Moving Robot Grid Mapping for Unsearched Boundary Path Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing moving robots face challenges in accurately distinguishing between searched and unsearched regions, particularly in environments with few features, leading to inefficient path planning and map creation.
Innovation Solution
The use of LiDAR, ultrasonic, and 3D sensors, along with image processing, to create a cell-based grid map and identify optimal boundary lines between searched and unsearched areas, enabling efficient path planning and map updating.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If feature points are extracted from images to create search paths, then the robot can navigate the environment, but in environments with few features, uncertainty remains high leading to redundant searching
Solution Approach 1:
The patent segments the environment into a grid map with discrete cells, where each cell is marked as searched or unsearched. This segmentation allows the robot to systematically track which areas have been explored and which remain, eliminating redundant searching in already-explored regions while maintaining navigation capability in feature-poor environments.
Solution Approach 2:
The patent changes the parameter representation from continuous feature point coordinates to discrete grid cell states (searched/unsearched). This parameter transformation enables the robot to maintain location awareness and plan paths based on grid map information rather than relying on feature point extraction, thereby improving both search efficiency and location recognition accuracy.
2Productivity
If grid map is used for search traveling, then the robot can systematically explore the environment, but the boundary between searched and unsearched regions cannot be accurately extracted
Solution Approach 1:
The patent uses visual color coding to represent different grid cell states: white for searched regions and black for unsearched regions. This visual differentiation enables accurate boundary extraction between searched and unsearched areas, allowing the robot to precisely identify and navigate to boundaries for efficient map creation.
3Measurement precision
If the robot continuously searches based on high uncertainty feature points, then location accuracy may be improved, but time is wasted searching the same region repeatedly
Solution Approach 1:
The patent implements feedback through the grid map that records which cells have been searched. This feedback mechanism prevents the robot from revisiting and re-searching already-explored regions, thereby eliminating redundant search time while maintaining accurate self-location recognition through grid map-based positioning rather than feature point uncertainty.
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
This approach allows for accurate recognition of unsearched regions and efficient path planning, reducing redundant searches and improving map creation robustness in changing environments.
Implementation Method 1
a sensor unit configured to create LiDAR data regarding an external geometry, a distance to an object, and the like through a LIDAR sensor
Implementation Method 2
a sensor unit configured to create LiDAR data regarding an external geometry, a distance to an object, and the like through a LIDAR sensor, an ultrasonic sensor
Data Source
Figure 1A~1B
Figure 1C~1D
Figure 2~3
AI summary
Creating a map of a moving robot includes: receiving sensor data regarding a distance to an external object through a distance measurement sensor; creating a cell-based grid map based on the sensor data; performing image processing to distinguish between regions in the grid map and create a boundary line between the regions; selecting an optimal boundary line if one or more boundary lines exist; planning a path to the optimal boundary line; and updating the grid map, while moving along the path, whereby a map may be automatically created.