Environment Map Reliability Layer for Precise Vehicle Localization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current environment representation methods for autonomously navigating vehicles and drones are plagued by inaccuracies due to limited angular resolution, reflective surfaces, transparent obstacles, and dynamic changes in the environment, leading to unreliable position determination and path planning.
Innovation Solution
Incorporating reliability data into environment representations, which indicate the detectability of features by measuring devices, allowing for location-resolved storage and updating of map data and reliability values, and using particle filter algorithms for position determination and path planning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional environment representation methods are used, then the system can operate with simple data structures, but the position determination and path planning accuracy deteriorate due to unreliable feature detection
Solution Approach 1:
The environment representation is segmented into multiple data layers: base map data, reliability data, and history data. Each layer serves a specific function, allowing the system to process and store information in a modular fashion that improves position determination accuracy without creating an unmanageable monolithic structure
Solution Approach 2:
Reliability and history data are pre-calculated and stored alongside map features before actual navigation tasks. This preliminary preparation allows the system to quickly access pre-evaluated detection reliability information during runtime, improving position determination accuracy without adding computational complexity during critical navigation operations
2Measurement precision
If all detected features are treated with equal reliability, then the processing logic remains simple, but navigation accuracy deteriorates due to undifferentiated treatment of reliable and unreliable detections
Solution Approach 1:
Different reliability values are assigned to different spatial locations and feature types based on local detection conditions. The system evaluates and stores reliability data specific to each map feature, allowing path planning to weight features according to their local detection reliability rather than applying a uniform evaluation criterion throughout the entire environment
3Reliability
If the environment representation is updated frequently to reflect dynamic changes, then the representation remains current, but computational resources and processing time are consumed
Solution Approach 1:
The system performs periodic updates of reliability and history data at scheduled intervals rather than continuously processing every sensor input. This periodic evaluation maintains representation accuracy by regularly incorporating new detection information while avoiding the continuous computational burden of real-time processing for every environmental change
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An environment representation device (50) has a data carrier (51) and an associated interface device (52), wherein the data carrier contains data representing an environment, with map data parts (51a) that spatially specify features of an environment or allow the derivation of such feature information, and with reliability data parts (51b) that spatially specify reliability data of features of an environment or allow the derivation of such reliability data and that spatially specify how reliably the respective represented features were assessed to be detectable. The interface device makes map data and reliability data accessible to each other in a spatially resolved manner.