Mobile Object Self-Positioning With Parallel Map Set Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing mobile object control systems face challenges in estimating self-position efficiently when dealing with large volumes of map data, and issues arise when maps have missing data, leading to processing bottlenecks and inaccurate positioning.
Innovation Solution
A mobile object control system that utilizes multiple map sets, each classified by conditions such as position, time, and lighting, performs parallel matching processes to select the most suitable map set for self-position estimation, thereby reducing processing load and improving accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a large number of map data are used for self-position estimation, then positioning accuracy is improved, but the amount of processing required increases
Solution Approach 1:
The patent divides the large number of map data into multiple map sets, where each map set contains a subset of maps. The recognition unit performs matching processes on multiple map sets in parallel, selecting the most appropriate map set based on matching results. This segmentation approach maintains positioning accuracy by utilizing comprehensive map data while improving processing efficiency through parallel processing and selective matching.
2Productivity
If multiple map sets are processed in parallel, then processing efficiency is improved, but device complexity increases
Solution Approach 1:
The system segments map data into multiple manageable map sets that can be processed in parallel. Each map set is handled independently through matching processes, allowing efficient utilization of computational resources while maintaining system manageability through structured organization of map data.
Solution Approach 2:
The system performs preliminary organization of map data into multiple map sets before the matching process. This preliminary segmentation and preparation enables subsequent parallel processing to proceed efficiently, reducing the complexity of real-time decision-making during the matching phase.
3Productivity
If a single map is used for positioning, then processing load is reduced, but positioning fails when map data is missing
Solution Approach 1:
Instead of relying on a single map, the patent segments map data into multiple map sets, where each map set contains multiple maps. This segmentation provides redundancy, ensuring that if one map or map set has missing data, other map sets can compensate, thereby maintaining positioning reliability without significantly increasing processing load through selective parallel processing.
Solution Approach 2:
The system prepares multiple map sets in advance as a cushion against potential data missing issues. By having multiple pre-prepared map sets with different data compositions, the system ensures that positioning can continue reliably even if some map data is missing or incomplete during operation.
Data Source
AI summary
A mobile object control device acquires a plurality of map sets each including a plurality of the maps, performs a matching process for each of the map sets between each of the plurality of maps included in each map set and an image obtained by capturing an image of a surrounding situation of a mobile object, selects any of the plurality of map sets on the basis of a plurality of matching results corresponding to the plurality of map sets, and estimates the self-position of the mobile object on the basis of at least one of the maps included in the selected map set.