Autonomous Vehicle Sensor Data Compression for Storage Limits
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face storage limitations due to the large volume of sensor data collected, which requires substantial memory space and frequent offloading, hindering operation and resource utilization when stored in uncompressed or losslessly compressed forms.
Innovation Solution
Implementing lossy compression algorithms, such as the H264 codec, on-board the autonomous vehicle to compress sensor data, which is then decompressed for processing, allowing for efficient storage and reduced bandwidth requirements during offloading.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If sensor data is stored in uncompressed or losslessly compressed forms, then data quality is preserved, but storage capacity requirements increase and offloading frequency increases
Solution Approach 1:
The patent applies lossy compression algorithms that transform the data representation parameters to achieve higher compression ratios. By adjusting compression parameters and accepting controlled quality degradation, the system reduces storage requirements while maintaining sufficient data utility for autonomous vehicle operations
Solution Approach 2:
The patent extracts and removes redundant or less critical information from sensor data during compression. By identifying and eliminating unnecessary data components, the system achieves reduced storage capacity requirements while preserving essential information needed for vehicle control and safety
2Reliability
If sensor data is stored in uncompressed or losslessly compressed forms, then data integrity is maintained, but offloading downtime increases
Solution Approach 1:
By changing the compression parameter from lossless to lossy, the patent significantly reduces data size, which directly decreases offloading time. The system optimizes the balance between data integrity and offloading efficiency by selecting appropriate compression levels
3Quantity of substance
If lossy compression is applied to sensor data, then storage capacity needs are reduced, but data quality deteriorates
Solution Approach 1:
The patent applies partial lossy compression, where only certain portions of the data undergo aggressive compression while critical information is preserved with higher fidelity. This selective approach maintains sufficient data quality for autonomous vehicle operations while achieving meaningful storage reductions
4Quantity of substance
If lossy compression is applied to sensor data, then bandwidth requirements during offloading are reduced, but compression and decompression processing time increases
Solution Approach 1:
The patent performs compression as a preliminary action before data offloading, reducing the subsequent offloading bandwidth requirements. By pre-compressing data during periods when processing resources are available, the system minimizes the impact on real-time operational bandwidth needs
Data Source
AI summary
A vehicle computing system onboard an autonomous vehicle can include one or more processors and one or more non-transitory computer-readable media that store instructions that, when executed by the one or more processors, cause the computing system to perform operations. The operations can include obtaining sensor data from one or more sensors of the autonomous vehicle; applying lossy compression to the sensor data to generate compressed sensor data; storing data describing the compressed sensor data; decompressing the compressed sensor data to generate decompressed sensor data; and inputting data describing the decompressed sensor data into an autonomy system comprising one or more machine-learned models. The autonomy system can be configured to control operations of the autonomous vehicle based on the decompressed sensor data.