Map Distortion Estimation for Autonomous Vehicle Localization

Solution Overview

Problem

Existing navigation systems face safety critical issues due to differences in localization determined using maps and other methods, leading to potential errors in vehicle pose estimation and navigation, particularly due to map distortion caused by measurement errors and sensor noise.

Innovation Solution

A machine learned model estimates map distortion to represent the misalignment between a map frame and an inertial frame, enabling vehicles to account for distortions and improve navigation accuracy by providing a map distortion value that can be used for vehicle pose estimation and sensor data reconciliation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If map data is used for vehicle localization and navigation, then navigation functionality is enabled, but map distortion causes errors in vehicle pose estimation and localization accuracy

Engineering Contradiction:

Improvenavigation safetyVSAvoidvehicle pose estimation accuracy

Core Design Contradiction:

ReliabilityVSMeasurement precision

Solution Approach 1:

The patent introduces an intermediary transformation process that converts map measurements from the map coordinate frame to the inertial coordinate frame. This intermediary transformation acts as a mediator between the map data and the vehicle localization system, eliminating the direct harmful effect of map distortion on pose estimation accuracy while preserving the navigation functionality.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent changes the coordinate frame parameters by transforming measurements from the map frame to the inertial frame. This parameter transformation adjusts the reference system to eliminate distortion effects, thereby improving measurement precision without sacrificing the ability to perform navigation using map data.

Inventive Principle:

Principle #35Parameter changes

2Device complexity

If map measurements are used directly for vehicle pose determination, then localization is simplified, but distortion between map frame and inertial frame causes errors

Engineering Contradiction:

Improvelocalization system complexityVSAvoidlocalization accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent introduces an intermediary transformation process that converts map measurements from the map coordinate frame to the inertial coordinate frame. This intermediary transformation acts as a mediator between the map data and the vehicle localization system, eliminating the direct harmful effect of map distortion on pose estimation accuracy while preserving the navigation functionality.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent changes the coordinate frame parameters by transforming measurements from the map frame to the inertial frame. This parameter transformation adjusts the reference system to eliminate distortion effects, thereby improving measurement precision without sacrificing the ability to perform navigation using map data.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS11543263B1Map distortion determination

Publication Date: 2023.01.03 ZOOX INC

AI summary

Techniques for determining distortion in a map caused by measurement errors are discussed herein. For example, such techniques may include implementing a model to estimate map distortion between the map frame and the inertial frame. Data such as sensor data, map data, and vehicle state data may be input into the model. A map distortion value output from the model may be used to compensate vehicle operations in a local region by approximating the distortion as linearly varying about the region. A vehicle, such as an autonomous vehicle, can be controlled to traverse an environment based on the trajectory.