Driver Mental-State Evaluation for Cognitive-Load Driving Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods struggle to effectively evaluate driving performance during varying cognitive loads due to the difficulty in collecting data in real-world scenarios, which poses risks and challenges in assessing factors like lane departures, speed deviations, and collisions.
Innovation Solution
A vehicle computing system that incorporates a driving performance evaluator, trained using data from a simulated environment, to predict driving performance based on biosignals and mental states, allowing for adjustments in vehicle behaviors such as ADAS interventions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If data collection is performed in real-world driving scenarios to evaluate driving performance under cognitive load, then the evaluation accuracy is improved, but safety risks and practical challenges increase due to the difficulty of collecting reliable data during actual high-stress driving conditions
Solution Approach 1:
The patent creates a virtual copy of the driving environment through high-fidelity simulation. The simulation system replicates real-world driving scenarios, road conditions, traffic patterns, and cognitive load tasks, allowing researchers to collect performance data in a safe virtual environment while maintaining ecological validity. This copying approach enables accurate measurement of driving performance under cognitive load without exposing participants to actual safety risks.
Solution Approach 2:
The simulation environment serves as an intermediary between the researcher and the driver. Instead of directly observing drivers in hazardous real-world conditions, the simulation mediates the data collection process by creating controlled virtual scenarios that mimic real driving demands. This intermediary system allows for precise control of cognitive load tasks and driving conditions while eliminating the safety hazards present in actual road testing.
2Object-affected harmful factors
If high-fidelity simulation environments are created to enable safe data collection, then safety is improved, but system complexity and resource requirements increase
Solution Approach 1:
The simulation system is divided into modular functional components: a driving scenario module that generates virtual road environments, a cognitive load task module that presents mental challenges to drivers, a data acquisition module that collects biosignals and driving behavior, and an analysis module that processes the collected data. This segmentation allows each component to be developed and validated independently, reducing overall system complexity while maintaining high-fidelity simulation capabilities.
Solution Approach 2:
The simulation platform is designed as a multi-functional system that can simultaneously perform multiple functions: it can present various cognitive load tasks (e.g., n-back tasks, mental arithmetic), simulate different driving conditions (highway, urban, adverse weather), collect multiple types of data (steering behavior, eye tracking, biosignals), and adapt to different research protocols. This universality reduces the need for multiple separate systems and simplifies the overall research infrastructure.
Data Source
AI summary
Methods and systems are herein providing for predicting driving performance based on mental state. In one example, a vehicle system comprises a vehicle computing system comprising one or more processors and memory storing instructions that, when executed by the one or more processors, cause the vehicle computing system to adjust one or more vehicle behaviors according to predicted driving performance, wherein the predicted driving performance is determined based on one or more mental states of a driver.