Spatio-Temporal Querying of Perception Streams With Spatial Regex
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current techniques for querying perception datasets in autonomous vehicles lack the computational complexity required for efficient spatial and temporal pattern matching, limiting the usefulness of collected data for training and operation.
Innovation Solution
Implementing spatio-temporal regular expressions (SpREs) that combine regular expressions with modal logic of topology to enable efficient and flexible querying of large perception datasets, allowing for fast and accurate pattern matching in spatial and temporal contexts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If current querying techniques are used for perception datasets, then the system is simple to implement, but the computational complexity required for efficient spatial and temporal pattern matching is insufficient
Solution Approach 1:
The patent transforms the querying approach by changing the parameter of pattern representation from simple queries to spatio-temporal regular expressions (SpREs). This enables complex spatial and temporal pattern matching while maintaining query efficiency through the mathematical framework of regular expressions extended to spatio-temporal domains.
Solution Approach 2:
The patent introduces SpREs as an intermediary formalism between traditional querying techniques and complex spatial-temporal pattern recognition. This intermediary layer provides the necessary computational complexity for efficient pattern matching while abstracting the underlying complexity from the querying interface.
2Measurement precision
If SpREs are implemented for pattern matching, then pattern matching accuracy and capability are improved, but the computational resources required increase
Solution Approach 1:
The patent performs preliminary compilation of SpRE patterns into optimized execution forms before actual pattern matching occurs. This pre-processing step reduces the computational energy required during runtime by preparing the pattern matching logic in advance, enabling accurate spatio-temporal pattern detection without excessive energy consumption during operation.
3Loss of information
If complex spatio-temporal pattern matching is performed, then the usefulness of perception data for training and operation is improved, but the processing time increases
Solution Approach 1:
The patent segments the spatio-temporal pattern matching process into distinct computational phases: spatial pattern recognition, temporal pattern recognition, and integration. This segmentation enables parallel processing of spatial and temporal components, reducing overall processing time while maintaining the ability to detect complex spatio-temporal patterns in perception data.
Data Source
AI summary
Systems and methods are provided that implement spatio-temporal query of perception data streams. A system is distinctly designed to implement efficient and flexible spatio-temporal queries, which conduct pattern matching over perception data streams for automotive applications, particularly autonomous vehicles. The system is also designed to enable the spatio-temporal queries to be expressed in SpREs (Spatial Regular Expressions), which is implemented as a querying language that combines the ease of REs (regular expressions) with the enhanced capabilities of spatial logic. Additionally, a method includes receiving a command associated with a spatio-temporal query, wherein the expression comprises spatial regular expressions (SpREs). Thereafter, performing the spatio-temporal query of a plurality of perception data streams using the SpREs, where the SpREs describe spatio-temporal patterns to be searched within the plurality of perception data streams.