ADAS Vehicle Localization Using Lane Curvature and Heading Fusion

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing vehicle navigation systems face challenges in accurately localizing vehicles when satellite signals are weak or lost, particularly in areas with limited satellite coverage such as remote mountains or densely structured cities.

Innovation Solution

An advanced driver assistance system (ADAS) that determines vehicle locations using a combination of lane sensing information, heading angle, and travel distances, fusing these data sources to maintain vehicle control even without reliable satellite navigation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If satellite navigation information is used for vehicle localization, then positioning accuracy is improved, but the system becomes unreliable in areas with weak or lost satellite signals

Engineering Contradiction:

Improvepositioning accuracyVSAvoidsystem reliability

Core Design Contradiction:

Measurement precisionVSReliability

Solution Approach 1:

The patent combines satellite navigation information with inertial measurement unit (IMU) data and map matching algorithms to create a hybrid positioning system. When satellite signals are weak or lost, the system seamlessly transitions to using IMU-based dead reckoning and map matching, ensuring continuous reliable positioning without complete dependence on satellite signals.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The system dynamically changes positioning parameters by switching between satellite-based GPS positioning and inertial-based dead reckoning positioning based on signal availability. When satellite signal strength falls below a threshold, the system transitions to using accelerometer and gyroscope data with different calculation parameters to maintain positioning accuracy.

Inventive Principle:

Principle #35Parameter changes

2Reliability

If multiple data sources are fused for vehicle localization, then reliability is improved, but device complexity increases

Engineering Contradiction:

Improvelocalization reliabilityVSAvoidsystem complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system employs a multi-functional localization module that can perform multiple positioning methods (satellite-based, inertial-based, map-matching) through a single integrated algorithm framework. This universal module automatically selects and switches between different positioning strategies based on available data sources, reducing the need for separate dedicated systems for each method.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS20250026354A1Controlling vehicle using vehicle curvature and heading angle

Publication Date: 2025.01.23 ATIEVA INC(US)

AI summary

A method comprises: determining that a vehicle is at a first location; controlling motion of the vehicle using an advanced driver assistance system (ADAS); determining a second location for the vehicle based on lane sensing information of a lane monitoring system of the vehicle and a first travel distance of the vehicle since the first location, the lane sensing information reflecting a lane curvature; determining a third location for the vehicle based on a heading angle of the vehicle and a second travel distance of the vehicle since the first location; determining a fourth location for the vehicle by fusing the second and third locations with each other; and controlling the motion of the vehicle using the ADAS based on the fourth location.