Dynamic Map Entity Prediction for Navigation Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current map display systems for vehicles, such as satellite maps, often lack real-time updates, leading to inaccurate information about changing entities like construction sites and seasonal changes, which can affect navigation.
Innovation Solution
A system that identifies entities changing over time, predicts their changes using historical data, and updates the map accordingly, incorporating sensors and machine learning to ensure accuracy and relevance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If satellite maps are not constantly updated, then map data storage and processing costs are reduced, but the accuracy and timeliness of map information deteriorates
Solution Approach 1:
The system enables map data to update itself automatically by detecting changes through sensors and comparing them with historical map data. The computational system autonomously identifies changed entities, determines their types, and updates map records without requiring manual intervention or constant full-map updates, thus maintaining high accuracy while improving update efficiency.
Solution Approach 2:
The system implements a feedback mechanism where sensor data from the vehicle is continuously compared with existing map data. When discrepancies are detected (indicating changes), the system processes this feedback information through entity determination and updates the map accordingly. This closed-loop feedback ensures map accuracy is maintained dynamically without requiring constant proactive updates.
2Reliability
If map updates are performed frequently, then map information accuracy is improved, but system complexity and computational resources increase
Solution Approach 1:
The system extracts only the changed portions of map data rather than processing entire maps. By identifying specific entities that have changed (construction sites, seasonal features, etc.) and updating only those records, the system maintains high navigation reliability while significantly reducing computational complexity and resource requirements compared to full-map frequent updates.
Solution Approach 2:
The system segments map data into discrete entities (construction sites, vegetation, water bodies, etc.) and processes changes at the entity level rather than treating maps as monolithic structures. This segmentation allows selective updating of only affected entities, reducing overall system complexity while maintaining navigation reliability through accurate, timely updates of critical elements.
3Loss of information
If all entities in map are monitored for changes, then completeness of map updates is improved, but processing time and computational load increase
Solution Approach 1:
The system performs partial monitoring by focusing computational resources on entities known to change frequently or are critical for navigation (construction sites, seasonal vegetation, water bodies). Rather than uniformly monitoring all map entities, the system applies change detection selectively to high-priority categories, ensuring update completeness for critical elements while reducing overall processing time and computational load.
Solution Approach 2:
The system applies different monitoring strategies to different types of entities based on their change characteristics. High-change entities like construction sites receive continuous attention, while stable entities are monitored less frequently. This local quality approach ensures complete tracking of dynamic elements without the overhead of uniform intensive monitoring across the entire map, optimizing the balance between completeness and time efficiency.
Data Source
AI summary
Provided herein is a system comprising: one or more processors; and a memory storing instructions that, when executed by the one or more processors, causes the system to perform: identifying, in a map, one or more entities that change over time; predicting an amount of change of the identified one or more entities over time; and updating the map based on the predicted amount of change of the identified one or more entities over time.