18183046. MINING LEGACY ROAD DATA TO TRAIN AN AUTONOMOUS VEHICLE YIELD PREDICTION MODEL simplified abstract (GM Cruise Holdings LLC)
Contents
MINING LEGACY ROAD DATA TO TRAIN AN AUTONOMOUS VEHICLE YIELD PREDICTION MODEL
Organization Name
Inventor(s)
Prathyush Katukojwala of Pasadena CA (US)
Nidhi Hiremath of Oakland CA (US)
Can Cui of San Francisco CA (US)
MINING LEGACY ROAD DATA TO TRAIN AN AUTONOMOUS VEHICLE YIELD PREDICTION MODEL - A simplified explanation of the abstract
This abstract first appeared for US patent application 18183046 titled 'MINING LEGACY ROAD DATA TO TRAIN AN AUTONOMOUS VEHICLE YIELD PREDICTION MODEL
Simplified Explanation: The technology disclosed in the patent application focuses on evaluating the performance of a planning module in an autonomous vehicle software stack by analyzing road data collected by the vehicle's sensors.
- The process involves receiving road data from the vehicle's sensors.
- The road data is provided to a planning module to determine yield projections for entities on the road.
- A yield prediction model is used to determine yield predictions for these entities.
- The performance of the planning module is then evaluated based on the yield projections and predictions for the entities.
- Systems and machine-readable media are also included in the technology.
Key Features and Innovation: - Evaluation of planning module performance in autonomous vehicles - Analysis of road data collected by vehicle sensors - Yield projections and predictions for entities on the road - Use of a yield prediction model - Systems and machine-readable media provided
Potential Applications: This technology can be applied in the development and improvement of autonomous vehicle software systems, enhancing their ability to predict and plan for various scenarios on the road.
Problems Solved: - Assessing the performance of planning modules in autonomous vehicles - Utilizing road data effectively for yield projections and predictions - Enhancing the overall functionality and safety of autonomous vehicles
Benefits: - Improved performance evaluation of planning modules - Enhanced predictive capabilities for entities on the road - Increased safety and efficiency in autonomous vehicle operations
Commercial Applications: Potential commercial applications of this technology include autonomous vehicle development, transportation systems, and smart city initiatives aimed at improving traffic flow and safety.
Prior Art: Prior research in the field of autonomous vehicles and artificial intelligence may provide insights into similar technologies or methodologies for evaluating planning module performance.
Frequently Updated Research: Stay informed about the latest advancements in autonomous vehicle technology, artificial intelligence, and predictive modeling to enhance the understanding and application of this innovative solution.
Questions about Autonomous Vehicle Planning Module Evaluation: 1. How does the technology in the patent application improve the performance evaluation of planning modules in autonomous vehicles? 2. What are the key components of the process for analyzing road data and determining yield projections and predictions for entities on the road?
Original Abstract Submitted
Aspects of the disclosed technology provide solutions for evaluating the performance of a planning module (or planning layer) of an autonomous vehicle (AV) software stack. In some aspects, a process of the disclosed technology can include steps for receiving road data comprising sensor data collected by an autonomous vehicle (AV), providing the road data to a planning module of the AV to determine a yield projection for each of the one or more entities, and providing the road data to a yield prediction model to determine a yield prediction for each of the one or more entities. In some aspects, the process can further include steps for evaluating a performance of the planning module of the AV based on the yield projection for each of the one or more entities and the yield prediction for each of the one or more entities. Systems and machine-readable media are also provided.
