ADS Scenario Description Generation for Privacy-Safe Fleet Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current ADS solutions face challenges with data collection from a fleet of vehicles due to bandwidth, storage, and data privacy constraints, making it difficult to maintain adequate performance over time and comply with regulatory frameworks.
Innovation Solution
A method and system that generates textual scenario descriptions from sensor data using embedding and description generator networks, allowing efficient data collection and transmission while preserving privacy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If sensor data from an entire fleet of vehicles is collected and transmitted to a centralized server, then the amount of data available for training and evaluation increases, but storage requirements and bandwidth consumption increase significantly
Solution Approach 1:
The patent extracts only the essential information from raw sensor data by generating textual scenario descriptions that capture critical driving events. Instead of transmitting entire sensor datasets, the system extracts and transmits only the meaningful narrative descriptions of scenarios, significantly reducing bandwidth consumption while preserving the value needed for ADS development.
Solution Approach 2:
The patent creates textual copies or representations of sensor data scenarios rather than transmitting the original raw data. The description generator network produces textual descriptions that serve as lightweight copies conveying the essential information about driving scenarios, enabling data collection without the storage and bandwidth burden of raw sensor data.
2Quantity of substance
If sensor data from an entire fleet of vehicles is collected and transmitted to a centralized server, then the amount of data available for training and evaluation increases, but storage requirements increase significantly
Solution Approach 1:
The patent extracts only the essential information from raw sensor data by generating textual scenario descriptions that capture critical driving events. Instead of storing entire sensor datasets, the system extracts and stores only the meaningful narrative descriptions of scenarios, significantly reducing storage requirements while preserving the value needed for ADS development.
Solution Approach 2:
The patent creates textual copies or representations of sensor data scenarios rather than storing the original raw data. The description generator network produces textual descriptions that serve as lightweight copies conveying the essential information about driving scenarios, enabling data collection without the storage burden of raw sensor data.
3Adaptability or versatility
If sensor data is collected from a fleet of vehicles, then more diverse scenarios are captured for ADS development, but data privacy concerns and regulatory restrictions increase
Solution Approach 1:
The patent extracts only the essential information needed for ADS development while leaving behind sensitive personal information. By generating textual descriptions that focus on driving scenarios, environmental conditions, and system responses rather than raw sensor data containing potential privacy-sensitive information, the system captures scenario diversity while mitigating privacy risks.
Solution Approach 2:
The description generator network acts as an intermediary between raw sensor data and the ADS development process. It transforms raw data into textual descriptions that serve as a privacy-preserving medium, allowing scenario diversity to be captured and utilized without directly exposing sensitive information from the original sensor data.
Data Source
Figure 1A
Figure 1B~1C
Figure 2
AI summary
A computer-implemented method (100) for providing data-insight for development of an automated driving system, ADS, of a vehicle. The method (100) comprising: obtaining (S102) sensor data pertaining to a driving scenario, said sensor data being captured by one or more sensors of the vehicle and depicting at least part of a surrounding environment of the vehicle; monitoring (S104) a fulfillment of one or more scenario triggers of the driving scenario, wherein fulfillment of the one or more scenario triggers is indicative of the driving scenario being a driving scenario of interest; in response to determining at least one of the one or more scenario triggers being fulfilled: generating (S106), by a description generator network, a scenario description, based at least on the obtained sensor data pertaining to said driving scenario and/or based on ADS data outputted from the ADS having processed said sensor data, wherein the scenario description comprises textual data about the driving scenario to which the obtained sensor data pertains; and storing (S108) the generated scenario description.