Map Acquisition Area Segmentation for Autonomous Driving
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for generating large-scale, high-precision maps for autonomous driving systems face challenges in achieving centimeter-level accuracy at a low cost, particularly due to limitations in data quality control, storage space, and transmission bandwidth in crowdsourcing modes, and are not well-suited for complex urban environments with weak GPS signals and multipath effects.
Innovation Solution
A method that divides acquisition areas into sub-areas based on reference maps, assigns tasks to acquisition entities, and utilizes these entities to collect and process data within their sub-areas, storing only necessary data and verifying map accuracy before transmission, thereby optimizing resource use and improving map production efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If crowdsourcing mode is used for large-scale map acquisition, then map coverage area increases, but data quality control and storage space requirements worsen
Solution Approach 1:
The patent divides the large-scale acquisition area into multiple sub-areas, and further segments data into different types (map data, positioning data, sensor data). By segmenting both spatially and by data type, the system can manage and store only relevant data for each sub-area and entity, preventing unnecessary data accumulation while maintaining comprehensive coverage.
Solution Approach 2:
The patent extracts and stores only necessary data for map generation, such as map data and positioning data, while excluding redundant information. The server extracts specific required data from acquisition entities based on their location and task, reducing overall storage requirements while maintaining map quality.
2Manufacturing precision
If comprehensive data is collected from acquisition entities, then map precision improves, but transmission bandwidth consumption increases
Solution Approach 1:
The server extracts only the necessary data types (map data, positioning data, sensor data) required for map generation from acquisition entities. This selective extraction ensures sufficient map precision while minimizing transmission bandwidth consumption by excluding redundant data.
Solution Approach 2:
The patent implements location-based data collection where acquisition entities only transmit data relevant to their current sub-area and task. Each entity collects and transmits data with appropriate quality and detail level for its specific location and function, optimizing bandwidth usage while maintaining overall map precision.
3Productivity
If multiple acquisition entities are deployed, then map production efficiency improves, but task management complexity increases
Solution Approach 1:
The patent segments the acquisition area into multiple sub-areas and assigns specific tasks to different acquisition entities based on their locations. This spatial segmentation simplifies task management by creating clear boundaries and responsibilities for each entity, reducing coordination complexity while maintaining high production efficiency through parallel operations.
Solution Approach 2:
The server implements a universal task management system that can dynamically assign, monitor, and coordinate multiple acquisition entities regardless of their specific locations or capabilities. This centralized multi-functional management approach handles complex coordination requirements while allowing individual entities to operate autonomously within their assigned tasks.
4Loss of information
If data is collected from all acquisition entities, then map completeness improves, but bandwidth usage and processing time increase
Solution Approach 1:
The server extracts only the essential data types needed for complete map generation (map data, positioning data, sensor data) from acquisition entities. This selective extraction ensures map completeness by capturing all necessary information while reducing processing time through minimized data volumes.
Solution Approach 2:
The patent collects slightly more data than strictly minimum required (excessive action) by gathering map data, positioning data, and sensor data from multiple entities, ensuring map completeness through redundancy. However, it processes only the essential portions needed for map generation, avoiding unnecessary processing overhead and reducing overall processing time.
Data Source
AI summary
Embodiments of the present disclosure provide a method and a device for acquiring a map, a device, and a computer readable storage medium. The method includes: acquiring a reference map of an acquisition area; dividing the acquisition area into a plurality of sub-areas based on the reference map; generating a plurality of acquisition tasks corresponding to the plurality of sub-areas, wherein each of the plurality of acquisition tasks is configured to acquire a map of each of the plurality of sub-areas; and assigning each of the plurality of acquisition tasks to an acquisition entity, to enable the acquisition entity to acquire the map of each of the plurality of sub-areas.