3D Reconstructed Map Fusion for Accurate UAV Path Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for generating flight paths for unmanned aerial vehicles (UAVs) using three-dimensional point-cloud maps do not effectively determine material attributes of objects, leading to inadequate obstacle detection and classification, which requires additional sensors for precise obstacle avoidance.
Innovation Solution
A method utilizing a three-dimensional reconstructed map that combines three-dimensional point-cloud map information with three-dimensional material map information, employing clustering algorithms and neural network models to identify obstacles and generate accurate flight paths, while also adjusting path information based on wind parameters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If three-dimensional point-cloud map information is used for path generation, then the flight path can be computed, but the material attributes of objects cannot be effectively determined, requiring additional sensors
Solution Approach 1:
The patent merges three-dimensional point-cloud map information (spatial structure) with three-dimensional material map information (material attributes) into a unified fused map. This combination allows the system to simultaneously obtain both geometric obstacle locations and material properties without adding separate sensing systems, thereby improving obstacle detection precision while avoiding increased device complexity
Solution Approach 2:
The fused map serves multiple functions: it provides spatial obstacle information for path planning, material attribute information for obstacle classification, and integrated data for both navigation and environmental understanding. This multi-functionality eliminates the need for separate sensors dedicated to different detection tasks
2Reliability
If additional sensors are equipped on the unmanned aerial vehicle to precisely determine obstacles, then the obstacle avoidance effect is improved, but the size and weight of the unmanned aerial vehicle increase
Solution Approach 1:
The patent introduces a fused map as an intermediary that bridges the gap between limited sensor data and comprehensive obstacle understanding. By integrating point-cloud spatial information with material map attributes, the fused map provides rich obstacle information that would otherwise require multiple specialized sensors, thereby maintaining high obstacle avoidance success rate while keeping the UAV lightweight
3Loss of information
If the data structure of point cloud information is rebuilt every time map information is updated, then the latest map data is obtained, but the flight performance and success rate are affected
Solution Approach 1:
The patent performs preliminary fusion of point-cloud map information and material map information to create a pre-integrated fused map before path generation. This preliminary action organizes and combines data structures in advance, so when map updates occur, the system can efficiently update the fused map without time-consuming reconstruction processes, thereby maintaining information freshness while preserving flight performance
Data Source
AI summary
A method for searching a path by using a 3D reconstructed map includes: receiving 3D point-cloud map information and 3D material map information; clustering the 3D point-cloud map information with a clustering algorithm to obtain clustering information, and identifying material attributes of objects in the 3D point-cloud map information with a material neural network model to obtain material attribute information; fusing the those map information based on their coordinate information, thereby outputting fused map information; identifying obstacle areas and non-obstacle areas in the fused map information based on an obstacle neural network model, the clustering information, and the material attribute information; and generating 3D path information according to the non-obstacle areas. Since the 3D path information is generated based on those map information, the obstacle areas and flight spaces are effectively determined to generate an accurate flight path.