Autonomous Driving Log Compression Based on Driver Monitoring State
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The challenge in autonomous driving systems is to ensure the capability of explaining autonomous driving control while managing storage capacity, as storing all data related to autonomous driving can lead to insufficient storage device capacity.
Innovation Solution
The autonomous driving system compresses or deletes specific log data when the operator's current state matches the ideal state, ensuring sufficient monitoring is performed, thereby reducing data volume and preserving storage capacity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If all log data related to autonomous driving is stored, then the capability of explanation of autonomous driving control is ensured, but the storage device capacity becomes insufficient
Solution Approach 1:
The patent applies local quality by differentiating the storage treatment of log data based on the operator's monitoring state. When the operator is in an ideal monitoring state, only essential log data is stored with high quality, while when monitoring is insufficient, comprehensive log data is stored. This selective approach ensures explanation capability is maintained for critical periods while reducing overall storage requirements.
Solution Approach 2:
The patent changes the storage parameter (data volume) based on the operator's monitoring state parameter. By dynamically adjusting what data to store according to whether the operator is adequately monitoring, the system optimizes between explanation capability and storage capacity utilization.
2Quantity of substance
If data compression or deletion is performed on log data, then the storage device capacity is preserved, but the capability of explanation of autonomous driving control may be reduced
Solution Approach 1:
The patent performs preliminary action by assessing the operator's monitoring state before determining the storage strategy. By evaluating whether the operator is in an ideal monitoring state in advance, the system can proactively decide to store only essential data, thereby preserving storage capacity while maintaining sufficient explanation capability for verification purposes.
Solution Approach 2:
The system uses feedback from the operator's monitoring state detection to dynamically adjust storage behavior. The monitoring state information feeds back into the storage decision-making process, allowing the system to adaptively balance between storage capacity preservation and explanation capability maintenance.
3Quantity of substance
If the operator's monitoring state is continuously monitored to determine data storage strategy, then the capability of explanation is maintained with reduced storage, but the system complexity increases
Solution Approach 1:
The patent applies self-service by having the operator's own monitoring behavior serve the dual purpose of both safety verification and storage optimization. The system leverages the natural monitoring actions of the operator to automatically determine storage strategies, reducing the need for additional complex monitoring infrastructure while achieving both safety and storage efficiency goals.
Data Source
AI summary
The present disclosure provides an autonomous driving system mounted on a vehicle and configured to perform autonomous driving of the vehicle by using a machine learning model. The autonomous driving system comprises processing circuitry and one or more storage devices. When the autonomous driving is performed, the processing circuitry is configured to execute acquiring log data related to the autonomous driving, acquiring a current state of an operator of the vehicle, acquiring an ideal state that is a state of the operator required by the autonomous driving system, and storing the log data in the one or more storage devices. Storing the log data includes compressing or deleting target data that is a part of the log data when the current state of the operator matches the ideal state.