Tesla patents system to pick which car sensor data helps train its AI
This patent describes a method where a car's main computer runs a neural network on camera and sensor data. If the system detects a situation it cannot confidently classify, a secondary 'trigger' network evaluates the data to decide if it is worth sending back to Tesla's servers to improve the software.
In the filing’s own words
Systems and methods for obtaining training data are described. An example method includes receiving sensor and applying a neural network to the sensor data. A trigger classifier is applied to an intermediate result of the neural network to determine a classifier score for the sensor data. Based at least in part on the classifier score, a determination is made whether to transmit via a computer network at least a portion of the sensor data. Upon a positive determination, the sensor data is transmitted and used to generate training data.
What exactly they claim (claim 1)
1. A method, comprising: receiving, by at least one processor, sensor data representing surroundings of a vehicle; executing, by the at least one processor, a first neural network to the sensor data to cause the first neural network to generate an intermediate result at an intermediate layer of the first neural network independent from outputs generated by trigger classifiers configured to receive the intermediate result as input, the first neural network configured to process a set of features of the surroundings of the vehicle to generate an output that is not based on outputs generated by trigger classifiers; determining, by the at least one processor, that the intermediate result meets a first trigger condition of one or more trigger conditions indicating that the first neural network cannot make a predetermined classification; in response to determining that the intermediate result meets the first trigger condition, executing, by the at least one processor, a second neural network comprising a trigger classifier independently trained remote from the vehicle using previous intermediate results for a target use case to process the intermediate result as an input from the first neural network to cause the trigger classifier to determine a classifier score for the sensor data associated with the intermediate result, the classifier score indicating a real-world object, a scenario, or a feature in the surroundings of the vehicle; determining, by the at least one processor, to transmit via a computer network at least a portion of the sensor data associated with the intermediate result in response to determining the classifier score, wherein the determining to transmit includes comparing the classifier score with a threshold value; and transmitting, by the at least one processor, the at least a portion of the sensor data associated with the intermediate result for use as training data for retraining the first neural network or a different neural network.
Facts
- Company
- Tesla (Tesla, Inc.)
- Official title
- System and method for obtaining training data
- Patent number
- US12792972B2
- Application number
- 17250825
- Filed
- Sep 13, 2019
- Granted
- Nov 10, 2026
- Inventors
- 1
- Claims
- 20
Classified under
G06N 20/10 Physics & computingG05D 1/0246 Physics & computingG06V 10/764 Physics & computingG06V 10/774 Physics & computingG06V 10/82 Physics & computingG06V 20/56 Physics & computingMore from Tesla in AI & software
- Tesla patents method to train self-driving software using simulated driving Oct 6, 2026
- Tesla patents method to share object labels between different car sensors Sep 17, 2026
- Tesla patents faster math for car navigation AI Oct 1, 2026
- Tesla patents faster math for self-driving AI Oct 1, 2026
- Tesla patents method to speed up AI calculations in self-driving cars Oct 1, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.