System And Method For Obtaining Training Data
Patent No. EP3850549 (titled "System And Method For Obtaining Training Data") was filed by Tesla on Sep 13, 2019. The application was issued on May 28, 2025.
Patent Summary
A vehicle-based processor system implements a method for neural network improvement by receiving sensor data, including images, and processing it via a neural network. A trigger classifier, trained on a remote system using a dataset of specific features of interest (e.g., edge-case objects), is applied to an intermediate neural network result to generate a classifier score. If the score exceeds a threshold, indicating the presence of the features of interest, the system transmits the sensor data to the remote system via a computer network. The remote system uses this data to train an updated neural network, which is then transmitted back to the vehicle. The vehicle subsequently utilizes the updated neural network to control the vehicle.
Patent Family
Patent Oppositions
Patent oppositions filed by competitors challenge the validity of a granted patent. These oppositions are typically based on claims of prior art, lack of novelty, or non-obviousness. They are a key part of the process for determining a patent's strength and enforceability.
Dossier Documents
The dossier documents provide a comprehensive record of the patent's prosecution history - including filings, correspondence, and decisions made by patent offices - and are crucial for understanding the patent's legal journey and any challenges it may have faced during examination.
Date
Description
EP3850549
- Application Number
- EP19859523A
- Filing Date
- Sep 13, 2019
- Status
- Granted And Under Opposition
- Apr 25, 2025
- Publication Date
- May 28, 2025
- External Links
- Slate, Register , Google Patents