Traffic Prediction Using Vehicle Density and Spacing Sensors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current traffic information prediction methods rely on past speed patterns, which are inadequate due to changes in weather, season, and traffic volume, leading to errors in speed prediction, especially when limited by the number of vehicle probe samples.
Innovation Solution
A device and method that utilize inter-vehicle spacing and density data from sensors to estimate vehicle density, incorporating deep learning for accurate speed prediction, allowing for the derivation of travel speed in consistent traffic conditions and improving prediction accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If past pattern speed is used for prediction, then prediction can be performed based on historical data, but prediction accuracy deteriorates due to changing weather, season, and traffic volume
Solution Approach 1:
The patent changes the prediction parameter from time-zone based speed patterns to density-based speed patterns. Instead of predicting speed based on time of day, the system uses vehicle density as the key parameter, allowing the prediction model to adapt to changing traffic conditions, weather, and seasonal variations by focusing on the actual density state rather than temporal patterns.
Solution Approach 2:
The system incorporates real-time density measurements from sensors into the prediction model, creating a feedback mechanism where current density data continuously updates the prediction. This allows the model to adjust to changing conditions dynamically, improving both accuracy and adaptability by incorporating current state information rather than relying solely on historical patterns.
2Reliability
If vehicle probe samples are used for prediction, then macroscopic congestion prediction is possible, but microscopic speed prediction for each time zone is limited due to sample constraints
Solution Approach 1:
The patent introduces density as an intermediary variable that bridges the gap between macroscopic probe data and microscopic speed predictions. Density serves as a mediator that can be reliably estimated from limited probe samples while still enabling accurate speed predictions for specific time zones and link units, overcoming the sample limitation by using density as an intermediate representation of traffic state.
Solution Approach 2:
The system changes the approach from directly using probe speed data to using density as the key parameter. By transforming the prediction basis from raw probe samples to density estimates, the system can achieve reliable microscopic predictions even with limited sample data, as density provides a more robust statistical foundation for prediction.
3Measurement precision
If density data is collected from sensors, then objective traffic condition determination is achieved, but data collection complexity increases
Solution Approach 1:
The patent makes the sensor system multi-functional by using the same density measurement infrastructure for multiple purposes: objective traffic condition determination, speed prediction, and congestion detection. This universal approach improves measurement precision while managing device complexity by consolidating functions into a single density estimation system rather than requiring separate specialized sensors for each function.
Data Source
AI summary
A device and a method for predicting traffic information are provided. The traffic information predicting device may include a data calculating device configured to derive inter-vehicle spacings, inter-vehicle head spacings, and a vehicle density using a plurality of sensors mounted on a vehicle, and a predicting device configured to derive travel speed data corresponding to the vehicle density and predict traffic information.