In-Vehicle Metadata Generation for Automotive Data Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles generate vast amounts of data, but existing technologies face challenges in efficiently processing and analyzing this data due to limitations in in-vehicle computing resources and constraints on time, bandwidth, and power consumption.
Innovation Solution
An automotive data processing system is deployed in a vehicle, comprising a storage subsystem and a processor. The processor identifies specified features-of-interest in the data, generates metadata that tags these features, and exports at least part of the metadata to an external system, allowing for selective retrieval of relevant data portions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If all vehicle-generated data is uploaded to remote processors, then comprehensive data analysis is achieved, but communication bandwidth and power consumption increase significantly
Solution Approach 1:
The patent extracts and processes only the essential metadata and selected portions of data locally in the vehicle using onboard processors, rather than uploading all raw data. This extraction approach identifies and retains only the most relevant information (e.g., features of interest, anomaly detections) for remote analysis, dramatically reducing communication bandwidth and power consumption while preserving analytical value.
Solution Approach 2:
The patent segments the data processing function into two parts: local preprocessing and metadata generation in the vehicle, and comprehensive analysis of selected portions at remote processors. This segmentation allows the vehicle to handle data locally using AI models and processors, filtering down to essential information before transmission, thereby reducing the energy cost of uploading complete datasets.
2Loss of information
If all vehicle-generated data is transferred to external systems, then complete data processing is achieved, but communication time and bandwidth requirements increase
Solution Approach 1:
The patent performs preliminary processing actions locally in the vehicle by generating metadata and identifying selected portions of data that require external analysis. This preliminary action of filtering and tagging data before transmission reduces the volume of data needing transfer, thereby minimizing communication time and bandwidth usage while ensuring that remote processors receive pre-processed, high-value information.
3Productivity
If comprehensive data is processed locally in the vehicle, then immediate data analysis is achieved, but in-vehicle computing resource demands increase
Solution Approach 1:
The patent introduces metadata as an intermediary layer between raw sensor data and remote processing. Instead of attempting to process all comprehensive data locally, the system generates compact metadata representations that capture essential information. This intermediary approach enables local processing of a manageable subset of data while maintaining the capability for comprehensive analysis through coordinated remote processing.
Data Source
AI summary
An automotive data processing system includes a storage subsystem and a processor. The storage subsystem is disposed in a vehicle and is configured to store at least data produced by one or more data sources of the vehicle. The processor is installed in a vehicle and is configured to apply, to the data stored in the storage subsystem or that is en route to be stored in the storage subsystem, at least one model that identifies one or more specified features-of-interest in the data, so as to generate metadata that tags occurrences of the specified features-of-interest in the stored data, and to export at least part of the metadata to an external system that is external to the vehicle.