18183040. YIELD PREDICTION MODEL TO COMPUTE AUTONOMOUS VEHICLE TRAJECTORIES simplified abstract (GM Cruise Holdings LLC)
Contents
YIELD PREDICTION MODEL TO COMPUTE AUTONOMOUS VEHICLE TRAJECTORIES
Organization Name
Inventor(s)
Can Cui of San Francisco CA (US)
Prathyush Katukojwala of Pasadena CA (US)
YIELD PREDICTION MODEL TO COMPUTE AUTONOMOUS VEHICLE TRAJECTORIES - A simplified explanation of the abstract
This abstract first appeared for US patent application 18183040 titled 'YIELD PREDICTION MODEL TO COMPUTE AUTONOMOUS VEHICLE TRAJECTORIES
The present disclosure pertains to improving autonomous vehicle (AV) navigation by enhancing AV decisions on when to yield to other vehicles in different driving scenarios.
- Receiving road data containing sensor data collected by an AV
- Extracting trajectory data for each entity from the road data
- Providing the trajectory data to a machine-learning model trained to predict yields for each entity
- Determining the AV's path based on the yield predictions for each entity
Potential Applications: - Autonomous driving systems - Traffic management systems - Vehicle safety technologies
Problems Solved: - Enhancing AV decision-making in yielding to other vehicles - Improving overall road safety and efficiency
Benefits: - Increased safety on the roads - Smoother traffic flow - Enhanced efficiency in AV navigation
Commercial Applications: Title: Autonomous Vehicle Yield Prediction System This technology can be utilized in autonomous vehicle systems, traffic management solutions, and vehicle safety applications. It has the potential to revolutionize the way AVs interact with other vehicles on the road, leading to safer and more efficient transportation systems.
Prior Art: Readers can explore prior research on machine learning models for AV navigation and yield predictions to gain a deeper understanding of the advancements in this field.
Frequently Updated Research: Stay updated on the latest developments in machine learning algorithms for AV navigation and real-time yield predictions to ensure the most cutting-edge applications of this technology.
Questions about Autonomous Vehicle Yield Prediction System:
1. How does this technology contribute to the advancement of autonomous driving systems? This technology enhances the decision-making process of AVs, leading to safer and more efficient navigation on the roads.
2. What are the potential implications of this innovation on traffic management systems? By improving yield predictions, this innovation can optimize traffic flow and reduce congestion on roadways.
Original Abstract Submitted
The present disclosure generally relates to autonomous vehicle (AV) navigation and, more specifically, to improving AV determinations regarding when to yield to other vehicles (entities) in various driving scenarios. In some aspects, a process of the disclosed technology includes steps for receiving road data comprising sensor data collected by an autonomous vehicle (AV), extracting trajectory data from the road data, for each of the one or more entities, and providing the trajectory data to a machine-learning (ML) model, wherein the ML model is trained to generate a yield prediction for each of the one or more entities. In some aspects, the process can further include steps for determining a path for the AV based on the yield prediction for each of the one or more entities. Systems and machine-readable media are also provided.
