Traffic Prediction Using Speed Deviation to Separate Signal Stops
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing navigation systems fail to accurately distinguish between traffic signals and actual traffic congestion, leading to inefficient route selection and increased travel time due to unknown traffic conditions.
Innovation Solution
A traffic information predicting apparatus that includes a communication module and processor to analyze driving speed deviation and average driving speed of vehicles to determine traffic situation types, distinguishing between stops at traffic signals and actual congestion, and generate predictive traffic information using machine learning models.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If navigation systems use traditional route selection methods (highway priority, national road priority, shortest distance), then route selection is simple and quick, but travel time increases and route efficiency deteriorates due to unknown traffic conditions
Solution Approach 1:
The system performs preliminary actions by collecting probe vehicle data in advance and processing it to generate predicted traffic information before the user makes route selection. The server proactively gathers data from multiple vehicles, calculates traffic situation types, and prepares predicted information for various routes ahead of time, allowing the user to select routes based on pre-computed traffic predictions rather than real-time conditions alone.
Solution Approach 2:
The system implements feedback by continuously collecting actual traffic data from probe vehicles, comparing it with predicted traffic information, and using this feedback to refine future predictions. The server receives real-time data from vehicles, processes it to determine actual traffic situations, and uses this information to improve the accuracy of predicted traffic information for subsequent route selections.
2Productivity
If navigation systems provide detailed real-time traffic information and multiple route selection methods, then route efficiency improves and travel time reduces, but system complexity increases due to need for continuous data collection and processing
Solution Approach 1:
The system introduces an intermediary server that acts as a mediator between multiple probe vehicles and the navigation system. The server collects data from numerous vehicles, processes and standardizes the information, determines traffic situation types, and generates predicted traffic information that can be used by the navigation system. This intermediary layer simplifies the complexity of handling data from multiple sources by centralizing the processing function.
Solution Approach 2:
The system applies parameter changes by transforming raw probe vehicle data into standardized traffic situation types (such as free flow, slow moving, stopped, congested) and then into predicted traffic information with specific parameters like predicted speed, delay time, and congestion level. This parameter transformation simplifies the complex raw data into usable formats for route selection while maintaining the essential traffic condition information.
3Speed
If navigation systems distinguish between traffic signal stops and actual congestion using only basic speed data, then processing is fast and simple, but accuracy of traffic situation detection deteriorates
Solution Approach 1:
The system segments the traffic detection task into multiple analytical components: it separately analyzes driving speed, driving time, and spatial distribution patterns of probe vehicles. By dividing the complex detection problem into these segments, the system can process each parameter efficiently while combining them to achieve high overall accuracy in distinguishing between traffic signal stops and actual congestion.
Solution Approach 2:
The system adds another dimension to traffic detection by incorporating temporal information (driving time, changes in speed over time) and spatial information (position of vehicles, density distribution) alongside basic speed data. This multi-dimensional approach allows the system to accurately distinguish between temporary stops at traffic signals and sustained congestion by analyzing patterns across multiple dimensions rather than relying on speed alone.
Data Source
AI summary
A traffic information predicting apparatus and a method thereof may include a communication module for receiving vehicle data from vehicles that are driving in a specified section and at least one processor electrically connected to the communication module. The at least one processor may obtain a driving speed deviation value of the vehicles and an average driving speed of the vehicles based on the vehicle data received through the communication module, may determine a traffic situation type based on the driving speed deviation value and the average driving speed, and may generate prediction traffic information based on the determined traffic situation type.