Aircraft Trajectory Prediction for Maneuvering Traffic Encounters
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current detect and avoid systems for autonomous aircraft operation rely on simplistic and rudimentary methods for predicting aircraft trajectories, which are inadequate when ownship and other aircraft are maneuvering at non-constant speeds, leading to inefficiencies in conflict detection and avoidance.
Innovation Solution
A policy-based traffic encounter assessment system that predicts the trajectory of both ownship and other aircraft using enhanced traffic and ownship state data, including maneuvering patterns and intent, to generate encounter assessment data for effective conflict detection and avoidance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If simplistic and rudimentary methods are used for predicting aircraft trajectory, then the system complexity is reduced, but the detection precision and reliability of conflict detection deteriorate
Solution Approach 1:
The patent applies dynamics by transitioning from static, simplistic trajectory prediction to dynamic prediction that adapts to changing flight conditions. The system continuously updates trajectory predictions based on real-time maneuvering patterns and non-constant speeds, allowing the prediction model to evolve with the actual flight dynamics rather than relying on fixed, predetermined paths.
Solution Approach 2:
The patent implements parameter changes by incorporating multiple varying parameters into the trajectory prediction process, including maneuvering patterns, intent data, and non-constant speed profiles. Instead of using fixed prediction parameters, the system dynamically adjusts prediction parameters based on detected traffic behavior, enabling accurate prediction despite changing flight conditions.
2Measurement precision
If enhanced traffic and ownship state data including maneuvering patterns and intent are used, then the detection precision and conflict detection capability are improved, but the device complexity and data processing requirements increase
Solution Approach 1:
The patent applies preliminary action by pre-processing and structuring traffic and ownship state data before it is needed for conflict detection. The system prepares maneuvering patterns, intent data, and trajectory predictions in advance, organizing this enhanced data into usable formats that reduce the computational burden during real-time conflict assessment, thereby managing complexity while maintaining high detection precision.
Solution Approach 2:
The patent uses an intermediary approach by introducing a dedicated trajectory prediction module that acts as a mediator between raw state data and conflict detection algorithms. This intermediary component processes enhanced data including maneuvering patterns and intent, transforming complex raw data into refined trajectory predictions that are more easily consumed by the conflict detection system, thus managing complexity while improving precision.
3Reliability
If trajectory prediction accounts for non-constant speeds and maneuvering, then the reliability of detect and avoid capability is improved, but the computational time and processing complexity increase
Solution Approach 1:
The patent implements periodic action by updating trajectory predictions at regular intervals rather than continuously calculating every possible variable. The system periodically reassesses traffic state data, maneuvering patterns, and intent information, performing computational updates at structured time steps that maintain reliability for conflict detection while preventing excessive computational time consumption through rhythmic, interval-based processing.
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
A method for policy-based traffic encounter assessment to detect and avoid traffic includes determining, by a processor, an ownship predicted trajectory of an aircraft. The aircraft is the ownship. The method also includes determining a traffic predicted trajectory of one or more other aircraft in the vicinity of the ownship. The one or more other aircraft includes traffic. The method also includes assessing an encounter between the ownship and the traffic, wherein assessing the encounter between the ownship and the traffic includes applying an encounter assessment policy to the traffic predicted trajectory and the ownship predicted trajectory. The method further includes generating encounter assessment data in response to assessing the encounter between the ownship and the traffic. The encounter assessment data is used to at least detect and avoid the traffic by the ownship.