Spatial Regular Expressions for Perception Data Pattern Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current techniques for querying perception data in autonomous vehicles do not support the computational complexity required for efficient spatial pattern matching, limiting the usefulness of information gleaned from vast datasets and hindering robust spatial perception capabilities.
Innovation Solution
Implementing Spatial Regular Expressions (SpREs) that combine regular expressions with modal logic of topology to enable efficient and flexible spatio-temporal querying of perception data streams, leveraging established libraries for fast processing and modular design.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional querying techniques are used for perception data, then the system is simple to implement, but the system cannot support the computational complexity required for efficient spatial pattern matching
Solution Approach 1:
The patent introduces SpRE (Spatio-Temporal Regular Expression) as an intermediary layer between conventional querying techniques and perception data. SpRE acts as a mediator that translates complex spatial pattern matching requirements into a formal language that can be efficiently processed, thereby enabling advanced spatial capabilities without directly complicating the underlying system architecture
Solution Approach 2:
The patent segments the complex spatial pattern matching problem into distinct components handled by SpRE syntax elements (spatial operators, temporal operators, and regular expression operators). This segmentation allows each component to be processed independently and efficiently, reducing the overall computational complexity while maintaining versatility
2Measurement precision
If comprehensive spatio-temporal pattern matching is performed on large perception datasets, then the detection accuracy of relevant scenarios is improved, but the processing time increases
Solution Approach 1:
The patent applies preliminary action by pre-compiling SpRE patterns into optimized execution plans before querying the perception data. This preparation work is done in advance, allowing the actual pattern matching process to execute efficiently without incurring compilation overhead during time-critical operations, thus maintaining high detection accuracy while reducing processing time
Solution Approach 2:
The patent implements periodic action through incremental pattern matching where the SpRE engine processes perception data in periodic batches or streams rather than analyzing entire datasets at once. This allows the system to maintain high detection accuracy on relevant patterns while managing processing time through periodic, manageable computation cycles
Data Source
AI summary
Systems and methods are provided that implement a spatio-temporal query of perception data streams. A system is designed to implement 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 a spatial regular expression (SpRE). Thereafter, performing the spatio-temporal query of one or more perception data streams using the SpRE, where the SpRE describes a spatio-temporal pattern between objects to be searched within the one or more perception data streams.