SlideShare une entreprise Scribd logo
1  sur  21
Télécharger pour lire hors ligne
© 2019 VSI Labs
Improving the Safety & Performance of
Automated Vehicles Through Precision
Localization
Phil Magney
VSI Labs
May 2019
© 2019 VSI Labs
VSI’s Range of Research
2
Industry Research
& Advisory
Testing &
Demonstration
Engineering
Services
• Applied research on active safety and
automated driving since 2014
• Supporting R&D & planning for automotive,
suppliers and technology industry
• VSI Offers various research portals
© 2019 VSI Labs
Automated Vehicle Trajectories
Series Production
Low Speed Shuttles
Robo-Taxis
3
© 2019 VSI Labs
Automated Driving Today – Series
Production Cars
Automated driving is born
from active safety systems
(active lane keeping,
adaptive cruise control, etc.)
Most L2 vehicles use
camera and radar
Lane centering, no organic
path planning
Localization – most L2
vehicles rely on SLAM
methods
4
© 2019 VSI Labs
Automated Driving
Today -- Shuttles
Driverless Shuttles – low
speed vehicles being
developed as fully automated
people movers
Shuttles operate on a “virtual
rail”
Shuttles will also use various
other sensors for collision
avoidance
Localization -- Shuttles use
correction services to
localization against a pre-
mapped course
5
© 2019 VSI Labs
Automated Driving
Today -- Robo Taxis
Many companies are
developing L4 “robo-taxis”
for deployment in metro
areas under a ride sharing
model
Robo-taxis use many
sensors including redundant
camera, Lidar, Radar, HD
maps, etc.
Localization -- Precision
localization against HD
maps, mainly using lidar
6
© 2019 VSI Labs
The Tech Behind Automated
Vehicle Systems
Sensors
Processors
Software
7
© 2019 VSI Labs
Anatomy of an Automated Vehicle
8
© 2019 VSI Labs
The Automation Pipeline
9
© 2019 VSI Labs
Sensor
Configurations
L1
Active Safety Features
L2
Lane Level
Automation
L2+
Multi Lane Automation
L3
Traffic Jam Pilot and
Hwy Pilot
L4/L5
Robo-taxi / MaaS
Camera Front facing
Rear facing (passive)
Front facing
Rear facing (passive)
Front facing x 2
Side facing x 2
Rear facing
Driver facing
Front facing x 2
Side facing x 2
Rear facing
Driver facing
Front facing x 3
Side facing x 4
Rear facing x 2
Thermal x 2
Driver facing
Radar Med-long range front
Short range side x 2
Med-long range front
Short range side x 2
Med-long range front
Short range side x 2
Short range front
Med-long range
Short range side x 2
Short range front
Med-long range
Short range side x 2
Imaging radar x 2
Ultrasonic 360 degree 360 degree 360 degree 360 degree 360 degree
LiDAR Solid state Solid state x 2 Solid state x 2
360 degree x 2
HD Maps ADAS model ADAS model
Lane model
Localization model
ADAS model
Lane model
Localization model
ADAS model
Lane model
Localization model
Inertial IMU IMU IMU IMU IMU
GNSS + Correction RTK RTK RTK
Total Sensors 7 8 16 18 28
Notes: This are proxy estimates based on OEM and fleets planned announcements. Sensor distribution may vary greatly among
OEMs. Maps are counted as a sensor as well as IMU, GNSS devices. Surround view applications are not included in this chart. Ultra
sonic is counted as one rather than discrete units. L3 – L5 are largely development sensor configurations, final production may
differ.
Automotive Sensor Proxy
10
© 2019 VSI Labs
Improving Safety Through
Precision Maps
11
© 2019 VSI Labs
Limitations of Vision-based Automation (basic L2)
12
© 2019 VSI Labs
Limitations of AVs in Poor Weather?
13
Sensors Fail
• Camera & Lidar fail quickly
• Radar still robust
Infrastructure Fails
• Lanes lines covered
• Localization assets hard to recognize
if they are covered in snow
What Does it Take?
• Precision localization – through
correction services
• V2I – through embedded cellular,
DSRC
• Virtual Infrastructure – Precision
Maps (lanes models, intersections,
and other metadata)
• Low Grip Algorithm
© 2019 VSI Labs
Absolute Localization (Ground Truth)
14
• GPS based accuracy is not enough and suffers from
outages
• Heighten the fixes with correction (RTK services) to w/I a
few centimeters
• Once base accuracy is enough, then you need to
localized against it between fixes
• Wheel odometry uses a starting position and wheel
speed to estimate a position from a fixed point
• Inertial measurement unit (IMU) senses the movement of
the vehicle in time via yaw, pitch, roll axis and magnetic
• Visual odometry estimates vehicle motion from a
sequence of camera frames
© 2019 VSI Labs
Relative Localization With Landmarks
• Landmark localization -
matches landmarks and
objects (signs, poles, and
other permanent objects
• In landmark-based
approaches the objects are
classified
• The challenge is the creation
and maintenance of these
maps, requires human
annotation
15
Source: Towards Data Science
© 2019 VSI Labs
Relative Localization With Lane Models
• Lane models provide virtual lane
and centerline trajectories from
which to localize against
• This is particularly important when
lanes lines are obstructed (i.e.
covered in snow)
• Lane models is vital to multilane
highways and intersection
traversals
• The challenge is the creation and
maintenance of these maps
16
© 2019 VSI Labs
What are Precision Maps & Who Supplies Them
• Road model (ADAS Map)
• Topology
• Routing
• Speed attributes, etc.)
• Lane Models
• Lane geometry
• Polylines
• Trajectories
• Localization Layer
• Landmarks
• Signs, barriers, poles etc.
• Edges and boundaries
• Voxels
• Confidence Index
17
© 2019 VSI Labs
How to Keep the Data Fresh
• Mapping data are always
changing
• Temporary lane closures or
detours
• Changes to the infrastructure
(bridges, landmarks, poles,
lights)
• How to detect changes, collect,
then validate those changes
• Requires fleets to crowd
source
• Requires connected vehicles
• Requires standardization of
message sets
18
© 2019 VSI Labs
Elements of Mapping Assets
19
Trajectories
• Geocoded Paths
Lane Models
• Lane Geometry
ADAS Map
• Speeds/Slopes/Curves
Localization Layers
Raw Images
Raw Point Clouds
Vixels (Voxels + RGB data)
Voxels (clusters of points)
Compressed Point Cloud
Object List (landmarks)
VolumeofData
Sense and React Sense and Align Sense and Position
HERE HD Live Maps
© 2019 VSI Labs
Closing Remarks
• Automation in series production is an extension of
ADAS.
• Couple camera and radar and you have L2
capabilities.
• Adding precision maps substantially improves the
performance and safety of automated vehicles:
• Mapping assets to improve localization
• Lane models tell you where you can and cannot
operate!
• ADAS attributes add speeds, curve, slope and
other important metadata
• Shuttles are a pragmatic approach to automation
• No path planning as you are using a recorded
path to create a virtual rail
• Robo-taxis will apply everything we have talked
about times three
• They will be highly constrained (largely because of
SOTIF – Safety Of the Intended Function)
20
© 2019 VSI Labs
Contact
21
Resources
www.VSL-Labs.com
Sign Up for Free White Papers
Request Services Agreement
Client Portal Registration Page
Contact Phil Magney
+1-952-215-1797

Contenu connexe

Plus de Edge AI and Vision Alliance

“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...Edge AI and Vision Alliance
 
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...Edge AI and Vision Alliance
 
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...Edge AI and Vision Alliance
 
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...Edge AI and Vision Alliance
 
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...Edge AI and Vision Alliance
 
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...Edge AI and Vision Alliance
 
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...Edge AI and Vision Alliance
 
“Updating the Edge ML Development Process,” a Presentation from Samsara
“Updating the Edge ML Development Process,” a Presentation from Samsara“Updating the Edge ML Development Process,” a Presentation from Samsara
“Updating the Edge ML Development Process,” a Presentation from SamsaraEdge AI and Vision Alliance
 
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...Edge AI and Vision Alliance
 
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...Edge AI and Vision Alliance
 
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...Edge AI and Vision Alliance
 
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...Edge AI and Vision Alliance
 
“Tracking and Fusing Diverse Risk Factors to Drive a SAFER Future,” a Present...
“Tracking and Fusing Diverse Risk Factors to Drive a SAFER Future,” a Present...“Tracking and Fusing Diverse Risk Factors to Drive a SAFER Future,” a Present...
“Tracking and Fusing Diverse Risk Factors to Drive a SAFER Future,” a Present...Edge AI and Vision Alliance
 
“MIPI CSI-2 Image Sensor Interface Standard Features Enable Efficient Embedde...
“MIPI CSI-2 Image Sensor Interface Standard Features Enable Efficient Embedde...“MIPI CSI-2 Image Sensor Interface Standard Features Enable Efficient Embedde...
“MIPI CSI-2 Image Sensor Interface Standard Features Enable Efficient Embedde...Edge AI and Vision Alliance
 
“Introduction to the CSI-2 Image Sensor Interface Standard,” a Presentation f...
“Introduction to the CSI-2 Image Sensor Interface Standard,” a Presentation f...“Introduction to the CSI-2 Image Sensor Interface Standard,” a Presentation f...
“Introduction to the CSI-2 Image Sensor Interface Standard,” a Presentation f...Edge AI and Vision Alliance
 
“Practical Approaches to DNN Quantization,” a Presentation from Magic Leap
“Practical Approaches to DNN Quantization,” a Presentation from Magic Leap“Practical Approaches to DNN Quantization,” a Presentation from Magic Leap
“Practical Approaches to DNN Quantization,” a Presentation from Magic LeapEdge AI and Vision Alliance
 
"Optimizing Image Quality and Stereo Depth at the Edge," a Presentation from ...
"Optimizing Image Quality and Stereo Depth at the Edge," a Presentation from ..."Optimizing Image Quality and Stereo Depth at the Edge," a Presentation from ...
"Optimizing Image Quality and Stereo Depth at the Edge," a Presentation from ...Edge AI and Vision Alliance
 
“Using a Collaborative Network of Distributed Cameras for Object Tracking,” a...
“Using a Collaborative Network of Distributed Cameras for Object Tracking,” a...“Using a Collaborative Network of Distributed Cameras for Object Tracking,” a...
“Using a Collaborative Network of Distributed Cameras for Object Tracking,” a...Edge AI and Vision Alliance
 
“A Survey of Model Compression Methods,” a Presentation from Instrumental
“A Survey of Model Compression Methods,” a Presentation from Instrumental“A Survey of Model Compression Methods,” a Presentation from Instrumental
“A Survey of Model Compression Methods,” a Presentation from InstrumentalEdge AI and Vision Alliance
 
“Reinventing Smart Cities with Computer Vision,” a Presentation from Hayden AI
“Reinventing Smart Cities with Computer Vision,” a Presentation from Hayden AI“Reinventing Smart Cities with Computer Vision,” a Presentation from Hayden AI
“Reinventing Smart Cities with Computer Vision,” a Presentation from Hayden AIEdge AI and Vision Alliance
 

Plus de Edge AI and Vision Alliance (20)

“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
 
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
 
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
 
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
 
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
 
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
 
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
 
“Updating the Edge ML Development Process,” a Presentation from Samsara
“Updating the Edge ML Development Process,” a Presentation from Samsara“Updating the Edge ML Development Process,” a Presentation from Samsara
“Updating the Edge ML Development Process,” a Presentation from Samsara
 
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
 
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
 
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
 
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
 
“Tracking and Fusing Diverse Risk Factors to Drive a SAFER Future,” a Present...
“Tracking and Fusing Diverse Risk Factors to Drive a SAFER Future,” a Present...“Tracking and Fusing Diverse Risk Factors to Drive a SAFER Future,” a Present...
“Tracking and Fusing Diverse Risk Factors to Drive a SAFER Future,” a Present...
 
“MIPI CSI-2 Image Sensor Interface Standard Features Enable Efficient Embedde...
“MIPI CSI-2 Image Sensor Interface Standard Features Enable Efficient Embedde...“MIPI CSI-2 Image Sensor Interface Standard Features Enable Efficient Embedde...
“MIPI CSI-2 Image Sensor Interface Standard Features Enable Efficient Embedde...
 
“Introduction to the CSI-2 Image Sensor Interface Standard,” a Presentation f...
“Introduction to the CSI-2 Image Sensor Interface Standard,” a Presentation f...“Introduction to the CSI-2 Image Sensor Interface Standard,” a Presentation f...
“Introduction to the CSI-2 Image Sensor Interface Standard,” a Presentation f...
 
“Practical Approaches to DNN Quantization,” a Presentation from Magic Leap
“Practical Approaches to DNN Quantization,” a Presentation from Magic Leap“Practical Approaches to DNN Quantization,” a Presentation from Magic Leap
“Practical Approaches to DNN Quantization,” a Presentation from Magic Leap
 
"Optimizing Image Quality and Stereo Depth at the Edge," a Presentation from ...
"Optimizing Image Quality and Stereo Depth at the Edge," a Presentation from ..."Optimizing Image Quality and Stereo Depth at the Edge," a Presentation from ...
"Optimizing Image Quality and Stereo Depth at the Edge," a Presentation from ...
 
“Using a Collaborative Network of Distributed Cameras for Object Tracking,” a...
“Using a Collaborative Network of Distributed Cameras for Object Tracking,” a...“Using a Collaborative Network of Distributed Cameras for Object Tracking,” a...
“Using a Collaborative Network of Distributed Cameras for Object Tracking,” a...
 
“A Survey of Model Compression Methods,” a Presentation from Instrumental
“A Survey of Model Compression Methods,” a Presentation from Instrumental“A Survey of Model Compression Methods,” a Presentation from Instrumental
“A Survey of Model Compression Methods,” a Presentation from Instrumental
 
“Reinventing Smart Cities with Computer Vision,” a Presentation from Hayden AI
“Reinventing Smart Cities with Computer Vision,” a Presentation from Hayden AI“Reinventing Smart Cities with Computer Vision,” a Presentation from Hayden AI
“Reinventing Smart Cities with Computer Vision,” a Presentation from Hayden AI
 

Dernier

SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024Lorenzo Miniero
 
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr LapshynFwdays
 
WordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your BrandWordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your Brandgvaughan
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Scott Keck-Warren
 
Training state-of-the-art general text embedding
Training state-of-the-art general text embeddingTraining state-of-the-art general text embedding
Training state-of-the-art general text embeddingZilliz
 
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage CostLeverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage CostZilliz
 
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationSafe Software
 
Story boards and shot lists for my a level piece
Story boards and shot lists for my a level pieceStory boards and shot lists for my a level piece
Story boards and shot lists for my a level piececharlottematthew16
 
Gen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfGen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfAddepto
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticscarlostorres15106
 
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Patryk Bandurski
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machinePadma Pradeep
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 3652toLead Limited
 
Commit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easyCommit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easyAlfredo García Lavilla
 
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
The Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdfThe Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdfSeasiaInfotech2
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii SoldatenkoFwdays
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationRidwan Fadjar
 
DevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsDevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsSergiu Bodiu
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek SchlawackFwdays
 

Dernier (20)

SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024
 
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
 
WordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your BrandWordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your Brand
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024
 
Training state-of-the-art general text embedding
Training state-of-the-art general text embeddingTraining state-of-the-art general text embedding
Training state-of-the-art general text embedding
 
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage CostLeverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
 
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
 
Story boards and shot lists for my a level piece
Story boards and shot lists for my a level pieceStory boards and shot lists for my a level piece
Story boards and shot lists for my a level piece
 
Gen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfGen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdf
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
 
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machine
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365
 
Commit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easyCommit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easy
 
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
The Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdfThe Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdf
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 Presentation
 
DevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsDevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platforms
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
 

"Improving the Safety and Performance of Automated Vehicles Through Precision Localization," a Presentation from VSI Labs

  • 1. © 2019 VSI Labs Improving the Safety & Performance of Automated Vehicles Through Precision Localization Phil Magney VSI Labs May 2019
  • 2. © 2019 VSI Labs VSI’s Range of Research 2 Industry Research & Advisory Testing & Demonstration Engineering Services • Applied research on active safety and automated driving since 2014 • Supporting R&D & planning for automotive, suppliers and technology industry • VSI Offers various research portals
  • 3. © 2019 VSI Labs Automated Vehicle Trajectories Series Production Low Speed Shuttles Robo-Taxis 3
  • 4. © 2019 VSI Labs Automated Driving Today – Series Production Cars Automated driving is born from active safety systems (active lane keeping, adaptive cruise control, etc.) Most L2 vehicles use camera and radar Lane centering, no organic path planning Localization – most L2 vehicles rely on SLAM methods 4
  • 5. © 2019 VSI Labs Automated Driving Today -- Shuttles Driverless Shuttles – low speed vehicles being developed as fully automated people movers Shuttles operate on a “virtual rail” Shuttles will also use various other sensors for collision avoidance Localization -- Shuttles use correction services to localization against a pre- mapped course 5
  • 6. © 2019 VSI Labs Automated Driving Today -- Robo Taxis Many companies are developing L4 “robo-taxis” for deployment in metro areas under a ride sharing model Robo-taxis use many sensors including redundant camera, Lidar, Radar, HD maps, etc. Localization -- Precision localization against HD maps, mainly using lidar 6
  • 7. © 2019 VSI Labs The Tech Behind Automated Vehicle Systems Sensors Processors Software 7
  • 8. © 2019 VSI Labs Anatomy of an Automated Vehicle 8
  • 9. © 2019 VSI Labs The Automation Pipeline 9
  • 10. © 2019 VSI Labs Sensor Configurations L1 Active Safety Features L2 Lane Level Automation L2+ Multi Lane Automation L3 Traffic Jam Pilot and Hwy Pilot L4/L5 Robo-taxi / MaaS Camera Front facing Rear facing (passive) Front facing Rear facing (passive) Front facing x 2 Side facing x 2 Rear facing Driver facing Front facing x 2 Side facing x 2 Rear facing Driver facing Front facing x 3 Side facing x 4 Rear facing x 2 Thermal x 2 Driver facing Radar Med-long range front Short range side x 2 Med-long range front Short range side x 2 Med-long range front Short range side x 2 Short range front Med-long range Short range side x 2 Short range front Med-long range Short range side x 2 Imaging radar x 2 Ultrasonic 360 degree 360 degree 360 degree 360 degree 360 degree LiDAR Solid state Solid state x 2 Solid state x 2 360 degree x 2 HD Maps ADAS model ADAS model Lane model Localization model ADAS model Lane model Localization model ADAS model Lane model Localization model Inertial IMU IMU IMU IMU IMU GNSS + Correction RTK RTK RTK Total Sensors 7 8 16 18 28 Notes: This are proxy estimates based on OEM and fleets planned announcements. Sensor distribution may vary greatly among OEMs. Maps are counted as a sensor as well as IMU, GNSS devices. Surround view applications are not included in this chart. Ultra sonic is counted as one rather than discrete units. L3 – L5 are largely development sensor configurations, final production may differ. Automotive Sensor Proxy 10
  • 11. © 2019 VSI Labs Improving Safety Through Precision Maps 11
  • 12. © 2019 VSI Labs Limitations of Vision-based Automation (basic L2) 12
  • 13. © 2019 VSI Labs Limitations of AVs in Poor Weather? 13 Sensors Fail • Camera & Lidar fail quickly • Radar still robust Infrastructure Fails • Lanes lines covered • Localization assets hard to recognize if they are covered in snow What Does it Take? • Precision localization – through correction services • V2I – through embedded cellular, DSRC • Virtual Infrastructure – Precision Maps (lanes models, intersections, and other metadata) • Low Grip Algorithm
  • 14. © 2019 VSI Labs Absolute Localization (Ground Truth) 14 • GPS based accuracy is not enough and suffers from outages • Heighten the fixes with correction (RTK services) to w/I a few centimeters • Once base accuracy is enough, then you need to localized against it between fixes • Wheel odometry uses a starting position and wheel speed to estimate a position from a fixed point • Inertial measurement unit (IMU) senses the movement of the vehicle in time via yaw, pitch, roll axis and magnetic • Visual odometry estimates vehicle motion from a sequence of camera frames
  • 15. © 2019 VSI Labs Relative Localization With Landmarks • Landmark localization - matches landmarks and objects (signs, poles, and other permanent objects • In landmark-based approaches the objects are classified • The challenge is the creation and maintenance of these maps, requires human annotation 15 Source: Towards Data Science
  • 16. © 2019 VSI Labs Relative Localization With Lane Models • Lane models provide virtual lane and centerline trajectories from which to localize against • This is particularly important when lanes lines are obstructed (i.e. covered in snow) • Lane models is vital to multilane highways and intersection traversals • The challenge is the creation and maintenance of these maps 16
  • 17. © 2019 VSI Labs What are Precision Maps & Who Supplies Them • Road model (ADAS Map) • Topology • Routing • Speed attributes, etc.) • Lane Models • Lane geometry • Polylines • Trajectories • Localization Layer • Landmarks • Signs, barriers, poles etc. • Edges and boundaries • Voxels • Confidence Index 17
  • 18. © 2019 VSI Labs How to Keep the Data Fresh • Mapping data are always changing • Temporary lane closures or detours • Changes to the infrastructure (bridges, landmarks, poles, lights) • How to detect changes, collect, then validate those changes • Requires fleets to crowd source • Requires connected vehicles • Requires standardization of message sets 18
  • 19. © 2019 VSI Labs Elements of Mapping Assets 19 Trajectories • Geocoded Paths Lane Models • Lane Geometry ADAS Map • Speeds/Slopes/Curves Localization Layers Raw Images Raw Point Clouds Vixels (Voxels + RGB data) Voxels (clusters of points) Compressed Point Cloud Object List (landmarks) VolumeofData Sense and React Sense and Align Sense and Position HERE HD Live Maps
  • 20. © 2019 VSI Labs Closing Remarks • Automation in series production is an extension of ADAS. • Couple camera and radar and you have L2 capabilities. • Adding precision maps substantially improves the performance and safety of automated vehicles: • Mapping assets to improve localization • Lane models tell you where you can and cannot operate! • ADAS attributes add speeds, curve, slope and other important metadata • Shuttles are a pragmatic approach to automation • No path planning as you are using a recorded path to create a virtual rail • Robo-taxis will apply everything we have talked about times three • They will be highly constrained (largely because of SOTIF – Safety Of the Intended Function) 20
  • 21. © 2019 VSI Labs Contact 21 Resources www.VSL-Labs.com Sign Up for Free White Papers Request Services Agreement Client Portal Registration Page Contact Phil Magney +1-952-215-1797