3D Point Cloud Filtering for Mobile Robot Exploration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous robot navigation systems, particularly in indoor environments, lack the ability to proactively search for open spaces for exploration, relying on reactive obstacle avoidance rather than planning ahead for opportunities.
Innovation Solution
A system utilizing one or more processors and a memory with executable instructions to process 3D point cloud data, determining the openness of candidate directions by filtering and calculating distances, setting a target direction for the mobile platform to move towards open spaces, and adjusting based on the presence of obstacles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If reactive obstacle avoidance control is used, then collision prevention is achieved, but proactive exploration of open spaces is not possible
Solution Approach 1:
The system performs preliminary analysis of the 3D point cloud data to identify open spaces before the robot moves. By pre-processing the spatial data and detecting opportunity spaces in advance, the robot can plan its navigation path proactively rather than reacting only when obstacles are detected, thus improving exploration efficiency while maintaining safety
Solution Approach 2:
The system transitions from traditional 2D obstacle avoidance to 3D open space exploration by utilizing 3D point cloud data. This dimensional enhancement allows the robot to perceive and navigate toward open spaces in three-dimensional space, enabling more effective exploration while maintaining collision prevention
2Productivity
If 3D point cloud processing is performed to identify open spaces, then exploration capability is improved, but computational complexity increases
Solution Approach 1:
The system extracts only the essential features from the 3D point cloud data needed for open space identification. By filtering and selecting relevant spatial information rather than processing the complete point cloud, the computational complexity is reduced while maintaining the ability to identify navigable open spaces effectively
Solution Approach 2:
The 3D space is segmented into different regions based on the point cloud data, allowing the system to identify open spaces as distinct navigable regions. This segmentation approach simplifies the computational task by dividing the complex 3D environment into manageable segments that can be processed and evaluated for exploration
Data Source
AI summary
Described is a system for finding open space for robot exploration. During operation, the system designates a straight forward direction as a default direction. It is determined if a filtered 3D point cloud has a sufficient number of cloud points. If not, the system determines if an obstacle is too close in a previous time. If so, a backward direction is set as a target direction and if not, the straight forward direction is set as the target direction. Alternatively, if there are a sufficient number of points, then calculate a distance of each point to a sensor center and determine if a number of times that the distance is smaller than a distance threshold is greater than a fixed number. The system either sets the backward direction as the target direction or estimates an openness of each candidate direction until a candidate direction is set as the target direction.