Autonomous Driving AI Data Saving Under In-Vehicle Memory Limits
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The limited capacity of in-vehicle memory devices poses a challenge in effectively managing data related to artificial intelligence (AI) for autonomous driving control, necessitating a method to appropriately save relevant data while preventing memory device space from becoming insufficient.
Innovation Solution
A method and device that determine whether AI is involved in computer processing and save input and output data based on a predetermined save condition, saving only data within a predetermined time frame based on the satisfaction of this condition.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If all data related to computer processing for autonomous driving control is saved in the in-vehicle memory device, then complete data for AI evaluation and verification is obtained, but the memory device capacity is exceeded
Solution Approach 1:
The patent extracts and saves only specific types of data that are essential for AI evaluation and verification, rather than saving all computer processing data. The management device identifies and extracts input data, output data, and intermediate data related to AI processing, saving only these relevant portions to the in-vehicle memory device while excluding unnecessary data, thus resolving the capacity conflict.
Solution Approach 2:
The patent segments the vast amount of autonomous driving data into distinct categories: input data from sensors, output data from AI processing, and intermediate data from processing stages. By segmenting data types and applying different saving strategies to each category, the system efficiently utilizes limited memory capacity while preserving all data necessary for AI evaluation.
2Quantity of substance
If selective saving of data is performed to preserve memory space, then free space in the memory device is maintained, but completeness of AI-related data may be compromised
Solution Approach 1:
The patent implements a feedback mechanism where the management device continuously monitors the types and amounts of data being generated, the current memory device capacity, and the requirements for AI evaluation. Based on this feedback, the system dynamically adjusts which data to save and when to transmit data to the server, ensuring both memory constraints are met and AI data completeness is maintained.
3Quantity of substance
If data is transmitted immediately to the server, then memory capacity requirements are reduced, but real-time evaluation and verification of AI cannot be performed
Solution Approach 1:
The patent performs preliminary saving of essential AI-related data to the in-vehicle memory device before transmission to the server. By pre-saving input data, output data, and critical intermediate data locally, the system enables immediate real-time evaluation and verification of AI processing while minimizing the need for large-capacity memory devices. Non-critical data is transmitted asynchronously to the server for later analysis.
Data Source
AI summary
A method for managing data related to a vehicle in which autonomous driving control is performed is provided. In the method, it is determined whether artificial intelligence is involved in computer processing for performing the autonomous driving control. In the method, it is also determined whether a predetermined save condition is satisfied. When it is determined that the artificial intelligence is involved in the computer processing and it is determined that the predetermined save condition is satisfied, input and output data of the computer processing within a predetermined save time is saved based on a timing at which it is determined that the predetermined save condition is satisfied in a memory device of the vehicle.