Autonomous UAV Flight Control With Safe-Envelope Emergency Switching

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for controlling unmanned aircraft lack guaranteed safety, relying on unproven artificial intelligence mechanisms and human supervision, which can lead to accidents and injuries.

Innovation Solution

A fully autonomous control system comprising a first decision module, a simplex control module with high-performance and high-safety controllers, which determines piloting commands based on predefined safe states and switches to emergency mode when conditions are met, ensuring the aircraft remains within a safe envelope.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If human supervision or unproven AI mechanisms are used to control unmanned aircraft, then operational flexibility is maintained, but flight safety cannot be guaranteed

Engineering Contradiction:
Improveflight safetyVSAvoidcontrol system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The control system is segmented into three distinct modules: a high-performance controller for nominal operation, a high-safety controller for safe-state monitoring, and a decision module for mode switching. This segmentation allows each module to specialize in specific functions, with the high-safety controller dedicated solely to safety assurance through safe-state verification, thereby guaranteeing flight safety while maintaining manageable complexity through clear functional separation.

Inventive Principle:
Principle #1Segmentation

2Reliability

If a fully autonomous control system with multiple controllers is implemented, then flight safety is guaranteed, but system complexity increases

Engineering Contradiction:
Improveflight safetyVSAvoidoperation simplicity
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The fully autonomous control system operates independently without human intervention by implementing self-service mechanisms. The decision module automatically monitors safe-state conditions and switches between controllers based on real-time safety assessments, while the high-safety controller continuously verifies aircraft state against predefined safe states. This self-service autonomy guarantees flight safety through automated safety management while simplifying operation by eliminating the need for human pilot input during critical safety decisions.

Inventive Principle:
Principle #25Self-service

3Reliability

If safe-state monitoring is continuously performed, then aircraft remains within safe envelope, but computational load increases

Engineering Contradiction:
Improvesafety assuranceVSAvoidcomputational energy
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The system applies partial monitoring action by focusing computational resources on critical safe-state parameters rather than continuously analyzing all possible flight variables. The high-safety controller monitors a predefined set of safe states representing critical flight envelopes, applying just enough monitoring to guarantee safety without excessive computational overhead. This selective monitoring approach ensures safety assurance while optimizing energy consumption by avoiding unnecessary computational analysis of non-critical parameters.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS20230205204A1Method for controlling a robot-aircraft and corresponding control system
Publication Date: 2023.06.29 THALES SA
  • US20230205204A1 patent drawing
  • US20230205204A1 patent drawing
  • US20230205204A1 patent drawing

AI summary

Method for controlling an unmanned aircraft piloted by a fully autonomous control system including a first decision module and a simplex piloting control module including a high-performance controller, a high-safety controller and a second decision module, the high-performance and high-safety controllers determining piloting commands for the robot-aircraft, according to which: —as long as a set of conditions is verified, implementation by the first decision module of a nominal piloting mode with delivery to the output of the automatic control system of the piloting commands delivered to the output of the simplex piloting control module; —otherwise, switching to an emergency piloting mode, an emergency piloting command is delivered to the output of the automatic control system for execution by the robot-aircraft, the first decision module preventing the delivery to the output of the automatic control system of the piloting commands delivered to the output of the simplex module.