Sensor-Based HD Map Creation with Static-Dynamic Object Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies face challenges in efficiently generating accurate map data and performing localization for autonomous systems using sensor data from RADAR and LIDAR sensors.
Innovation Solution
The system processes RADAR and LIDAR sensor data to differentiate between static and dynamic objects, and uses this information to generate high-definition map data and perform localization operations for autonomous vehicles and machines.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sensor data from RADAR and LIDAR sensors is processed to generate map data, then the accuracy and detail of the map is improved, but the computational complexity and processing time increase
Solution Approach 1:
The system segments the sensor data processing by separating static object detection from dynamic object detection. Static objects are identified and excluded from localization calculations, while dynamic objects are retained. This segmentation reduces the complexity of map generation by dividing the problem into manageable parts with different processing requirements.
Solution Approach 2:
The system extracts and removes dynamic objects from the sensor data before generating the map. By taking out the dynamic objects that would complicate the map structure, the system achieves simpler, more accurate static maps while still maintaining awareness of dynamic elements for localization purposes.
2Adaptability or versatility
If dynamic objects are included in the map data, then the map reflects current environmental conditions, but the localization accuracy deteriorates due to false positives
Solution Approach 1:
The system implements dynamic filtering by continuously identifying and excluding detected dynamic objects from the map generation process. This dynamic approach allows the map to remain accurate and static in nature, while the system adapts to changing environmental conditions by实时更新 the list of dynamic objects to be excluded.
3Area of stationary object
If all sensor data points are processed, then complete environmental coverage is achieved, but the data processing time and resource consumption increase
Solution Approach 1:
The system extracts and removes points corresponding to dynamic objects from the sensor data before processing. This extraction reduces the total number of data points that need to be processed for map generation, thereby improving processing efficiency while maintaining complete coverage of static environmental features.
Solution Approach 2:
The system performs partial processing by focusing computational resources only on static objects for map generation, while handling dynamic objects separately for localization. This partial action approach improves overall processing efficiency by avoiding unnecessary computation on dynamic elements that don't contribute to the static map structure.
Data Source
AI summary
One or more embodiments of the present disclosure relate to generation of map data. In these or other embodiments, the generation of the map data may include determining whether objects indicated by the sensor data are static objects or dynamic objects. Additionally or alternatively, sensor data may be removed or included in the map data based on determinations as to whether it corresponds to static objects or dynamic objects.