microsoft azure in autonomous driving · microsoft antimalware for azure. sensor data fusion tools...
TRANSCRIPT
Microsoft Azure in
Autonomous Driving
We ensure your data is always under your control
We guarantee that the brand and customer experience belongs to you
We complement OEMs and suppliers – not compete
Microsoft’s approach to automotive
OEM System Engineering Process
Regional
Architecture (s)
Feasibility
Study/concept
Exploration
Changes
and Upgrades
Retirement/
replacement
Concepts of
Operations
System
Requirements
High-Level
Design
Detailed Design
Software/Hardware
Development Field
Installation
Unit/Device
Testing
Subsystem
Verification
System
Verification &
Deployment
System
Validation
Operations
and
Maintenance
Engineering Development Product Validation Manufacturing & Service
System Validation Plan
System Verification Plan(System Acceptance)
Subsystem Verification Plan (Subsystem Acceptance)
Unit/Device Test
Plan
Document/Approval
Implementation
Development Processes
Time Line
Lifecycle Processes
Sensor/ Algorithm
Testing (Open Loop)
Process,
Sample, Reduce
Test Vehicle Ingest/ Store Integrate Build
Train
Simulate
ReplayTag
Render/Convert
Control Logic
Validation
Performance
Simulation
Generate
Code
Software
in the loop
Hardware
in the loop
F(x)
Test-Drive
DATA INGEST & CURATE TEST | TRAIN | SIMULATE BUILD | VALIDATE
• Cloud and Analytics partner for
ACM, an autonomous and smart
mobility test facility
• Leveraged by all OEMs, tier ones and
technology start ups
• Engaged with ACM to influence
standards
Industry
Academia Government
• Open source AD Platform
• 200+ Member Consortium
• Microsoft is the cloud provider for
Project Apollo worldwide with the
exception of China
• OpenADx
• Interoperable Eclipse Framework
LG’s autonomous vehicle program had unique requirements,
including portability, security, and fast turnaround time; Data
Box Disk was the perfect solution.
“We needed a way to transfer massive amounts of data for
our autonomous vehicle projects, based all around the
world. The solution needed to be portable, simple to use,
cost-effective and, of course, very secure. The Azure Data
Box Disk met all of those criteria.”
– Hyoyuel (Andy) Kim, Senior Manager, LG Electronics.
Products and services
Azure Data Box Disk
Azure Blob Storage
Organization size
91,000
Industry
Automotive
electronics
Country
Worldwide
Azure Express Route
Azure Storage, Data Lake Gen2
Azure Data Box
Azure Compute
Azure Batch AI
Cycle Cloud
Databricks & HDInsight
Azure Machine Learning
Cognitive Services
Azure IoT Edge
Container and Kubernetes , Visual
Studio Team Services
Azure Key Vault, AAD
Test Vehicle Ingest/ Store
Test-Drive
Integrate Build
Train
Simulate
ReplayTag
Sensor/ Algorithm
Testing (Open Loop)
Process,
Sample, Reduce
Render/Convert
Control Logic
Validation
Performance
Simulation
Generate
Code
Software
in the loop
Hardware
in the loop
DATA INGEST & CURATE TEST | TRAIN | SIMULATE BUILD | VALIDATE
F(x)
In-car
data
storage
Data
reduction,
redaction
Azure blob
storage (cool,
archive)
ML
Advanced
Analytics
Azure
Container
Service
Container
RegistrySource
Control
CI/CD flows
HDInsight,
Azure
Databricks
ADLS Gen 2 and Azure blob
storage Hot Tier
Async
upload
Fast
upload
DATA INGEST
IoT Edge
Cycle Cloud
PowerBICosmosDB
SOFTWARE TOOLS AND DEVOPS PLATFORM
Stream Analytics
Machine Learning
Batch
Logic App
Machine Learning
Data Factory
Azure GPU
VM
Kubernetes
ServiceSimplygon
HDInsight
Service Bus Databricks
Virtual machine
Cosmos DB
Sensor/ Algorithm
Testing (Open Loop)
Process,
Sample, Reduce
Test Vehicle Ingest/ Store Integrate Build
Train
Simulate
ReplayTag
Render/Convert
Control Logic
Validation
Performance
Simulation
Generate
Code
Software
in the loop
Hardware
in the loop
F(x)
Test-Drive
DATA INGEST & CURATE TEST | TRAIN | SIMULATE BUILD | VALIDATE
Offline Data Transfer Online Data Transfer
Data Box Heavy
• Capacity: 1000TB
• Weight 500+ lbs
• Secure, ruggedized
appliance
• Currently in Preview
• Same service as Data Box,
but targeted to petabyte-
sized datasets.
Data Box Gateway
• Virtual device provisioned in
your hypervisor
• Supports storage gateway,
SMB, NFS, Azure blob, files
• Currently in preview
• Virtual network transfer
appliance (VM), runs on your
choice of hardware.
Data Box Edge
• Local Cache Capacity: ~12 TB
• Includes Data Box Gateway
and Azure IoT Edge.
• Currently in preview
• Data Box Edge manages
uploads to Azure and can
pre-process data prior to
upload.
Data Box
• Capacity: 100 TB
• Weight: ~50 lbs
• Secure, ruggedized
appliance
• Data Box enables bulk
migration to Azure when
network isn’t an option.
Data Box Disk
• Capacity: 8TB ea.; 40TB/order
• Secure, ruggedized USB
drives orderable in packs of
5 (up to 40TB).
• Currently in Preview
• Perfect for projects that
require a smaller form factor,
e.g., autonomous vehicles.
Order Fill UploadSend Return Cloud to Edge Edge to Cloud Pre-processing ML Inferencing
Network Data Transfer Edge Compute
Connecting your data center and Azure
Predictable performance and Secure
100 + Express Route partners
Ingest up to PB of data daily with Azure Networking Express Route Service
Private, high speed network connections
Massive Data Ingest – ExpressRoute
Store up to Exabytes of data in massively scalable object storage for
unstructured data
Frequently accessed data
Lowest transaction cost
Immediate (ms)
Less frequently accessed data
Lower capacity
cost
Immediate (ms)
Rarely accessed data
Lowest capacity cost
Hours
Data Storage – Azure Blob Storage
• Foundational service for Microsoft
• >40 million transactions per second
• Multi-PB accounts
• 50+Gbps account throughput
• Continued enhancements under
development
• Client & Service Encryption
• AAD Integration + ACLs
• Broad & deep compliance portfolio
Scalable
Performant
Secure &
Compliant
• Multiple redundancy options
• Strong consistency, data integrity
• Policy: Versioning & WORM locks
Durable
• Integrated storage tiers
• Lifecycle management
• Rich metrics
Cost
Effective
Security management
Data protection
Network security
Threat protection
Identity & access management
Azure Active Directory
Multi-Factor
Authentication
Role Based Access
Control
Encryption
(Disks, Storage, SQL)
Azure Key Vault
VNET, VPN, NSG
Application Gateway
(WAF), Azure Firewall
DDoS Protection
Standard
ExpressRoute
Azure Security Center
Azure Log Analytics
+ Partner Solutions
Azure Active Directory
(Identity Protection)
Microsoft Antimalware
for Azure
Sensor data fusion tools
Data extraction
Labeling and annotation
Data analysis
Data anonymization
Workflow orchestration and
managed services
Partner-based Solutions
AnnotationData
Preparation
Data
Extraction
Microsoft Services
Blob Cognitive Services Services Logic HDInsight Databricks Cosmos DB BatchSearchApps Functions
Data selection and transformation, PII data
redaction, annotation and training data
preparation
Analyze your Data in one place
Azure HDInsight
IoT Hub
Event Hubs
Data Warehouse
Data Factory
App Insights Log Analytics
Monitor
CDN
Search Power BI
Blob Storage Pillars
Open &
Interoperable
Manageable &
Cost Efficient
Scalable &
Performant
Secure &
Compliant
Durable &
Available
Machine Learning
Stream Analytics
Batch
Functions
Data Lake Analytics
Big Data Use Cases
Ingest & ETL Streaming Analytics & Machine Learning Data Aggregation Presentation
Manageable &
Cost Efficient
Scalable &
Performant
Secure &
Compliant
Semantic Segmentation
Each Pixel of the image is assigned a category
Object Detection & Classification
Bounding box drawn around each
object of interest
3D Point Cloud Labeling
Objects of interest as assigned a category in 3D LIDAR point cloud
Deploy AI models in Azure for auto-
labeling images to optimize for speed
of labeling and possibly cost
Sensor/ Algorithm
Testing (Open Loop)
Process,
Sample, Reduce
Test Vehicle Ingest/ Store Integrate Build
Train
Simulate
ReplayTag
Render/Convert
Control Logic
Validation
Performance
Simulation
Generate
Code
Software
in the loop
Hardware
in the loop
DATA INGEST & CURATE TEST | TRAIN | SIMULATE BUILD | VALIDATE
F(x)
Test-Drive
Open loop testing (e.g. ADTF)
Partnership Opportunities
Scene Reconstruction
and Replay
Microsoft Services
Blob Cycle Cloud CPUCompute
Batch Service BusCosmos
DBPowerBIKey VaultLogic Apps
Verification and validation of training
algorithms and sensors via open loop testing
Simulation tools for sensor and algorithm
validation Algorithm scoring Results AnalysisTest
repository
Workflow Management Services
Comprehensive Validation framework
Build and deploy deep learning models
Azure ML Services
Scale out clusters
Azure
databricks
Notebooks
Azure
databricks
Scale out clusters
Batch AI
Caffe2
MS cognitive
toolkit
Keras
TensorFlow
Choose VMs for your modeling needs
Process video using GPU-based VMs
Run experiments in parallel
Provision resources automatically
Leverage popular deep learning toolkits
Develop your language of choice
Scale compute
resources in any environment
Quickly evaluate
and identify the right model
Streamline
AI development efforts
Leverage your favorite deep learning frameworks
TensorFlow MS Cognitive Toolkit PyTorch Scikit-Learn ONNX Caffe2 MXNet Chainer
Operationalize and manage models with ease
Identify and promote your best models
Capture model telemetry
Retrain models with APIs
Deploy models anywhere
Scale out to containers
Infuse intelligence into the IoT edge
Build and deploy models in minutes
Iterate quickly on serverless infrastructure
Easily change environments
Proactively manage
model performance
Deploy models
closer to your data
Bring models
to life quickly
Train and evaluate models
Azure
databricks
Model MGMT, experimentation, and run history
Azure
ML services
Containers
AKS ACI
IoT edge
Simulation is the fastest way to “drive” the billions of miles needed to discover the breadth of real-world
anomalies required to develop AD solutions.
Scenario Simulation
Scenario definition and simulation for path
planning and navigational maneuvers
(overtake, parallel parking, etc) using post
perception object level simulation.
Run 7200 simulated scenarios covering ~5000
miles per day/per node
Sensor Simulation
Photo-realistic rendering of modeled sensors
(Lidar, radar, RGB cameras) for the training
and validation of Perception AI algorithms.
Render once, test many times
Mathematical based simulation for
Structural CAD design, Fluid dynamics,
Thermo dynamics, material properties
Design sensor properties and placement
on vehicle options at scale before
hardware prototyping is needed. Simulate
accidents and AD navigation to a safe
stop
Engineering Simulation
Build
Test-Drive
Integrate
Test Vehicle Fleet
Ingest/StoreTrain
Sensor Fusion,
Process, Sample,
Reduce, Tag, QA
Performance
Simulation
Control Logic
Validation
Generate
Code
Algorithm
Validation Engine
Simulation
Engine
Production Vehicle Fleet
Training
Dataset
Render/convert
Hardware
in the loop
F(x)
Software
in the loop
Simulation/Reinforcement Learning Centric Model
“Drive Millions, Train on Billions”
Sensor/ Algorithm
Testing (Open Loop)
Process,
Sample, Reduce
Test Vehicle Ingest/ Store
Test-Drive
Integrate Build
Train
Simulate
ReplayTag
Render/Convert
Control Logic
Validation
Performance
Simulation
Generate
Code
Software
in the loop
Hardware
in the loop
F(x)
DATA INGEST & CURATE TEST | TRAIN | SIMULATE BUILD | VALIDATE
Test-Drive
Control Logic
Validation
Performance
Simulation
Generate
Code
Software
in the loop
Hardware
in the loop
F(x)
Microsoft Services
Batch Active Directory Container service Blob storage GPU VM
Comprehensive test management
framework
Partner-based Solutions
HIL solutions
Embedded system validation via hardware-in-
loop and software-in-loop
System validation tools
Workflow management services
Managed services
© Copyright Microsoft Corporation. All rights reserved.