Driver Aggression Monitoring for Vehicle Energy Use Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Drivers' aggressive habits lead to increased energy use, reduced vehicle stability, and accelerated component wear, with existing systems failing to provide accurate range estimations due to varying driving styles.
Innovation Solution
A system that determines driver aggression ratings through Hidden Markov Models, using sensors to monitor accelerations and predict future energy use, providing real-time feedback and reports to improve driving efficiency and range estimation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Use of energy by moving object
If driver aggression is monitored and feedback is provided to improve driving habits, then energy use efficiency improves and vehicle range extends, but system complexity increases due to the need for sensors, processing algorithms, and feedback mechanisms
Solution Approach 1:
The vehicle's existing sensors and control systems are leveraged to serve multiple functions: they not only control vehicle operations but also monitor driver behavior and provide feedback. This multi-functionality reduces the need for additional dedicated components, thereby limiting system complexity while achieving energy efficiency improvements.
Solution Approach 2:
A feedback mechanism is implemented that provides real-time or near-real-time information to the driver about their driving behavior and its impact on energy consumption. This feedback loop enables drivers to adjust their behavior to improve efficiency without requiring complex automated control systems, thus balancing system complexity with energy savings.
2Loss of information
If real-time monitoring and prediction systems are implemented to improve range estimation, then driver satisfaction and trip planning improve, but computational requirements and processing time increase
Solution Approach 1:
The system pre-processes and stores driver behavior patterns and vehicle performance data during normal operation. When range estimation is needed, this pre-processed information is quickly retrieved and combined with current conditions to provide accurate predictions. This preliminary preparation reduces the computational burden and processing time during actual range calculation.
Solution Approach 2:
The system dynamically adjusts the level of detail and computational complexity of predictions based on available data, time constraints, and driving conditions. By changing parameters such as the time window for analysis, the granularity of behavior patterns, and the complexity of prediction algorithms, the system achieves accurate enough estimates without excessive processing time.
3Stability of the object's composition
If aggressive driving behavior is detected and feedback is provided, then energy consumption decreases and vehicle stability improves, but driver convenience may be reduced due to additional monitoring and potential restrictions
Solution Approach 1:
The system primarily serves the driver by providing information and enabling them to make better driving decisions themselves, rather than imposing restrictive controls. The driver retains full control over vehicle operation while benefiting from the monitoring insights, thus maintaining convenience while improving stability and efficiency.
Solution Approach 2:
Rather than imposing restrictions, the system provides informative feedback about driving behavior and its effects on vehicle stability and energy consumption. This feedback empowers drivers to self-correct their behavior, maintaining their autonomy and convenience while achieving the desired stability improvements.
Data Source
AI summary
A method of determining energy use during operation of a vehicle is described. The method includes: determining an aggression rating associated with current use of a vehicle; determining a first driver state as a function of the determined aggression rating over time; determining an energy use level as a function of the first driver state; determining a prevalence of the first driver state; and providing a prediction of future energy use based at least in part on the prevalence of the first driver state.