Autonomous Driving Prediction Using Leader-Follower Path Evaluation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous driving systems rely solely on real-time sensor data for collision risk assessment, which is inadequate for ensuring the accuracy of predicted driving information, especially in complex traffic environments with multiple participants.
Innovation Solution
A method and apparatus that determine a leader-follower relationship between a target vehicle and obstacles based on motion parameters and path information, using high-definition maps and real-time perception, to predict and evaluate optimal driving information through forward simulation and evaluation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If the system relies solely on real-time sensor data for collision risk assessment, then the system complexity is reduced, but the accuracy of predicted driving information deteriorates
Solution Approach 1:
The system performs preliminary path prediction for multiple traffic participants before making collision risk assessment decisions. By predicting future paths of the ego vehicle and surrounding traffic participants ahead of time, the system accumulates necessary information that improves assessment accuracy without requiring complex real-time calculations during critical decision moments
Solution Approach 2:
The system introduces an intermediary evaluation mechanism that assesses collision risk by comparing predicted paths with safety constraints. This intermediary evaluation layer processes the relationship between multiple traffic participants' predicted trajectories and identifies potential collision risks, thereby improving prediction accuracy through structured intermediate analysis
2Measurement precision
If the system analyzes leader-follower relationships and future paths of multiple traffic participants, then the accuracy of collision risk assessment is improved, but the computational complexity increases
Solution Approach 1:
The system segments the complex traffic environment into independent leader-follower relationship pairs. By identifying and analyzing each relationship separately (e.g., ego vehicle as leader/follower relative to different obstacles), the system breaks down the overall computational problem into manageable segments that can be processed independently and efficiently
Solution Approach 2:
The system applies different analysis depths to different traffic scenarios based on their local characteristics. For critical leader-follower relationships with potential collision risks, the system performs detailed path prediction and evaluation, while for less critical scenarios, it uses simplified assessment methods, thereby optimizing computational resource allocation
3Speed
If the system uses real-time sensor data only, then the response speed is fast, but the reliability of driving information prediction deteriorates
Solution Approach 1:
The system performs preliminary path predictions for multiple traffic participants using current sensor data before actual collision risk events occur. By pre-calculating expected trajectories and positions, the system prepares prediction results in advance, ensuring both fast response when needed and improved reliability through pre-validated predictions
Data Source
AI summary
Provided is a driving information prediction method, apparatus, and autonomous driving vehicle, which relate to the field of autonomous driving, especially to the field of artificial intelligence, and particularly to the technical fields of autonomous driving and intelligent transportation. The method includes: determining a first leader-follower relationship between a target vehicle and a first obstacle based on a motion parameter of the target vehicle at a current moment, path information of the target vehicle within a first time period, a motion parameter of the first obstacle at the current moment, and predicted path information of the first obstacle within the first time period; obtaining first predicted driving information based on the first leader-follower relationship; and determining first optimal driving information based on an evaluation result corresponding to the first predicted driving information.