Waymo LLC (20240311269). SIMULATOR METRICS FOR AUTONOMOUS DRIVING simplified abstract
Contents
SIMULATOR METRICS FOR AUTONOMOUS DRIVING
Organization Name
Inventor(s)
Brandyn Allen White of Mountain View CA (US)
Alex Richard Kuefler of San Jose CA (US)
Paul Marie Vincent Mougin of Oxford (GB)
SIMULATOR METRICS FOR AUTONOMOUS DRIVING - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240311269 titled 'SIMULATOR METRICS FOR AUTONOMOUS DRIVING
Simplified Explanation: The patent application describes methods, systems, and apparatus for selecting simulators to evaluate control software for autonomous vehicles. It involves receiving data on a driving scenario, generating simulations using a simulator, and determining the realism of the simulator based on predicted values compared to actual values.
Key Features and Innovation:
- Selecting simulators for evaluating control software for autonomous vehicles
- Receiving data on driving scenarios and low-level statistics
- Generating simulations using a simulator
- Determining the realism of the simulator based on predicted values
- Assessing the likelihood of the simulator accurately representing the driving scenario
Potential Applications: This technology can be applied in the development and testing of control software for autonomous vehicles, ensuring that simulators accurately represent real-world driving scenarios.
Problems Solved: The technology addresses the challenge of selecting appropriate simulators to evaluate control software for autonomous vehicles accurately.
Benefits:
- Improved accuracy in evaluating control software for autonomous vehicles
- Enhanced realism in simulator-based testing
- Efficient development and testing processes for autonomous vehicle technology
Commercial Applications: Potential commercial applications include software development companies, automotive manufacturers, and research institutions working on autonomous vehicle technology.
Prior Art: Prior art related to this technology may include research on simulator-based testing for autonomous vehicles and control software evaluation methods.
Frequently Updated Research: Ongoing research in this field may focus on enhancing simulator realism, improving predictive modeling for driving scenarios, and optimizing control software evaluation processes.
Questions about Autonomous Vehicle Simulator Selection: 1. How does this technology improve the accuracy of evaluating control software for autonomous vehicles? 2. What are the potential commercial implications of using simulators to test autonomous vehicle technology?
Original Abstract Submitted
methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting simulators for evaluating control software for autonomous vehicles. in one aspect, a system comprises: receiving data specifying a driving scenario in an environment; receiving an actual value of a low-level statistic measuring a corresponding property of the driving scenario; generating simulations of the driving scenario using a simulator; determining, for each simulation, a respective predicted value of the low-level statistic that measures the corresponding property of the simulation; determining, from the respective predicted values for the simulations, a likelihood assigned to the actual value of the low-level statistic by the simulations; and determining, from the likelihood, a low-level metric for the simulator and for the driving scenario that measures a realism of the simulator with respect to the corresponding property of the driving scenario.
