Driving Information Estimation Using ANFIS Speed Deviations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing driving information estimation methods lack accuracy due to failure to consider real-time traffic conditions and ambient environmental variables, leading to inefficient vehicle control.
Innovation Solution
A method using an adaptive neuro-fuzzy inference system (ANFIS) to generate speed deviations based on driving characteristics such as driver type, traffic flow, weather, and road conditions, which are used to create a speed profile for predicting vehicle power usage and determining driving range.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If typical driving pattern estimation is used, then the estimation process is simple, but the accuracy of driving information decreases due to not considering real-time traffic conditions and environmental variables
Solution Approach 1:
The estimation system is divided into multiple independent modules: a driving pattern recognition module that processes historical data, a real-time information acquisition module that gathers traffic and environmental data, and an integrated estimation module that combines both. This segmentation allows the system to maintain high accuracy through comprehensive data processing while managing complexity through modular architecture.
Solution Approach 2:
An intermediary integration module is introduced that receives both typical driving patterns and real-time information, processes them together, and generates the final driving information estimation. This intermediary component enables the system to leverage the simplicity of typical patterns while incorporating the accuracy benefits of real-time data without requiring complete system redesign.
2Measurement precision
If real-time information from multiple sources is integrated, then the accuracy of driving information estimation increases, but the system complexity and data processing requirements increase
Solution Approach 1:
The system performs preliminary classification and filtering of real-time information from multiple sources before integration. Data acquisition modules pre-process traffic conditions, environmental variables, and vehicle sensor data into standardized formats, reducing the complexity of subsequent integration and analysis while maintaining comprehensive data coverage for accurate estimation.
Solution Approach 2:
The estimation system is designed with universal data processing capabilities that can handle multiple types of real-time information (traffic flow, weather conditions, road conditions, vehicle sensors) through a unified framework. This multi-functional approach allows the system to process diverse data sources using common algorithms and structures, reducing overall system complexity despite the variety of inputs.
Data Source
AI summary
Disclosed are a method and an apparatus for estimating driving information, the apparatus receives a driving route of a vehicle, generates speed deviations corresponding to points on the driving route, and generates a speed profile that is a sequence of predicted speeds corresponding to the points based on the speed deviations and average speeds corresponding to the points.