Adaptive Rationalizer for Road Geometry Discrepancy Handling

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Advanced driver assistance systems (ADAS) in vehicles face challenges in accurately determining vehicle dynamics and roadway geometry, leading to discrepancies between sensor data and map data, which can result in uncertainties and errors in navigation and control.

Innovation Solution

A computing device is configured to calculate a rationalization value based on differences between vehicle dynamics data and map-based roadway geometry data, including curvature, bank angle, and grade angle estimation errors, and to modify vehicle states or generate alerts based on these values, transitioning between autonomous and semi-autonomous states as needed.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If sensor data and map data are used to determine vehicle dynamics and roadway geometry, then navigation capability is improved, but measurement precision deteriorates due to discrepancies between sensor data and map data

Engineering Contradiction:

Improvenavigation capabilityVSAvoidroadway geometry accuracy

Core Design Contradiction:

Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The patent introduces an adaptive rationalizer as an intermediary component that mediates between sensor data and map data. The rationalizer calculates a rationalization value that quantifies the discrepancy between these two data sources and uses this information to adaptively weight their contributions to roadway geometry determination, thereby resolving the contradiction between navigation capability and measurement precision

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system dynamically changes the weighting parameters of sensor data and map data based on the calculated rationalization value. When discrepancies are detected, the system adjusts the relative importance of each data source, allowing it to adapt to varying conditions and maintain measurement precision while preserving navigation capability

Inventive Principle:

Principle #35Parameter changes

2Reliability

If adaptive rationalization is implemented to handle data discrepancies, then reliability is improved, but device complexity increases

Engineering Contradiction:

Improvecontrol system reliabilityVSAvoidprocessing system complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The adaptive rationalizer implements a feedback mechanism where the rationalization value calculated from data discrepancies feeds back into the control system to adjust data weighting and control decisions. This feedback loop improves reliability by continuously adapting to data quality variations while maintaining a relatively simple system architecture through reuse of existing sensor and map data

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS11987251B2Adaptive rationalizer for vehicle perception systems toward robust automated driving control

Publication Date: 2024.05.21 GM GLOBAL TECHNOLOGY OPERATIONS LLC

AI summary

A system includes a computing device. The computing device includes a processor and a memory, the memory including instructions such that the processor is configured to: transform vehicle dynamics data to corresponding roadway geometry data, calculate a rationalization value based on a difference between the roadway geometry data and map-based roadway geometry data, and determine whether to modify a vehicle state based on the rationalization value.