Nvidia corporation (20240183752). SIMULATING REALISTIC TEST DATA FROM TRANSFORMED REAL-WORLD SENSOR DATA FOR AUTONOMOUS MACHINE APPLICATIONS simplified abstract

SIMULATING REALISTIC TEST DATA FROM TRANSFORMED REAL-WORLD SENSOR DATA FOR AUTONOMOUS MACHINE APPLICATIONS

Organization Name

nvidia corporation

Inventor(s)

Jesse Hong of Edgewater NJ (US)

Urs Muller of Keyport NJ (US)

Bernhard Firner of Highland Park NJ (US)

Zongyi Yang of Eatontown NJ (US)

Joyjit Daw of New York NY (US)

David Nister of Bellevue WA (US)

Roberto Giuseppe Luca Valenti of Holmdel NJ (US)

Rotem Aviv of San Diego CA (US)

SIMULATING REALISTIC TEST DATA FROM TRANSFORMED REAL-WORLD SENSOR DATA FOR AUTONOMOUS MACHINE APPLICATIONS - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240183752 titled 'SIMULATING REALISTIC TEST DATA FROM TRANSFORMED REAL-WORLD SENSOR DATA FOR AUTONOMOUS MACHINE APPLICATIONS

Simplified Explanation

The abstract of the patent application describes a method for generating test data for vehicle functions using real-world sensor data. The sensor data is transformed or augmented to represent different test scenarios, and the efficacy of the vehicle system is evaluated based on the processed test data.

• Real-world sensor data is recorded and used to generate additional or transformed sensor data for testing vehicle functions.
• The generated test data is processed by the vehicle system to evaluate its performance against test criteria.
• The method allows for testing vehicles in a variety of scenarios by creating test sets with different instances of sensor data.

Potential Applications

The technology can be applied in the automotive industry for testing advanced driver assistance systems (ADAS) and autonomous vehicles.

Problems Solved

1. Efficient testing of vehicle functions in various scenarios without the need for extensive real-world testing. 2. Ensuring the reliability and effectiveness of ADAS and autonomous vehicle systems through comprehensive testing.

Benefits

1. Cost-effective testing of vehicle functions using simulated test profiles. 2. Improved safety and performance of ADAS and autonomous vehicles through rigorous testing. 3. Accelerated development and deployment of advanced vehicle technologies.

Potential Commercial Applications

Optimizing testing processes for automotive manufacturers and suppliers to ensure the quality and reliability of ADAS and autonomous vehicle systems.

Possible Prior Art

One possible prior art could be the use of simulation software to test vehicle functions, but the specific method of generating test data from real-world sensor data may be a novel approach.

How does this technology impact the development timeline of new vehicle functions?

The technology allows for faster and more efficient testing of vehicle functions, potentially speeding up the development timeline of new features.

What are the potential limitations of using simulated test data compared to real-world testing?

Simulated test data may not fully capture the complexity and variability of real-world driving scenarios, which could impact the accuracy of the test results.

Original Abstract Submitted

in various examples, sensor data recorded in the real-world may be leveraged to generate transformed, additional, sensor data to test one or more functions of a vehicle—such as a function of an aeb, cmw, ldw, alc, or acc system. sensor data recorded by the sensors may be augmented, transformed, or otherwise updated to represent sensor data corresponding to state information defined by a simulation test profile for testing the vehicle function(s). once a set of test data has been generated, the test data may be processed by a system of the vehicle to determine the efficacy of the system with respect to any number of test criteria. as a result, a test set including additional or alternative instances of sensor data may be generated from real-world recorded sensor data to test a vehicle in a variety of test scenarios.