Autonomous Path Perception Ensemble for Redundant Lane Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional autonomous vehicle systems rely on a single data source for path perception, making real-time accuracy assessment impractical and leading to potential failures, especially in challenging scenarios like high curvature roads or multi-way intersections, due to the lack of redundancy and diversity in path perception inputs.
Innovation Solution
Implementing a system that utilizes a plurality of input signals from deep neural networks, high-definition maps, and object traces to generate a diverse and redundant understanding of the driving surface, allowing for real-time assessment of path perception quality and reliability through ensemble methods, which combine multiple path perception approaches to produce a more accurate and reliable lane mapping and path computation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single data source is used for path perception, then device complexity is reduced, but reliability deteriorates due to lack of redundancy and inability to perform real-time accuracy assessment
Solution Approach 1:
The patent combines multiple path perception data sources including deep neural network outputs, high-definition map data, and object trace information into a unified ensemble assessment framework. This merging allows the system to evaluate path perception accuracy by comparing results across different sources in real-time, thereby improving reliability without requiring overly complex individual components
Solution Approach 2:
The ensemble assessment system serves multiple functions simultaneously: it validates path perception accuracy, identifies unreliable predictions, provides real-time feedback for system improvement, and maintains operational continuity by switching between different data sources. This multi-functionality addresses reliability concerns while keeping the overall system architecture manageable
2Reliability
If multiple input signals from diverse sources are used, then reliability is improved through redundancy and diversity, but device complexity increases due to ensemble processing requirements
Solution Approach 1:
The patent segments the path perception system into distinct functional modules: deep neural network processing, high-definition map integration, object trace generation, and ensemble assessment. Each module handles a specific aspect of path perception, and the segmentation allows for independent optimization and maintenance of each component while benefiting from their combined reliability
Solution Approach 2:
The ensemble assessment acts as an intermediary layer that mediates between multiple diverse data sources and the final path perception output. It harmonizes the different formats and reliability levels of input signals, performing consistency checks and weighted integration to produce a unified, reliable path perception result without requiring complex direct integration between all source components
3Ease of operation
If a single path perception signal is used, then ease of operation is maintained, but measurement precision deteriorates due to inability to assess path perception accuracy in real-time
Solution Approach 1:
The patent implements a feedback mechanism where the ensemble assessment continuously evaluates the reliability of path perception signals and provides real-time feedback on accuracy. This feedback loop allows the system to identify unreliable predictions, adjust processing parameters, and improve overall measurement precision without requiring complex manual intervention or operation
4Measurement precision
If diverse path perception inputs are processed, then measurement precision is improved through ensemble methods, but loss of time increases due to processing multiple signals
Solution Approach 1:
The patent applies partial action by performing ensemble assessment selectively based on operational context and reliability needs. In normal conditions, the system processes essential signals with standard depth, while in critical situations or when reliability is questionable, it activates full ensemble processing. This approach achieves high measurement precision when needed while minimizing unnecessary processing time during routine operations
Data Source
AI summary
In various examples, a path perception ensemble is used to produce a more accurate and reliable understanding of a driving surface and/or a path there through. For example, an analysis of a plurality of path perception inputs provides testability and reliability for accurate and redundant lane mapping and/or path planning in real-time or near real-time. By incorporating a plurality of separate path perception computations, a means of metricizing path perception correctness, quality, and reliability is provided by analyzing whether and how much the individual path perception signals agree or disagree. By implementing this approach—where individual path perception inputs fail in almost independent ways—a system failure is less statistically likely. In addition, with diversity and redundancy in path perception, comfortable lane keeping on high curvature roads, under severe road conditions, and/or at complex intersections, as well as autonomous negotiation of turns at intersections, may be enabled.