Occupancy Map Updates Using Fleet Sensor Discrepancy Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional maps used by autonomous vehicles lack the accuracy and timeliness required for safe navigation due to limitations in sensor data collection and the expense and inefficiency of traditional mapping methods, which cannot keep pace with frequent road changes.
Innovation Solution
An online system that builds and updates high-definition maps using sensor data from autonomous vehicles, allowing for continuous data collection and sharing to improve map accuracy and freshness, enabling precise vehicle location and safe navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional survey teams use drivers with specially outfitted cars and high resolution sensors to create maps, then map accuracy can be improved, but the cost and time required to complete mapping increases significantly
Solution Approach 1:
Autonomous vehicles perform their own mapping and map validation using their onboard sensors, eliminating the need for dedicated survey teams. Each vehicle independently collects sensor data, detects map discrepancies, and contributes to map updates, making the system self-servicing and highly scalable
Solution Approach 2:
The patent combines mapping functions with the autonomous vehicle's primary navigation and sensing operations. The same sensors used for autonomous driving (cameras, LIDAR, etc.) are also used for map creation and validation, merging multiple functions into a unified system that eliminates redundant equipment and personnel
2Quantity of substance
If survey fleets use a limited number of expensive survey cars to maintain maps, then cost is controlled, but the ability to capture frequent road updates decreases
Solution Approach 1:
Every autonomous vehicle in the fleet serves as its own survey vehicle, continuously collecting and validating map data. This eliminates the need for a separate, limited survey fleet while ensuring that map updates are captured by any vehicle that encounters changes, dramatically increasing both the number of vehicles contributing to mapping and the freshness of map data
Solution Approach 2:
The autonomous vehicles perform multiple functions simultaneously: navigation, obstacle detection, and map maintenance. This multi-functionality allows the entire fleet to participate in map updates without requiring specialized survey vehicles, making the system both cost-effective and highly responsive to road changes
3Duration of action of stationary object
If conventional maps are updated periodically, then map stability is maintained, but the timeliness of capturing road changes decreases
Solution Approach 1:
The system performs continuous map validation and update as autonomous vehicles traverse roads. Instead of periodic updates, the map is continuously checked against current sensor data, ensuring that road changes are detected and incorporated immediately when encountered, eliminating information loss between update cycles
Solution Approach 2:
The system implements a feedback mechanism where autonomous vehicles detect map discrepancies by comparing sensor data with existing maps, report these discrepancies to a central system, and trigger map updates. This closed-loop feedback ensures that road changes are rapidly identified and incorporated into updated maps, maintaining both timeliness and accuracy
Data Source
AI summary
An online system builds a high definition (HD) map for a geographical region based on sensor data captured by a plurality of autonomous vehicles driving through a geographical region. The autonomous vehicles detect map discrepancies based on differences in the surroundings observed using sensor data compared to the high definition map and send messages describing these map discrepancies to the online system. The online system updates existing occupancy maps to improve the accuracy of the occupancy maps (OMaps), and to thereby improve passenger and pedestrian safety. While vehicles are in motion, they can continuously collect data about their surroundings. When new data is available from the various vehicles within a fleet, this can be updated in a local representation of the occupancy map and can be passed to the online HD map system (e.g., in the cloud) for updating the master occupancy map shared by all of the vehicles.