Autonomous Vehicle Position Sensor Switching for Map Localization

Solution Overview

Problem

Autonomous vehicles face challenges in accurately determining their position on high-precision maps, especially in scenarios where traditional sensors like cameras and LiDAR units are limited by environmental conditions or lack of road surface and structure information.

Innovation Solution

The vehicle selectively uses a camera or LiDAR unit as a position sensor based on the availability of road surface and structure information, combining two-dimensional and three-dimensional data to identify its position on a map, and switches between sensors depending on the driving situation, such as changing lanes or turning.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a camera is used as a position sensor, then two-dimensional road surface information can be obtained, but three-dimensional structure information cannot be acquired

Engineering Contradiction:

Improveposition determination accuracyVSAvoidthree-dimensional structure information

Core Design Contradiction:

Measurement precisionVSLoss of information

Solution Approach 1:

The patent combines data from multiple sensors (camera and LiDAR) to create a comprehensive position determination system. The controller selectively uses camera data for 2D road surface information and LiDAR data for 3D structure information, merging these complementary data sources to achieve accurate localization in various environmental conditions.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The system dynamically selects which sensor to use based on environmental conditions and driving situations. The controller determines whether to use camera or LiDAR data based on real-time assessment of available information, making the position determination system adaptive to changing conditions such as lighting, weather, and road features.

Inventive Principle:

Principle #15Dynamics

2Measurement precision

If a LiDAR unit is used as a position sensor, then three-dimensional structure information can be obtained, but two-dimensional road surface information cannot be acquired

Engineering Contradiction:

Improveposition determination accuracyVSAvoidtwo-dimensional road surface information

Core Design Contradiction:

Measurement precisionVSLoss of information

Solution Approach 1:

The patent combines data from multiple sensors (camera and LiDAR) to create a comprehensive position determination system. The controller selectively uses camera data for 2D road surface information and LiDAR data for 3D structure information, merging these complementary data sources to achieve accurate localization in various environmental conditions.

Inventive Principle:

Principle #5Merging (Combining)

3Adaptability or versatility

If traditional sensors are used in impaired environmental conditions, then position determination accuracy deteriorates

Engineering Contradiction:

Improveenvironmental condition adaptabilityVSAvoidposition determination accuracy

Core Design Contradiction:

Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The system dynamically selects which sensor to use based on environmental conditions and driving situations. The controller determines whether to use camera or LiDAR data based on real-time assessment of available information, making the position determination system adaptive to changing conditions such as lighting, weather, and road features.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes operational parameters by switching between different sensor modalities (camera vs. LiDAR) depending on environmental conditions. This parameter change allows the system to maintain accurate position determination across diverse conditions including poor lighting, weather variations, and different road types.

Inventive Principle:

Principle #35Parameter changes

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This approach enables accurate and efficient localization of the vehicle on high-precision maps, even in conditions where traditional sensors are impaired, by leveraging both 2D and 3D data to ensure reliable autonomous driving.

Implementation Method 1

a light detection and ranging (LiDAR) unit comprising LiDAR circuitry configured to obtain three-dimensional (3D) spatial information regarding structures proximate the vehicle

Methodology Applied

Scientific EffectLight Detection And Ranging (LiDAR): LIDAR

Data Source

PatentUS11255974B2Method of determining position of vehicle and vehicle using the same

Publication Date: 2022.02.22 SAMSUNG ELECTRONICS CO LTD

AI summary

Provided is an autonomous vehicle including a storage configured to store a map including two-dimensionally represented road surface information and three-dimensionally represented structure information, a camera configured to obtain a two-dimensional (2D) image of a road surface in a vicinity of the vehicle, a light detection and ranging (LiDAR) unit configured to obtain three-dimensional (3D) spatial information regarding structures in a vicinity of the vehicle, and a controller comprising processing circuitry configured to determine at least one of the camera or the LiDAR unit as a position sensor, based on whether it is possible to obtain information regarding the road surface and/or the structures in the vicinity of the vehicle, to identify a position of the vehicle on the map corresponding to a current position of the vehicle using the position sensor, and performing autonomous driving based on the identified position on the map.