Diese Präsentation wurde erfolgreich gemeldet.
Wir verwenden Ihre LinkedIn Profilangaben und Informationen zu Ihren Aktivitäten, um Anzeigen zu personalisieren und Ihnen relevantere Inhalte anzuzeigen. Sie können Ihre Anzeigeneinstellungen jederzeit ändern.
馬路 徹 技術顧問、GPUエバンジェリスト
車載ディープラーニング及び自動運転用プラットフォーム
NVIDIA DRIVE PX2
講演目次
• NVIDIAの自動車ビジネス
• ディープラーニングによる先進の画像認識
• GPU: ディープラーニング及び超並列処理のための
エンジン
• ディープラーニング及び超並列処理用
車載プラットフォームDRIVE PX2
• ADA...
NVIDIAの自動車ビジネス
10 Years
10+M
Units Shipped
Car Models
80
Automotive Experience
NVIDIA SDK (SOFTWARE DEVELOPMENT KIT)
The Essential Resource for OEM, Tier1, Eco System Proliferation
developer.nvidia.com...
NVIDIA CONFIDENTIAL. DO NOT DISTRIBUTE.
THE NEW
REALIZATION
"Modules, modules and more modules. There's
so many modules th...
Localization
Planning
Visualization
Perception
Self-Driving
Software
AI - Speech
SurroundView
Smart Mirror
GPU Virt
Cockpi...
ディープラーニングによる先進の画像認識
DL REVOLUTIONIZE CAR COMPUTER VISION
CONVENTIONAL
DEEP NEURAL NETWORK
(…)
Required Separate Algorithms/Apps
- Pedestrian: ...
39%
55%
72%
88%
30%
40%
50%
60%
70%
80%
90%
100%
7/2015 8/2015 9/2015 10/2015 11/2015 12/2015
Top Score
KITTI Dataset: Obj...
EVERYBODY USING GPU !
(Not the latest Ranking)
Courtesy of Cityscape
Courtesy of Daimler
Courtesy of Audi
“Using NVIDIA DIGITS deep
learning platform, in less than
four hours we achieved over 96%
accuracy using Ruhr University
B...
GPU: ディープラーニング及び
超並列処理のためのエンジン
NVIDIA CONFIDENTIAL. DO NOT DISTRIBUTE.
NVIDIA GPU BIG CONRIBUTION ON SUPERCOMPUTER
USING CUDA (GPU Massive Parallel Compu...
LEAPS IN SUPERCOMPUTER GPU ADOPTION
0
20
40
60
80
100
120
Nov 2013 Nov 2014 Nov 2015
#acceleratedsystems
Accelerated Syste...
超並列プログラミング環境CUDA
代表的なCUDA対応ライブラリ
cuDNN ディープラーニング
cuBLAS 行列演算(密行列)
cuSPARSE 行列演算(疎行列)
cuFFT フーリエ変換
cuRAND 乱数生成
NPP 画像処理プリミテ...
2012 20142008 2010 2016 2018
48
36
12
0
24
60
72
Tesla
Fermi
Kepler
Maxwell
Pascal
Mixed Precision
Double Precision
3D Mem...
NVIDIA ONE-ARCHITECTURE
FROM SUPER COMPUTER TO AUTOMOTIVE SOC
Tesla
In Super Computers
Quadro
In Work Stations
GeForce
In ...
PARALLEL PROCESSING AND AI/DL EVERYWHERE
WITH ONE-ARCHITECTURE OVER ALL
PRODUCTS/PLATFORMS
TITAN X/Graphics Card
NVIDIA Te...
DRIVE PX AUTO-PILOT
CAR COMPUTER
NVIDIA GPU DEEP LEARNING
SUPERCOMPUTER
Trained
Neural Net Model
Classified Object
!
WHAT ...
ディープラーニング及び超並列処理用
車載プラットフォームDRIVE PX2
DRIVE PX2 ENGAGEMENTS >100
Passenger Car OEMs
~25 ~10 ~20
Commercial Car OEMs
~10 ~50
TAAS
(Transportation As A Service)
T...
DL: VERY FAST DEVELOPMENT SPEED
TOWARDS TOP SCORE(1)
DRIVE PX PLATFORM
SOLUTION • Drive PX is a computing platform for
ADA...
Proprietary & Confidential
All Information Subject to Change
DRIVE PX
Camera Inputs
 Dual Tegra X1
 8 CPU Cores
 Maxwel...
DRIVE PX HARNESS FROM CAR CONNECTOR
CAN, LIN, FlexRay and Ethernet Supported
48-pin Automotive Grade
Vehicle Harness
CAN 2...
Proprietary & Confidential
All Information Subject to Change
DRIVE PX2
 Dual Next Generation
Tegra
 Dual Discrete GPUs
...
DRIVE PX2 COMPUTATION ENGINES
Denver Denver
A57 A57 A57 A57
Pascal
Integrated GPU
Pascal
Discrete GPU
8GB
LPDDR4
128bit
UM...
DRIVE PX2 INTERFACES
 Sensor Fusion Interfaces
GMSL Camera, CAN, GbE, BroadR-Reach,
FlexRay, LIN, GPIO
 Displays/Cockpit...
DRIVE PX2 SOFTWARE
 NVIDIA Vibrante Linux
& Comprehensive BSP
 Rich Autonomous Driving
DRIVE Works SDK
 SDK, Samples an...
DRIVE PX ANALYSIS AS AN SEOOC
(SAFETY ELEMENTS OUT OF CONTEXT)
 NVIDIA DRIVE PX as an SEooC is developed based on
“Assump...
ADAS及び自動運転用SWフレームワーク
DRIVE WORKS
NVIDIA DRIVEWORKS
COMPUTEWORKS
Detection Localization HD Maps
GAMEWORKS VRWORKS DESIGNWORKS DRIVEWORKS JETPACK
Sensor Fusi...
AND OTHER SUPPORTING SDKS
DIGITS Workflow VisionWorks
and other technologies such as:
GIE (GPU Inference Engine), System T...
The NVIDIA DriveWorks SDK gives developers
a foundation to build applications across the
self-driving pipeline — perceptio...
自動運転稼動状況の可視化
NEW AI DRIVING
Training on
DGX-1
Driving with
DriveWorks
KALDI
LOCALIZATION
MAPPING
DRIVENET
DAVENET
NVIDIA DGX-1 NVIDIA D...
直近の自動運転関連応用事例
(公開情報)
As a part of VOLVO Drive
Me project, they will run
100 autonomous driving
test cars in 2017.
These cars will be
equipped w...
WORLD’S FIRST AUTONOMOUS CAR RACE
 10 teams, 20 identical cars
 DRIVE PX 2: The “brain” of
every car
 2016/17 Formula E...
FAST-SPEED RACING ALGORITHM ALREADY THERE
• Calculate the optimized trajectory from
the weighted average of 2,560 differen...
THANK YOU
車載組み込み用ディープラーニング・エンジン NVIDIA DRIVE PX
車載組み込み用ディープラーニング・エンジン NVIDIA DRIVE PX
Nächste SlideShare
Wird geladen in …5
×

車載組み込み用ディープラーニング・エンジン NVIDIA DRIVE PX

5.421 Aufrufe

Veröffentlicht am

2016年7月22日(金)のNVIDIA Deep Learning Day 2016 Summer の講演資料です。

エヌビディア合同会社 技術顧問 馬路 徹

NVIDIA DRIVE PX2 は高度な画像認識等を可能とするディープラーニング及び自動運転の主要な機能を実現する DriveWorks SDK を実装した車載組込み用プラットフォームです。本講演では NVIDIA DRIVE PX2 の概要と画像認識、自動運転等の応用例もご紹介します。

Veröffentlicht in: Technologie
  • -- DOWNLOAD THIS BOOKS INTO AVAILABLE FORMAT -- ......................................................................................................................... ......................................................................................................................... Download FULL PDF EBOOK here { http://bit.ly/2m77EgH } ......................................................................................................................... (Unlimited)
       Antworten 
    Sind Sie sicher, dass Sie …  Ja  Nein
    Ihre Nachricht erscheint hier
  • accessibility Books Library allowing access to top content, including thousands of title from favorite author, plus the ability to read or download a huge selection of books for your pc or smartphone within minutes.........ACCESS WEBSITE Over for All Ebooks ..... (Unlimited) ......................................................................................................................... Download FULL PDF EBOOK here { http://bit.ly/2m6jJ5M } .........................................................................................................................
       Antworten 
    Sind Sie sicher, dass Sie …  Ja  Nein
    Ihre Nachricht erscheint hier
  • If you want to download or read this book, Copy link or url below in the New tab ......................................................................................................................... DOWNLOAD FULL PDF EBOOK here { http://bit.ly/2m6jJ5M } ......................................................................................................................... Download EPUB Ebook here { http://bit.ly/2m6jJ5M } ......................................................................................................................... Download Doc Ebook here { http://bit.ly/2m6jJ5M } ......................................................................................................................... .........................................................................................................................
       Antworten 
    Sind Sie sicher, dass Sie …  Ja  Nein
    Ihre Nachricht erscheint hier
  • accessibility Books Library allowing access to top content, including thousands of title from favorite author, plus the ability to read or download a huge selection of books for your pc or smartphone within minutes ,Download or read Ebooks here ... ......................................................................................................................... Download FULL PDF EBOOK here { http://bit.ly/2m6jJ5M }
       Antworten 
    Sind Sie sicher, dass Sie …  Ja  Nein
    Ihre Nachricht erscheint hier
  • accessibility Books Library allowing access to top content, including thousands of title from favorite author, plus the ability to read or download a huge selection of books for your pc or smartphone within minutes ,Download or read Ebooks here ... ......................................................................................................................... Download FULL PDF EBOOK here { http://bit.ly/2m6jJ5M }
       Antworten 
    Sind Sie sicher, dass Sie …  Ja  Nein
    Ihre Nachricht erscheint hier

車載組み込み用ディープラーニング・エンジン NVIDIA DRIVE PX

  1. 1. 馬路 徹 技術顧問、GPUエバンジェリスト 車載ディープラーニング及び自動運転用プラットフォーム NVIDIA DRIVE PX2
  2. 2. 講演目次 • NVIDIAの自動車ビジネス • ディープラーニングによる先進の画像認識 • GPU: ディープラーニング及び超並列処理のための エンジン • ディープラーニング及び超並列処理用 車載プラットフォームDRIVE PX2 • ADAS及び自動運転用SWフレームワーク DRIVE WORK • 自動運転稼動状況の可視化 • 直近の自動運転関連応用事例(公開情報)
  3. 3. NVIDIAの自動車ビジネス
  4. 4. 10 Years 10+M Units Shipped Car Models 80 Automotive Experience
  5. 5. NVIDIA SDK (SOFTWARE DEVELOPMENT KIT) The Essential Resource for OEM, Tier1, Eco System Proliferation developer.nvidia.com | Available Now
  6. 6. NVIDIA CONFIDENTIAL. DO NOT DISTRIBUTE. THE NEW REALIZATION "Modules, modules and more modules. There's so many modules there. If we were to strip off this car, we'd probably have a basketful of Modules -- little black boxes that do something. It's getting out of control. They're very expensive. They're tough to package. They're very complex. “I’d like to see a monster module that controls the entire vehicle and that's easier to upgrade.“ Ralph Gilles, Fiat Chrysler Automobiles Global Design Chief Automotive News, February 28, 2016
  7. 7. Localization Planning Visualization Perception Self-Driving Software AI - Speech SurroundView Smart Mirror GPU Virt Cockpit Software Cockpit Computer Self-Driving Computer Two computers replace many ECUs Both have access to cameras/sensors Multiple OSs, Displays Powered by Artificial Intelligence Upgradeable SW replaces HW ECUs One architecture Higher performance Lower total cost THE FUTURE OF CAR COMPUTERS ONLY TWO MAIN INTEGRATED MODULES DRIVE CX DRIVE PX
  8. 8. ディープラーニングによる先進の画像認識
  9. 9. DL REVOLUTIONIZE CAR COMPUTER VISION CONVENTIONAL DEEP NEURAL NETWORK (…) Required Separate Algorithms/Apps - Pedestrian: HOG etc - Traffic Sign: Hough Transform + Character Recog. etc Only simple context recognition - Pedestrian Y/N Only (no additional info) - Speed Limit Signs Only One Deep Neural Net App can Detect various Objects - Pedestrian, Cars, Traffic Signs, lanes - Also with many attributes (Car: Police Car, Van, Sedan, Truck, Ambulance….)
  10. 10. 39% 55% 72% 88% 30% 40% 50% 60% 70% 80% 90% 100% 7/2015 8/2015 9/2015 10/2015 11/2015 12/2015 Top Score KITTI Dataset: Object Detection NVIDIA DRIVENet KITTY Database Object Detection VERY SHORT TIME TO GET TOP-CLASS SCORE
  11. 11. EVERYBODY USING GPU ! (Not the latest Ranking)
  12. 12. Courtesy of Cityscape Courtesy of Daimler Courtesy of Audi
  13. 13. “Using NVIDIA DIGITS deep learning platform, in less than four hours we achieved over 96% accuracy using Ruhr University Bochum’s traffic sign database. While others invested years of development to achieve similar levels of perception with classical computer vision algorithms, we have been able to do it at the speed of light.” Matthias Rudolph, Director of Architecture, Driver Assistance Systems, Audi
  14. 14. GPU: ディープラーニング及び 超並列処理のためのエンジン
  15. 15. NVIDIA CONFIDENTIAL. DO NOT DISTRIBUTE. NVIDIA GPU BIG CONRIBUTION ON SUPERCOMPUTER USING CUDA (GPU Massive Parallel Computing) CUDA: Compute Unified Device Architecture From SC TOP500 November 2015
  16. 16. LEAPS IN SUPERCOMPUTER GPU ADOPTION 0 20 40 60 80 100 120 Nov 2013 Nov 2014 Nov 2015 #acceleratedsystems Accelerated Systems x2 from 2013 to 2015 96% of New Systems using NVIDIA GPU
  17. 17. 超並列プログラミング環境CUDA 代表的なCUDA対応ライブラリ cuDNN ディープラーニング cuBLAS 行列演算(密行列) cuSPARSE 行列演算(疎行列) cuFFT フーリエ変換 cuRAND 乱数生成 NPP 画像処理プリミティブ cuSOLVER 行列ソルバ (y=Ax) Thrust C++テンプレートライブラリ … https://developer.nvidia.com/gpu-accelerated-libraries CUDA (Compute Unified Device Architecture)
  18. 18. 2012 20142008 2010 2016 2018 48 36 12 0 24 60 72 Tesla Fermi Kepler Maxwell Pascal Mixed Precision Double Precision 3D Memory NVLink Volta SOLID GPU ROADMAP SGEMM/W
  19. 19. NVIDIA ONE-ARCHITECTURE FROM SUPER COMPUTER TO AUTOMOTIVE SOC Tesla In Super Computers Quadro In Work Stations GeForce In PCs Mobile GPU In Tegra Automotive Tegra
  20. 20. PARALLEL PROCESSING AND AI/DL EVERYWHERE WITH ONE-ARCHITECTURE OVER ALL PRODUCTS/PLATFORMS TITAN X/Graphics Card NVIDIA Tegra/Jetson NVIDIA Tesla/Supercomputer, HPC NVIDIA Tegra/DRIVE PX
  21. 21. DRIVE PX AUTO-PILOT CAR COMPUTER NVIDIA GPU DEEP LEARNING SUPERCOMPUTER Trained Neural Net Model Classified Object ! WHAT TRULY SCALABLE GPU ARCHITECTURE ENABLES TIME-CONSUMING TRAINING ON SERVER & REAL-TIME RECOGNITION ON EMBEDDED SYSTEM Camera Inputs
  22. 22. ディープラーニング及び超並列処理用 車載プラットフォームDRIVE PX2
  23. 23. DRIVE PX2 ENGAGEMENTS >100 Passenger Car OEMs ~25 ~10 ~20 Commercial Car OEMs ~10 ~50 TAAS (Transportation As A Service) Tier 1s Eco System Partners (R&D, Universities, OS, Sensor, ISV etc)
  24. 24. DL: VERY FAST DEVELOPMENT SPEED TOWARDS TOP SCORE(1) DRIVE PX PLATFORM SOLUTION • Drive PX is a computing platform for ADAS / autonomous driving • End-to-End platform optimized for deep learning (Super Computer – DRIVE PX) • Open and Scalable SW Stack: DRIVE Works • Scalable architecture from ADAS to Autonomous Driving (One Tegra to 2 x Tegra + 2 x discrete GPU) DL Training Workstation/SuperComputer DRIVE PX
  25. 25. Proprietary & Confidential All Information Subject to Change DRIVE PX Camera Inputs  Dual Tegra X1  8 CPU Cores  Maxwell GPU  850GFLOPS (FP32)  12 simultaneous LVDS camera inputs  2 LVDS display ports Display Ports Car Connector
  26. 26. DRIVE PX HARNESS FROM CAR CONNECTOR CAN, LIN, FlexRay and Ethernet Supported 48-pin Automotive Grade Vehicle Harness CAN 2.0 (x6) FlexRay (x2) LIN (x4) UART (x1) Ethernet (x1) 1x Power
  27. 27. Proprietary & Confidential All Information Subject to Change DRIVE PX2  Dual Next Generation Tegra  Dual Discrete GPUs  12 CPU Cores  Pascal GPU  8TFLOPS (FP32)  24DL TOPS  12 simultaneous LVDS camera inputs Dual Tegras on Top Dual Discrete GPUs on the Bottom Liquid Cooled if All Devices used
  28. 28. DRIVE PX2 COMPUTATION ENGINES Denver Denver A57 A57 A57 A57 Pascal Integrated GPU Pascal Discrete GPU 8GB LPDDR4 128bit UMA 4GB GDDR5 PCIex4 Denver Denver A57 A57 A57 A57 Pascal Integrated GPU Pascal Discrete GPU 8GB LPDDR4 128bit UMA 4GB GDDR5 PCIex4 1Gb Ether GPU TOTAL PERFORMANCE - 8TFLOPS (FP32) - 24DL TOPS HIGH PERFORMANCE 12CPUs - 2 x Quad ARM A57 - 2 x Dual Denver (ARM 64b compatible) SCALABLE - Scalable Platform Max: 2-Tegras + 2-dGPUs Min: 1-Tegra REDUNDANCY - For Function Safety DEDICATED MEMORY for each GPU TEGRA A PASCAL A TEGRA B PASCAL B
  29. 29. DRIVE PX2 INTERFACES  Sensor Fusion Interfaces GMSL Camera, CAN, GbE, BroadR-Reach, FlexRay, LIN, GPIO  Displays/Cockpit Computer Interfaces HDMI, FPDLink III and GMSL  Development and Debug Interfaces HDMI, GbE, 10GbE, USB3, USB 2 (UART/debug), JTAG 70 Gigabits per second of I/O Auto Grade connectors Debug/Lab interfaces TEGRA A PASCAL A TEGRA B PASCAL B Gb Ether ASIL-D Safety MCU DRIVE PX2 Gb Ether Camera BroadR-Reach CAN GPIOs Display LIN FlexRay USB3.0 USB2.0 Gb Ether JTAG 10Gb Ether Display(HDMI)
  30. 30. DRIVE PX2 SOFTWARE  NVIDIA Vibrante Linux & Comprehensive BSP  Rich Autonomous Driving DRIVE Works SDK  SDK, Samples and more A full stack of rich software components
  31. 31. DRIVE PX ANALYSIS AS AN SEOOC (SAFETY ELEMENTS OUT OF CONTEXT)  NVIDIA DRIVE PX as an SEooC is developed based on “Assumptions on use in Vehicles” including external interfaces  Safety Manual, FMEAD: NVIDIA as a developer of this SEooC will provide the assumptions to the Tier1s and OEMs  In order to have a compete safety case, these “assumptions” are validated by OEMs, Tier1s in the context of the actual Vehicle system  In case that NVIDIA SEooC does not fulfill the Vehicle requirements, “a modification needs to be made” to either the Vehicle or the SEooC Quantitative Analysis FEMDA/FTA SEooC Done SEooC: Safety Elements out of Context HARA: Hazard Analysis and Risk Assessment FEMDA: Failure Mode Effects and Diagnostic Analysis FTA: Fault Tree Analysis
  32. 32. ADAS及び自動運転用SWフレームワーク DRIVE WORKS
  33. 33. NVIDIA DRIVEWORKS COMPUTEWORKS Detection Localization HD Maps GAMEWORKS VRWORKS DESIGNWORKS DRIVEWORKS JETPACK Sensor Fusion and other technologies such as Driving, Planning AI/DL is now used in Detection (Perception) Other Features are accelerated by CUDA (GPU Massive-Parallel Computing)
  34. 34. AND OTHER SUPPORTING SDKS DIGITS Workflow VisionWorks and other technologies such as: GIE (GPU Inference Engine), System Trace, Visual Profiler Deep Learning SDK
  35. 35. The NVIDIA DriveWorks SDK gives developers a foundation to build applications across the self-driving pipeline — perception, localization, planning and visualization. And we can bring all of these technologies together into a beautiful cockpit visualization to give the driver confidence that the car is accurately seeing the world around him. “As a leading provider of graphical hardware for gamers and researchers alike, NVIDIA has a lot of expertise in building systems that can make sense of video input and make it something understandable.” — Business Insider Localization Planning Visualization Perception DRIVEWORKS 37
  36. 36. 自動運転稼動状況の可視化
  37. 37. NEW AI DRIVING Training on DGX-1 Driving with DriveWorks KALDI LOCALIZATION MAPPING DRIVENET DAVENET NVIDIA DGX-1 NVIDIA DRIVE PX
  38. 38. 直近の自動運転関連応用事例 (公開情報)
  39. 39. As a part of VOLVO Drive Me project, they will run 100 autonomous driving test cars in 2017. These cars will be equipped with NVIDIA’s Deep Learning Car Computer DRIVE PX2.
  40. 40. WORLD’S FIRST AUTONOMOUS CAR RACE  10 teams, 20 identical cars  DRIVE PX 2: The “brain” of every car  2016/17 Formula E season
  41. 41. FAST-SPEED RACING ALGORITHM ALREADY THERE • Calculate the optimized trajectory from the weighted average of 2,560 different trajectories (each looking 2.5sec ahead) calculated in parallel on the monster NVIDIA GPU 60-times every sec. • Using just one sampled trajectory will be very jerky. Thus 2,560 trajectories are weighted averaged. • The dynamics model is a linear function of 25 features based on an analytical vehicle model • On Car GPU used there is NVIDIA GTX750Ti (640-cores, 1,305-GFLOPS) Georgia Tech MPPI (Model Predictive Path Integral control) Algorithm Doing by itself: Counter Steering, Power Slide…. Max speed 100km/Hr
  42. 42. THANK YOU

×