Map Drift Detection Using Local-Global Trajectory Comparison
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face navigation challenges due to errors in global maps, particularly in complex environments with poor localization accuracy, leading to unsafe situations.
Innovation Solution
Implementing a local map with a high refresh rate, independent of the global map, to accurately represent the vehicle's environment and calculate the drift between the global and local maps, allowing for updates to improve navigation accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If a global map is used for navigation, then the vehicle can operate in large environments, but localization accuracy deteriorates in complex environments
Solution Approach 1:
The patent divides the mapping system into two segments: a global map for large-area coverage and a local map for high-precision localization. The local map is generated at a higher refresh rate and is associated with a voxel space representing the immediate environment, while the global map provides broader context. This segmentation allows the system to leverage the strengths of both map types.
Solution Approach 2:
The patent introduces a temporal dimension by operating at two different refresh rates. The local map is updated at a higher frequency than the global map, creating a multi-timescale system. This dimensional approach allows real-time localization improvements without requiring continuous global map updates.
2Measurement precision
If the global map is updated frequently, then localization accuracy improves, but energy consumption and computational load increase
Solution Approach 1:
The patent applies partial action by updating only the local map at high frequency while maintaining the global map at a lower refresh rate. This selective updating strategy provides sufficient localization accuracy for safe operation without the excessive energy consumption that would result from continuously updating the entire global map.
Solution Approach 2:
The system segments the map updating function, assigning different update frequencies to different map components. The local map receives frequent updates for immediate navigation needs, while the global map is updated less frequently, reducing overall computational and energy demands.
3Reliability
If drift between global and local maps is corrected continuously, then navigation safety improves, but system complexity increases
Solution Approach 1:
The patent implements a feedback mechanism where the system continuously monitors drift between the global and local maps by comparing the vehicle's pose estimates from both maps. When drift exceeds a threshold, the system corrects the global map pose using the more accurate local map data, ensuring navigation safety without requiring complex continuous correction algorithms.
Data Source
AI summary
Techniques for determining errors or drifts between maps used for updating maps and/or controlling a system which uses the map. In some examples, a first, global, map may be received or determined. Sensor data may then be used to localize a system with respect to the first map and to generate a first trajectory relative to the first map. The sensor data may be used to create a second map and a second trajectory for navigating the system relative to the second map. Differences between the first and second trajectories (or portions thereof), when compared in a common reference frame, may be used as an indication of drift between various processes or errors in the maps and, subsequently, be used for updating the first map and/or controlling the system.