Driver-Aware Vehicle Trajectory Prediction for Inattentive Driving
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle trajectory prediction systems rely on assumptions about driver awareness, which can lead to inaccurate predictions and potentially dangerous situations, especially when drivers are not attentive to adjacent vehicles.
Innovation Solution
A trajectory prediction system that determines a driver's awareness of adjacent vehicles by monitoring their gaze and awareness of objects in the environment, altering past track data of adjacent vehicles based on this awareness, and transmitting altered data to a prediction module to generate more accurate future trajectories.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If driver awareness is not considered in trajectory prediction, then the prediction system is simpler and faster, but the prediction accuracy deteriorates when drivers are inattentive
Solution Approach 1:
The patent introduces driver awareness state as an intermediary variable that mediates between raw sensor data and trajectory predictions. The system uses eye tracking and attention models to determine whether the driver is aware of surrounding vehicles, then adjusts predictions based on this intermediate awareness state rather than directly processing all raw sensor inputs
Solution Approach 2:
The prediction system is segmented into multiple independent modules: a driver monitoring module that tracks awareness state, a trajectory prediction module that generates predictions, and an adjustment module that modifies predictions based on awareness state. This segmentation allows each module to operate independently and improves overall system manageability
2Reliability
If driver awareness monitoring is added to improve prediction accuracy, then trajectory predictions become more reliable, but the system complexity and computational load increase
Solution Approach 1:
The system performs preliminary assessment of driver awareness state continuously in the background using eye tracking and attention models before critical prediction moments occur. This preliminary action ensures that when trajectory predictions are needed, the awareness state is already determined and ready for immediate use
Solution Approach 2:
The driver monitoring system uses the vehicle's existing sensor infrastructure (cameras, eye trackers) to self-determine driver awareness state without requiring external monitoring equipment. The system serves itself by utilizing its own computational resources to analyze driver behavior patterns
3Measurement precision
If the system monitors driver gaze and awareness continuously, then prediction accuracy improves, but energy consumption and processing time increase
Solution Approach 1:
Instead of continuous monitoring at maximum resolution, the system uses periodic sampling of driver gaze direction and awareness state at strategically chosen intervals. The monitoring intensity is adjusted periodically based on driving conditions, reducing computational load during low-risk periods while maintaining accuracy during critical situations
Solution Approach 2:
The system applies full monitoring resources only when partially needed - specifically when the driver's gaze deviates from the road or when surrounding vehicles are detected. During normal driving conditions, the system uses reduced monitoring intensity, applying excessive action only when necessary to maintain safety
Data Source
AI summary
Systems, methods, and other embodiments described herein relate to predicting future trajectories of ado vehicles and an ego vehicle based on the awareness of the driver of the ego vehicle towards the ado vehicles. In one embodiment, a method includes determining an awareness of a driver of an ego vehicle to ado vehicles in the vicinity of the ego vehicle. The method also includes altering track data of ado vehicles based on a lack of awareness of the driver towards the ado vehicles. The method also includes transmitting altered track data of the ado vehicles to a prediction module. The prediction module predicts future trajectories of the ado vehicles and the ego vehicle based on the altered track data and an ego vehicle track data.