Autonomous Driving Route Selection for Vehicle Memory Limits
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The limited memory capacity in vehicles executing autonomous driving control using machine learning models can become filled with log data during operation, leading to the inability to store new log data generated during the control process.
Innovation Solution
An autonomous driving system that predicts the fluctuation of log data along potential routes and selects the route with the maximum future memory space availability by integrating the generated log data quantity and potential data reduction methods, ensuring sufficient memory space for continuous data storage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If log data is continuously stored in the memory device during autonomous driving control, then the data quantity for verification increases, but the free space of the memory device becomes filled leading to inability to store new log data
Solution Approach 1:
The system predicts the log data quantity for each candidate route before selection, and estimates future memory free space at destination. This preliminary prediction allows the system to proactively choose routes that will not cause memory overflow, preventing the problem before it occurs.
Solution Approach 2:
The system continuously monitors current memory free space and uses this feedback to adjust route selection decisions. The prediction of future free space is based on current status, creating a closed-loop control that adapts to changing memory conditions.
2Quantity of substance
If the memory device free space is monitored and data is transmitted when full, then storage capacity is optimized, but new log data cannot be stored from the middle of autonomous driving control when free space is filled
Solution Approach 1:
Instead of reacting when memory is full, the system predicts future memory usage for each candidate route and selects routes that maintain adequate free space. This preliminary action prevents memory overflow before it occurs, ensuring continuous storage capability throughout the autonomous driving task.
3Reliability
If multiple candidate routes are evaluated for log data fluctuation, then memory management is optimized, but the route selection complexity increases
Solution Approach 1:
The system uses the existing autonomous driving route planning framework to perform memory-aware route selection. The same processing circuitry that plans driving routes also predicts log data quantities and selects routes based on memory constraints, eliminating the need for a separate complex memory management system.
Data Source
AI summary
An autonomous driving route along which autonomous driving control of a vehicle is executed is set. In the setting of the autonomous driving route, at least two candidates of a route from a current location to a destination of the vehicle are set. Next, for each of the at least two candidates, a fluctuation amount of log data that fluctuates in a memory device during a travel of the vehicle along the candidate of the route. Next, a future value of a free space in the memory device at which the vehicle arrives at a destination of the candidate of the route for each of the at least two candidates based on the fluctuation amount of the log data. Then, one candidate of the route from the at least two candidates of which the future value of the free space is the maximum is selected as the autonomous driving route.