Target Intention Prediction Using Time-Continuous Velocity Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current obstacle prediction methods for vehicles, especially in complex urban environments, are inaccurate due to their failure to consider time continuity and the dynamic nature of obstacles, leading to inefficient collision avoidance in automated driving systems.
Innovation Solution
A target intention predicting method and system that involves obtaining and mapping host vehicle and target datasets to a high-resolution map, calculating updated velocities, and predicting future target positions by considering time continuity and classifying targets to adjust prediction accuracy, allowing for efficient obstacle avoidance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional obstacle prediction methods are used that predict motion based on single time point data, then the analysis process is simple, but the prediction accuracy deteriorates due to ignoring time continuity
Solution Approach 1:
The system performs preliminary actions by collecting and storing target position and velocity data across multiple time points before making predictions. This preliminary data accumulation enables more accurate prediction by considering time continuity, resolving the contradiction between simple analysis and accurate prediction.
Solution Approach 2:
The system transitions from static single-time-point analysis to dynamic multi-time-point analysis. By continuously updating target velocity and position data over time, the system adapts to changing motion patterns, improving prediction accuracy while managing complexity through systematic data processing.
2Adaptability or versatility
If multi-directional intersection environments with mixed traffic are analyzed using conventional methods, then the system can handle diverse traffic scenarios, but the analysis accuracy deteriorates due to changeable obstacle tracks
Solution Approach 1:
The system handles dynamic traffic scenarios by continuously updating target velocity and position data across multiple time points. This dynamic approach allows the system to adapt to changeable obstacle tracks in multi-directional intersections while maintaining high prediction accuracy through time-continuous analysis.
Solution Approach 2:
The system segments the complex traffic environment into individual target objects, each with its own trajectory and velocity characteristics. By analyzing each target separately across multiple time points, the system can handle diverse traffic scenarios accurately without being overwhelmed by environmental complexity.
Data Source
AI summary
A target intention predicting method including a dataset obtaining step and a calculating and map mapping step is provided. A host vehicle positioning dataset of a host vehicle and a plurality of target datasets of a target are obtained. Each of the target datasets corresponds to each of a plurality of time points of a time line, and each of the target datasets includes a target position and a target velocity. The host vehicle positioning dataset is mapped to a map. The target position at the last one of the time points is mapped to the map. An updated velocity of the target is calculated according to the target velocities of the target datasets, and the updated velocity is mapped to the map to predicting a target future position of the target on the map at a future time point according to the updated velocity.