Weather Warning Polygons from Sparse Vehicle Sensor Data

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing navigation and automated driving systems face challenges in accurately detecting and representing weather events like rain and fog using sparse vehicle sensor data, due to computational burdens and limited computing resources, which can lead to delayed warnings and increased accident risks.

Innovation Solution

A method that involves receiving sensor data, identifying relevant map tiles, calculating confidence levels, clustering tiles, and generating polygons to represent weather events efficiently, using a processor to minimize calculations and reduce latency in warning delivery.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional methods are used to process all map tiles for weather event detection, then detection accuracy may be maintained, but computational load increases significantly and processing time increases

Engineering Contradiction:

Improveweather event detection accuracyVSAvoidcomputational load

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent divides the map into discrete map tiles and processes only those tiles that are relevant to detected weather events. Instead of processing all map tiles uniformly, the system segments the geographic area and selectively processes tiles based on sensor data correlations, thereby reducing computational load while maintaining detection accuracy for relevant areas.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent applies different processing quality levels to different map tiles based on their relevance to weather events. Tiles containing sensor data correlations are processed with high quality for accurate weather event detection, while tiles without correlations use lower quality or are skipped entirely, optimizing the balance between detection accuracy and computational resources.

Inventive Principle:

Principle #3Local quality

2Reliability

If comprehensive processing of all map tiles is performed, then weather event detection reliability is improved, but warning delivery latency increases

Engineering Contradiction:

Improveweather event detection reliabilityVSAvoidwarning delivery latency

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent performs preliminary processing by pre-identifying map tiles that contain sensor data correlations before weather event detection is needed. This preliminary action prepares the system in advance, so when weather events occur, only pre-identified relevant tiles need to be processed, significantly reducing warning delivery latency while maintaining detection reliability.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent processes only a partial set of map tiles - specifically those that contain sensor data correlations - rather than performing exhaustive processing of all tiles. This partial action is sufficient to maintain detection reliability for relevant weather events while dramatically reducing processing time and latency.

Inventive Principle:

Principle #16Partial or excessive action

3Measurement precision

If all map tiles are processed with high quality, then detection precision is maintained, but computing resources are consumed excessively

Engineering Contradiction:

Improvedetection precisionVSAvoidcomputing resource consumption

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent extracts and processes only the essential subset of map tiles that contain sensor data correlations, removing unnecessary processing of irrelevant tiles. This extraction approach maintains detection precision for tiles that matter while eliminating wasteful consumption of computing resources on tiles that do not contribute to weather event detection.

Inventive Principle:

Principle #2Taking out (Extraction)

4Productivity

If the system processes only relevant map tiles, then computational efficiency is improved, but detection coverage may be reduced

Engineering Contradiction:

Improvecomputational efficiencyVSAvoiddetection coverage

Core Design Contradiction:

ProductivityVSArea of stationary object

Solution Approach 1:

The patent uses sensor data correlations as feedback to dynamically identify which map tiles are relevant for processing. This feedback mechanism ensures that the system processes the correct tiles - those that actually contain weather event information - thereby maintaining comprehensive detection coverage while improving computational efficiency through selective processing.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS11846522B2Warning polygons for weather from vehicle sensor data

Publication Date: 2023.12.19 HERE GLOBAL BV

AI summary

An apparatus is configured to perform a method for generating warning polygons for weather events in a geographic region. The method includes receiving measurement data from one or more sensors, identifying at least one location from the measurement data, identifying a map tile within a predetermined distance to the at least one location, defining an index including the map tile in response to identification that the map tile is within the predetermined distance to the at least one location, calculating a confidence level for the map tile accessed from the index, comparing the confidence level for the map tile to a threshold confidence level, clustering the map tile in a map tile cluster in response to the confidence level exceeding the threshold level, and calculating a polygon based on the map tile cluster such that the polygon intersects the geographic region.