Vehicle Sensor Data Collection for Missing Field Records
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomously operating vehicles may fail to handle new driving scenarios due to gaps in their field data records, leading to errors when encountering unrepresented data such as new traffic signs or environments.
Innovation Solution
A method and device for collecting sensor data in vehicles, where request data identifying missing records in existing field data are received, and corresponding sensor data are continuously recorded, stored in short-term memory, and acknowledged for storage in a second memory before deletion, thereby closing data gaps.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If all sensor data are continuously stored in memory, then complete field data records are available for training, but storage and processing system demands become extreme and may be impossible to meet
Solution Approach 1:
The patent extracts only the essential elements (request data describing missing records) from the complete sensor data stream, transmitting only these critical components rather than the entire data set. This reduces storage and processing demands while maintaining the ability to close gaps in field data records.
Solution Approach 2:
The patent segments the field data collection process into distinct components: request data generation, sensor data recording, data matching, and selective storage. This segmentation allows the system to handle data collection efficiently by processing only relevant portions rather than managing complete continuous streams.
2Reliability
If a large fleet of vehicles stores large quantities of sensor data, then comprehensive field data records can be maintained, but regulatory and operational appropriateness is compromised
Solution Approach 1:
The system extracts only the specific sensor data that correspond to missing records identified in request data, rather than storing all sensor data generated by vehicles. This extraction approach maintains data completeness for training purposes while dramatically reducing the total quantity of data that needs to be stored and managed across the fleet.
3Reliability
If sensor data are stored continuously without selection, then all driving scenarios are captured, but data collection efficiency decreases and user intervention may be required
Solution Approach 1:
The system implements feedback through request data that inform vehicles which specific driving scenarios or data records are missing from the field data set. This feedback mechanism enables targeted data collection, improving efficiency by directing vehicles to capture only the specific scenarios needed to close gaps, rather than relying on continuous indiscriminate recording.
Solution Approach 2:
The system enables vehicles to automatically determine which sensor data to store by comparing recorded data against request data criteria. This self-service capability allows vehicles to autonomously make decisions about data retention without requiring user intervention or centralized control, thereby improving data collection efficiency while maintaining comprehensive scenario coverage.
Data Source
AI summary
A computer-implemented method for collecting sensor data of a vehicle. The method includes receiving of request data that describe at least one data record missing in an existing field data record, in the vehicle. The method furthermore includes a continuous recording of sensor data for the vehicle while the vehicle is in operation and storing recorded sensor data in a short-term memory. The method also includes receiving an acknowledge signal to the effect that certain recorded sensor data correspond to a missing data record, and storing the certain recorded sensor data in a second memory before the recorded sensor data are deleted from the short-term memory.