Aircraft Goal-Driven Action Planning for Unanticipated Conditions

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current automated aircraft systems using decision trees are limited in providing actions for unanticipated conditions, leading to increased workloads for flight crews as they require human intervention to handle unforeseen situations, limiting the system's capability to support pilots with actionable information during flights.

Innovation Solution

A method and system that dynamically identifies and selects a sequence of actions to reach a target state for an aircraft by determining the current mission state and reselecting actions in response to changes, allowing for dynamic goal adaptation without requiring human intervention, using a computer system to manage aircraft operations and reduce pilot workload.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If rule-based automated aircraft systems using decision trees are used, then the system behavior is predictable and easy to evaluate, but the system is limited in performing actions for unanticipated conditions

Engineering Contradiction:
Improvepredictability of system behaviorVSAvoidcapability to handle unanticipated conditions
Core Design Contradiction:
ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent transitions from static decision trees to dynamic goal-oriented action planning where the system continuously evaluates current state, selects actions from a pool of potential actions, and adapts to changing conditions. The automated system dynamically generates and updates action sequences based on current aircraft state and mission goals, enabling adaptability to unanticipated conditions while maintaining reliability through systematic evaluation.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system changes from fixed rule-based parameters to dynamic state-based parameters. Instead of following predetermined decision tree paths, the system evaluates current mission state variables and selects actions based on changing parameters, allowing the system to adapt to new conditions while maintaining structured decision-making processes.

Inventive Principle:
Principle #35Parameter changes

2Device complexity

If rule-based decision tree systems are used, then the system structure is simple and easy to implement, but human intervention is required for unforeseen situations increasing flight crew workload

Engineering Contradiction:
Improvesimplicity of system structureVSAvoidflight crew workload
Core Design Contradiction:
Device complexityVSEase of operation

Solution Approach 1:

The automated aircraft system performs self-service by autonomously generating and executing action sequences without requiring human intervention. The system independently evaluates its current state, selects appropriate actions from a predefined pool, and implements corrective maneuvers, thereby reducing flight crew workload while maintaining system simplicity through automated goal-oriented planning.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system prepares multiple potential action sequences in advance based on possible mission states and goals. By pre-defining a pool of potential actions and their associated preconditions and effects, the system can quickly select and execute appropriate sequences without requiring complex real-time human decision-making, thus reducing crew workload while maintaining operational simplicity.

Inventive Principle:
Principle #10Preliminary action

3Reliability

If automated aircraft systems require human intervention for unanticipated conditions, then system reliability is maintained through human judgment, but operational efficiency decreases due to increased pilot workload

Engineering Contradiction:
Improvesystem reliability through human judgmentVSAvoidoperational efficiency
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The system implements continuous feedback loops where the automated aircraft system monitors its current mission state, compares it against goals, and automatically adjusts its action sequences. This closed-loop control maintains reliability by systematically evaluating system state and selecting appropriate actions, while improving operational efficiency by eliminating the need for human intervention in routine decision-making processes.

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP3786752B1Automated aircraft system with goal driven action planning
Publication Date: 2024.06.26 THE BOEING CO
  • EP3786752B1 patent drawingFigure 1
  • EP3786752B1 patent drawingFigure 2~4
  • EP3786752B1 patent drawingFigure 5

AI summary

A method, apparatus, and system for controlling an aircraft (100). A target state (114) for the aircraft (100) is identified. A current mission state (122) is determined for the aircraft (100). A sequence of actions (126) is selected from a pool of potential actions (130) to reach the target state (114) from the current mission state (122) for the aircraft (100). The sequence of actions (126) is selected based on the current mission state (122). The actions (128) in the sequence of actions (126) for which preconditions (132) for the actions (128) that have been met are performed. The actions (128) are performed in an order (134) defined by the sequence of actions (126).