UAS Deconfliction Control With Wind-Based LMA Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional Detect-and-Avoid (DAA) systems for unmanned aerial systems (UAS) fail to accurately predict the trajectories of low-maneuverability aircraft (LMAs) due to reliance on kinematic models, leading to suboptimal avoidance maneuvers and potential mission failure or component damage, and neglect the host vehicle's internal health status in avoidance calculations.
Innovation Solution
An AI-driven Cooperative Deconfliction System (CDS) that integrates wind-governed trajectory prediction and prognostic health monitoring to ensure safe, long-term operations by classifying LMAs, computing probabilistic future paths, and planning optimal avoidance maneuvers based on the host UAS's health status.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If standard kinematic models are used to predict LMA trajectories, then the prediction process is simple and fast, but the trajectory prediction accuracy deteriorates
Solution Approach 1:
The system changes the fundamental parameters of the prediction model from standard kinematic parameters (velocity, acceleration) to meteorological parameters (wind vectors, atmospheric conditions). This allows accurate prediction of LMA trajectories by modeling the wind-governed motion characteristics specific to low-maneuverability aircraft.
Solution Approach 2:
The prediction system dynamically adapts its modeling approach based on the detected aircraft type. When LMA is detected via classification, the system switches from static kinematic models to dynamic wind-field models that account for environmental factors, enabling accurate trajectory prediction while maintaining computational efficiency through conditional model selection.
2Reliability
If aggressive avoidance maneuvers are executed to ensure collision-free operation, then external safety is improved, but internal component stress and power consumption increase
Solution Approach 1:
The system incorporates real-time feedback from the PHM system regarding the host UAS's component health status and power levels. This feedback loop enables the avoidance planning to adjust maneuver aggressiveness based on current internal conditions, selecting less stressful trajectories when components are healthy and more conservative paths when stress margins are low, thereby optimizing the balance between collision avoidance and power consumption.
Solution Approach 2:
The avoidance maneuver characteristics dynamically adapt based on real-time health status data. The system adjusts maneuver parameters such as turn rate, acceleration, and trajectory deviation according to current component stress margins and power availability, enabling flexible optimization of the trade-off between external safety and internal resource preservation.
3Reliability
If conventional DAA systems focus only on external collision risk, then the avoidance calculation is straightforward, but mission failure risk increases due to unaccounted internal stress
Solution Approach 1:
The system merges previously separate functions into a unified avoidance planning framework that simultaneously considers external collision risk and internal health status. The PHM system and DAA system are integrated such that component stress margins and power consumption are incorporated into the same optimization calculation as collision probability, enabling comprehensive reliability assessment in a single coordinated process.
Data Source
AI summary
A system for safe, autonomous deconfliction of an Unmanned Aerial System (UAS) from a low-maneuverability aircraft (LMA), such as a hot air balloon. The system includes a multi-sensor fusion module for cross-modal classification of the LMA; a specialized Intent Prediction Module that generates a three-dimensional Cone of Probability (C) for the LMA's future trajectory based on real-time meteorological data (W); and a Prognostic-Informed AI Control (PI-AIC) module. The PI-AIC module calculates an optimal avoidance trajectory (Topt) by minimizing a multi-objective cost function (J) that heavily penalizes intersection with C. Crucially, the optimization is subject to a Prognostic Health Constraint (PHC) requiring the maneuver to be achievable without compromising the predicted Remaining Useful Life (RUL) or Remaining Battery Capacity (RBC) of the host UAS below a predetermined Safety Margin (Sm).