Autonomous Driving Log Storage Based on Operator Monitoring State
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The challenge is to ensure the capability of explaining autonomous driving control while reducing the data volume stored in storage devices, as storing all data related to autonomous driving can lead to insufficient storage capacity.
Innovation Solution
The autonomous driving system compresses or deletes part of the log data when the operator's current state matches the ideal state, ensuring sufficient monitoring is performed, thereby reducing the data volume stored.
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 different log data based on their importance. Critical log data (related to safety, accidents, and operator non-monitoring states) is stored in full detail, while non-critical log data (during normal operator monitoring states) is compressed or deleted. This selective storage approach ensures explanation capability for important events while preserving storage capacity.
Solution Approach 2:
The patent implements discarding and recovering by selectively deleting or compressing log data that is less important for verification purposes. When the operator is in an ideal monitoring state, certain log data can be discarded or compressed. However, the system recovers full storage capability by retaining critical log data that must be preserved for safety verification and accident analysis.
2Quantity of substance
If data compression or deletion is performed to reduce storage volume, then storage device capacity is preserved, but the capability of explanation of autonomous driving control may be compromised
Solution Approach 1:
The patent applies preliminary action by pre-defining compression/deletion rules based on operator states before actual data storage decisions are made. The system preliminarily identifies which operator states (ideal monitoring vs. non-monitoring) warrant data compression or full retention, and pre-establishes the criteria for what log data should be compressed or deleted. This prevents loss of critical information while enabling storage optimization.
Solution Approach 2:
The patent implements feedback by continuously monitoring the operator's state and using this information to dynamically adjust data storage decisions. The system feedbacks from operator monitoring status to the log data storage process, ensuring that compression or deletion only occurs when the operator is in an ideal monitoring state, thereby maintaining explanation capability when it matters most.
3Quantity of substance
If log data is compressed or deleted when operator monitoring is sufficient, then data volume is reduced, but verification capability may be weakened
Solution Approach 1:
The patent applies segmentation by dividing log data into different segments based on operator monitoring states. Log data is segmented into critical segments (when operator is not monitoring) and non-critical segments (when operator is monitoring). This segmentation allows differential storage treatment, compressing or deleting non-critical segments while preserving critical segments, thereby reducing overall data volume while maintaining verification capability for important events.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The present disclosure provides an autonomous driving system (100) mounted on a vehicle (1) and configured to perform autonomous driving of the vehicle (1) by using a machine learning model. The autonomous driving system (100) comprises one or more processors (110) and one or more storage devices (120). When the autonomous driving is performed, the one or more processors (110) are configured to execute acquiring log data (LOG) related to the autonomous driving, acquiring a current state of an operator of the vehicle (1), acquiring an ideal state that is a state of the operator required by the autonomous driving system (100), and storing the log data (LOG) in the one or more storage devices (120). Storing the log data (LOG) includes compressing or deleting target data that is a part of the log data (LOG) when the current state of the operator matches the ideal state.