Mobile Object Positioning Using Sensor Fusion and Map Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing method for estimating the position of a mobile object, such as an Automated Guided Vehicle (AGV), suffers from decreased accuracy as the moving distance increases, making high-reliability estimation challenging.
Innovation Solution
An information processing apparatus that combines first and second processing results from a depth sensor and image capturing apparatus installed on the mobile object with map-related information, and a monitoring camera's observation result, using different processing methods to determine the position and orientation of the mobile object, enhancing accuracy through integration of these results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a single sensor or processing method is used to estimate the position of the mobile object, then the device complexity is low, but the measurement precision decreases as the moving distance increases
Solution Approach 1:
The patent combines multiple processing methods (first processing method using depth sensor and second processing method using image capturing apparatus) to determine the position of the mobile object. By merging the results from different sensors and processing approaches, the system achieves high-reliability position estimation that maintains accuracy over long distances, resolving the contradiction between measurement precision and device complexity
Solution Approach 2:
The patent introduces map-related information as an intermediary element that mediates between the sensor measurements and the final position determination. The map information serves as a reference framework that enhances the accuracy of position estimation by providing contextual spatial relationships, allowing the system to achieve high precision without proportionally increasing device complexity
2Reliability
If multiple processing methods and data sources are integrated to improve position estimation accuracy, then the measurement precision increases, but the device complexity and processing requirements increase
Solution Approach 1:
The patent segments the position determination process into distinct processing methods: a first processing method using depth sensor data and a second processing method using image capturing apparatus. Each segment handles specific aspects of position estimation independently, then their results are combined. This segmentation allows the system to achieve high reliability through multiple data sources while managing complexity by organizing processing into modular, separate stages
3Measurement precision
If a single processing method is used, then the processing time is short, but the position estimation accuracy decreases over long distances
Solution Approach 1:
The patent performs preliminary processing of sensor data through multiple processing methods before final position determination. By pre-processing depth sensor and image capturing apparatus data through separate processing methods and preparing map-related information in advance, the system establishes a robust foundation for accurate position estimation that maintains precision over long distances without excessive processing delays
Data Source
AI summary
There is provided with an information processing apparatus. An acquisition unit acquires a first processing result including information for identifying the position of the mobile object and a second processing result including information for identifying the position of the mobile object. The first processing result is obtained by executing a first processing method on an image obtained by measuring at least surroundings of the mobile object by using a light receiving sensor installed on the mobile object. The second processing result is obtained by executing a second processing method different from the first processing method on an observation result obtained by observing the mobile object by using a light receiving sensor installed at a location at which it is possible to observe the mobile object.