Autonomous Driving Sensor Sampling for Efficient Map Data Storage
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous driving systems for mobile robots face challenges in normal operation due to high data processing loads and insufficient storage capacity, particularly when identifying location information and storing map data for navigation.
Innovation Solution
An autonomous driving control apparatus that dynamically adjusts sampling rates for sensing data from different sensors, generates voxel data for identified objects, and stores map data efficiently, using different weights for data meeting specified conditions to optimize processing and storage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a large amount of sensing data is collected and processed to identify location information and generate map data, then the accuracy and completeness of location information is improved, but the data processing load increases and storage capacity becomes insufficient
Solution Approach 1:
The patent applies different sampling rates to different spatial regions based on their importance. High-sampling-rate regions are applied to areas with specified objects (obstacles, targets) where high measurement precision is needed, while low-sampling-rate regions are applied to empty spaces where lower precision is acceptable. This resolves the contradiction by making data quality local rather than uniform, improving accuracy where needed while reducing overall data volume and processing load.
Solution Approach 2:
The patent dynamically changes the sampling rate parameter based on the presence of specified objects. When specified objects are detected in certain regions, the sampling rate is increased for those regions; when no specified objects are present, the sampling rate is decreased. This parameter adaptation allows the system to maintain high location accuracy for important objects while reducing the overall data processing burden across the entire sensing area.
2Measurement precision
If a high sampling rate is applied to all sensing data to ensure accurate location information, then measurement precision is improved, but storage requirements increase and processing complexity increases
Solution Approach 1:
Instead of applying a uniform high sampling rate to all sensing data, the patent applies high sampling rates only to local regions containing specified objects, while using lower sampling rates in other regions. This ensures measurement precision is maintained where it matters (around obstacles and targets) while significantly reducing the total quantity of sensed data that needs to be stored and processed.
3Measurement precision
If detailed map data is stored for all areas to improve navigation accuracy, then location information accuracy is improved, but storage capacity requirements increase
Solution Approach 1:
The patent stores map data with varying levels of detail based on regional importance. Areas containing specified objects are stored with high sampling rates and detailed information, while empty areas are stored with lower sampling rates and less detail. This allows the system to maintain high navigation accuracy in critical regions while minimizing overall storage capacity requirements.
Data Source
AI summary
An autonomous driving control apparatus includes a sensor device, a memory storing instructions, and a controller. The autonomous driving control apparatus obtains first sensing data about a driving path of a driving device using a first sensor, identifies a first specified object included in the first sensing data and meeting a specified condition, identifies a first sampling rate to be applied to a first point cloud data corresponding to the first specified object, obtains second sensing data about the driving path using a second sensor, identifies a second specified object included in the second sensing data, identifies a second sampling rate to be applied to second point cloud data corresponding to the second specified object, and samples the first sensing data and the second sensing data respectively using the first sampling rate and the second sampling rate.