Vehicle Route Mapping for Reliable Driving Condition Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for predicting future driving conditions for vehicles are unreliable due to incomplete information and lack of adaptability to specific vehicle types and routes, especially for public transportation vehicles like buses and trolleybuses.
Innovation Solution
A method that involves gathering sensor data while the vehicle travels, determining its position, associating the data with the position, creating a map, updating the map in real time, and using this map to predict future driving conditions based on the vehicle's position and route history.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If navigation assistance systems are used to predict driving conditions, then some prediction capability is provided, but the prediction reliability is insufficient due to incomplete information and lack of route-specific data
Solution Approach 1:
The system performs preliminary data collection during test drives before actual operation, gathering route-specific information in advance. This allows the prediction system to have pre-collected data about upcoming routes, eliminating the need to rely on incomplete navigation assistance system information during critical prediction moments.
Solution Approach 2:
The system uses the vehicle's own sensors and onboard systems to collect and store route-specific data independently. By utilizing the vehicle's inherent capabilities (sensors, processors, memory) to gather and process its own operational data, the system creates self-sufficient route profiles without relying on external navigation systems.
2Measurement precision
If general navigation data is used for prediction, then some route information is available, but the data lacks vehicle-specific and route-specific details needed for accurate prediction
Solution Approach 1:
The system creates customized route profiles tailored to specific vehicle types and individual routes. Each profile contains locally optimized parameters such as vehicle-specific acceleration patterns, route-specific topography data, and location-dependent traffic conditions. This localized approach ensures high prediction accuracy for each vehicle-route combination rather than using generic data.
Solution Approach 2:
The prediction system dynamically adapts to different vehicle types and routes by collecting and storing vehicle-specific operational data. The system modifies its prediction models based on the specific characteristics of each vehicle (mass, powertrain type, driving style) and each route (topography, traffic patterns), making the system versatile across different applications while maintaining high precision.
3Reliability
If map data is collected offline from multiple sources, then comprehensive route information can be gathered, but the process is complex and time-consuming
Solution Approach 1:
The system automatically collects and processes route data using the vehicle's own sensors and onboard computers during normal operation. This self-service approach eliminates the need for complex offline data collection processes involving multiple external sources, manual processing, and centralized databases. The vehicle independently generates its own route profiles during test drives.
Solution Approach 2:
The system performs test drives to collect route-specific data, then stores this information for future use. By discarding the need for complex ongoing data collection processes and recovering previously collected route information from memory, the system simplifies operations while maintaining high prediction reliability for repeated routes.
4Measurement precision
If real-time map updates are performed, then the prediction remains current and accurate, but the processing load and energy consumption increase
Solution Approach 1:
The system collects and processes route data during preliminary test drives before actual operation begins. By performing data collection and processing in advance when the vehicle is already in motion, the system prepares prediction models without adding extra processing load during critical prediction moments, optimizing the balance between accuracy and energy consumption.
Data Source
AI summary
In a method for predicting future driving conditions for a vehicle (1), sensor data (2) are gathered while the vehicle (1) is traveling on a route. A position of the vehicle (1) is also determined. The gathered data are associated with the determined vehicle position. A map (9) is created depending on the associated data. When the route is traveled again, the map is updated in real time depending on associated data from the repeated traveling. Finally, a prediction of future driving conditions is obtained based on the determined vehicle position and the map (9).