Mobile Robot Mapping With LiDAR Node-Grid Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing mobile robot mapping techniques face challenges in accurately generating maps, particularly in distinguishing between dynamic and fixed obstacles, and in environments with few features, leading to inefficiencies and potential collisions due to direction limitations and inaccurate obstacle classification.
Innovation Solution
The mobile robot employs a combination of LiDAR sensors and image processing to create both node-based and grid-based maps, using LiDAR data to determine open movement directions and update node data, while image processing distinguishes between searched and unsearched regions to optimize path planning and map creation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If a topological map is created using only distance information from distance sensors, then map creation is simple, but the connection relationship between nodes becomes inaccurate and dynamic obstacles cannot be properly distinguished
Solution Approach 1:
The patent combines distance information from distance sensors with image information from image sensors to create a comprehensive map. This merging of multiple information sources allows the system to maintain simple map creation processes while significantly improving node connection accuracy and enabling proper distinction between dynamic and fixed obstacles through multi-modal data fusion.
Solution Approach 2:
The patent introduces image information as an intermediary element that mediates between simple distance-based mapping and accurate environmental understanding. The image data serves as a bridge that enhances the basic distance information, providing visual context that improves node connection accuracy without complicating the overall mapping process.
2Ease of operation
If feature points are extracted from images to create search paths, then path planning is possible, but uncertainty in featureless environments causes continuous searching of the same region
Solution Approach 1:
The patent changes the parameters used for path planning by incorporating multiple types of information (distance, image, and their fused data) instead of relying solely on image feature points. This parameter change allows the system to maintain path planning capabilities while improving search reliability in featureless environments through alternative or complementary parameters.
Solution Approach 2:
The patent creates a universal mapping approach that works across different environment types by combining multiple sensing modalities. The system can function effectively in both feature-rich and featureless environments by utilizing the complementary strengths of distance sensors and image sensors, making the path planning reliable across diverse conditions.
3Device complexity
If only node information is used for map creation, then directional movement is simple, but the robot cannot navigate in all directions efficiently
Solution Approach 1:
The patent adds another dimension of information (image data) to the traditional node-based mapping approach. This dimensional enhancement provides additional spatial context that enables the robot to navigate in all directions efficiently while maintaining relatively simple system architecture. The extra dimensional information from images complements the node structure without significantly increasing complexity.
4Productivity
If grid-based search is used, then coverage is systematic, but boundaries between searched and unsearched regions cannot be accurately extracted
Solution Approach 1:
The patent merges grid-based search systematicity with image-based boundary detection precision. By combining the structured approach of grid searching with the visual boundary identification capabilities of image processing, the system achieves both systematic coverage and accurate extraction of boundaries between searched and unsearched regions.
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 enables the mobile robot to accurately and efficiently generate maps, minimizing collisions and path repetition by accurately classifying obstacles and navigating through complex environments.
Implementation Method 1
a light detection and ranging (LiDAR) sensor 175 that outputs a laser and acquires external geometry information based on reception pattern of the laser
Implementation Method 2
acquires external geometry information based on reception pattern of the laser
Data Source
AI summary
Provided is a mobile robot including a traveling unit configured to move a main body, a light detection and ranging (LiDAR) sensor configured to acquire external geometry information of the main body, and a controller configured to create node data based on LiDAR data sensed by the LiDAR sensor, to create grid map based on the LiDAR data and the node data, to create first map data based on the node data, to update the grid map based on the first map data, and to image-process the updated grid map to create second map data, where a map may be quickly and safely created without an environmental restriction, by effectively combining a node-based map creating method and a grid-based map creating method.