Scouting Objective Generation for Autonomous Fleet Map Updates
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for updating map information used by autonomous vehicles are inefficient, as they often require significant time and resources, and may not detect all changes in the environment, especially when vehicles are also providing transportation services.
Innovation Solution
A scouting system that generates new scouting objectives based on notifications from vehicles identifying inconsistencies between detected features and pre-stored map information, defining areas to be scouted and configuring vehicles for data capture, allowing for passive detection of changes and efficient objective generation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional scouting methods are used (assigning persons or random vehicle patterns), then map information can be updated, but significant time and resources are required and not all changes are detected
Solution Approach 1:
The system implements feedback by using vehicles' sensor data to detect inconsistencies between actual environmental features and pre-stored map information. When discrepancies are found (such as new roads, construction zones, or changed landmarks), the system automatically generates scouting objectives to verify and update the map data, creating a closed-loop feedback mechanism that continuously improves map accuracy without requiring dedicated scouting resources.
Solution Approach 2:
Vehicles performing their primary transportation function simultaneously contribute to map updates by detecting and reporting environmental changes. The system leverages the vehicles' existing sensors and navigation capabilities to perform scouting tasks without requiring separate dedicated scouting vehicles or personnel, thus achieving self-service where the transportation fleet updates its own operational data.
2Measurement precision
If traditional scouting methods are used (assigning persons or random vehicle patterns), then map information can be updated, but resource requirements are significant
Solution Approach 1:
The system makes the transportation vehicles multi-functional by enabling them to perform both their primary transportation role and secondary map scouting functions simultaneously. The same sensors used for navigation and obstacle detection are repurposed to identify environmental changes, eliminating the need for dedicated scouting resources and achieving universal utilization of existing fleet assets.
Solution Approach 2:
The transportation fleet serves dual purposes by automatically detecting and reporting map inconsistencies during normal operations. This self-service approach eliminates the need for separate scouting personnel or dedicated scouting vehicles, significantly reducing resource requirements while maintaining comprehensive detection capabilities.
3Productivity
If vehicles provide transportation services while updating maps, then resource efficiency improves, but map information accuracy may be compromised
Solution Approach 1:
The system maintains accuracy by implementing a feedback verification mechanism. When vehicles detect potential map inconsistencies during transportation, these observations are flagged as scouting objectives and subsequently verified by other vehicles or centralized processing. This feedback loop ensures that incidental detections are validated before permanent map updates occur, preserving accuracy while enabling efficient simultaneous operations.
Solution Approach 2:
The system performs preliminary detection during normal transportation operations, identifying potential map inconsistencies before they become critical issues. These preliminary findings are then subjected to verification and validation processes, allowing the system to maintain high accuracy standards while continuously updating maps through the fleet's regular operations.
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.