Autonomous Vehicle Semantic Map Updates for Lane Change Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face navigation issues due to outdated maps, which are not updated quickly enough to reflect changing road conditions, leading to restricted areas and inefficiencies in route planning and execution.
Innovation Solution
A system that enables autonomous vehicles to update semantic labels of their maps in real-time using sensor data, allowing for detection of lane line changes and triggering updates without the need for special purpose mapping vehicles, thereby reducing downtime and workload on these vehicles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If maps are updated using special purpose mapping vehicles, then map data accuracy is improved, but update time and productivity deteriorate
Solution Approach 1:
The autonomous vehicle performs dual functions: it operates as a transportation vehicle and simultaneously acts as a mobile mapping device. The sensor system originally designed for navigation and obstacle detection is also used for map update operations, eliminating the need for dedicated mapping vehicles and significantly improving update speed while maintaining data quality
Solution Approach 2:
The system creates a simplified representation of road features by detecting lane line inconsistencies and generating updated map data based on these detections. The sensor system captures environmental data and processes it to create updated semantic labels and map portions, effectively copying and updating map information from the vehicle's operational data
2Reliability
If maps are updated frequently, then navigation reliability is improved, but computational resources and energy consumption increase
Solution Approach 1:
The system extracts only the necessary information for map updates by specifically detecting lane line inconsistencies rather than processing all sensor data. The inconsistency detection module identifies only those features that differ from the stored map data, filtering out redundant information and reducing computational energy requirements while maintaining navigation reliability
Solution Approach 2:
The system performs partial map updates by only processing and updating portions of the map where inconsistencies are detected, rather than reprocessing the entire map. This selective update approach reduces computational energy consumption while ensuring that critical navigation areas are kept current
Data Source
AI summary
The present technology provides systems, methods, and devices that can update aspects of a map as an autonomous vehicle navigates a route, and therefore avoids the need for dispatching a special purpose mapping vehicle for these updates. As the autonomous vehicle navigates the route, data captured by at least one sensor of an autonomous vehicle can indicate an inconsistency between pre-mapped from a high-resolution sensor system describing a location on a map, and current data describing a new feature of the location. The current data can be clustered together based on a threshold spatial closeness, where the clustering describes the new feature, and semantic labels of the pre-mapped data from the high-resolution sensor system can be updated based on the new feature described by the clustered current data.