Vision-Guided Multirotor Collection on Glare-Prone Water Surfaces
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous object collection from water surfaces using UAVs is challenging due to issues such as random motion of floating objects, reflection and glare from water surfaces, and unpredictable current flow, which complicate aerial grasping and landing on moving targets.
Innovation Solution
A multirotor system equipped with a boundary layer sliding mode control (BLSMC) and a computationally efficient contour-based object detection algorithm, utilizing a linear polarization filter and specularity removal, along with a net-based collection mechanism, to enhance object detection and tracking on water surfaces.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a robotic manipulator is added to the multirotor for aerial grasping, then the grasping capability is improved, but the aircraft gross weight increases and flight time decreases
Solution Approach 1:
The patent extracts the grasping function from a complex robotic manipulator and implements it through a simpler net-based collection mechanism. The net is deployed from the multirotor to capture floating objects, eliminating the need for heavy robotic arms while maintaining aerial grasping capability.
Solution Approach 2:
The patent replaces the mechanical robotic manipulator system with a net deployment mechanism. Instead of using complex mechanical arms with multiple degrees of freedom, the system uses a net that can be deployed and retrieved, significantly reducing weight while achieving the same functional goal of object collection.
2Device complexity
If traditional object detection is used on water surfaces, then the detection process is simple, but reflection and glare from water surfaces prevent accurate detection
Solution Approach 1:
The patent changes the optical parameters of the water surface by using a linear polarization filter. This filter blocks polarized light reflections from the water surface while allowing non-polarized light from objects to pass through, effectively removing glare and enabling accurate object detection.
Solution Approach 2:
The patent introduces a polarization filter as an intermediary between the camera and the water surface. This intermediary component modifies the light properties, blocking reflected polarized light while transmitting light from objects, thereby enabling clear detection despite the challenging water surface conditions.
3Device complexity
If conventional sliding mode control is used, then the control method is simple, but it exhibits chattering behavior that reduces control precision
Solution Approach 1:
The patent transforms the static switching surface of conventional sliding mode control into a dynamic switching surface that adapts during the control process. This dynamic adjustment eliminates the chattering phenomenon while maintaining the robustness and simplicity of sliding mode control, achieving precise landing without excessive control complexity.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The system achieves a 91.6% success rate in collecting floating objects of varying shapes and sizes, demonstrating robustness under different weather conditions and modeling uncertainties.
Implementation Method 1
utilizing a linear polarization filter and specularity removal
Data Source
AI summary
Various embodiments of a vision-guided unmanned aerial vehicle (UAV) system to identify and collect foreign objects from the surface of a body of water are disclosed herein. A vision system and methodology has been developed to reduce reflections and glare from a water surface to better identify an object for removal. A linearized polarization filter and a specularity-removal algorithm is used to eliminate excessive reflection and glare. A contour-based detection algorithm is implemented for detecting the targeted objects on water surface. Further, the system includes a boundary layer sliding mode control (BLSMC) methodology to reduce and minimize position and velocity errors between the UAV and object in the presence of modeling and parameter uncertainties due to variation in a moving water surface.