Autonomous Vehicle Data Collection Selective Archiving
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous and semi-autonomous vehicles face challenges in efficiently collecting and transmitting vast amounts of data due to storage limitations and transmission constraints, such as unavailable connections or high costs, which hinder the review of significant actions and their reasoning.
Innovation Solution
A system and method that selectively identifies and archives operational vehicle data based on a pre-defined model, generating performance measurements and determining information gain to decide whether data should be transmitted to a non-local storage location for further analysis, archiving data that meets a threshold to reduce computational and transmission costs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If all operational data is transmitted to cloud server for review, then complete data analysis is achieved, but transmission cost and bandwidth requirements increase significantly
Solution Approach 1:
The system extracts only the most valuable operational data that exceeds normal performance thresholds from the complete dataset, separating critical information from routine data. This extraction approach transmits only essential data to the cloud server, reducing transmission costs while maintaining analysis effectiveness for significant events.
Solution Approach 2:
The vehicle performs local data processing and filtering to identify regions of interest in the operational data. By applying quality assessment locally at the vehicle, the system determines which data segments warrant transmission, optimizing the balance between data completeness and transmission resource consumption.
2Loss of information
If all operational data is stored locally in the vehicle, then complete data is preserved, but storage requirements and computational burden increase
Solution Approach 1:
The system extracts and retains only high-value operational data that exceeds performance thresholds locally, while allowing routine data to be discarded or archived. This selective retention reduces local storage requirements while preserving the most informative data for future analysis and model improvement.
Solution Approach 2:
The system discards low-value operational data that falls within normal performance ranges, freeing up storage capacity. Critical data that exceeds thresholds is retained and can be recovered or transmitted for further analysis, optimizing the trade-off between storage consumption and data utility.
3Loss of information
If transmission connection is maintained continuously for data upload, then real-time cloud synchronization is achieved, but energy consumption and transmission costs increase
Solution Approach 1:
Instead of continuous transmission, the system employs periodic or event-driven data upload based on performance threshold exceedances. Transmission connections are activated only when significant operational data is detected, reducing energy consumption while maintaining synchronization of critical information with the cloud server.
Data Source
AI summary
Systems and methods to systematically identify and collect operational vehicle data for selective transmission to a non-local storage location for further analysis and use in training autonomous and semi-autonomous vehicles are provided. The systems and methods provided overcome limitations in storage and transmission of collected data by selectively archiving only that collected driving data warranting further analysis.