode gas exiting at least one fuel cell is recirculated via an anode circuit (), wherein liquid water () contained in the anode gas is separated with the aid of a water separator () integrated into the anode circuit (), is collected in a container (), and is removed from the container () by opening a drain valve (), and the anode circuit () is flushed by opening a purge valve () integrated into the container () of the water separator (), wherein the hydrogen content is measured with the aid of a hydrogen sensor () connected downstream of the purge valve (). according to the invention, when the purge valve () is open and a delayed increase in the hydrogen content is detected with the aid of the hydrogen sensor (), the “container full” state is detected.
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, H01M8/0444, H01M8/04492, H01M8/04828, H01M8/10
CPC Code(s): H01M8/04156
Abstract: the invention also relates to a control device () for carrying out the method or individual method steps.
20250112956. METHODS FOR CREATING A HONEYPOT_simplified_abstract_(robert bosch gmbh)
Inventor(s): Christopher Huth of Heilbronn DE for robert bosch gmbh, 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 creating a honeypot. the method includes sending requests to a target system; observing the responses of the target system to the requests; in accordance with the observed responses of the target system, creating a state machine model for the behavior of a network protocol according to which the target system responds to requests; and creating a honeypot that responds to requests in accordance with the state machine model.
20250112957. METHOD FOR GENERATING A HONEYPOT_simplified_abstract_(robert bosch gmbh)
Inventor(s): Christopher Huth of Heilbronn DE for robert bosch gmbh, 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 training a large language model to respond to operating system command line interface commands like a command line interface of the target system, and generating a honeypot that uses the trained large language model to respond to operating system command line interface commands it receives.
Inventor(s): Daniel Krebs of Aufhausen DE for robert bosch gmbh, Jens Baringhaus of Sindelfingen DE for robert bosch gmbh
IPC Code(s): H01L29/66, H01L21/02, H01L21/308, H01L29/16, H01L29/20, H01L29/775
CPC Code(s): H10D30/014
Abstract: a method for producing a power semiconductor component having a plurality of fins. the method includes: creating a plurality of mesas starting from a front side of a semiconductor substrate into a drift layer of the semiconductor substrate by means of etching, each mesa being arranged between a first trench and a second trench. each mesa has a width greater than 500 nm. the method further includes applying a mask layer to the top side, the first side surface, the second side surface, the first trench bottom surface and the second trench bottom surface; creating a structured mask by removing the mask layer in certain regions, so that an exposed surface is created; creating fins by machining the exposed surface; removing the structured mask and completing the power semiconductor component.
- Robert Bosch GmbH
- B60T7/06
- G05G1/46
- CPC B60T7/06
- Robert bosch gmbh
- B60W50/029
- B60W50/02
- B60W50/14
- CPC B60W50/029
- B61K9/12
- B61L15/00
- B61L23/04
- CPC B61K9/12
- B81C1/00
- B81B7/00
- CPC B81C1/00793
- F17C13/02
- CPC F17C13/025
- G01S7/4911
- G01S7/481
- G01S7/51
- CPC G01S7/4911
- G01S7/52
- G01S15/931
- CPC G01S7/52004
- G05B19/418
- CPC G05B19/41875
- G06F8/35
- G06F11/3604
- CPC G06F8/35
- G06F9/50
- CPC G06F9/5027
- G06F11/36
- G06F8/51
- G06F8/77
- CPC G06F11/3616
- G06N3/098
- CPC G06N3/098
- G06V10/764
- G06V10/74
- G06V10/774
- G06V10/82
- G06V20/56
- CPC G06V10/764
- G06V10/776
- G06V40/40
- H04N19/46
- CPC G06V10/774
- G06V10/778
- G06V10/96
- G06V20/70
- CPC G06V10/778
- G07C5/08
- B60L58/30
- F02D41/22
- F02M26/49
- G07C5/10
- CPC G07C5/0816
- G10L21/18
- CPC G10L21/18
- H01M8/0267
- B33Y80/00
- H01M8/0202
- H01M8/04007
- CPC H01M8/0267
- H01M8/04119
- H01M8/04089
- H01M8/0444
- H01M8/04492
- H01M8/04828
- H01M8/10
- CPC H01M8/04156
- H04L9/40
- CPC H04L63/1491
- H01L29/66
- H01L21/02
- H01L21/308
- H01L29/16
- H01L29/20
- H01L29/775
- CPC H10D30/014