Road-Section Weighting for Junction-Aware Speed Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for predicting vehicle arrival time and speed fail to accurately reflect real-time traffic conditions, especially at junctions, interchanges, and intersections, due to uniform weighting of road sections, leading to inaccurate speed and arrival time estimations.
Innovation Solution
A speed prediction device and method that selects specific road sections and rear sections for weighting, using an artificial neural network to predict future speeds by processing driving information, time information, and congestion indicators, and generating predicted speeds through a trained model.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If uniform weighting is applied to all road sections for speed estimation, then the calculation process is simple, but the prediction accuracy deteriorates because actual traffic conditions at junctions, interchanges, and intersections are not reflected correctly
Solution Approach 1:
The patent applies different weighting factors to different road sections based on their local characteristics. Specifically, junction sections (JC), interchange sections (IC), and intersection sections are assigned different weights from ordinary road sections. This local differentiation allows the system to account for varying traffic conditions at different locations, improving prediction accuracy while maintaining a relatively simple calculation framework.
2Measurement precision
If real-time traffic data collection is implemented for accurate arrival time prediction, then the prediction accuracy improves, but the system complexity and data processing requirements increase
Solution Approach 1:
The patent divides the road network into distinct segments or sections (ordinary sections, junction sections, interchange sections, intersection sections). By segmenting the road into these manageable units with specific characteristics, the system can collect and process traffic data in a structured manner. This segmentation reduces the overall complexity by breaking down the large-scale data collection problem into smaller, more manageable sections that can be processed independently and then aggregated.
3Adaptability or versatility
If AI technology is used to predict traffic conditions, then the ability to reflect real-time varying traffic conditions improves, but the computational requirements and processing time increase
Solution Approach 1:
The patent employs machine learning models to predict traffic conditions in advance for upcoming road sections. By performing preliminary predictions using historical data and current traffic patterns, the system can prepare estimated traffic conditions before vehicles actually reach those sections. This preliminary action reduces the need for intensive real-time computation during critical moments, as the AI has already processed and predicted the traffic conditions in advance.
Data Source
AI summary
A speed prediction device may comprise: a selection circuit selecting a prediction section of a road for which to predict the speed of a vehicle and rear sections located behind the prediction section in a traveling direction of the vehicle; a receiving circuit receiving driving information including the speeds of vehicles passing the prediction section and the rear sections; a processing circuit generating processing information including an average speed obtained by sequentially weighting the prediction section and rear sections in order of relative distance from the prediction section and calculating an average using the weights and the driving information; and a generating circuit generating a predicted speed by inputting the processing information to a prediction model trained to predict a future speed of a vehicle.