Inferring Aircraft Intent from Observed Trajectories
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods lack efficient ways to infer an aircraft's intent from its observed trajectory without requiring special airborne equipment or additional data communication infrastructure, limiting the availability of aircraft intent data for air traffic management and analysis.
Innovation Solution
A computer-implemented method using evolutionary algorithms to infer aircraft intent from observed trajectories, leveraging radar and ADS data, by generating and evolving candidate aircraft intents that match the observed trajectory, with a cost function to measure goodness and constrain solutions to ensure accuracy and practicality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If aircraft intent data is obtained from aircraft or operators directly, then data accuracy is improved, but data availability is reduced due to restricted access
Solution Approach 1:
The patent uses observed trajectory data as an intermediary to infer aircraft intent. Instead of directly accessing intent data from aircraft or operators (which is restricted), the system uses trajectory observations from radar/ADS as a mediator to indirectly obtain intent information through inference algorithms
Solution Approach 2:
The patent replaces direct data collection mechanisms with computational inference. Instead of mechanically obtaining intent data through aircraft communications or operator reports, the system uses algorithmic inference based on trajectory patterns to substitute and derive intent information
2Adaptability or versatility
If evolutionary algorithms are used to infer aircraft intent from trajectory data, then data availability is improved, but computational complexity increases
Solution Approach 1:
The patent creates candidate aircraft intent objects that copy the structure and properties of actual aircraft intent. These virtual intent objects are generated, evaluated, and evolved to match observed trajectory data, allowing the system to work with simplified representations rather than complex real-time intent data
3Ease of operation
If trajectory observation data is used to infer aircraft intent, then ease of operation is improved, but measurement precision deteriorates due to indirect inference
Solution Approach 1:
The patent implements feedback through the evaluation of candidate intent objects against observed trajectory data. The system continuously refines intent inferences by comparing predicted trajectories (derived from inferred intent) with actual observed trajectories, adjusting the inference to minimize discrepancies and improve precision
Solution Approach 2:
The system uses the observed trajectory data itself to serve dual purposes: both as the input for inference and as the validation criterion. The trajectory data feeds the inference process and simultaneously provides the feedback mechanism to assess and refine the accuracy of the inferred intent
Data Source
Figure 1~2
Figure 3a~3c
Figure 4
AI summary
The present invention provides a method of inferring the aircraft intent of an aircraft from an observed trajectory. Aircraft performance data relating to that type of aircraft is retrieved from memory, along with atmospheric conditions along the observed trajectory. An initial set of candidate aircraft intents is generated. Each aircraft intent provides an unambiguous description of how the aircraft may be flown that allows a determination of an unambiguous resulting trajectory. A computer system calculates a trajectory defined by each candidate aircraft intent and forms a cost function from a comparison of each calculated trajectory to the observed trajectory. An evolutionary algorithm evolves the initial candidate aircraft intents, wherein the evolutionary algorithm uses the multi-objective cost function to obtain a cost function value that measures the goodness of each candidate aircraft intent. One or more candidate aircraft intents with the best cost function value or values respectively may be provided.