18183052. EVALUATING YIELD PREDICTION MODEL PERFORMANCE simplified abstract (GM Cruise Holdings LLC)
Contents
EVALUATING YIELD PREDICTION MODEL PERFORMANCE
Organization Name
Inventor(s)
Can Cui of San Francisco CA (US)
Prathyush Katukojwala of Pasadena CA (US)
EVALUATING YIELD PREDICTION MODEL PERFORMANCE - A simplified explanation of the abstract
This abstract first appeared for US patent application 18183052 titled 'EVALUATING YIELD PREDICTION MODEL PERFORMANCE
The disclosed technology involves evaluating the performance of a yield prediction model used in path planning decisions for autonomous vehicles.
- Legacy road data is received and AV plan information is extracted from it, including the original path selected by the AV.
- The legacy road data is provided to a yield prediction model to generate predictions for entities in the environment.
- An alternate path is determined based on the yield predictions, and the model is evaluated using the original and alternate paths.
- Key Features and Innovation:**
- Utilizes legacy road data to inform path planning decisions for autonomous vehicles.
- Evaluates the performance of a yield prediction model in real-world scenarios.
- Provides a method for generating alternate paths based on yield predictions.
- Potential Applications:**
- Autonomous vehicle navigation systems.
- Traffic management and optimization.
- Urban planning and infrastructure development.
- Problems Solved:**
- Enhances the accuracy of path planning decisions for autonomous vehicles.
- Improves safety and efficiency in navigating complex environments.
- Optimizes traffic flow and reduces congestion.
- Benefits:**
- Increased reliability and performance of autonomous vehicles.
- Enhanced safety for passengers and pedestrians.
- Improved overall traffic management and urban mobility.
- Commercial Applications:**
- Automotive industry for autonomous vehicle development.
- Transportation and logistics companies for fleet management.
- Smart city initiatives for urban planning and infrastructure optimization.
- Questions about Autonomous Vehicle Path Planning:**
1. How does the technology improve the safety of autonomous vehicles in complex environments? 2. What are the potential implications of using yield prediction models in urban traffic management?
- Frequently Updated Research:**
Ongoing research in the field of autonomous vehicle navigation and traffic optimization may provide further insights into the effectiveness of yield prediction models in real-world scenarios.
Original Abstract Submitted
Aspects of the disclosed technology provide solutions for evaluating the performance of a yield prediction model that is used to inform path planning decisions made by a planning module of an autonomous vehicle (AV) software stack. In some aspects, a process of the disclosed technology includes steps for receive legacy road data, extracting AV plan information from the legacy road data, the AV plan information comprising an original path selected by the AV for navigating through the environment, and providing the legacy road data to a yield prediction model to generate a yield prediction for each of the one or more entities in the environment. In some aspects, the process can further include steps for determining an alternate path based on the yield prediction for each of the one or more entities, and evaluating the yield prediction model based on the original path selected by the AV and the alternate path. Systems and machine-readable media are also provided.
