Local Sensor Map Generation for Real-Time Road Rule Updates
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous vehicles rely on labor-intensive, outdated pre-generated detailed maps for navigation, which become inaccurate due to road modifications and require human annotation, limiting their real-time adaptability and accuracy.
Innovation Solution
A system that uses locally captured sensor data, such as from cameras and Lidar sensors, to identify lane segments and observables, and determines driving rules in real-time through a rules of the road module, allowing for automatic generation and updating of driving rules without human intervention.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If pre-generated detailed maps are used for autonomous vehicle navigation, then navigation decisions can be made based on detailed environmental data, but the maps become outdated quickly due to road modifications and require labor-intensive human annotation
Solution Approach 1:
The system enables autonomous vehicles to self-generate and self-update map data using their own sensors and onboard processors. The vehicle captures sensor data, identifies lane segments and observables, and determines driving rules locally without requiring external human annotation or centralized map updates, thus achieving real-time adaptability to road modifications
Solution Approach 2:
The system performs preliminary identification of lane segments and observables from sensor data before navigation decisions are required. By pre-processing sensor data to extract relevant road features and determine driving rules in advance, the system prepares up-to-date navigation information dynamically as the vehicle moves through modified road conditions
2Loss of information
If pre-generated detailed maps are manually annotated, then comprehensive driving information can be captured, but the process becomes labor intensive and time consuming
Solution Approach 1:
The system replaces the mechanical process of manual human annotation with automated electronic processing. Sensors capture road environment data, and onboard processors automatically identify lane segments, observables, and determine driving rules through computational algorithms, eliminating the need for manual map annotation while maintaining information completeness
Solution Approach 2:
The system creates digital copies of road features directly from sensor data rather than manually transcribing them. Sensors capture optical and spatial information about lane segments and road observables, which are then processed into structured digital representations that can be immediately used for navigation, replacing labor-intensive manual copying and annotation processes
3Reliability
If traditional high-definition maps are used, then detailed road information is available, but they cannot quickly adapt to construction and road modifications
Solution Approach 1:
The system transitions from static pre-generated maps to dynamic real-time map generation. The autonomous vehicle continuously captures sensor data and updates lane segment identification and driving rules dynamically as it travels, allowing the navigation system to adapt immediately to road modifications without waiting for periodic manual map updates
Solution Approach 2:
The system implements feedback by continuously comparing sensor data against determined driving rules and updating map information based on actual observed road conditions. This closed-loop approach ensures that navigation information remains accurate and current, automatically adjusting to construction zones and road modifications as they are encountered
Data Source
AI summary
A rules of the road module and database determines rules using information about segments identified from locally captured image data and observables identified in the image data.