NVIDIA Corporation patent applications on December 19th, 2024
Patent Applications by NVIDIA Corporation on December 19th, 2024
NVIDIA Corporation: 15 patent applications
NVIDIA Corporation has applied for patents in the areas of G06F40/284 (8), G06F40/40 (3), G01C21/00 (2), G06F40/30 (2), G06N3/0455 (2) G06F40/284 (6), B60W60/0016 (1), G01C21/34 (1), G01C21/3841 (1), G06F11/267 (1)
With keywords such as: data, language, environment, tokenized, map, generate, based, input, such, and representation in patent application abstracts.
Patent Applications by NVIDIA Corporation
Inventor(s): Zhiqi Li of Shanghai (CN) for nvidia corporation, Zhiding Yu of Cupertino CA (US) for nvidia corporation, David Austin of Phoenix AZ (US) for nvidia corporation, Shiyi Lan of Sunnyvale CA (US) for nvidia corporation, Jan Kautz of Lexington MA (US) for nvidia corporation, Jose Manuel Alvarez Lopez of Mountain View CA (US) for nvidia corporation
IPC Code(s): B60W60/00, B60W40/02, G06T3/00, G06V20/58
CPC Code(s): B60W60/0016
Abstract: apparatuses, systems, and techniques of using one or more machine learning processes (e.g., neural network(s)) to predict occupancy using an image input. in at least one embodiment, image data is processed using a neural network to predict occupancy in a 3d voxel space. in at least one embodiment, image data is processed using a neural network to detect objects in a 3d space.
Inventor(s): Shuang Wu of Fremont CA (US) for nvidia corporation, Denis Laprise of Palo Alto CA (US) for nvidia corporation, Mark Wheeler of Saratoga CA (US) for nvidia corporation
IPC Code(s): G01C21/34, G06F40/284, G08G1/0968
CPC Code(s): G01C21/34
Abstract: approaches presented herein provide for the generation of a tokenized description of an environment for use in making decisions with respect to the environment. in particular, a large language model (llm) can be used to generate a tokenized text string representation of an environment using sensor information captured at a specific location, as well as information about the semantics, topology, and geometry of the environment. a similarity-based search can be performed against tokenized descriptions for various locations until a single high-quality match is identified, and the geographic position of the match can be inferred to correspond to the current position of a vehicle that captured the sensor data. the current location and tokenized description can also be provided to a language model, along with a road-level route plan, in order to generate more detailed routing information that is optimized based on the additional information available in the tokenized description for a sequence of goals corresponding to the route plan.
Inventor(s): Yu Zhang of Santa Clara CA (US) for nvidia corporation, Lin Yang of Santa Clara CA (US) for nvidia corporation
IPC Code(s): G01C21/00, G06T7/73, G06T11/20, G06T17/00, G06V10/764, G06V10/82, G06V20/56
CPC Code(s): G01C21/3841
Abstract: systems and methods related to ground truth data generation using maps and sensor data are disclosed. in some embodiments, a label corresponding to a feature included in a map may be assigned to an image based at least on the feature also being depicted in the image. in these and other embodiments, the labeled image may be used as training data (e.g., ground truth data) for one or more neural networks.
Inventor(s): Jonah Alben of San Jose CA (US) for nvidia corporation, Sachin Idgunji of San Jose CA (US) for nvidia corporation, Jue Wu of Los Gatos CA (US) for nvidia corporation, Shantanu Sarangi of Saratoga CA (US) for nvidia corporation
IPC Code(s): G06F11/267, G06F1/3296, G06F11/22, G06F11/27, G06F11/273
CPC Code(s): G06F11/267
Abstract: in various examples, one or more components or regions of a processing unit-such as a processing core, and/or component thereof—may be tested for faults during deployment in the field. to perform testing while in deployment, the state of a component subject to test may be retrieved and/or stored during the test to maintain state integrity, the component may be clamped to communicatively isolate the component from other components of the processing unit, a test vector may be applied to the component, and the output of the component may be compared against an expected output to determine if any faults are present. the state of the component may be restored after testing, and the clamp removed, thereby returning the component to its operating state without a perceivable detriment to operation of the processing unit in deployment.
Inventor(s): Shuang Wu of Fremont CA (US) for nvidia corporation, Denis Laprise of Palo Alto CA (US) for nvidia corporation, Mark Wheeler of Saratoga CA (US) for nvidia corporation
IPC Code(s): G06F40/284, G01C21/00
CPC Code(s): G06F40/284
Abstract: approaches presented herein provide for the identification of differences between local map data, for a region of a physical environment, and observation or perception data generated by one or more machines or other such sources. in at least one embodiment, sensors on an ego machine can capture sensor data for a region in which the ego machine is located, and a language model on the ego machine can compare this sensor data, or perception data generated using the sensor data, against the local map data. the language model can generate a tokenized description of identified differences, in a domain-specific language. the tokenized description can be transmitted to a map management service that can compare these differences against differences identified by other machines, for example, to determine whether to update and redistribute at least a portion of the map data.
Inventor(s): Shuang Wu of Fremont CA (US) for nvidia corporation, Denis Laprise of Palo Alto CA (US) for nvidia corporation, Ge Cong of Pleasanton CA (US) for nvidia corporation, Mark Wheeler of Saratoga CA (US) for nvidia corporation
IPC Code(s): G06F40/284, G06V20/64
CPC Code(s): G06F40/284
Abstract: approaches presented herein provide for the automated, end-to-end generation of map data based at least in part on sensor data captured for an environment. at least one language model can be used to generate a text-based, tokenized description of the environment that includes semantics, topology, geometry, and/or other information for the environment. a generation pipeline can use one or more language models in one or more stages, and the data passed between stages can be in a determined tokenized representation format, as may correspond to a tokenized text string in a specific structured language.
Inventor(s): Shuang Wu of Fremont CA (US) for nvidia corporation, Denis Laprise of Palo Alto CA (US) for nvidia corporation, Ming Cui of San Jose CA (US) for nvidia corporation, Ge Cong of Pleasanton CA (US) for nvidia corporation, Mark Wheeler of Saratoga CA (US) for nvidia corporation
IPC Code(s): G06F40/284, G06F40/40
CPC Code(s): G06F40/284
Abstract: approaches presented herein provide for the performance of quality assurance-related tasks with respect to a representation of an environment, such as a set of generated map data. in particular, a language model can be used to generate a tokenized representation of a map using information such as the semantics, topology, and/or geometry determinable from the map data. a language model-generated representation can comply with real-world rules and constructs, and can account for omissions or errors in the input data based upon known relationships and semantics for various objects in the environment. one or more language models can be used to not only identify potential issues in the map data, but also to make recommendations for modifications and/or to generate plaintext descriptions of the issues, modifications, or recommendations to assist a human reviewer in addressing the issues.
Inventor(s): Fengqing Mai of Mountain View CA (US) for nvidia corporation, Xianglong Han of Sunnyvale CA (US) for nvidia corporation, Ming Cui of San Jose CA (US) for nvidia corporation
IPC Code(s): G06F40/284, G06N3/0455, G06N3/08
CPC Code(s): G06F40/284
Abstract: approaches presented herein provide for the training of a language model to provide human-style reasoning or “train-of-thought” support for generated inferences. in at least one embodiment, a language model can be used to assist in the generation and/or annotation of content for a specific domain or type of data. this can include, for example, tasks such as performing quality checks for high definition (hd), standard definition (sd), and/or navigational maps. in the mapping context, a language model can be trained using a large set of rules relevant to the mapping domain, in order to become a domain expert. in addition to training the language model on domain-specific rules and data, the language model can be further trained based at least in part on human feedback, such as corrections made to map data by an authorized human.
Inventor(s): Denis Laprise of Palo Alto CA (US) for nvidia corporation, Shuang Wu of Fremont CA (US) for nvidia corporation, Mark Wheeler of Saratoga CA (US) for nvidia corporation
IPC Code(s): G06F40/284, G01C21/32, G06F40/40
CPC Code(s): G06F40/284
Abstract: approaches presented herein provide for the generation of a realistic, higher resolution representation of an environment using a trained language model. in at least one embodiment, map data representative of at least a portion of the environment can be obtained. this map data can be processed using a language model to generate a first tokenized description of the environment based on the input map data. this first tokenized description, which may be in a domain-specific language, can be passed as input to a language model, such as the same language model, which can generate a second tokenized description of the environment that is also in the domain-specific language, but includes additional detail and thus provides a higher resolution representation. this additional detail may include filling in of gaps or accounting for omissions, but may also include inferring aspects such as continuous lanes or complex intersection topography not identified in the input map data. the additional detail may also include additional objects inferred to be appropriate for the environment.
Inventor(s): Denis Laprise of Palo Alto CA (US) for nvidia corporation, Shuang Wu of Fremont CA (US) for nvidia corporation, Ge Cong of Pleasanton CA (US) for nvidia corporation, Mark Wheeler of Saratoga CA (US) for nvidia corporation
IPC Code(s): G06F40/284, G06F40/30, G06F40/40
CPC Code(s): G06F40/284
Abstract: approaches presented herein provide for the ability to process, store, index, and search geospatial information such as maps with flexible granularity. a set of observations, such as may include sensor data captured for a region of an environment, can be fed as input to a language model. the language model can generate a tokenized description of the region, as may include a text string of tokens encapsulating semantics, topology, geometry, and/or other aspects of the region. a feature vector or embeddings for the region can be generated based on the tokenized description, and a similarity search performed against a vector database, for example, to identify similar feature vectors corresponding to similar regions or domains. labels or other information associated with these similar feature vectors can be automatically applied to the example region. clustering of feature vectors or other embeddings can also be performed based in part on the similarity.
Inventor(s): Xianchao Wu of Tokyo (JP) for nvidia corporation, Peiying Ruan of Kanazawa (JP) for nvidia corporation, Yi Dong of Lexington MA (US) for nvidia corporation
IPC Code(s): G06N3/0455, G10L15/18
CPC Code(s): G06N3/0455
Abstract: in various examples, techniques for accelerating inference in text and speech processing for conversational ai systems and applications is described herein. systems and methods are disclosed that use one or more techniques, such as token merging, in order to reduce a number of tokens processed by one or more machine learning models. for instance, the machine learning model(s) may process text and, based at least on the processing, generate scores (e.g., attention scores) indicating relationships between tokens associated with the text. the machine learning model(s) may then use the scores to merge at least one pair of the tokens. as described herein, the merging may reduce the overall number of tokens associated with the text while still maintaining the same semantic meaning as the original text. next, the machine learning model(s) may process the reduce number of tokens in order to determine an output associated with the text.
Inventor(s): Peter KARKUS of Zurich (CH) for nvidia corporation, Tong CHE of San Jose CA (US) for nvidia corporation, Christopher MAES of San Jose CA (US) for nvidia corporation, Shie MANNOR of Haifa (IL) for nvidia corporation, Marco PAVONE of Stanford CA (US) for nvidia corporation, Yunfei SHI of Santa Clara CA (US) for nvidia corporation, Heng YANG of Cambridge MA (US) for nvidia corporation
IPC Code(s): G06N3/092
CPC Code(s): G06N3/092
Abstract: one embodiment of a method for controlling a system includes generating a plurality of initializations using a trained machine learning model, performing a plurality of instances of an iterative technique based on the plurality of initializations to generate a plurality of results, generating a control signal based on one or more results included in the plurality of results, and transmitting the control signal to the system to cause the system to perform one or more operations.
Inventor(s): Shuang Wu of Fremont CA (US) for nvidia corporation, Denis Laprise of Palo Alto CA (US) for nvidia corporation, Mark Wheeler of Saratoga CA (US) for nvidia corporation, James Wu of Foster City CA (US) for nvidia corporation
IPC Code(s): G06T17/05, G06F40/284, G06F40/30
CPC Code(s): G06T17/05
Abstract: approaches presented herein provide for the generation of a text-based representation of an environment. in particular, a large language model (llm) can be used to generate a tokenized text string representation of an environment using information such as the semantics, topology, and geometry of the environment. a language model-generated representation can comply with real-world rules and constructs, and can account for omissions or errors in the input data based upon known relationships and semantics for various objects in the environment. such representations can be used to generate reconstructions of existing environments, correct or augment previously-constructed representations, or generate representations of new but realistic environments that comply with real-world rules. a text-based representation can comprise a one-dimensional string of tokens, which can encapsulate the important spatial information and semantics of an environment.
Inventor(s): Mehmet Kemal KOCAMAZ of San Jose CA (US) for nvidia corporation, Parthiv PARIKH of San Jose CA (US) for nvidia corporation, Baris Evrim DEMIROZ of Campbell CA (US) for nvidia corporation, Sangmin OH of San Jose CA (US) for nvidia corporation
IPC Code(s): G06V10/74, G06V10/86
CPC Code(s): G06V10/761
Abstract: in various examples, a technique for low-latency fusion and tracking of objects from multiple cameras is disclosed that includes determining a plurality of input objects and corresponding object characteristics, individual input objects and respective object characteristics being determined based at least on an image generated using a respective camera. the technique also includes identifying at least one subset of the plurality of input objects, the at least one subset corresponding to a respective physical object and comprising at least one input object that satisfies a similarity criterion. the technique further includes generating an output object associated with one or more smoothed object characteristics, the output object being generated based at least on two or more input objects included in the at least one subset of the plurality of input objects. the at least one subset corresponds to a physical object that is visible to two or more cameras.
Inventor(s): Cagri Erbagci of Pittsburgh PA (US) for nvidia corporation, Burak Erbagci of Pittsburgh PA (US) for nvidia corporation, Lalit Gupta of FREMONT CA (US) for nvidia corporation, Jesse San-Jey Wang of Santa Clara CA (US) for nvidia corporation
IPC Code(s): G11C7/12, G11C7/10
CPC Code(s): G11C7/12
Abstract: negative bit line voltage assist mechanisms for multi-bank machine memories utilizing multiple local io drivers include a shared boost capacitor configured to generate a negative bit line voltage assist for write operations by local io drivers, where the boost capacitor is configured to selectively couple to one of the local io drivers during the write operation.
NVIDIA Corporation patent applications on December 19th, 2024
- NVIDIA Corporation
- B60W60/00
- B60W40/02
- G06T3/00
- G06V20/58
- CPC B60W60/0016
- Nvidia corporation
- G01C21/34
- G06F40/284
- G08G1/0968
- CPC G01C21/34
- G01C21/00
- G06T7/73
- G06T11/20
- G06T17/00
- G06V10/764
- G06V10/82
- G06V20/56
- CPC G01C21/3841
- G06F11/267
- G06F1/3296
- G06F11/22
- G06F11/27
- G06F11/273
- CPC G06F11/267
- CPC G06F40/284
- G06V20/64
- G06F40/40
- G06N3/0455
- G06N3/08
- G01C21/32
- G06F40/30
- G10L15/18
- CPC G06N3/0455
- G06N3/092
- CPC G06N3/092
- G06T17/05
- CPC G06T17/05
- G06V10/74
- G06V10/86
- CPC G06V10/761
- G11C7/12
- G11C7/10
- CPC G11C7/12
