Vehicle Trajectory Planning Using Driver-Aware Path Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current intelligent vehicle trajectory planning methods are inadequate due to reliance on static obstacle trajectory analysis, leading to uncertainty and inaccurate predictions, especially when dealing with human-driven vehicles whose behavior is subjective and variable.
Innovation Solution
An intelligent driving domain controller that obtains and predicts vehicle trajectories using communication technology, determining driving modes (autonomous or manual) and employing customized trajectory prediction models based on historical driver data to accurately forecast vehicle paths, ensuring collision avoidance and improved safety.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If static obstacle trajectory analysis is used for path planning, then the path planning process is simple, but the prediction accuracy is low and collision risk increases
Solution Approach 1:
The system performs preliminary trajectory prediction for obstacles before actual path planning occurs. By predicting obstacle trajectories in advance using historical data and current state information, the system prepares collision avoidance strategies proactively rather than reactively, improving prediction accuracy while maintaining manageable complexity through structured data collection and processing
Solution Approach 2:
The patent introduces an intermediary prediction module that acts as a mediator between obstacle detection and path planning. This module processes obstacle trajectory data, applies prediction algorithms, and outputs predicted trajectories to the path planning system, effectively decoupling the complexity of prediction from the path planning logic while improving overall accuracy
2Reliability
If unified rule-based trajectory prediction is used, then the prediction method is simple and consistent, but it cannot accurately predict trajectories of human-driven vehicles with subjective behavior
Solution Approach 1:
The system dynamically adapts its prediction approach based on obstacle type. For human-driven vehicles, it employs more complex prediction models that consider behavioral patterns and historical data, while for autonomous vehicles it uses simpler rule-based predictions. This dynamic adjustment of model complexity based on the specific obstacle being tracked improves reliability without unnecessarily increasing overall system complexity
Solution Approach 2:
The patent changes prediction parameters based on the target vehicle's driving mode. When tracking human-driven vehicles, the system adjusts prediction parameters to account for subjective behavior patterns, using historical trajectory data and behavioral analysis. This parameter adaptation allows the system to handle the complexity of human behavior only when necessary, improving reliability for critical cases while maintaining simplicity for routine scenarios
3Loss of information
If only current moment obstacle data is used for prediction, then the data processing is fast and simple, but the prediction cannot account for dynamic trajectory changes over time
Solution Approach 1:
The system extracts only the essential historical trajectory information needed for prediction, rather than processing complete historical data. By selecting and extracting key positional and velocity data points from the past, the system maintains prediction accuracy while significantly reducing computational burden and processing time, thus minimizing information loss without excessive time cost
Data Source
Figure 1
Figure 2
Figure 3
AI summary
This application provides a method and an apparatus for planning a vehicle trajectory, an intelligent driving domain controller, and an intelligent vehicle, so that the intelligent vehicle implements accurate trajectory planning. The method includes: An intelligent driving domain controller of a first vehicle obtains a first trajectory of the first vehicle, obtains a second trajectory of at least one second vehicle based on a first communications technology, and then determines trajectory planning of the first vehicle based on the first trajectory and the second trajectory of the at least one second vehicle. In this way, a vehicle predicts a vehicle trajectory by using different rules, to more accurately plan a driving trajectory of the vehicle, and driving safety of the intelligent vehicle is improved.