UAV Collision Avoidance with Multi-Sensor Pilot Override
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous vehicle navigation systems are inadequate for detecting and avoiding stationary and moving obstacles in cluttered environments, particularly for unmanned aerial vehicles (UAVs) and micro-air vehicles (MAVs, as they often rely on GPS, which is inaccurate in varied terrains and cannot recognize all objects.
Innovation Solution
A dynamic obstacle-avoidance system equipped with multiple sensors, including acoustic and visual sensors, that override pilot or autopilot commands to prevent collisions by generating control commands through a proportional-derivative (PD) controller, allowing the vehicle to detect and avoid obstacles without requiring modifications to the existing flight-control system or vehicle structure.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GPS is used for navigation, then the system is simple and inexpensive, but the accuracy varies widely and many objects cannot be recognized
Solution Approach 1:
The patent combines multiple sensor types (acoustic sensors, visual sensors, and other sensors) into an integrated obstacle detection system. This merging of different sensing modalities allows the system to achieve high measurement precision for obstacle detection while maintaining compatibility with existing flight-control systems, thereby resolving the contradiction between accuracy and complexity.
Solution Approach 2:
The obstacle detection system is designed to be sensor- and vehicle-agnostic, capable of working with various sensor types and aircraft configurations. This multi-functionality allows the system to achieve accurate obstacle detection across different environments without requiring complex customizations for each specific application.
2Reliability
If the obstacle-avoidance system overrides pilot commands, then collision safety is improved, but the ease of operation is reduced
Solution Approach 1:
The system continuously monitors obstacle proximity and provides feedback to the flight-control system. When an obstacle is detected within a critical distance, the system automatically generates override commands to prevent collision. This feedback mechanism ensures high collision avoidance reliability while maintaining pilot awareness and control during normal operation.
Solution Approach 2:
The system takes preliminary action by continuously scanning for obstacles and preparing avoidance commands before a collision threat becomes critical. This proactive approach ensures that when override commands are issued, they are already optimized for safe avoidance, thereby maintaining both reliability and operational ease.
3Difficulty of detecting and measuring
If multiple sensors are added to detect obstacles, then detection capability is improved, but the device complexity increases
Solution Approach 1:
The obstacle detection system is segmented into modular sensor components (acoustic sensors, visual sensors, and other sensors) that can be independently configured and integrated. This segmentation allows the system to achieve comprehensive obstacle detection capability while maintaining manageable complexity through standardized interfaces and modular architecture.
Data Source
Figure 1
Figure 2a
Figure 2b
AI summary
An obstacle-avoidance system for a vehicle, the obstacle-avoidance system may comprise: a communication device; a plurality of sensors, the plurality of sensors configured to detect collision threats within a predetermined distance of the vehicle; and a processor. The processor may communicatively couple to the communication device and the plurality of sensors and configured to receive navigation commands being communicated to a control system via said communication device. The processor may also receive, from at least one of said plurality of sensors, obstruction data reflecting the position of an obstruction. Using the obstruction data, the processor identifies a direction for avoiding said obstruction. In response, the processor may output, via said communication device, a command to said control system causing the vehicle to travel in said flight direction. Using the obstruction data, the processor may further perform a landing assist module, a three-region collision protection function with pilot override, and/or a target-filtering function.