Control method of mobile robot
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing mobile robot technologies face challenges in accurately recognizing their position on a map, especially under varying illumination conditions and in situations like kidnapping, where external factors disrupt their navigation, leading to inefficiencies and increased costs due to reliance on infrared signals, laser sensors, or ultrasonic sensors.
Innovation Solution
A method involving the generation of two basic maps under different illumination conditions, merging them to create a unified map that allows for accurate position estimation regardless of illumination, using image information from the ceiling to simplify device implementation and enhance estimation accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If infrared signals are used for position recognition, then the mobile robot can move to limited destinations, but the robot cannot move to any other destination and may roam indefinitely
Solution Approach 1:
The patent replaces infrared signal-based passive navigation with active laser scanning and map-building systems. The mobile robot uses laser sensors to actively scan the environment, construct maps, and determine positions through coordinate transformations, substituting the limited infrared approach with a more capable active sensing system.
Solution Approach 2:
The patent creates a digital copy of the physical environment through map construction. The laser sensor data is processed to generate a virtual map representation that the robot uses for navigation and position recognition, allowing the robot to operate without relying on predefined infrared signal destinations.
2Reliability
If laser sensors or ultrasonic sensors are used to recognize current position in position jumping situations, then position recognition is possible, but cost is increased
Solution Approach 1:
The patent makes the laser sensor serve multiple functions: it is used both for constructing the environmental map and for determining the robot's current position through coordinate transformations. This multi-functional use eliminates the need for separate positioning sensors, reducing overall system cost while maintaining reliable position recognition even in kidnapping situations.
3Measurement precision
If feature points from ceiling images are used for position estimation, then position recognition is achieved, but feature points change depending on illumination conditions
Solution Approach 1:
The patent performs preliminary map construction during a learning phase when the robot explores the environment. The map is built in advance and stored, containing information about the environment that can be used for position estimation later. This preliminary action separates map acquisition from position recognition, allowing the system to handle illumination changes during operation.
Solution Approach 2:
The patent introduces a coordinate transformation system as an intermediary between the laser sensor data and the image-based feature points. The laser sensor provides a stable reference frame, and through coordinate transformations, the system can match image features with map data regardless of illumination conditions, acting as a mediator that bridges the two sensing modalities.
Data Source
Figure 1
Figure 2~3
Figure 4~5
AI summary
A method of controlling a mobile robot includes a first basic learning process of generating a first basic map based on environment information acquired in a traveling process, a second basic learning process of generating a second basic map based on environment information acquired in a separate traveling process, and a merging process of merging the first basic map and the second basic map to generate a merged map.