HD Map Task Scheduling for Parallel Labeling and Version Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional Geographic Information Systems (GIS) are inadequate for generating and updating High-Definition (HD) maps for autonomous vehicles, as they are limited to two-dimensional data, require direct network connectivity, and lack scalability and task management capabilities, making them inefficient for the precise and distributed data needs of autonomous vehicles.
Innovation Solution
A highly distributed and scalable GIS system is developed to automate the generation, revision, and distribution of HD maps, incorporating task management, access control, version control, and release management to optimize mapping throughput and quality, allowing for minimal user input and simultaneous editing by multiple users.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If conventional Geographic Information Systems (GIS) are used for map generation, then the system is simple to operate, but the manufacturing precision and data dimensionality are insufficient for autonomous vehicle requirements
Solution Approach 1:
The system segments the map generation process into multiple independent task stages (data collection, processing, validation, distribution) that can be executed separately and in parallel across different computing devices, enabling high precision without requiring a monolithic complex system
Solution Approach 2:
The system transitions from conventional 2D GIS maps to multi-dimensional HD maps incorporating 3D spatial data, sensor data layers, and temporal information, achieving higher manufacturing precision by adding dimensional complexity rather than increasing overall system complexity
2Adaptability or versatility
If conventional GIS systems require direct network connectivity to create and update maps, then data distribution is centralized, but the scalability and distribution capability are limited
Solution Approach 1:
The system segments map data into discrete task stages and distributes them across multiple independent nodes in a task graph, allowing each node to operate autonomously with local data processing capabilities, thereby enhancing distribution capability without requiring complex centralized network infrastructure
Solution Approach 2:
The system introduces task graphs and workflow orchestration as intermediaries between data sources and map consumers, enabling scalable distribution through standardized interfaces and protocols that simplify network complexity while enhancing adaptability
3Productivity
If conventional GIS systems permit only one human or machine to edit data sources at a time, then data consistency is maintained, but the productivity and mapping throughput are reduced
Solution Approach 1:
The system segments the editing process into discrete task stages with defined dependencies, allowing multiple users to work on different stages simultaneously while maintaining data consistency through stage-gated validation and version control mechanisms
Solution Approach 2:
The system implements automated feedback loops including quality assurance validation, conflict detection, and version control that monitor and maintain data consistency across parallel editing operations, enabling high productivity without sacrificing reliability
4Measurement precision
If conventional GIS systems generate maps only accurate up to tens of meters, then the device complexity is low, but the measurement precision is insufficient for autonomous vehicle navigation
Solution Approach 1:
The system transitions from 2D map representations to multi-dimensional HD maps incorporating 3D spatial coordinates, sensor data layers, and temporal dimensions, achieving centimeter-level measurement precision by utilizing additional dimensional information rather than increasing processing complexity of traditional 2D data
Data Source
AI summary
The present technology pertains to a task management system for map labeling tasks. The system can determine when one task is dependent on completion of another task and schedule those tasks accordingly. Further the system can ensure that tasks are completed with a proper priority and can track completion of these tasks. The present technology ensures sufficient work is completed to speed up map release versions.