Dynamic Task Allocation Using Operator Cognitive State Monitoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current human-autonomy teaming systems in urban air mobility and space exploration lack seamless, real-time responsiveness for efficient and safe dynamic allocation of tasks between human operators and autonomous systems, especially in complex and dynamic scenarios, with existing systems being limited to laboratory settings and partially autonomous systems.
Innovation Solution
A method and system that utilize psychophysiological sensors to monitor and assess operator states, dynamically allocate and reallocate tasks between human operators and autonomous systems through a Dynamic Function Allocation Control Collaboration Protocol (DFACCto), incorporating eye-tracking data and machine learning algorithms to predict cognitive states and mitigate risks, enabling collaborative task management between human and automation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If human operators are used in UAM and space exploration systems, then decision-making authority and adaptability are maintained, but operational costs increase and human error risks persist
Solution Approach 1:
The system dynamically allocates tasks between human operators and autonomous systems based on real-time assessment of operator cognitive states. When operators are assessed as being in optimal cognitive states, they retain decision-making authority. When cognitive degradation is detected, the system automatically transfers tasks to autonomous systems, creating a dynamic adaptation that resolves the contradiction between human adaptability and error reduction.
Solution Approach 2:
The system changes the operational parameter of task allocation based on measured cognitive state parameters. By continuously monitoring psychophysiological indicators and adjusting the degree of automation accordingly, the system transitions between human-controlled and autonomous modes, optimizing both adaptability and reliability through parameter-driven adaptation.
2Reliability
If fully autonomous flight control systems are implemented, then operational costs are reduced and human error is eliminated, but public trust and confidence decrease
Solution Approach 1:
The system incorporates continuous feedback loops where psychophysiological sensors monitor operator states and feed this information back to the task allocation algorithm. This feedback mechanism allows the system to demonstrate human oversight and adaptability, building public trust while maintaining the reliability benefits of autonomous operation. The feedback also enables real-time adjustment of automation levels based on actual operational needs.
Solution Approach 2:
The system serves multiple functions simultaneously: it operates autonomously to eliminate human error, maintains the capability for human oversight to build public trust, and dynamically adjusts between these modes based on operational context. This multi-functionality allows the system to satisfy conflicting requirements of reliability and adaptability.
3Productivity
If dynamic task allocation between human and autonomous systems is implemented, then operational efficiency is improved, but system complexity increases
Solution Approach 1:
The system replaces complex mechanical or procedural task allocation mechanisms with psychophysiological sensing and machine learning-based cognitive state assessment. By using biological signals (eye-tracking, EEG, GSR) and computational algorithms to automatically determine optimal task allocation, the system achieves operational efficiency without requiring complex manual coordination procedures.
Solution Approach 2:
The system performs self-assessment of operator cognitive states through integrated psychophysiological sensors and automatically adjusts task allocation without external intervention. This self-service capability simplifies the overall system architecture by eliminating the need for external monitoring and manual task reallocation, thereby improving efficiency while managing complexity through automation.
4Measurement precision
If psychophysiological sensors and machine learning algorithms are used to monitor operator states, then real-time task reallocation accuracy is improved, but system complexity and cost increase
Solution Approach 1:
The system segments the monitoring function into multiple independent psychophysiological sensor channels (eye-tracking, EEG, GSR, heart rate) that can be independently processed and combined. This segmentation allows for modular implementation, where each sensor type contributes specific cognitive state information without requiring a single complex monitoring system, thereby improving measurement precision while managing complexity through modular architecture.
Data Source
AI summary
A method for determining a human operator's visual attention to an operating panel of a vehicle during vehicle operation is described. The method includes: receiving and processing data indicative of the human operator's gaze direction from at least one monitoring device over a period of time; determining, by the processor, an approximate location of the human operator's gaze on the operating panel at different individual times over the period of time; identifying, by the processor, any individual areas-of-interest (AOI) located at each of the determined approximate locations of the human operator's gaze; and calculating, by the processor, a value for at least one metric using at least the determined approximate locations at different individual times and the identification of any individual AOI at the determined approximate locations to determine the human operator's attention to the operating panel.