Scouting Objective Generation for Lane-Bounded Map Updates
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for updating map information in autonomous vehicles are inefficient and resource-intensive, as they often require manual scouting or random vehicle driving, which are slow and costly.
Innovation Solution
A fleet management system generates scouting objectives automatically based on notifications from vehicles identifying changes in the environment, using the vehicles' perception systems to detect inconsistencies between the real world and stored map information, defining scouting areas with first and second bounds to efficiently update the map data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual scouting or random vehicle driving is used to update map information, then map accuracy can be maintained, but the process becomes slow and resource-intensive
Solution Approach 1:
The system uses the autonomous vehicles themselves to perform scouting tasks during their normal operations. Vehicles automatically detect and report map inconsistencies without requiring dedicated scouting missions, making the fleet serve its own mapping needs and eliminating the need for separate manual scouting resources
Solution Approach 2:
The system implements a feedback mechanism where vehicles continuously monitor their environment, compare observed features against stored map information, and automatically report discrepancies. This closed-loop feedback enables continuous map validation and updates based on real-world observations during regular vehicle operations
2Measurement precision
If dedicated scouting missions are assigned to update map information, then comprehensive coverage is achieved, but vehicle availability for transportation services decreases
Solution Approach 1:
The autonomous vehicles perform multiple functions simultaneously: they provide transportation services during normal operations while also conducting map validation and scouting during their routes. The same vehicles used for passenger transport serve as mobile mapping sensors, eliminating the need for dedicated scouting vehicles and maintaining full fleet availability for both purposes
Solution Approach 2:
Map updating activities occur continuously during vehicle operations rather than requiring separate dedicated missions. Vehicles constantly collect and report map data throughout their transportation routes, ensuring continuous map maintenance without interrupting service availability. The scouting function is integrated into the operational workflow rather than being a separate activity
3Measurement precision
If extensive areas are scouted to ensure complete map coverage, then mapping accuracy improves, but time and computational resources increase
Solution Approach 1:
The system extracts and processes only the specific portions of the map that contain inconsistencies or changes. Rather than re-scouting entire areas, the system identifies and targets only the discrete locations where map accuracy issues were detected, significantly reducing the scope and time required for validation while maintaining overall map accuracy
Solution Approach 2:
The scouting effort is concentrated locally at specific problem areas rather than distributed uniformly across entire regions. When a vehicle detects a map inconsistency, the system generates a targeted scouting objective for that specific location and surrounding area, applying intensive validation only where needed rather than wasting resources on already-accurate map sections
Data Source
AI summary
Aspects of the disclosure relate to generating scouting objectives in order to update map information used to control a fleet of vehicles in an autonomous driving mode. For instance, a notification from a vehicle of the fleet identifying a feature and a location of the feature may be received. A first bound for a scouting area may be identified based on the location of the feature. A second bound for the scouting area may be identified based on a lane closest to the feature. A scouting objective may be generated for the feature based on the first bound and the second bound.