Autonomous Driving Path Planning Under Storage Capacity Limits

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

In-vehicle storage devices for autonomous driving systems face capacity limitations, risking insufficient storage of critical data logs due to capacity shortages.

Innovation Solution

The system dynamically adjusts data accuracy based on remaining storage capacity, generating 'target data' with reduced accuracy when capacity is low to conserve space, allowing for continued data logging and ensuring safety margins in path planning.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If high-accuracy recognition data is stored continuously, then data quality for autonomous driving verification is improved, but storage device capacity becomes insufficient

Engineering Contradiction:

Improverecognition data accuracyVSAvoidstorage capacity

Core Design Contradiction:

Measurement precisionVSQuantity of substance

Solution Approach 1:

The system dynamically adjusts the accuracy level of recognition data based on remaining storage capacity. When storage is sufficient, high-accuracy data is stored; when storage becomes limited, the system transitions to storing low-accuracy data, creating a dynamic adaptation mechanism that resolves the contradiction between data quality and storage quantity

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The accuracy parameter of recognition data is changed based on storage conditions. The system modifies the data quality parameter (from high to low accuracy) in response to storage capacity changes, allowing continuous operation while managing storage constraints

Inventive Principle:

Principle #35Parameter changes

2Reliability

If data logging continues at full accuracy, then complete driving scenarios are recorded, but storage device becomes full and cannot store necessary data

Engineering Contradiction:

Improvedata logging completenessVSAvoidstorage capacity

Core Design Contradiction:

ReliabilityVSQuantity of substance

Solution Approach 1:

The system performs preliminary assessment of storage capacity before data logging. By checking remaining storage space in advance and predicting when capacity will be exhausted, the system can proactively switch to low-accuracy mode before storage becomes full, ensuring continuous logging capability

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system prepares alternative data logging modes (low-accuracy mode) in advance to cushion against storage capacity exhaustion. This preparatory measure ensures that data logging can continue without interruption even when storage becomes limited

Inventive Principle:

Principle #11Beforehand cushioning (Prior cushioning)

Data Source

PatentUS20250018974A1Autonomous driving system and control method

Publication Date: 2025.01.16 TOYOTA JIDOSHA KK

AI summary

The present disclosure relates to an autonomous driving system mounted on a vehicle. The autonomous driving system comprises a storage device and processing circuitry. The processing circuitry is configured to execute acquiring recognition data by recognizing a situation around the vehicle, generating a path plan for the vehicle based on the recognition data, performing autonomous driving control of the vehicle in accordance with the path plan, and storing a data log related to the autonomous driving control in the storage device. The data log includes a log of data used for generating the path plan. Generating the path plan includes acquiring a remaining capacity of the storage device, generating target data being the recognition data with reduced accuracy, and generating the path plan that can be generated using the target data when the remaining capacity is equal to or less than a predetermined amount.