SlideShare une entreprise Scribd logo
1  sur  63
Télécharger pour lire hors ligne
How to Build a Data Closed-loop Platform for
Autonomous Driving?
Yu Huang
Sunnyvale, California
Yu.huang07@gmail.com
Outline
• Introduction;
• data driven models for autonomous driving;
• cloud computing infrastructure and big data processing;
• annotation tools for training data;
• large scale model training platform;
• model testing and verification;
• related machine learning techniques;
• Conclusion.
Introduction
• Development engineering of autonomous driving is to solve a “long-tail problem” of rare events;
• Corner cases occurring, bring valuable sources for data-driven algorithms & models.
https://www.self-driving-cars.org/
• Tesla’s data engine
ICML 2019
Introduction
• Google Waymo‘s ML factory
Introduction
MIT 2019
• Nvidia’s AV ML platform MAGLEV
Introduction
data driven models for autonomous driving
• Usually the self driving platform is classified as end-to-end (E2E) or modular system
“A Survey of Autonomous Driving: Common Practices and Emerging Technologies” 
data driven models for autonomous driving
• Usually it is obvious that the E2E system applies data driven models
“E2E Learning of Driving Models with Surround-View Cameras and Route Planners”
data driven models for autonomous driving
• Modular system
• Perception
• Mapping-Localization
• Prediction
• Planning
• Control
• Sensor Data Preprocessing
• Simulation
data driven models for autonomous driving
• Perception: 2D/3D detection, segmetation, tracking and (early/late) fusion etc.
data driven models for autonomous driving
• Perception: 2D/3D detection, segmentation, tracking and (early/late) fusion etc.
data driven models for autonomous driving
• Mapping-Localization: semantic map, feature design, map update/online mapping, SLAM,
pose estimation and odometry etc.
data driven models for autonomous driving
• Prediction: trajectory forecasting, agent behavior & interaction, multimodal, and perception-
prediction etc.
data driven models for autonomous driving
• Planning: reinforcement learning, imitation learning, inverse reinforcement learning, localization
& personalization of planning (aggressive or conservative), prediction-planning, and mapping-
localization-prediction-planning etc.
data driven models for autonomous driving
• Planning: reinforcement learning, imitation learning, inverse reinforcement learning,
localization & personalization of planning (aggressive or conservative), prediction-planning,
and mapping-localization-prediction-planning etc.
data driven models for autonomous driving
• Control: reinforcement learning, imitation learning, inverse reinforcement learning, and
planning-control etc.
data driven models for autonomous driving
• Sensor Data Preprocessing: pollution/dust detection, defogging, deraining, desnowing,
denoising, and enhancement etc.
data driven models for autonomous driving
• Simulation: vehicle/human, sensor, traffic, road and environment modeling
etc.
cloud computing infrastructure and big data processing
• Data batch/stream processing, workflow management, distributed
computing, state monitoring and data storage.
AWS Momenta
Amazon Elastic Compute
Cloud(EC2)
Amazon Elasticsearch Service
Amazon Kinesis
Amazon SageMaker
cloud computing infrastructure and big data processing
• Data batch/stream processing, workflow management, distributed
computing, state monitoring and data storage.
cloud computing infrastructure and big data processing
• Data batch/stream processing, workflow management, distributed
computing, state monitoring and data storage.
Apache Spark
Apache Kafka
Apache Flink
Apache Airflow
cloud computing infrastructure and big data processing
• Data batch/stream processing, resource monitoring & scheduling, workflow
management, distributed computing, state monitoring and data storage.
Apache Cassandra
Apache HBase
Apache Mesos
cloud computing infrastructure and big data processing
• Data batch/stream processing, resource monitoring & scheduling, workflow
management, distributed computing, state monitoring and data storage.
Kubernetes
Apache Hudi
Presto
annotation tools for training data
• There are manual, semi-automatic or full automatic tools for annotation.
annotation tools for training data
• There are manual, semi-automatic or full automatic tools for annotation.
annotation tools for training data
• There are manual, semi-automatic or full automatic tools for annotation.
annotation tools for training data
• There are manual, semi-automatic or full automatic tools for annotation.
annotation tools for training data
• visualization tools are used for viewing/debugging/replaying the data, besides of annotation.
Uber open sourced visualization tool: Autonomous Visualization System (AVS)
annotation tools for training data
• visualization tools are used for viewing/debugging/replaying the data, besides of annotation.
”XVIZ“- Protocol for Real-Time Transfer and Visualization of Autonomy Data
annotation tools for training data
• visualization tools are used for viewing/debugging/replaying the data, besides of annotation.
streetscape.gl:a visualization toolkit for autonomy and robotics data encoded in the XVIZ protocol.
large scale model training platform
• There are open deep learning training platforms, previously as Caffe, now the most popular ones
are Tensorflow and PyTorch.
large scale model training platform
• There are open deep learning training platforms, previously as Caffe, now the most popular ones
are Tensorflow and PyTorch.
Ring AllReduce Architecture
Parameter Server Architecture (PS)
model testing and verification
• Model Testing and Verification: simulation (MIL/SIL/HIL/VIL), closed driving
district, open driving area & users (such as Tesla’s shadow mode) .
model testing and verification
• Model Testing and Verification(MIL/SIL/HIL/VIL)
LiDARsim
model testing and verification
• Model Testing and Verification(MIL/SIL/HIL/VIL)
S3:Shape, Skeleton, and Skinning
model testing and verification
• Model Testing and Verification(MIL/SIL/HIL/VIL)
SceneGen
model testing and verification
• Model Testing and Verification(MIL/SIL/HIL/VIL)
TrafficSim
model testing and verification
• Model Testing and Verification(MIL/SIL/HIL/VIL)
GeoSim
model testing and verification
• Model Testing and Verification(MIL/SIL/HIL/VIL)
AdvSim
model testing and verification
• Model Testing and Verification(MIL/SIL/HIL/VIL)
SurfelGAN
model testing and verification
• Testing from closed driving district
model testing and verification
• Testing from open driving area
model testing and verification
• Testing from users (such as Tesla’s shadow mode)
related machine learning techniques
• Active learning
• OOD detection & Corner case detection
• Data augmentation/Adversarial learning
• Transfer learning/Domain adaptation
• AutoML/Meta-learning
• Semi-supervised learning
• Self-supervised learning
• Zero/Few shot learning
• Continual learning/Open world learning
related machine learning techniques
• active learning : The goal
of active learning is to find effective
ways to choose data points to label,
from a pool of unlabeled data points, in
order to maximize the accuracy. Active
learning is typically an iterative process
in which a model is learned at each
iteration and a set of points is chosen
to be labelled from a pool of unlabeled
points using some heuristics.
related machine learning techniques
• active learning:
related machine learning techniques
•OOD detection & Corner case detection: To detect OOD samples based on uncertainty estimate is
important in safety-critical applications; The challenging task of corner case detection, aims at
detecting these unusual situations, which could become critical to communicate this to the
autonomous driving system (online use case), also in offline mode to screen vast amounts of data and
select only the relevant situations.
related machine learning techniques
• Data augmentation/Adversarial learning: Data Augmentation
encompasses a suite of techniques that enhance the size and quality of training
datasets such that better Deep Learning models can be built using them;
Adversarial training can be an effective method for searching for augmentations.
related machine learning techniques
• Data augmentation/Adversarial learning:
related machine learning techniques
• Transfer learning/Domain adaptation: Transfer learning (TL) relaxes the hypothesis
that the training data must be independent and identically distributed (i.i.d.) with the test data,
which motivates us to use transfer learning to against the problem of insufficient training data;
Domain adaptation (DA) is a particular case of transfer learning (TL) that utilizes labeled data in
one or more relevant source domains to execute new tasks in a target domain.
related machine learning techniques
• Transfer learning/Domain adaptation
related machine learning techniques
• AutoML/Meta-learning: Automated Machine Learning (AutoML) is designed to reduce the
demand for data scientists and enable domain experts to automatically build machine learning
applications without much requirement for statistical and machine learning knowledge; Meta-
learning is closely related to AutoML since they share the same objectives of study, namely the
learning tools and learning problem.
related machine learning techniques
• Semi-supervised learning: Self-supervised Learning is to leverage the unlabeled data
to produce a prediction function with trainable parameters, that is more accurate than what
would have been obtained by only using the labeled data.
related machine learning techniques
• Semi-supervised learning:
related machine learning techniques
• Self-supervised learning: Self-supervised learning viewed as a branch
of unsupervised learning, which aims at recovering, not discovering; It uses
a pretext task to learn representations on unlabeled data.
related machine learning techniques
•Zero/Few shot learning: Zero-shot learning (ZSL) aims to recognize objects
whose instances may not be seen during training. Zero shot learning belongs to
transfer learning; Few-Shot Learning (FSL) comes for learning from limited
supervised information to get the hang of the task; Many FSL methods are meta-
learning methods, using the meta-learner as prior knowledge.
related machine learning techniques
•Zero/Few shot learning:
related machine learning techniques
•Zero/Few shot learning:
related machine learning techniques
• Continual learning/Open world learning: Continual learning can
continually accumulate knowledge over different tasks without the need to retrain
from scratch; Open set recognition (OSR), requiring the classifiers to not only
accurately classify the seen classes, but also effectively deal with unseen ones;
Open world learning can be seen as a sub task of continual learning.
related machine learning techniques
• Continual learning/Open world learning:
related machine learning techniques
• Continual learning/Open world learning:
Conclusion
• In summary, the key in the data closed loop building is the
sourceful data.
• The data driven models or algorithms applied to solve
autonomous driving tasks is the base.
• The trend for this system upgrade depends on:
Ø Data mode (camera, LiDAR, radar, IMU etc.)
Ø Data driven model architecture (AutoML)
Ø Policy to select and use the data (Corner case).
Thank You

Contenu connexe

Tendances

ensemble learning
ensemble learningensemble learning
ensemble learning
butest
 
Machine Learning Models in Production
Machine Learning Models in ProductionMachine Learning Models in Production
Machine Learning Models in Production
DataWorks Summit
 
Column oriented database
Column oriented databaseColumn oriented database
Column oriented database
Kanike Krishna
 

Tendances (20)

Frequent Itemset Mining(FIM) on BigData
Frequent Itemset Mining(FIM) on BigDataFrequent Itemset Mining(FIM) on BigData
Frequent Itemset Mining(FIM) on BigData
 
05 Clustering in Data Mining
05 Clustering in Data Mining05 Clustering in Data Mining
05 Clustering in Data Mining
 
K Nearest Neighbor Algorithm
K Nearest Neighbor AlgorithmK Nearest Neighbor Algorithm
K Nearest Neighbor Algorithm
 
Introduction to ML (Machine Learning)
Introduction to ML (Machine Learning)Introduction to ML (Machine Learning)
Introduction to ML (Machine Learning)
 
Ensemble learning
Ensemble learningEnsemble learning
Ensemble learning
 
ensemble learning
ensemble learningensemble learning
ensemble learning
 
Evaluating and Selecting a Learning Management System
Evaluating and Selecting a Learning Management SystemEvaluating and Selecting a Learning Management System
Evaluating and Selecting a Learning Management System
 
MLOps Using MLflow
MLOps Using MLflowMLOps Using MLflow
MLOps Using MLflow
 
Learning from imbalanced data
Learning from imbalanced data Learning from imbalanced data
Learning from imbalanced data
 
The New Perception Framework in Autonomous Driving: An Introduction of BEV N...
The New Perception Framework  in Autonomous Driving: An Introduction of BEV N...The New Perception Framework  in Autonomous Driving: An Introduction of BEV N...
The New Perception Framework in Autonomous Driving: An Introduction of BEV N...
 
Machine Learning Models in Production
Machine Learning Models in ProductionMachine Learning Models in Production
Machine Learning Models in Production
 
A quick demo of Top2Vec With application on 2020 10-K business descriptions
A quick demo of Top2Vec With application on 2020 10-K business descriptionsA quick demo of Top2Vec With application on 2020 10-K business descriptions
A quick demo of Top2Vec With application on 2020 10-K business descriptions
 
AI meets Big Data
AI meets Big DataAI meets Big Data
AI meets Big Data
 
Introduction to Apache Hadoop Ecosystem
Introduction to Apache Hadoop EcosystemIntroduction to Apache Hadoop Ecosystem
Introduction to Apache Hadoop Ecosystem
 
Apache HBase™
Apache HBase™Apache HBase™
Apache HBase™
 
Supervised learning
  Supervised learning  Supervised learning
Supervised learning
 
Column oriented database
Column oriented databaseColumn oriented database
Column oriented database
 
Types of Machine Learning
Types of Machine LearningTypes of Machine Learning
Types of Machine Learning
 
MLOps Virtual Event | Building Machine Learning Platforms for the Full Lifecycle
MLOps Virtual Event | Building Machine Learning Platforms for the Full LifecycleMLOps Virtual Event | Building Machine Learning Platforms for the Full Lifecycle
MLOps Virtual Event | Building Machine Learning Platforms for the Full Lifecycle
 
Automated Machine Learning (Auto ML)
Automated Machine Learning (Auto ML)Automated Machine Learning (Auto ML)
Automated Machine Learning (Auto ML)
 

Similaire à How to Build a Data Closed-loop Platform for Autonomous Driving?

Machine Learning Training Bootcamp
Machine Learning Training BootcampMachine Learning Training Bootcamp
Machine Learning Training Bootcamp
Tonex
 

Similaire à How to Build a Data Closed-loop Platform for Autonomous Driving? (20)

Week 12: Cloud AI- DSA 441 Cloud Computing
Week 12: Cloud AI- DSA 441 Cloud ComputingWeek 12: Cloud AI- DSA 441 Cloud Computing
Week 12: Cloud AI- DSA 441 Cloud Computing
 
Automated Machine Learning
Automated Machine LearningAutomated Machine Learning
Automated Machine Learning
 
Azure Machine Learning Dotnet Campus 2015
Azure Machine Learning Dotnet Campus 2015 Azure Machine Learning Dotnet Campus 2015
Azure Machine Learning Dotnet Campus 2015
 
Machine learning and azure ml studio
Machine learning and azure ml studioMachine learning and azure ml studio
Machine learning and azure ml studio
 
Machine Learning Training Bootcamp
Machine Learning Training BootcampMachine Learning Training Bootcamp
Machine Learning Training Bootcamp
 
Building High Available and Scalable Machine Learning Applications
Building High Available and Scalable Machine Learning ApplicationsBuilding High Available and Scalable Machine Learning Applications
Building High Available and Scalable Machine Learning Applications
 
Machine learning and Autonomous System
Machine learning and Autonomous SystemMachine learning and Autonomous System
Machine learning and Autonomous System
 
A survey on Machine Learning In Production (July 2018)
A survey on Machine Learning In Production (July 2018)A survey on Machine Learning In Production (July 2018)
A survey on Machine Learning In Production (July 2018)
 
unit 1.2 supervised learning.pptx
unit 1.2 supervised learning.pptxunit 1.2 supervised learning.pptx
unit 1.2 supervised learning.pptx
 
How to Make Cars Smarter: A Step Towards Self-Driving Cars
How to Make Cars Smarter: A Step Towards Self-Driving CarsHow to Make Cars Smarter: A Step Towards Self-Driving Cars
How to Make Cars Smarter: A Step Towards Self-Driving Cars
 
Machine learning
Machine learningMachine learning
Machine learning
 
Introduction to Machine learning
Introduction to Machine learningIntroduction to Machine learning
Introduction to Machine learning
 
Machine learning
Machine learningMachine learning
Machine learning
 
MACHINE LEARNING PRESENTATION (ARTIFICIAL INTELLIGENCE)
MACHINE LEARNING PRESENTATION (ARTIFICIAL INTELLIGENCE)MACHINE LEARNING PRESENTATION (ARTIFICIAL INTELLIGENCE)
MACHINE LEARNING PRESENTATION (ARTIFICIAL INTELLIGENCE)
 
credit card fraud detection
credit card fraud detectioncredit card fraud detection
credit card fraud detection
 
Machine Learning in the Real World
Machine Learning in the Real WorldMachine Learning in the Real World
Machine Learning in the Real World
 
J sai subrahmanyam_Resume
J sai subrahmanyam_ResumeJ sai subrahmanyam_Resume
J sai subrahmanyam_Resume
 
AI for Software Engineering
AI for Software EngineeringAI for Software Engineering
AI for Software Engineering
 
Design Like a Pro: Machine Learning Basics
Design Like a Pro: Machine Learning BasicsDesign Like a Pro: Machine Learning Basics
Design Like a Pro: Machine Learning Basics
 
Azure Machine Learning
Azure Machine LearningAzure Machine Learning
Azure Machine Learning
 

Plus de Yu Huang

Plus de Yu Huang (20)

Application of Foundation Model for Autonomous Driving
Application of Foundation Model for Autonomous DrivingApplication of Foundation Model for Autonomous Driving
Application of Foundation Model for Autonomous Driving
 
BEV Joint Detection and Segmentation
BEV Joint Detection and SegmentationBEV Joint Detection and Segmentation
BEV Joint Detection and Segmentation
 
BEV Object Detection and Prediction
BEV Object Detection and PredictionBEV Object Detection and Prediction
BEV Object Detection and Prediction
 
Fisheye based Perception for Autonomous Driving VI
Fisheye based Perception for Autonomous Driving VIFisheye based Perception for Autonomous Driving VI
Fisheye based Perception for Autonomous Driving VI
 
Fisheye/Omnidirectional View in Autonomous Driving V
Fisheye/Omnidirectional View in Autonomous Driving VFisheye/Omnidirectional View in Autonomous Driving V
Fisheye/Omnidirectional View in Autonomous Driving V
 
Fisheye/Omnidirectional View in Autonomous Driving IV
Fisheye/Omnidirectional View in Autonomous Driving IVFisheye/Omnidirectional View in Autonomous Driving IV
Fisheye/Omnidirectional View in Autonomous Driving IV
 
Prediction,Planninng & Control at Baidu
Prediction,Planninng & Control at BaiduPrediction,Planninng & Control at Baidu
Prediction,Planninng & Control at Baidu
 
Cruise AI under the Hood
Cruise AI under the HoodCruise AI under the Hood
Cruise AI under the Hood
 
LiDAR in the Adverse Weather: Dust, Snow, Rain and Fog (2)
LiDAR in the Adverse Weather: Dust, Snow, Rain and Fog (2)LiDAR in the Adverse Weather: Dust, Snow, Rain and Fog (2)
LiDAR in the Adverse Weather: Dust, Snow, Rain and Fog (2)
 
Scenario-Based Development & Testing for Autonomous Driving
Scenario-Based Development & Testing for Autonomous DrivingScenario-Based Development & Testing for Autonomous Driving
Scenario-Based Development & Testing for Autonomous Driving
 
Annotation tools for ADAS & Autonomous Driving
Annotation tools for ADAS & Autonomous DrivingAnnotation tools for ADAS & Autonomous Driving
Annotation tools for ADAS & Autonomous Driving
 
Simulation for autonomous driving at uber atg
Simulation for autonomous driving at uber atgSimulation for autonomous driving at uber atg
Simulation for autonomous driving at uber atg
 
Multi sensor calibration by deep learning
Multi sensor calibration by deep learningMulti sensor calibration by deep learning
Multi sensor calibration by deep learning
 
Prediction and planning for self driving at waymo
Prediction and planning for self driving at waymoPrediction and planning for self driving at waymo
Prediction and planning for self driving at waymo
 
Jointly mapping, localization, perception, prediction and planning
Jointly mapping, localization, perception, prediction and planningJointly mapping, localization, perception, prediction and planning
Jointly mapping, localization, perception, prediction and planning
 
Data pipeline and data lake for autonomous driving
Data pipeline and data lake for autonomous drivingData pipeline and data lake for autonomous driving
Data pipeline and data lake for autonomous driving
 
Open Source codes of trajectory prediction & behavior planning
Open Source codes of trajectory prediction & behavior planningOpen Source codes of trajectory prediction & behavior planning
Open Source codes of trajectory prediction & behavior planning
 
Lidar in the adverse weather: dust, fog, snow and rain
Lidar in the adverse weather: dust, fog, snow and rainLidar in the adverse weather: dust, fog, snow and rain
Lidar in the adverse weather: dust, fog, snow and rain
 
Autonomous Driving of L3/L4 Commercial trucks
Autonomous Driving of L3/L4 Commercial trucksAutonomous Driving of L3/L4 Commercial trucks
Autonomous Driving of L3/L4 Commercial trucks
 
3-d interpretation from single 2-d image V
3-d interpretation from single 2-d image V3-d interpretation from single 2-d image V
3-d interpretation from single 2-d image V
 

Dernier

Call Girls In Bangalore ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bangalore ☎ 7737669865 🥵 Book Your One night StandCall Girls In Bangalore ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bangalore ☎ 7737669865 🥵 Book Your One night Stand
amitlee9823
 
VIP Call Girls Palanpur 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Palanpur 7001035870 Whatsapp Number, 24/07 BookingVIP Call Girls Palanpur 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Palanpur 7001035870 Whatsapp Number, 24/07 Booking
dharasingh5698
 
VIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 BookingVIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 Booking
dharasingh5698
 
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
dollysharma2066
 
Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar ≼🔝 Delhi door step de...
Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar  ≼🔝 Delhi door step de...Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar  ≼🔝 Delhi door step de...
Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar ≼🔝 Delhi door step de...
9953056974 Low Rate Call Girls In Saket, Delhi NCR
 
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak HamilCara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
Cara Menggugurkan Kandungan 087776558899
 
Call Girls in Netaji Nagar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Netaji Nagar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort ServiceCall Girls in Netaji Nagar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Netaji Nagar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
9953056974 Low Rate Call Girls In Saket, Delhi NCR
 

Dernier (20)

Booking open Available Pune Call Girls Koregaon Park 6297143586 Call Hot Ind...
Booking open Available Pune Call Girls Koregaon Park  6297143586 Call Hot Ind...Booking open Available Pune Call Girls Koregaon Park  6297143586 Call Hot Ind...
Booking open Available Pune Call Girls Koregaon Park 6297143586 Call Hot Ind...
 
Generative AI or GenAI technology based PPT
Generative AI or GenAI technology based PPTGenerative AI or GenAI technology based PPT
Generative AI or GenAI technology based PPT
 
Double rodded leveling 1 pdf activity 01
Double rodded leveling 1 pdf activity 01Double rodded leveling 1 pdf activity 01
Double rodded leveling 1 pdf activity 01
 
KubeKraft presentation @CloudNativeHooghly
KubeKraft presentation @CloudNativeHooghlyKubeKraft presentation @CloudNativeHooghly
KubeKraft presentation @CloudNativeHooghly
 
Water Industry Process Automation & Control Monthly - April 2024
Water Industry Process Automation & Control Monthly - April 2024Water Industry Process Automation & Control Monthly - April 2024
Water Industry Process Automation & Control Monthly - April 2024
 
Call Girls In Bangalore ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bangalore ☎ 7737669865 🥵 Book Your One night StandCall Girls In Bangalore ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bangalore ☎ 7737669865 🥵 Book Your One night Stand
 
Thermal Engineering-R & A / C - unit - V
Thermal Engineering-R & A / C - unit - VThermal Engineering-R & A / C - unit - V
Thermal Engineering-R & A / C - unit - V
 
VIP Call Girls Palanpur 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Palanpur 7001035870 Whatsapp Number, 24/07 BookingVIP Call Girls Palanpur 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Palanpur 7001035870 Whatsapp Number, 24/07 Booking
 
Call Girls Walvekar Nagar Call Me 7737669865 Budget Friendly No Advance Booking
Call Girls Walvekar Nagar Call Me 7737669865 Budget Friendly No Advance BookingCall Girls Walvekar Nagar Call Me 7737669865 Budget Friendly No Advance Booking
Call Girls Walvekar Nagar Call Me 7737669865 Budget Friendly No Advance Booking
 
VIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 BookingVIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 Booking
 
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
 
Intro To Electric Vehicles PDF Notes.pdf
Intro To Electric Vehicles PDF Notes.pdfIntro To Electric Vehicles PDF Notes.pdf
Intro To Electric Vehicles PDF Notes.pdf
 
Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar ≼🔝 Delhi door step de...
Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar  ≼🔝 Delhi door step de...Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar  ≼🔝 Delhi door step de...
Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar ≼🔝 Delhi door step de...
 
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak HamilCara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
 
Unit 1 - Soil Classification and Compaction.pdf
Unit 1 - Soil Classification and Compaction.pdfUnit 1 - Soil Classification and Compaction.pdf
Unit 1 - Soil Classification and Compaction.pdf
 
University management System project report..pdf
University management System project report..pdfUniversity management System project report..pdf
University management System project report..pdf
 
(INDIRA) Call Girl Bhosari Call Now 8617697112 Bhosari Escorts 24x7
(INDIRA) Call Girl Bhosari Call Now 8617697112 Bhosari Escorts 24x7(INDIRA) Call Girl Bhosari Call Now 8617697112 Bhosari Escorts 24x7
(INDIRA) Call Girl Bhosari Call Now 8617697112 Bhosari Escorts 24x7
 
Top Rated Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...
Top Rated  Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...Top Rated  Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...
Top Rated Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...
 
Double Revolving field theory-how the rotor develops torque
Double Revolving field theory-how the rotor develops torqueDouble Revolving field theory-how the rotor develops torque
Double Revolving field theory-how the rotor develops torque
 
Call Girls in Netaji Nagar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Netaji Nagar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort ServiceCall Girls in Netaji Nagar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Netaji Nagar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
 

How to Build a Data Closed-loop Platform for Autonomous Driving?

  • 1. How to Build a Data Closed-loop Platform for Autonomous Driving? Yu Huang Sunnyvale, California Yu.huang07@gmail.com
  • 2. Outline • Introduction; • data driven models for autonomous driving; • cloud computing infrastructure and big data processing; • annotation tools for training data; • large scale model training platform; • model testing and verification; • related machine learning techniques; • Conclusion.
  • 3. Introduction • Development engineering of autonomous driving is to solve a “long-tail problem” of rare events; • Corner cases occurring, bring valuable sources for data-driven algorithms & models. https://www.self-driving-cars.org/
  • 4. • Tesla’s data engine ICML 2019 Introduction
  • 5. • Google Waymo‘s ML factory Introduction MIT 2019
  • 6. • Nvidia’s AV ML platform MAGLEV Introduction
  • 7. data driven models for autonomous driving • Usually the self driving platform is classified as end-to-end (E2E) or modular system “A Survey of Autonomous Driving: Common Practices and Emerging Technologies” 
  • 8. data driven models for autonomous driving • Usually it is obvious that the E2E system applies data driven models “E2E Learning of Driving Models with Surround-View Cameras and Route Planners”
  • 9. data driven models for autonomous driving • Modular system • Perception • Mapping-Localization • Prediction • Planning • Control • Sensor Data Preprocessing • Simulation
  • 10. data driven models for autonomous driving • Perception: 2D/3D detection, segmetation, tracking and (early/late) fusion etc.
  • 11. data driven models for autonomous driving • Perception: 2D/3D detection, segmentation, tracking and (early/late) fusion etc.
  • 12. data driven models for autonomous driving • Mapping-Localization: semantic map, feature design, map update/online mapping, SLAM, pose estimation and odometry etc.
  • 13. data driven models for autonomous driving • Prediction: trajectory forecasting, agent behavior & interaction, multimodal, and perception- prediction etc.
  • 14. data driven models for autonomous driving • Planning: reinforcement learning, imitation learning, inverse reinforcement learning, localization & personalization of planning (aggressive or conservative), prediction-planning, and mapping- localization-prediction-planning etc.
  • 15. data driven models for autonomous driving • Planning: reinforcement learning, imitation learning, inverse reinforcement learning, localization & personalization of planning (aggressive or conservative), prediction-planning, and mapping-localization-prediction-planning etc.
  • 16. data driven models for autonomous driving • Control: reinforcement learning, imitation learning, inverse reinforcement learning, and planning-control etc.
  • 17. data driven models for autonomous driving • Sensor Data Preprocessing: pollution/dust detection, defogging, deraining, desnowing, denoising, and enhancement etc.
  • 18. data driven models for autonomous driving • Simulation: vehicle/human, sensor, traffic, road and environment modeling etc.
  • 19. cloud computing infrastructure and big data processing • Data batch/stream processing, workflow management, distributed computing, state monitoring and data storage. AWS Momenta Amazon Elastic Compute Cloud(EC2) Amazon Elasticsearch Service Amazon Kinesis Amazon SageMaker
  • 20. cloud computing infrastructure and big data processing • Data batch/stream processing, workflow management, distributed computing, state monitoring and data storage.
  • 21. cloud computing infrastructure and big data processing • Data batch/stream processing, workflow management, distributed computing, state monitoring and data storage. Apache Spark Apache Kafka Apache Flink Apache Airflow
  • 22. cloud computing infrastructure and big data processing • Data batch/stream processing, resource monitoring & scheduling, workflow management, distributed computing, state monitoring and data storage. Apache Cassandra Apache HBase Apache Mesos
  • 23. cloud computing infrastructure and big data processing • Data batch/stream processing, resource monitoring & scheduling, workflow management, distributed computing, state monitoring and data storage. Kubernetes Apache Hudi Presto
  • 24. annotation tools for training data • There are manual, semi-automatic or full automatic tools for annotation.
  • 25. annotation tools for training data • There are manual, semi-automatic or full automatic tools for annotation.
  • 26. annotation tools for training data • There are manual, semi-automatic or full automatic tools for annotation.
  • 27. annotation tools for training data • There are manual, semi-automatic or full automatic tools for annotation.
  • 28. annotation tools for training data • visualization tools are used for viewing/debugging/replaying the data, besides of annotation. Uber open sourced visualization tool: Autonomous Visualization System (AVS)
  • 29. annotation tools for training data • visualization tools are used for viewing/debugging/replaying the data, besides of annotation. ”XVIZ“- Protocol for Real-Time Transfer and Visualization of Autonomy Data
  • 30. annotation tools for training data • visualization tools are used for viewing/debugging/replaying the data, besides of annotation. streetscape.gl:a visualization toolkit for autonomy and robotics data encoded in the XVIZ protocol.
  • 31. large scale model training platform • There are open deep learning training platforms, previously as Caffe, now the most popular ones are Tensorflow and PyTorch.
  • 32. large scale model training platform • There are open deep learning training platforms, previously as Caffe, now the most popular ones are Tensorflow and PyTorch. Ring AllReduce Architecture Parameter Server Architecture (PS)
  • 33. model testing and verification • Model Testing and Verification: simulation (MIL/SIL/HIL/VIL), closed driving district, open driving area & users (such as Tesla’s shadow mode) .
  • 34. model testing and verification • Model Testing and Verification(MIL/SIL/HIL/VIL) LiDARsim
  • 35. model testing and verification • Model Testing and Verification(MIL/SIL/HIL/VIL) S3:Shape, Skeleton, and Skinning
  • 36. model testing and verification • Model Testing and Verification(MIL/SIL/HIL/VIL) SceneGen
  • 37. model testing and verification • Model Testing and Verification(MIL/SIL/HIL/VIL) TrafficSim
  • 38. model testing and verification • Model Testing and Verification(MIL/SIL/HIL/VIL) GeoSim
  • 39. model testing and verification • Model Testing and Verification(MIL/SIL/HIL/VIL) AdvSim
  • 40. model testing and verification • Model Testing and Verification(MIL/SIL/HIL/VIL) SurfelGAN
  • 41. model testing and verification • Testing from closed driving district
  • 42. model testing and verification • Testing from open driving area
  • 43. model testing and verification • Testing from users (such as Tesla’s shadow mode)
  • 44. related machine learning techniques • Active learning • OOD detection & Corner case detection • Data augmentation/Adversarial learning • Transfer learning/Domain adaptation • AutoML/Meta-learning • Semi-supervised learning • Self-supervised learning • Zero/Few shot learning • Continual learning/Open world learning
  • 45. related machine learning techniques • active learning : The goal of active learning is to find effective ways to choose data points to label, from a pool of unlabeled data points, in order to maximize the accuracy. Active learning is typically an iterative process in which a model is learned at each iteration and a set of points is chosen to be labelled from a pool of unlabeled points using some heuristics.
  • 46. related machine learning techniques • active learning:
  • 47. related machine learning techniques •OOD detection & Corner case detection: To detect OOD samples based on uncertainty estimate is important in safety-critical applications; The challenging task of corner case detection, aims at detecting these unusual situations, which could become critical to communicate this to the autonomous driving system (online use case), also in offline mode to screen vast amounts of data and select only the relevant situations.
  • 48. related machine learning techniques • Data augmentation/Adversarial learning: Data Augmentation encompasses a suite of techniques that enhance the size and quality of training datasets such that better Deep Learning models can be built using them; Adversarial training can be an effective method for searching for augmentations.
  • 49. related machine learning techniques • Data augmentation/Adversarial learning:
  • 50. related machine learning techniques • Transfer learning/Domain adaptation: Transfer learning (TL) relaxes the hypothesis that the training data must be independent and identically distributed (i.i.d.) with the test data, which motivates us to use transfer learning to against the problem of insufficient training data; Domain adaptation (DA) is a particular case of transfer learning (TL) that utilizes labeled data in one or more relevant source domains to execute new tasks in a target domain.
  • 51. related machine learning techniques • Transfer learning/Domain adaptation
  • 52. related machine learning techniques • AutoML/Meta-learning: Automated Machine Learning (AutoML) is designed to reduce the demand for data scientists and enable domain experts to automatically build machine learning applications without much requirement for statistical and machine learning knowledge; Meta- learning is closely related to AutoML since they share the same objectives of study, namely the learning tools and learning problem.
  • 53. related machine learning techniques • Semi-supervised learning: Self-supervised Learning is to leverage the unlabeled data to produce a prediction function with trainable parameters, that is more accurate than what would have been obtained by only using the labeled data.
  • 54. related machine learning techniques • Semi-supervised learning:
  • 55. related machine learning techniques • Self-supervised learning: Self-supervised learning viewed as a branch of unsupervised learning, which aims at recovering, not discovering; It uses a pretext task to learn representations on unlabeled data.
  • 56. related machine learning techniques •Zero/Few shot learning: Zero-shot learning (ZSL) aims to recognize objects whose instances may not be seen during training. Zero shot learning belongs to transfer learning; Few-Shot Learning (FSL) comes for learning from limited supervised information to get the hang of the task; Many FSL methods are meta- learning methods, using the meta-learner as prior knowledge.
  • 57. related machine learning techniques •Zero/Few shot learning:
  • 58. related machine learning techniques •Zero/Few shot learning:
  • 59. related machine learning techniques • Continual learning/Open world learning: Continual learning can continually accumulate knowledge over different tasks without the need to retrain from scratch; Open set recognition (OSR), requiring the classifiers to not only accurately classify the seen classes, but also effectively deal with unseen ones; Open world learning can be seen as a sub task of continual learning.
  • 60. related machine learning techniques • Continual learning/Open world learning:
  • 61. related machine learning techniques • Continual learning/Open world learning:
  • 62. Conclusion • In summary, the key in the data closed loop building is the sourceful data. • The data driven models or algorithms applied to solve autonomous driving tasks is the base. • The trend for this system upgrade depends on: Ø Data mode (camera, LiDAR, radar, IMU etc.) Ø Data driven model architecture (AutoML) Ø Policy to select and use the data (Corner case).