Dynamic Task Allocation Protocol for Human-Autonomy Workload Handoffs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current human-autonomy teaming systems in UAM and space exploration lack seamless, real-time responsiveness for dynamic task allocation and re-allocation between human operators and autonomous systems, especially in scenarios involving pilot distraction, impairment, or incapacitation, limiting their effectiveness in highly autonomous environments.
Innovation Solution
A Dynamic Function Allocation Control Collaboration Protocol (DFACCto) that monitors the cognitive and physical state of human operators using psychophysiological sensors, dynamically reallocates tasks between human and autonomous systems, and invokes autonomous control when necessary, allowing for continuous, context-based task assignment and re-assignment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If tasks are dynamically reallocated to autonomous systems based on operator state, then productivity is improved, but system complexity increases due to continuous monitoring and real-time decision-making requirements
Solution Approach 1:
The system segments the overall control function into distinct task categories (safety-critical tasks, routine tasks, complex decision-making tasks) and allocates them differently based on operator state. This segmentation allows the system to manage complexity by handling different task types through specialized protocols rather than a monolithic control architecture
Solution Approach 2:
The patent introduces an intermediary task allocation system that acts as a mediator between the operator and the autonomous system. This intermediary layer processes operator state data, determines appropriate task allocations, and manages the handoff between human and autonomous control, simplifying the overall system architecture by centralizing the decision-making logic
2Measurement precision
If psychophysiological sensors are used to monitor operator state in real-time, then task allocation accuracy is improved, but device complexity and cost increase
Solution Approach 1:
The system uses multi-functional sensors that can detect multiple cognitive state indicators simultaneously (e.g., eye trackers that monitor both gaze direction and blink rate, heart rate monitors that detect both HRV and stress levels). This multi-functionality improves measurement precision without proportionally increasing system complexity, as a single sensor provides multiple data streams for cognitive state assessment
Solution Approach 2:
The patent employs relatively simple, inexpensive sensors (eye trackers, heart rate monitors, skin conductance sensors) rather than complex neuroimaging equipment. These sensors provide sufficient precision for task allocation decisions while keeping the system cost-effective and practically deployable in aviation and space exploration contexts
Data Source
AI summary
A dynamic function allocation (DFA) framework balances the workload or achieves other mitigating optimizations for a human operator of a vehicle by dynamically distributing operational functional tasks between the operator and the vehicle's or robot's automation in real-time. DFA operations include those for aviation, navigation, and communication, or to meet other operational needs. The DFA framework provides an intuitive command/response interface to vehicle (e.g., aircraft), vehicle simulator, or robotic operations by implementing a Dynamic Function Allocation Control Collaboration Protocol (DFACCto). DFACCto simulates or implements autonomous control of robot's or vehicle's functional tasks and reallocates some or all tasks between a human pilot and an autonomous system when such reallocation is preferred, and implements the reallocation. The reallocation is implemented in the event of the human's distraction or incapacitation, in the event another non-nominal or non-optimal cognitive or physical state is detected, or when reallocation need is otherwise-determined.