Mobile Robot Location Estimation Using Fused LiDAR and Camera Sensors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for mobile robot location recognition and map creation are susceptible to environmental changes such as lighting variations and object location changes, leading to inaccuracies in estimating the current location.
Innovation Solution
A mobile robot system that combines vision-based and LiDAR-based location recognition technologies, using a camera and laser, to create a robust map and accurately estimate location by fusing different kinds of sensor data, including LiDAR odometry and iterative closest point (ICP) matching.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If vision-based location recognition using camera and feature point matching is used, then location recognition can be performed, but accuracy varies due to environmental changes such as lighting variations and object location changes
Solution Approach 1:
The patent combines vision-based location recognition (using camera and feature point matching) with LiDAR-based location recognition (using laser ranging and ICP algorithm) into a fused system. The controller integrates results from both methods to determine final location information, thereby maintaining accuracy while improving robustness to environmental changes like lighting variations.
Solution Approach 2:
The system dynamically adjusts the weighting or selection of location recognition methods based on environmental conditions. When vision-based recognition becomes unreliable due to lighting changes, the system shifts reliance toward LiDAR-based recognition, changing operational parameters to maintain overall accuracy across varying environments.
2Reliability
If only vision-based location recognition is used, then the system structure can be simpler, but reliability decreases under varying environmental conditions
Solution Approach 1:
The patent merges multiple sensor systems (camera and LiDAR) with different operating principles into a unified location recognition system. This combination increases reliability by providing redundant and complementary measurement methods, while the controller manages the complexity through integrated processing of both sensor data streams.
Solution Approach 2:
The controller acts as an intermediary that receives data from both vision-based and LiDAR-based sensors, processes and fuses this information, and produces reliable location estimates. This mediator coordinates the complex interactions between different sensor systems, managing overall system complexity while maintaining high reliability.
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 provides accurate and reliable location recognition and map creation that is resilient to environmental changes, enabling efficient navigation and cleaning operations.
Implementation Method 1
a LiDAR sensor for acquiring geometry information outside the main body
Implementation Method 2
a camera sensor for acquiring an image of the outside of the main body
Data Source
Figure 1~2
Figure 3~4
Figure 5
AI summary
Disclosed is a mobile robot including a traveling unit configured to move a main body, a LiDAR sensor configured to acquire geometry information outside the main body, a camera sensor configured to acquire an image of the outside of the main body, and a controller configured to create odometry information based on sensing data of the LiDAR sensor and to perform feature matching between images input from the camera sensor based on the odometry information in order to estimate the current location, whereby the camera sensor and the LiDAR sensor may be effectively fused to accurately perform location estimation.