Airport Surface Trajectory Coding for Predictable Vehicle Routing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for predicting and optimizing surface vehicle trajectories in high-density airport environments are limited by their reliance on human skills, lack of consideration for vehicle parameters, and vulnerability to human errors, leading to safety concerns and inefficiencies, including increased fuel consumption and air pollution.
Innovation Solution
A system and method using the Terrestrial Intent Description Language (TIDL) to unambiguously code vehicle trajectories based on control operations and vehicle configuration elements, enabling optimized and predictable vehicle movements by translating high-level movement requirements into detailed actions and vehicle-specific actuator commands, incorporating vehicle parameters for accurate trajectory prediction and optimization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If waypoint-based trajectory descriptions are used, then trajectory prediction is simplified, but vehicle parameters are not considered making prediction inaccurate in congested environments
Solution Approach 1:
The patent transforms the trajectory description from simple waypoint coordinates to a parameter-rich format that includes vehicle-specific dynamic parameters (acceleration, deceleration, turn rates, dimensions). This parameter transformation enables accurate prediction of vehicle behavior in congested environments while maintaining computational tractability through structured parameter sets.
2Ease of operation
If human skills and procedures are relied upon for traffic management, then operational flexibility is maintained, but human errors increase vulnerability in high-density traffic
Solution Approach 1:
The system enables vehicles to autonomously generate and optimize their own trajectories by encoding intent in TIDL and computing optimal paths considering vehicle parameters and environmental constraints. This self-service capability reduces dependence on human operators while maintaining operational flexibility through automated decision-making.
Solution Approach 2:
The patent implements continuous feedback loops where vehicle state, environmental conditions, and trajectory execution are monitored and used to dynamically adjust planned paths. This feedback mechanism enhances reliability by detecting and correcting deviations or conflicts in real-time, reducing vulnerability to human errors.
3Productivity
If traditional trajectory optimization is applied, then individual vehicle efficiency is improved, but system-wide de-confliction and collision prevention are insufficient
Solution Approach 1:
The patent merges individual vehicle trajectory optimization with system-wide de-confliction by integrating vehicle-specific parameter modeling with centralized or distributed conflict detection and resolution algorithms. This unified approach simultaneously optimizes individual vehicle efficiency while ensuring collision prevention through coordinated path planning.
4Measurement precision
If localization accuracy is improved using advanced sensors and infrastructure, then positioning precision increases, but system complexity and cost increase
Solution Approach 1:
The TIDL framework and trajectory prediction algorithm serve multiple functions: they encode vehicle intent, predict future positions, enable conflict detection, and support optimization. This multi-functionality allows the system to achieve high localization accuracy through software-based trajectory inference rather than relying solely on complex hardware sensor systems.
Data Source
Figure 1~2
Figure 3~4
Figure 5~6
AI summary
System and method comprising a plurality of surface vehicles (1) and a plurality of events (2) to be performed by each of the surface vehicles (1). Each of the vehicles (1) is equipped with an electronic control unit (6) comprising a receiver (7) and a decoder (8) for the instructions received from a vehicle (1) movement optimizer (5). The plurality of events (2) comprise instructions of movements from an origin to a destination, and actions (15) for each of the surface vehicles (1). The decoder (8) decodes instructions received from the surface vehicle (1) movement optimizer (5). The optimizer (5) configures an optimized schedule (4) of the preliminary plan (3) by modifying the events (2) based on either the vehicle attributes(12) or updates (11) submitted by the electronic control unit (6) from the vehicle (1) to the optimizer (5).