NVIDIA had 135 patents in robotics during Q2 2024. NVIDIA Corp filed patents in Q2 2024 related to improving efficiency in processing authorization requests for cloud-based services, determining associations between objects in sensor data for autonomous vehicle perception systems, generating digital representations of environments with multiple objects, training machine learning models for specific domains, and estimating object poses for collision-free motion generation. These patents involve techniques such as using neural network models, location tracking data, keypoint predictions, and segmentation of objects in the environment. GlobalData’s report on NVIDIA gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
Access deeper industry intelligence
Experience unmatched clarity with a single platform that combines unique data, AI, and human expertise.
NVIDIA had no grants in robotics as a theme in Q2 2024.
Recent Patents
Application: Determining object associations using machine learning in autonomous systems and applications (Patent ID: US20240211748A1)
The patent filed by NVIDIA Corp. describes systems and methods for determining associations between objects in sensor data and predicted states of those objects in multi-sensor systems, particularly in autonomous or semi-autonomous vehicle perception systems. The disclosed systems use neural network models, such as multi-layer perceptron (MLP) models, to learn association costs between sensor measurements and predicted object states. During training, the systems generate data to update the neural network parameters, allowing the models to provide association costs between sensor data and predicted states during deployment.
The patent includes claims for a processor that determines predicted object states, generates association scores using neural network models based on sensor data and input parameters, and updates environmental data based on the association scores. The processor can be part of various systems, including control systems for autonomous machines, perception systems, simulation operations, deep learning operations, and more. Additionally, methods are described for determining predicted object states, generating association scores based on neural network models processing multi-sensor data, and updating object tracks accordingly. The methods involve using MLP models, input parameters related to predicted states or sensor identification, and generating neural network models based on modeling data.
To know more about GlobalData’s detailed insights on NVIDIA, buy the report here.
Data Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.
