Object Characterization via Grid Map Quantization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for characterizing objects in autonomous driving systems face challenges in reducing processing time while maintaining high spatial accuracy, particularly with high-resolution measurement data from location sensors like LIDAR, Radar, and ultrasonic sensors, which increases computational complexity.
Innovation Solution
The method involves quantizing measurement samples from high-resolution location sensors into a grid map with lower spatial resolution, assigning weight coefficients based on measurement accuracy, and computing line parameters to characterize objects, thereby reducing computational complexity and processing time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If high spatial resolution measurement samples are used from location sensors, then measurement precision is improved, but processing time increases
Solution Approach 1:
The patent segments the high-resolution measurement data by dividing the spatial environment into discrete cells of varying resolutions. Different regions are represented at different levels of detail, allowing the system to process only the necessary amount of data for each area, thus reducing overall processing time while maintaining measurement precision where needed.
Solution Approach 2:
The patent applies local quality by assigning different resolution levels to different spatial regions based on their importance. High-resolution representation is allocated to regions containing objects of interest, while low-resolution representation is used for background or less critical areas, optimizing the balance between measurement precision and processing efficiency.
2Measurement precision
If multiple location sensors are combined to achieve increased spatial resolution, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent merges data from multiple location sensors into a unified grid map representation. By combining sensor inputs at the data processing level rather than requiring complex coordinated sensor systems, the approach achieves increased spatial resolution while managing device complexity through data fusion rather than hardware complexity.
Solution Approach 2:
The patent creates a universal grid map data structure that can accommodate and integrate data from various types of location sensors (LIDAR, radar, ultrasonic sensors). This multi-functional representation allows different sensor types to contribute to the same spatial model, reducing the need for sensor-specific processing complexity.
Data Source
AI summary
A concept of characterizing an object based on measurement samples from one or more location sensors, the measurement samples having a first spatial resolution. The measurement samples are quantized to a grid map of weighted cells having a second spatial resolution lower than the first spatial resolution, wherein a measurement sample contributes to a weight coefficient of one or more weighted cells depending on a measurement accuracy. Parameters of one or more lines fitting the weighted cells are computed to obtain a characterization of the object.