18093479. PSEUDO-RANDOM SEQUENCES FOR SELF-SUPERVISED LEARNING OF TRAFFIC SCENES simplified abstract (GM Cruise Holdings LLC)
Contents
PSEUDO-RANDOM SEQUENCES FOR SELF-SUPERVISED LEARNING OF TRAFFIC SCENES
Organization Name
Inventor(s)
Chingiz Tairbekov of San Francisco CA (US)
PSEUDO-RANDOM SEQUENCES FOR SELF-SUPERVISED LEARNING OF TRAFFIC SCENES - A simplified explanation of the abstract
This abstract first appeared for US patent application 18093479 titled 'PSEUDO-RANDOM SEQUENCES FOR SELF-SUPERVISED LEARNING OF TRAFFIC SCENES
The abstract describes a method for generating self-supervised neural networks using pseudo-random sequences of traffic scenes for training autonomous vehicles.
- Obtaining sensor data collected for a scene associated with an autonomous vehicle.
- Generating numerical representations of the sensor data to represent elements in the scene.
- Determining the semantic meaning of the numerical representations using a neural network.
Potential Applications: - Autonomous driving systems - Robotics - Computer vision technology
Problems Solved: - Enhancing the training of neural networks for autonomous vehicles - Improving the understanding of sensor data in complex scenes
Benefits: - Increased accuracy and efficiency in autonomous vehicle systems - Enhanced safety and reliability in self-driving technology
Commercial Applications: Self-driving car technology: This innovation can be applied to enhance the performance and safety of autonomous vehicles, leading to potential commercial applications in the automotive industry.
Questions about self-supervised neural networks for autonomous vehicles: 1. How does this method improve the training of neural networks for autonomous vehicles? 2. What are the potential implications of using pseudo-random sequences of traffic scenes for self-supervised training?
Original Abstract Submitted
Systems and techniques are provided for generating self-supervised neural networks and using pseudo-random sequences of traffic scenes for self-supervised training. An example method can include obtaining sensor data collected for a scene associated with an autonomous vehicle (AV), the sensor data describing, measuring, or depicting one or more elements in the scene; generating one or more sets of numerical representations of the sensor data, wherein each numerical representation of the one or more sets of numerical representations represents at least one element of the one or more elements; and determine, via a neural network, a semantic meaning of at least one numerical representation from the one or more sets of numerical representations of the sensor data, the at least one numerical representation corresponding to the at least one element of the one or more elements.
