SlideShare ist ein Scribd-Unternehmen logo
1 von 31
Downloaden Sie, um offline zu lesen
シニア・ソリューションアーキテクト 馬路 徹, 2015年9月18日
車載用ADAS/自動運転プラットフォームDRIVE PX
及びコックピト・プラットフォームDRIVE CXのご紹介
2
Agenda
Autonomous Driving System Architecture and
DRIVE PX/CX Implementations
DRIVE PX for Map Module, AI Module and
Computer Vision
DRIVE CX for HMI Module
Summary
3
Autonomous Driving System Architecture
Typical Architecture
地図モジュール
- 固定道路地図
- ローカルダイナミックマップ
- 目標走行軌跡生成
速度制御モジュール
- Adaptive Cruise Control
- Pre-Crush System
エンジン・ブレーキ
操舵制御モジュール
(車線維持制御)
ハンドル
HMI モジュール
-手動、自動切換え操作システム
- 稼動状況表示
ビッグデータ、道路・交通情報等(車外データ)
走行環境センシングおよび障害物認識
- 前方の障害物センシング(ミリ波レーダ、レーザレーダ、カメラ)
- レーンマーカセンシング
測位
GPS
参考文献:「自動運転 システム構成と要素技術」、保坂明夫、青木啓二、津川定之 森北出版、2015年7月
Reference: “Automated Driving System and Technologies”, Akio Hosaka et al,
Morikita Publishing Co., Ltd., July 2015
人工知能モジュール
- 環境理解
- 判断
- 目標走行軌跡修正
修正
指示
修正
指示
道路地図
交通情報等
道路線形
障害物
位置等
車間
距離
白線距離
4
Autonomous Driving System Architecture
Typical Architecture
MAP MODULE
- Road Map
- Local Dynamic Map
- Target Path Generation
SPEED CONTROL
MODULE
- Adaptive Cruise Control
- Pre-Crush System
Engine, Break
STEERING CONTROL
MODULE
- Lane Keep Control
Steering
HMI MODULE
- Auto/Manual Mode SW
Operation
- System Operation Status
Big Data, Road, Traffic Information etc
Driving Environment Sensing and Obstacle Recognition
- Front Obstacles Sensing (Mili-wave Radar, Laser Radar, Camera)
- Lane Marker Sensing
Position
Sensing
GPS
AI MODULE
- Environment Recognition
- Decision Making
- Target Path Tuning
Adjusting
Acceleration
Adjusting
Direction
Road Map
Traffic Information
Road Structure
Obstacle
Location
Car
Distance
Lane Distance
参考文献:「自動運転 システム構成と要素技術」、保坂明夫、青木啓二、津川定之 森北出版、2015年7月
Reference: “Automated Driving System and Technologies”, Akio Hosaka et al,
Morikita Publishing Co., Ltd., July 2015
5
Autonomous Driving System Architecture
MAP MODULE implementation by DRIVE PX/CUDA
SPEED CONTROL
MODULE
- Adaptive Cruise Control
- Pre-Crush System
Engine, Break
STEERING CONTROL
MODULE
- Lane Keep Control
Steering
HMI MODULE
- Auto/Manual Mode SW
Operation
- System Operation Status
Big Data, Road, Traffic Information etc
Driving Environment Sensing and Obstacle Recognition
- Front Obstacles Sensing (Mili-wave Radar, Laser Radar, Camera)
- Lane Marker Sensing
Position
Sensing
GPS
AI MODULE
- Environment Recognition
- Decision Making
- Target Path Tuning
Adjusting
Acceleration
Adjusting
Direction
Road Map
Traffic Information
Road Structure
Obstacle
Location
Car
Distance
Lane Distance
DRIVE PX / CUDA
MAP MODULE
- Road Map
- Local Dynamic Map
- Target Path Generation
参考文献:「自動運転 システム構成と要素技術」、保坂明夫、青木啓二、津川定之 森北出版、2015年7月
Reference: “Automated Driving System and Technologies”, Akio Hosaka et al,
Morikita Publishing Co., Ltd., July 2015
6
Autonomous Driving System Architecture
+ AI MODULE implementation by DRIVE PX/DL
SPEED CONTROL
MODULE
- Adaptive Cruise Control
- Pre-Crush System
Engine, Break
STEERING CONTROL
MODULE
- Lane Keep Control
Steering
HMI MODULE
- Auto/Manual Mode SW
Operation
- System Operation Status
Big Data, Road, Traffic Information etc
Driving Environment Sensing and Obstacle Recognition
- Front Obstacles Sensing (Mili-wave Radar, Laser Radar, Camera)
- Lane Marker Sensing
Position
Sensing
GPS
Adjusting
Direction
Road Map
Traffic Information
Road Structure
Obstacle
Location
Car
Distance
Lane Distance
DRIVE PX / CUDA DRIVE PX / DL
MAP MODULE
- Road Map
- Local Dynamic Map
- Target Path Generation
AI MODULE
- Environment Recognition
- Decision Making
- Target Path Tuning
Adjusting
Acceleration
参考文献:「自動運転 システム構成と要素技術」、保坂明夫、青木啓二、津川定之 森北出版、2015年7月
Reference: “Automated Driving System and Technologies”, Akio Hosaka et al,
Morikita Publishing Co., Ltd., July 2015
7
Autonomous Driving System Architecture
+ HMI MODULE Implementation by DRIVE CX/HMI
SPEED CONTROL
MODULE
- Adaptive Cruise Control
- Pre-Crush System
Engine, Break
STEERING CONTROL
MODULE
- Lane Keep Control
Steering
Big Data, Road, Traffic Information etc
Driving Environment Sensing and Obstacle Recognition
- Front Obstacles Sensing (Mili-wave Radar, Laser Radar, Camera)
- Lane Marker Sensing
Position
Sensing
GPS
Adjusting
Direction
Road Map
Traffic Information
Road Structure
Obstacle
Location
Car
Distance
Lane Distance
DRIVE PX / CUDA DRIVE PX / DL
DRIVE CX/HMI
MAP MODULE
- Road Map
- Local Dynamic Map
- Target Path Generation
AI MODULE
- Environment Recognition
- Decision Making
- Target Path Tuning
HMI MODULE
- Auto/Manual Mode SW
Operation
- System Operation
Status
Adjusting
Acceleration
参考文献:「自動運転 システム構成と要素技術」、保坂明夫、青木啓二、津川定之 森北出版、2015年7月
Reference: “Automated Driving System and Technologies”, Akio Hosaka et al,
Morikita Publishing Co., Ltd., July 2015
8
Autonomous Driving System Architecture
+ Computer Vision Processing by DRIVE PX/DL & CV -> Almost All Processings by Tegra
SPEED CONTROL
MODULE
- Adaptive Cruise Control
- Pre-Crush System
Engine, Break
STEERING CONTROL
MODULE
- Lane Keep Control
Steering
Big Data, Road, Traffic Information etc
Position
Sensing
GPS
Adjusting
Direction
Road Map
Traffic Information
Road Structure
Obstacle
Location
Car
Distance
Lane Distance
DRIVE PX / CUDA DRIVE PX / DL
DRIVE CX/HMI
MAP MODULE
- Road Map
- Local Dynamic Map
- Target Path Generation
AI MODULE
- Environment Recognition
- Decision Making
- Target Path Tuning
HMI MODULE
- Auto/Manual Mode SW
Operation
- System Operation
Status
Computer Vision
Deep Learning
VisionWorks
DRIVE PX / DL & CV
Adjusting
Acceleration
参考文献:「自動運転 システム構成と要素技術」、保坂明夫、青木啓二、津川定之 森北出版、2015年7月
Reference: “Automated Driving System and Technologies”, Akio Hosaka et al,
Morikita Publishing Co., Ltd., July 2015
9
10
Audi zFAS Example as a Low-Speed Autonomous Driving:
Obstacle Recognition, Target Path Generation by one Tegar K1
From
GTC2015
11
Deep Learning Revolutionize 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….)
12
TEGRA X1 CLASSIFICATION Performance
AlexNet
0
10
20
30
40
50
60
70
80
90
100
Tegra K1 Tegra X1
IMAGES/SECOND
13
14
Growing Performance of Automotive Tegra Products
will allow further Integration in the Future
Tegra 2 Tegra 3
Tegra 4
Tegra K1
0
200
400
600
800
1000
1200
GFLOPS
FP16/INT16
Core i7
Tegra X1
CPU
GPU
GPU
CPU
Tegra X1 (FP16)
Note: 4790K Core i7, CPU @ 4GHz, GPU @ 350 MHz
TIME
15
DRIVE PX
For Map Module, AI Module and Computer Vision
16
DRIVE PX
An advanced computing platform based on NVIDIA
Tegra processors for autonomous driving cars
FEATURES
The ability to capture and process multiple
HD camera and sensor inputs
A rich middleware for computer graphics,
computer vision and deep learning
A powerful and easy to develop platform for
algorithm research and rapid prototyping
NVIDIA CONFIDENTIAL — DRIVE PX DEVELOPMENT PLATFORM Preliminary information — Subject to change
17Proprietary & Confidential
All Information Subject to Change
DRIVE PX Camera & Display Interfaces
Group A Group B Group C
 12 simultaneous LVDS
camera inputs
• All cameras
synchronized within
each Group (3 groups)
 2 LVDS display ports
Display
18
Other Interfaces to Aurix
CAN*, LIN*, FlexRay* and Ethernet
48-pin Automotive Grade
Vehicle Harness
CAN 2.0 (x6)
FlexRay (x2)
LIN (x4)
UART (x1)
Ethernet (x1)
1x Power
19
Hardware Specs
PROCESSORS
Dual Tegra X1 VCM; each VCM consists of:
Tegra X1 processor
DRAM: 4GB
NOR FLASH: 64MB
eMMC: 64GB
Inter-Tegra X1 VCM Communication
SPI and USB 3.0 for direct inter-Tegra communication and through
Ethernet Switch
ASIL-D MCU
Camera and IO controls through ASIL-D MCU.
NVIDIA CONFIDENTIAL — DRIVE PX DEVELOPMENT PLATFORM Preliminary information — Subject to change
20
Hardware Specs
PERIPHERALS
Sensors:
Vision Sensors interface:
12x LVDS Cameras
Sensor Interfaces for Radar, LIDAR, Vehicle Dynamics etc.:
CAN 2.0; LIN; Ethernet; Flexray
Displays:
LVDS interface (x2)
Power Management of ECU:
System power monitor/control — ASIL-D MCU
NVIDIA CONFIDENTIAL — DRIVE PX DEVELOPMENT PLATFORM Preliminary information — Subject to change
21
DRIVE PX
software specs
OS: NVIDIA Vibrante Linux 4.0
64-bit Kernel Linux, Quickboot, AutoSAR RunTimeEnvironment
Graphics:
Open GL ES 3.1
Development Tools/Samples: Delivered through Jetpack 2.x
Graphics debugger, PerfKit, DNN Classifier Sample,
Vision Works 1.0 (beta) Computer Vision libraries and Samples
ASIL MCU Support for CAN, Ethernet, Flexray and LIN; AutoSAR framework
External Storage for Video Recording
USB3.0 interface for camera output in RAW or H.265/H.264 encoded formats
Camera: NVMedia and Driver support for LVDS camera
Open Source Collaboration initiatives/Compliance:
Yocto 1.8
Genivi7 Compliant
NVIDIA CONFIDENTIAL — DRIVE PX DEVELOPMENT PLATFORM Preliminary information — Subject to change
22
WORLD CLASS SOFTWARE TOOLS
Faster debug and analysis reduces development costs
Preliminary information — Subject to change
TEGRA GRAPHICS DEBUGGER
Visualize GPU performance metrics
Automated analysis of GPU bottlenecks
PERFKIT
Performance monitoring
Automated bottleneck analysis
ECLIPSE IDE
Standard Linux development environment
23
DRIVE PX LINUX SOFTWARE STACK
Preliminary information — Subject to change
Imaging
(Camera)
Pipeline
Linux
Performance Microprocessor A
Graphics/ComputeNVMedia
CUDA/EGL/
Open GL ES
Tegra™ X1 Hardware (ARM, GPU & SoC Peripherals) Safety MCU
Safety MCU
MCA
L
Applications
T1/OEM SW OS/3rd SW/HW NVIDIA Licensed SW Drive PX Hardware
Elektrobit
AUTOSAR
BSW on
Linux
Linux
Performance Microprocessor B
Tegra™ X1 Hardware (ARM, GPU & SoC Peripherals)
AUTOSAR
BSW on
Linux
ApplicationsApplications
Linux
BSP/Drivers
Filesystem(s)
Linux
BSP/Drivers
Graphics/Compute
CV/DL Libraries
Imaging
(Camera)
Pipeline
Graphics/Compute NVMedia
CUDA/EGL/
Open GL ES
Filesystem(s)
Graphics/Compute
CV/DL Libraries
AUTOSAR
on
Safety
MCU
24
DRIVE CX
For HMI MODULE
25NVIDIA CONFIDENTIAL
THE SOUL OF
NVIDIA DRIVE™ CX
DIGITAL COCKPIT CAR COMPUTER
Natural Speech
OTA updates
Advanced Visuals
Hypervisor – Cluster Cockpit
26
DRIVE CXTODAY
ADVANCED VISUALS – Digital CLUSTER
27
DRIVE CX ADAS
Also supported by DRIVE PX
Best-in-Class
Surround View
28
NVIDIA DRIVE Design
Design Studio
Professional artist environment
Design Architect
Integrated engineering
environment
NVIDIA’s HMI Platform version 8.0
29
Today
(no internet
connection)
Google
(with Internet
Connection)
DRIVE CX
(no internet
connection)
ACCURACY LOW
1M parameters
HIGH
30M parameters
HIGH
30M parameters
VOCABULARY SMALL
50k words
LARGE
4M words
LARGE
4M words
SPEED SLOW
500+ ms latency
FAST
… or no response
(lost internet
connection)
FAST
… always
Fail-safe NATURAL LANGUAGE SPEECH
30
SUMMARY
1. Autonomous Driving System Architecture consists of Sensing Module, Map
Module, AI Module and HMI Module. DRIVE PX and CX can implement all
functions with CUDA, Deep Learning , Computer Vision and HMI Frameworks.
2. DRIVE PX consists of two powerful Tegra X1 processors with the total
performance of 2.3TFLOPS. It comes with a rich middleware for GPU
Computing, Deep Learning and Computer Vision.
3. DRIVE CX powerful Tegra X1 processor enables the fail-safe Natural Speech
Recognition, advanced visual quality which offers a safe, versatile and high-
quality HMI. This is essential for the critical human-car interaction in the
Autonomous Driving Cars.
4. Today, we might start with a few DRIVE PX and a DRIVE CX. However, the
continuous performance and feature enhancement in the future will make it
possible to implement the total system by a single DRIVE platform if required.
THANK YOU

Weitere ähnliche Inhalte

Was ist angesagt?

GTC China 2016
GTC China 2016GTC China 2016
GTC China 2016NVIDIA
 
組み込みから HPC まで ARM コアで実現するエコシステム
組み込みから HPC まで ARM コアで実現するエコシステム組み込みから HPC まで ARM コアで実現するエコシステム
組み込みから HPC まで ARM コアで実現するエコシステムShinnosuke Furuya
 
GPU Accelerated Deep Learning for CUDNN V2
GPU Accelerated Deep Learning for CUDNN V2GPU Accelerated Deep Learning for CUDNN V2
GPU Accelerated Deep Learning for CUDNN V2NVIDIA
 
Nvidia Deep Learning Solutions - Alex Sabatier
Nvidia Deep Learning Solutions - Alex SabatierNvidia Deep Learning Solutions - Alex Sabatier
Nvidia Deep Learning Solutions - Alex SabatierSri Ambati
 
NVIDIA Overview 2015
NVIDIA Overview 2015NVIDIA Overview 2015
NVIDIA Overview 2015NVIDIA
 
GPU Technology Conference 2014 Keynote
GPU Technology Conference 2014 KeynoteGPU Technology Conference 2014 Keynote
GPU Technology Conference 2014 KeynoteNVIDIA
 
Visual Computing: The Road Ahead, NVIDIA CEO Jen-Hsun Huang at CES 2015
Visual Computing: The Road Ahead, NVIDIA CEO Jen-Hsun Huang at CES 2015 Visual Computing: The Road Ahead, NVIDIA CEO Jen-Hsun Huang at CES 2015
Visual Computing: The Road Ahead, NVIDIA CEO Jen-Hsun Huang at CES 2015 NVIDIA
 
“Efficient Video Perception Through AI,” a Presentation from Qualcomm
“Efficient Video Perception Through AI,” a Presentation from Qualcomm“Efficient Video Perception Through AI,” a Presentation from Qualcomm
“Efficient Video Perception Through AI,” a Presentation from QualcommEdge AI and Vision Alliance
 
GTC 2012 Jen-Hsun Huang Keynote
GTC 2012 Jen-Hsun Huang KeynoteGTC 2012 Jen-Hsun Huang Keynote
GTC 2012 Jen-Hsun Huang KeynoteNVIDIA
 
Investor Day 2013 Jen-Hsun Huang Presentation
Investor Day 2013 Jen-Hsun Huang PresentationInvestor Day 2013 Jen-Hsun Huang Presentation
Investor Day 2013 Jen-Hsun Huang PresentationNVIDIA
 
Accelerated Computing: The Path Forward
Accelerated Computing: The Path ForwardAccelerated Computing: The Path Forward
Accelerated Computing: The Path ForwardNVIDIA
 
Opening Keynote at GTC 2015: Leaps in Visual Computing
Opening Keynote at GTC 2015: Leaps in Visual ComputingOpening Keynote at GTC 2015: Leaps in Visual Computing
Opening Keynote at GTC 2015: Leaps in Visual ComputingNVIDIA
 
NVIDIA PRO VR DAY 2017 基調講演
NVIDIA PRO VR DAY 2017 基調講演NVIDIA PRO VR DAY 2017 基調講演
NVIDIA PRO VR DAY 2017 基調講演NVIDIA Japan
 
CE-4114, Screen Mirror, a unified screen mirroring solution that utilizes AMD...
CE-4114, Screen Mirror, a unified screen mirroring solution that utilizes AMD...CE-4114, Screen Mirror, a unified screen mirroring solution that utilizes AMD...
CE-4114, Screen Mirror, a unified screen mirroring solution that utilizes AMD...AMD Developer Central
 
“Market Analysis on SoCs for Imaging, Vision and Deep Learning in Automotive ...
“Market Analysis on SoCs for Imaging, Vision and Deep Learning in Automotive ...“Market Analysis on SoCs for Imaging, Vision and Deep Learning in Automotive ...
“Market Analysis on SoCs for Imaging, Vision and Deep Learning in Automotive ...Edge AI and Vision Alliance
 
GTC 2013 Jen-Hsun Huang Keynote
GTC 2013 Jen-Hsun Huang KeynoteGTC 2013 Jen-Hsun Huang Keynote
GTC 2013 Jen-Hsun Huang KeynoteNVIDIA
 
Hire a Machine to Code - Michael Arthur Bucko & Aurélien Nicolas
Hire a Machine to Code - Michael Arthur Bucko & Aurélien NicolasHire a Machine to Code - Michael Arthur Bucko & Aurélien Nicolas
Hire a Machine to Code - Michael Arthur Bucko & Aurélien NicolasWithTheBest
 
GTC 2018 で発表された自動運転最新情報
GTC 2018 で発表された自動運転最新情報GTC 2018 で発表された自動運転最新情報
GTC 2018 で発表された自動運転最新情報NVIDIA Japan
 
GTC Taiwan 2017 自主駕駛車輛發展平台與技術研發
GTC Taiwan 2017 自主駕駛車輛發展平台與技術研發 GTC Taiwan 2017 自主駕駛車輛發展平台與技術研發
GTC Taiwan 2017 自主駕駛車輛發展平台與技術研發 NVIDIA Taiwan
 

Was ist angesagt? (20)

GTC China 2016
GTC China 2016GTC China 2016
GTC China 2016
 
組み込みから HPC まで ARM コアで実現するエコシステム
組み込みから HPC まで ARM コアで実現するエコシステム組み込みから HPC まで ARM コアで実現するエコシステム
組み込みから HPC まで ARM コアで実現するエコシステム
 
GPU Accelerated Deep Learning for CUDNN V2
GPU Accelerated Deep Learning for CUDNN V2GPU Accelerated Deep Learning for CUDNN V2
GPU Accelerated Deep Learning for CUDNN V2
 
JETSON : AI at the EDGE
JETSON : AI at the EDGEJETSON : AI at the EDGE
JETSON : AI at the EDGE
 
Nvidia Deep Learning Solutions - Alex Sabatier
Nvidia Deep Learning Solutions - Alex SabatierNvidia Deep Learning Solutions - Alex Sabatier
Nvidia Deep Learning Solutions - Alex Sabatier
 
NVIDIA Overview 2015
NVIDIA Overview 2015NVIDIA Overview 2015
NVIDIA Overview 2015
 
GPU Technology Conference 2014 Keynote
GPU Technology Conference 2014 KeynoteGPU Technology Conference 2014 Keynote
GPU Technology Conference 2014 Keynote
 
Visual Computing: The Road Ahead, NVIDIA CEO Jen-Hsun Huang at CES 2015
Visual Computing: The Road Ahead, NVIDIA CEO Jen-Hsun Huang at CES 2015 Visual Computing: The Road Ahead, NVIDIA CEO Jen-Hsun Huang at CES 2015
Visual Computing: The Road Ahead, NVIDIA CEO Jen-Hsun Huang at CES 2015
 
“Efficient Video Perception Through AI,” a Presentation from Qualcomm
“Efficient Video Perception Through AI,” a Presentation from Qualcomm“Efficient Video Perception Through AI,” a Presentation from Qualcomm
“Efficient Video Perception Through AI,” a Presentation from Qualcomm
 
GTC 2012 Jen-Hsun Huang Keynote
GTC 2012 Jen-Hsun Huang KeynoteGTC 2012 Jen-Hsun Huang Keynote
GTC 2012 Jen-Hsun Huang Keynote
 
Investor Day 2013 Jen-Hsun Huang Presentation
Investor Day 2013 Jen-Hsun Huang PresentationInvestor Day 2013 Jen-Hsun Huang Presentation
Investor Day 2013 Jen-Hsun Huang Presentation
 
Accelerated Computing: The Path Forward
Accelerated Computing: The Path ForwardAccelerated Computing: The Path Forward
Accelerated Computing: The Path Forward
 
Opening Keynote at GTC 2015: Leaps in Visual Computing
Opening Keynote at GTC 2015: Leaps in Visual ComputingOpening Keynote at GTC 2015: Leaps in Visual Computing
Opening Keynote at GTC 2015: Leaps in Visual Computing
 
NVIDIA PRO VR DAY 2017 基調講演
NVIDIA PRO VR DAY 2017 基調講演NVIDIA PRO VR DAY 2017 基調講演
NVIDIA PRO VR DAY 2017 基調講演
 
CE-4114, Screen Mirror, a unified screen mirroring solution that utilizes AMD...
CE-4114, Screen Mirror, a unified screen mirroring solution that utilizes AMD...CE-4114, Screen Mirror, a unified screen mirroring solution that utilizes AMD...
CE-4114, Screen Mirror, a unified screen mirroring solution that utilizes AMD...
 
“Market Analysis on SoCs for Imaging, Vision and Deep Learning in Automotive ...
“Market Analysis on SoCs for Imaging, Vision and Deep Learning in Automotive ...“Market Analysis on SoCs for Imaging, Vision and Deep Learning in Automotive ...
“Market Analysis on SoCs for Imaging, Vision and Deep Learning in Automotive ...
 
GTC 2013 Jen-Hsun Huang Keynote
GTC 2013 Jen-Hsun Huang KeynoteGTC 2013 Jen-Hsun Huang Keynote
GTC 2013 Jen-Hsun Huang Keynote
 
Hire a Machine to Code - Michael Arthur Bucko & Aurélien Nicolas
Hire a Machine to Code - Michael Arthur Bucko & Aurélien NicolasHire a Machine to Code - Michael Arthur Bucko & Aurélien Nicolas
Hire a Machine to Code - Michael Arthur Bucko & Aurélien Nicolas
 
GTC 2018 で発表された自動運転最新情報
GTC 2018 で発表された自動運転最新情報GTC 2018 で発表された自動運転最新情報
GTC 2018 で発表された自動運転最新情報
 
GTC Taiwan 2017 自主駕駛車輛發展平台與技術研發
GTC Taiwan 2017 自主駕駛車輛發展平台與技術研發 GTC Taiwan 2017 自主駕駛車輛發展平台與技術研發
GTC Taiwan 2017 自主駕駛車輛發展平台與技術研發
 

Andere mochten auch

CES 2017: NVIDIA Highlights
CES 2017: NVIDIA HighlightsCES 2017: NVIDIA Highlights
CES 2017: NVIDIA HighlightsNVIDIA
 
GTC 2016 ディープラーニング最新情報
GTC 2016 ディープラーニング最新情報GTC 2016 ディープラーニング最新情報
GTC 2016 ディープラーニング最新情報NVIDIA Japan
 
ADI 2016 Automotive Report
ADI 2016 Automotive ReportADI 2016 Automotive Report
ADI 2016 Automotive ReportAdobe
 
Artificial Intelligence: Predictions for 2017
Artificial Intelligence: Predictions for 2017Artificial Intelligence: Predictions for 2017
Artificial Intelligence: Predictions for 2017NVIDIA
 
GTC 2016 基調講演からディープラーニング関連情報のご紹介
GTC 2016 基調講演からディープラーニング関連情報のご紹介GTC 2016 基調講演からディープラーニング関連情報のご紹介
GTC 2016 基調講演からディープラーニング関連情報のご紹介NVIDIA Japan
 
GTC 2016 ディープラーニング最新情報
GTC 2016 ディープラーニング最新情報GTC 2016 ディープラーニング最新情報
GTC 2016 ディープラーニング最新情報NVIDIA Japan
 
NVIDIA 更新情報: Tesla P100 PCIe/cuDNN 5.1
NVIDIA 更新情報: Tesla P100 PCIe/cuDNN 5.1NVIDIA 更新情報: Tesla P100 PCIe/cuDNN 5.1
NVIDIA 更新情報: Tesla P100 PCIe/cuDNN 5.1NVIDIA Japan
 
組込みソフトウェア開発に対する弊社の取り組み事例
組込みソフトウェア開発に対する弊社の取り組み事例組込みソフトウェア開発に対する弊社の取り組み事例
組込みソフトウェア開発に対する弊社の取り組み事例ESM SEC
 
What I learned designing a car user experience
What I learned designing a car user experienceWhat I learned designing a car user experience
What I learned designing a car user experienceLuc van Loon
 
Foundation of business com chapter1
Foundation of business com chapter1Foundation of business com chapter1
Foundation of business com chapter1Rahman Ashik
 
ISCA 2014 | Heterogeneous System Architecture (HSA): Architecture and Algorit...
ISCA 2014 | Heterogeneous System Architecture (HSA): Architecture and Algorit...ISCA 2014 | Heterogeneous System Architecture (HSA): Architecture and Algorit...
ISCA 2014 | Heterogeneous System Architecture (HSA): Architecture and Algorit...HSA Foundation
 
GTC Japan 2016 Rescaleセッション資料「クラウドHPC ではじめるDeep Learning」- Oct/5/2016 at GTC ...
GTC Japan 2016 Rescaleセッション資料「クラウドHPC ではじめるDeep Learning」- Oct/5/2016 at GTC ...GTC Japan 2016 Rescaleセッション資料「クラウドHPC ではじめるDeep Learning」- Oct/5/2016 at GTC ...
GTC Japan 2016 Rescaleセッション資料「クラウドHPC ではじめるDeep Learning」- Oct/5/2016 at GTC ...Rescale Japan株式会社
 
人工知能研究のための視覚情報処理
人工知能研究のための視覚情報処理人工知能研究のための視覚情報処理
人工知能研究のための視覚情報処理Koki Nakamura
 
Wenyuan xu Minrui Yan can you trust autonomous vehicles_slides_liu_final-ja
Wenyuan xu Minrui Yan can you trust autonomous vehicles_slides_liu_final-jaWenyuan xu Minrui Yan can you trust autonomous vehicles_slides_liu_final-ja
Wenyuan xu Minrui Yan can you trust autonomous vehicles_slides_liu_final-jaPacSecJP
 
運用自動化に向けての現場からの課題
運用自動化に向けての現場からの課題運用自動化に向けての現場からの課題
運用自動化に向けての現場からの課題Yoshiki Ishida
 
Enabling Cognitive Workloads on the Cloud: GPUs with Mesos, Docker and Marath...
Enabling Cognitive Workloads on the Cloud: GPUs with Mesos, Docker and Marath...Enabling Cognitive Workloads on the Cloud: GPUs with Mesos, Docker and Marath...
Enabling Cognitive Workloads on the Cloud: GPUs with Mesos, Docker and Marath...Indrajit Poddar
 
Using Xeon + FPGA for Accelerating HPC Workloads
Using Xeon + FPGA for Accelerating HPC WorkloadsUsing Xeon + FPGA for Accelerating HPC Workloads
Using Xeon + FPGA for Accelerating HPC Workloadsinside-BigData.com
 
Thinking of Cloud? Options for Automotive Companies
Thinking of Cloud? Options for Automotive CompaniesThinking of Cloud? Options for Automotive Companies
Thinking of Cloud? Options for Automotive CompaniesCognizant
 

Andere mochten auch (20)

CES 2017: NVIDIA Highlights
CES 2017: NVIDIA HighlightsCES 2017: NVIDIA Highlights
CES 2017: NVIDIA Highlights
 
GTC 2016 ディープラーニング最新情報
GTC 2016 ディープラーニング最新情報GTC 2016 ディープラーニング最新情報
GTC 2016 ディープラーニング最新情報
 
ADI 2016 Automotive Report
ADI 2016 Automotive ReportADI 2016 Automotive Report
ADI 2016 Automotive Report
 
Artificial Intelligence: Predictions for 2017
Artificial Intelligence: Predictions for 2017Artificial Intelligence: Predictions for 2017
Artificial Intelligence: Predictions for 2017
 
GTC 2016 基調講演からディープラーニング関連情報のご紹介
GTC 2016 基調講演からディープラーニング関連情報のご紹介GTC 2016 基調講演からディープラーニング関連情報のご紹介
GTC 2016 基調講演からディープラーニング関連情報のご紹介
 
GTC 2016 ディープラーニング最新情報
GTC 2016 ディープラーニング最新情報GTC 2016 ディープラーニング最新情報
GTC 2016 ディープラーニング最新情報
 
NVIDIA 更新情報: Tesla P100 PCIe/cuDNN 5.1
NVIDIA 更新情報: Tesla P100 PCIe/cuDNN 5.1NVIDIA 更新情報: Tesla P100 PCIe/cuDNN 5.1
NVIDIA 更新情報: Tesla P100 PCIe/cuDNN 5.1
 
組込みソフトウェア開発に対する弊社の取り組み事例
組込みソフトウェア開発に対する弊社の取り組み事例組込みソフトウェア開発に対する弊社の取り組み事例
組込みソフトウェア開発に対する弊社の取り組み事例
 
What I learned designing a car user experience
What I learned designing a car user experienceWhat I learned designing a car user experience
What I learned designing a car user experience
 
Foundation of business com chapter1
Foundation of business com chapter1Foundation of business com chapter1
Foundation of business com chapter1
 
ISCA 2014 | Heterogeneous System Architecture (HSA): Architecture and Algorit...
ISCA 2014 | Heterogeneous System Architecture (HSA): Architecture and Algorit...ISCA 2014 | Heterogeneous System Architecture (HSA): Architecture and Algorit...
ISCA 2014 | Heterogeneous System Architecture (HSA): Architecture and Algorit...
 
GTC Japan 2016 Rescaleセッション資料「クラウドHPC ではじめるDeep Learning」- Oct/5/2016 at GTC ...
GTC Japan 2016 Rescaleセッション資料「クラウドHPC ではじめるDeep Learning」- Oct/5/2016 at GTC ...GTC Japan 2016 Rescaleセッション資料「クラウドHPC ではじめるDeep Learning」- Oct/5/2016 at GTC ...
GTC Japan 2016 Rescaleセッション資料「クラウドHPC ではじめるDeep Learning」- Oct/5/2016 at GTC ...
 
人工知能研究のための視覚情報処理
人工知能研究のための視覚情報処理人工知能研究のための視覚情報処理
人工知能研究のための視覚情報処理
 
Wenyuan xu Minrui Yan can you trust autonomous vehicles_slides_liu_final-ja
Wenyuan xu Minrui Yan can you trust autonomous vehicles_slides_liu_final-jaWenyuan xu Minrui Yan can you trust autonomous vehicles_slides_liu_final-ja
Wenyuan xu Minrui Yan can you trust autonomous vehicles_slides_liu_final-ja
 
運用自動化に向けての現場からの課題
運用自動化に向けての現場からの課題運用自動化に向けての現場からの課題
運用自動化に向けての現場からの課題
 
Busines Plan
Busines PlanBusines Plan
Busines Plan
 
Enabling Cognitive Workloads on the Cloud: GPUs with Mesos, Docker and Marath...
Enabling Cognitive Workloads on the Cloud: GPUs with Mesos, Docker and Marath...Enabling Cognitive Workloads on the Cloud: GPUs with Mesos, Docker and Marath...
Enabling Cognitive Workloads on the Cloud: GPUs with Mesos, Docker and Marath...
 
Using Xeon + FPGA for Accelerating HPC Workloads
Using Xeon + FPGA for Accelerating HPC WorkloadsUsing Xeon + FPGA for Accelerating HPC Workloads
Using Xeon + FPGA for Accelerating HPC Workloads
 
Tesla analysis 2014
Tesla analysis 2014Tesla analysis 2014
Tesla analysis 2014
 
Thinking of Cloud? Options for Automotive Companies
Thinking of Cloud? Options for Automotive CompaniesThinking of Cloud? Options for Automotive Companies
Thinking of Cloud? Options for Automotive Companies
 

Ähnlich wie 1050: 車載用ADAS/自動運転プラットフォームDRIVE PX及びコックピット・プラットフォームDRIVE CXのご紹介

OSGi Technology in the Vehicle - H U Michel
OSGi Technology in the Vehicle - H U MichelOSGi Technology in the Vehicle - H U Michel
OSGi Technology in the Vehicle - H U Michelmfrancis
 
한컴MDS_RTMaps_멀티 센서 애플리케이션 개발
한컴MDS_RTMaps_멀티 센서 애플리케이션 개발한컴MDS_RTMaps_멀티 센서 애플리케이션 개발
한컴MDS_RTMaps_멀티 센서 애플리케이션 개발HANCOM MDS
 
“Advancing Embedded Vision for an Autonomous World,” a Presentation from Qual...
“Advancing Embedded Vision for an Autonomous World,” a Presentation from Qual...“Advancing Embedded Vision for an Autonomous World,” a Presentation from Qual...
“Advancing Embedded Vision for an Autonomous World,” a Presentation from Qual...Edge AI and Vision Alliance
 
Commercial Vehicle AWS Cloud Service 商用車 AWS 雲端服務
Commercial Vehicle AWS Cloud Service 商用車 AWS 雲端服務Commercial Vehicle AWS Cloud Service 商用車 AWS 雲端服務
Commercial Vehicle AWS Cloud Service 商用車 AWS 雲端服務Amazon Web Services
 
Jorge Sebastiao "Using AI for Smart traffic Management"
Jorge Sebastiao "Using AI for Smart traffic Management"Jorge Sebastiao "Using AI for Smart traffic Management"
Jorge Sebastiao "Using AI for Smart traffic Management"Lviv Startup Club
 
Computer Vision for Advanced Driver Assistance Systems (Olga Mirkina Technolo...
Computer Vision for Advanced Driver Assistance Systems (Olga Mirkina Technolo...Computer Vision for Advanced Driver Assistance Systems (Olga Mirkina Technolo...
Computer Vision for Advanced Driver Assistance Systems (Olga Mirkina Technolo...IT Arena
 
MIPI DevCon 2020 | MIPI DevCon 2020 | How MIPI Interfaces Solve Challenges in...
MIPI DevCon 2020 | MIPI DevCon 2020 | How MIPI Interfaces Solve Challenges in...MIPI DevCon 2020 | MIPI DevCon 2020 | How MIPI Interfaces Solve Challenges in...
MIPI DevCon 2020 | MIPI DevCon 2020 | How MIPI Interfaces Solve Challenges in...MIPI Alliance
 
Connected cars by Smart Driving Labs
Connected cars by Smart Driving LabsConnected cars by Smart Driving Labs
Connected cars by Smart Driving LabsMauroBenigno4
 
Building a Smart City in Automotive
Building a Smart City in AutomotiveBuilding a Smart City in Automotive
Building a Smart City in AutomotiveGlobalLogic Ukraine
 
Ids sdd-jlr manual 02 02-12 (1)
Ids sdd-jlr manual 02 02-12 (1)Ids sdd-jlr manual 02 02-12 (1)
Ids sdd-jlr manual 02 02-12 (1)Boualam Mohammed
 
Accident Avoidance by using Road Sign Recognition System
Accident Avoidance by using Road Sign Recognition SystemAccident Avoidance by using Road Sign Recognition System
Accident Avoidance by using Road Sign Recognition SystemIRJET Journal
 
Solutions for ADAS and AI data engineering using OpenPOWER/POWER systems
Solutions for ADAS and AI data engineering using OpenPOWER/POWER systemsSolutions for ADAS and AI data engineering using OpenPOWER/POWER systems
Solutions for ADAS and AI data engineering using OpenPOWER/POWER systemsGanesan Narayanasamy
 
Open Network Edge Services Software for 5G and Edge
Open Network Edge Services Software for 5G and EdgeOpen Network Edge Services Software for 5G and Edge
Open Network Edge Services Software for 5G and EdgeLiz Warner
 
Autonomous Vehicles: the Intersection of Robotics and Artificial Intelligence
Autonomous Vehicles: the Intersection of Robotics and Artificial IntelligenceAutonomous Vehicles: the Intersection of Robotics and Artificial Intelligence
Autonomous Vehicles: the Intersection of Robotics and Artificial IntelligenceWiley Jones
 
Ai and traffic management application v1.0
Ai and traffic management application v1.0Ai and traffic management application v1.0
Ai and traffic management application v1.0Jorge Sebastiao
 
Marek Jersak. Autonomous Drive – From Sensors to Motion
Marek Jersak. Autonomous Drive – From Sensors to MotionMarek Jersak. Autonomous Drive – From Sensors to Motion
Marek Jersak. Autonomous Drive – From Sensors to MotionIT Arena
 
Marek Jersak «Autonomous Drive – From Sensors to Motion».
Marek Jersak «Autonomous Drive – From Sensors to Motion».Marek Jersak «Autonomous Drive – From Sensors to Motion».
Marek Jersak «Autonomous Drive – From Sensors to Motion».LogeekNightUkraine
 
Intel Vision for-autonomous-driving
Intel Vision for-autonomous-drivingIntel Vision for-autonomous-driving
Intel Vision for-autonomous-drivingDESMOND YUEN
 
TII_Thierry_LESTABLE_WCNC_2022_v10_Short.pdf
TII_Thierry_LESTABLE_WCNC_2022_v10_Short.pdfTII_Thierry_LESTABLE_WCNC_2022_v10_Short.pdf
TII_Thierry_LESTABLE_WCNC_2022_v10_Short.pdfThierry Lestable
 

Ähnlich wie 1050: 車載用ADAS/自動運転プラットフォームDRIVE PX及びコックピット・プラットフォームDRIVE CXのご紹介 (20)

OSGi Technology in the Vehicle - H U Michel
OSGi Technology in the Vehicle - H U MichelOSGi Technology in the Vehicle - H U Michel
OSGi Technology in the Vehicle - H U Michel
 
한컴MDS_RTMaps_멀티 센서 애플리케이션 개발
한컴MDS_RTMaps_멀티 센서 애플리케이션 개발한컴MDS_RTMaps_멀티 센서 애플리케이션 개발
한컴MDS_RTMaps_멀티 센서 애플리케이션 개발
 
“Advancing Embedded Vision for an Autonomous World,” a Presentation from Qual...
“Advancing Embedded Vision for an Autonomous World,” a Presentation from Qual...“Advancing Embedded Vision for an Autonomous World,” a Presentation from Qual...
“Advancing Embedded Vision for an Autonomous World,” a Presentation from Qual...
 
Commercial Vehicle AWS Cloud Service 商用車 AWS 雲端服務
Commercial Vehicle AWS Cloud Service 商用車 AWS 雲端服務Commercial Vehicle AWS Cloud Service 商用車 AWS 雲端服務
Commercial Vehicle AWS Cloud Service 商用車 AWS 雲端服務
 
Jorge Sebastiao "Using AI for Smart traffic Management"
Jorge Sebastiao "Using AI for Smart traffic Management"Jorge Sebastiao "Using AI for Smart traffic Management"
Jorge Sebastiao "Using AI for Smart traffic Management"
 
Computer Vision for Advanced Driver Assistance Systems (Olga Mirkina Technolo...
Computer Vision for Advanced Driver Assistance Systems (Olga Mirkina Technolo...Computer Vision for Advanced Driver Assistance Systems (Olga Mirkina Technolo...
Computer Vision for Advanced Driver Assistance Systems (Olga Mirkina Technolo...
 
MIPI DevCon 2020 | MIPI DevCon 2020 | How MIPI Interfaces Solve Challenges in...
MIPI DevCon 2020 | MIPI DevCon 2020 | How MIPI Interfaces Solve Challenges in...MIPI DevCon 2020 | MIPI DevCon 2020 | How MIPI Interfaces Solve Challenges in...
MIPI DevCon 2020 | MIPI DevCon 2020 | How MIPI Interfaces Solve Challenges in...
 
Connected cars by Smart Driving Labs
Connected cars by Smart Driving LabsConnected cars by Smart Driving Labs
Connected cars by Smart Driving Labs
 
Building a Smart City in Automotive
Building a Smart City in AutomotiveBuilding a Smart City in Automotive
Building a Smart City in Automotive
 
Ids sdd-jlr manual 02 02-12 (1)
Ids sdd-jlr manual 02 02-12 (1)Ids sdd-jlr manual 02 02-12 (1)
Ids sdd-jlr manual 02 02-12 (1)
 
Accident Avoidance by using Road Sign Recognition System
Accident Avoidance by using Road Sign Recognition SystemAccident Avoidance by using Road Sign Recognition System
Accident Avoidance by using Road Sign Recognition System
 
Solutions for ADAS and AI data engineering using OpenPOWER/POWER systems
Solutions for ADAS and AI data engineering using OpenPOWER/POWER systemsSolutions for ADAS and AI data engineering using OpenPOWER/POWER systems
Solutions for ADAS and AI data engineering using OpenPOWER/POWER systems
 
Open Network Edge Services Software for 5G and Edge
Open Network Edge Services Software for 5G and EdgeOpen Network Edge Services Software for 5G and Edge
Open Network Edge Services Software for 5G and Edge
 
Mobileye Project
Mobileye ProjectMobileye Project
Mobileye Project
 
Autonomous Vehicles: the Intersection of Robotics and Artificial Intelligence
Autonomous Vehicles: the Intersection of Robotics and Artificial IntelligenceAutonomous Vehicles: the Intersection of Robotics and Artificial Intelligence
Autonomous Vehicles: the Intersection of Robotics and Artificial Intelligence
 
Ai and traffic management application v1.0
Ai and traffic management application v1.0Ai and traffic management application v1.0
Ai and traffic management application v1.0
 
Marek Jersak. Autonomous Drive – From Sensors to Motion
Marek Jersak. Autonomous Drive – From Sensors to MotionMarek Jersak. Autonomous Drive – From Sensors to Motion
Marek Jersak. Autonomous Drive – From Sensors to Motion
 
Marek Jersak «Autonomous Drive – From Sensors to Motion».
Marek Jersak «Autonomous Drive – From Sensors to Motion».Marek Jersak «Autonomous Drive – From Sensors to Motion».
Marek Jersak «Autonomous Drive – From Sensors to Motion».
 
Intel Vision for-autonomous-driving
Intel Vision for-autonomous-drivingIntel Vision for-autonomous-driving
Intel Vision for-autonomous-driving
 
TII_Thierry_LESTABLE_WCNC_2022_v10_Short.pdf
TII_Thierry_LESTABLE_WCNC_2022_v10_Short.pdfTII_Thierry_LESTABLE_WCNC_2022_v10_Short.pdf
TII_Thierry_LESTABLE_WCNC_2022_v10_Short.pdf
 

Mehr von NVIDIA Japan

HPC 的に H100 は魅力的な GPU なのか?
HPC 的に H100 は魅力的な GPU なのか?HPC 的に H100 は魅力的な GPU なのか?
HPC 的に H100 は魅力的な GPU なのか?NVIDIA Japan
 
NVIDIA cuQuantum SDK による量子回路シミュレーターの高速化
NVIDIA cuQuantum SDK による量子回路シミュレーターの高速化NVIDIA cuQuantum SDK による量子回路シミュレーターの高速化
NVIDIA cuQuantum SDK による量子回路シミュレーターの高速化NVIDIA Japan
 
Physics-ML のためのフレームワーク NVIDIA Modulus 最新事情
Physics-ML のためのフレームワーク NVIDIA Modulus 最新事情Physics-ML のためのフレームワーク NVIDIA Modulus 最新事情
Physics-ML のためのフレームワーク NVIDIA Modulus 最新事情NVIDIA Japan
 
20221021_JP5.0.2-Webinar-JP_Final.pdf
20221021_JP5.0.2-Webinar-JP_Final.pdf20221021_JP5.0.2-Webinar-JP_Final.pdf
20221021_JP5.0.2-Webinar-JP_Final.pdfNVIDIA Japan
 
開発者が語る NVIDIA cuQuantum SDK
開発者が語る NVIDIA cuQuantum SDK開発者が語る NVIDIA cuQuantum SDK
開発者が語る NVIDIA cuQuantum SDKNVIDIA Japan
 
NVIDIA Modulus: Physics ML 開発のためのフレームワーク
NVIDIA Modulus: Physics ML 開発のためのフレームワークNVIDIA Modulus: Physics ML 開発のためのフレームワーク
NVIDIA Modulus: Physics ML 開発のためのフレームワークNVIDIA Japan
 
NVIDIA HPC ソフトウエア斜め読み
NVIDIA HPC ソフトウエア斜め読みNVIDIA HPC ソフトウエア斜め読み
NVIDIA HPC ソフトウエア斜め読みNVIDIA Japan
 
HPC+AI ってよく聞くけど結局なんなの
HPC+AI ってよく聞くけど結局なんなのHPC+AI ってよく聞くけど結局なんなの
HPC+AI ってよく聞くけど結局なんなのNVIDIA Japan
 
Magnum IO GPUDirect Storage 最新情報
Magnum IO GPUDirect Storage 最新情報Magnum IO GPUDirect Storage 最新情報
Magnum IO GPUDirect Storage 最新情報NVIDIA Japan
 
データ爆発時代のネットワークインフラ
データ爆発時代のネットワークインフラデータ爆発時代のネットワークインフラ
データ爆発時代のネットワークインフラNVIDIA Japan
 
Hopper アーキテクチャで、変わること、変わらないこと
Hopper アーキテクチャで、変わること、変わらないことHopper アーキテクチャで、変わること、変わらないこと
Hopper アーキテクチャで、変わること、変わらないことNVIDIA Japan
 
GPU と PYTHON と、それから最近の NVIDIA
GPU と PYTHON と、それから最近の NVIDIAGPU と PYTHON と、それから最近の NVIDIA
GPU と PYTHON と、それから最近の NVIDIANVIDIA Japan
 
GTC November 2021 – テレコム関連アップデート サマリー
GTC November 2021 – テレコム関連アップデート サマリーGTC November 2021 – テレコム関連アップデート サマリー
GTC November 2021 – テレコム関連アップデート サマリーNVIDIA Japan
 
テレコムのビッグデータ解析 & AI サイバーセキュリティ
テレコムのビッグデータ解析 & AI サイバーセキュリティテレコムのビッグデータ解析 & AI サイバーセキュリティ
テレコムのビッグデータ解析 & AI サイバーセキュリティNVIDIA Japan
 
必見!絶対におすすめの通信業界セッション 5 つ ~秋の GTC 2020~
必見!絶対におすすめの通信業界セッション 5 つ ~秋の GTC 2020~必見!絶対におすすめの通信業界セッション 5 つ ~秋の GTC 2020~
必見!絶対におすすめの通信業界セッション 5 つ ~秋の GTC 2020~NVIDIA Japan
 
2020年10月29日 プロフェッショナルAI×Roboticsエンジニアへのロードマップ
2020年10月29日 プロフェッショナルAI×Roboticsエンジニアへのロードマップ2020年10月29日 プロフェッショナルAI×Roboticsエンジニアへのロードマップ
2020年10月29日 プロフェッショナルAI×RoboticsエンジニアへのロードマップNVIDIA Japan
 
2020年10月29日 Jetson活用によるAI教育
2020年10月29日 Jetson活用によるAI教育2020年10月29日 Jetson活用によるAI教育
2020年10月29日 Jetson活用によるAI教育NVIDIA Japan
 
2020年10月29日 Jetson Nano 2GBで始めるAI x Robotics教育
2020年10月29日 Jetson Nano 2GBで始めるAI x Robotics教育2020年10月29日 Jetson Nano 2GBで始めるAI x Robotics教育
2020年10月29日 Jetson Nano 2GBで始めるAI x Robotics教育NVIDIA Japan
 
COVID-19 研究・対策に活用可能な NVIDIA ソフトウェアと関連情報
COVID-19 研究・対策に活用可能な NVIDIA ソフトウェアと関連情報COVID-19 研究・対策に活用可能な NVIDIA ソフトウェアと関連情報
COVID-19 研究・対策に活用可能な NVIDIA ソフトウェアと関連情報NVIDIA Japan
 
Jetson Xavier NX クラウドネイティブをエッジに
Jetson Xavier NX クラウドネイティブをエッジにJetson Xavier NX クラウドネイティブをエッジに
Jetson Xavier NX クラウドネイティブをエッジにNVIDIA Japan
 

Mehr von NVIDIA Japan (20)

HPC 的に H100 は魅力的な GPU なのか?
HPC 的に H100 は魅力的な GPU なのか?HPC 的に H100 は魅力的な GPU なのか?
HPC 的に H100 は魅力的な GPU なのか?
 
NVIDIA cuQuantum SDK による量子回路シミュレーターの高速化
NVIDIA cuQuantum SDK による量子回路シミュレーターの高速化NVIDIA cuQuantum SDK による量子回路シミュレーターの高速化
NVIDIA cuQuantum SDK による量子回路シミュレーターの高速化
 
Physics-ML のためのフレームワーク NVIDIA Modulus 最新事情
Physics-ML のためのフレームワーク NVIDIA Modulus 最新事情Physics-ML のためのフレームワーク NVIDIA Modulus 最新事情
Physics-ML のためのフレームワーク NVIDIA Modulus 最新事情
 
20221021_JP5.0.2-Webinar-JP_Final.pdf
20221021_JP5.0.2-Webinar-JP_Final.pdf20221021_JP5.0.2-Webinar-JP_Final.pdf
20221021_JP5.0.2-Webinar-JP_Final.pdf
 
開発者が語る NVIDIA cuQuantum SDK
開発者が語る NVIDIA cuQuantum SDK開発者が語る NVIDIA cuQuantum SDK
開発者が語る NVIDIA cuQuantum SDK
 
NVIDIA Modulus: Physics ML 開発のためのフレームワーク
NVIDIA Modulus: Physics ML 開発のためのフレームワークNVIDIA Modulus: Physics ML 開発のためのフレームワーク
NVIDIA Modulus: Physics ML 開発のためのフレームワーク
 
NVIDIA HPC ソフトウエア斜め読み
NVIDIA HPC ソフトウエア斜め読みNVIDIA HPC ソフトウエア斜め読み
NVIDIA HPC ソフトウエア斜め読み
 
HPC+AI ってよく聞くけど結局なんなの
HPC+AI ってよく聞くけど結局なんなのHPC+AI ってよく聞くけど結局なんなの
HPC+AI ってよく聞くけど結局なんなの
 
Magnum IO GPUDirect Storage 最新情報
Magnum IO GPUDirect Storage 最新情報Magnum IO GPUDirect Storage 最新情報
Magnum IO GPUDirect Storage 最新情報
 
データ爆発時代のネットワークインフラ
データ爆発時代のネットワークインフラデータ爆発時代のネットワークインフラ
データ爆発時代のネットワークインフラ
 
Hopper アーキテクチャで、変わること、変わらないこと
Hopper アーキテクチャで、変わること、変わらないことHopper アーキテクチャで、変わること、変わらないこと
Hopper アーキテクチャで、変わること、変わらないこと
 
GPU と PYTHON と、それから最近の NVIDIA
GPU と PYTHON と、それから最近の NVIDIAGPU と PYTHON と、それから最近の NVIDIA
GPU と PYTHON と、それから最近の NVIDIA
 
GTC November 2021 – テレコム関連アップデート サマリー
GTC November 2021 – テレコム関連アップデート サマリーGTC November 2021 – テレコム関連アップデート サマリー
GTC November 2021 – テレコム関連アップデート サマリー
 
テレコムのビッグデータ解析 & AI サイバーセキュリティ
テレコムのビッグデータ解析 & AI サイバーセキュリティテレコムのビッグデータ解析 & AI サイバーセキュリティ
テレコムのビッグデータ解析 & AI サイバーセキュリティ
 
必見!絶対におすすめの通信業界セッション 5 つ ~秋の GTC 2020~
必見!絶対におすすめの通信業界セッション 5 つ ~秋の GTC 2020~必見!絶対におすすめの通信業界セッション 5 つ ~秋の GTC 2020~
必見!絶対におすすめの通信業界セッション 5 つ ~秋の GTC 2020~
 
2020年10月29日 プロフェッショナルAI×Roboticsエンジニアへのロードマップ
2020年10月29日 プロフェッショナルAI×Roboticsエンジニアへのロードマップ2020年10月29日 プロフェッショナルAI×Roboticsエンジニアへのロードマップ
2020年10月29日 プロフェッショナルAI×Roboticsエンジニアへのロードマップ
 
2020年10月29日 Jetson活用によるAI教育
2020年10月29日 Jetson活用によるAI教育2020年10月29日 Jetson活用によるAI教育
2020年10月29日 Jetson活用によるAI教育
 
2020年10月29日 Jetson Nano 2GBで始めるAI x Robotics教育
2020年10月29日 Jetson Nano 2GBで始めるAI x Robotics教育2020年10月29日 Jetson Nano 2GBで始めるAI x Robotics教育
2020年10月29日 Jetson Nano 2GBで始めるAI x Robotics教育
 
COVID-19 研究・対策に活用可能な NVIDIA ソフトウェアと関連情報
COVID-19 研究・対策に活用可能な NVIDIA ソフトウェアと関連情報COVID-19 研究・対策に活用可能な NVIDIA ソフトウェアと関連情報
COVID-19 研究・対策に活用可能な NVIDIA ソフトウェアと関連情報
 
Jetson Xavier NX クラウドネイティブをエッジに
Jetson Xavier NX クラウドネイティブをエッジにJetson Xavier NX クラウドネイティブをエッジに
Jetson Xavier NX クラウドネイティブをエッジに
 

Kürzlich hochgeladen

08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking MenDelhi Call girls
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slidevu2urc
 
Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Paola De la Torre
 
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure serviceWhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure servicePooja Nehwal
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonAnna Loughnan Colquhoun
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024The Digital Insurer
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptxHampshireHUG
 
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...gurkirankumar98700
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountPuma Security, LLC
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Miguel Araújo
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Drew Madelung
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Servicegiselly40
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Scriptwesley chun
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...apidays
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024The Digital Insurer
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Igalia
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc
 
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonetsnaman860154
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationMichael W. Hawkins
 

Kürzlich hochgeladen (20)

08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slide
 
Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101
 
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure serviceWhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
 
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path Mount
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Service
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
 
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonets
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day Presentation
 

1050: 車載用ADAS/自動運転プラットフォームDRIVE PX及びコックピット・プラットフォームDRIVE CXのご紹介

  • 1. シニア・ソリューションアーキテクト 馬路 徹, 2015年9月18日 車載用ADAS/自動運転プラットフォームDRIVE PX 及びコックピト・プラットフォームDRIVE CXのご紹介
  • 2. 2 Agenda Autonomous Driving System Architecture and DRIVE PX/CX Implementations DRIVE PX for Map Module, AI Module and Computer Vision DRIVE CX for HMI Module Summary
  • 3. 3 Autonomous Driving System Architecture Typical Architecture 地図モジュール - 固定道路地図 - ローカルダイナミックマップ - 目標走行軌跡生成 速度制御モジュール - Adaptive Cruise Control - Pre-Crush System エンジン・ブレーキ 操舵制御モジュール (車線維持制御) ハンドル HMI モジュール -手動、自動切換え操作システム - 稼動状況表示 ビッグデータ、道路・交通情報等(車外データ) 走行環境センシングおよび障害物認識 - 前方の障害物センシング(ミリ波レーダ、レーザレーダ、カメラ) - レーンマーカセンシング 測位 GPS 参考文献:「自動運転 システム構成と要素技術」、保坂明夫、青木啓二、津川定之 森北出版、2015年7月 Reference: “Automated Driving System and Technologies”, Akio Hosaka et al, Morikita Publishing Co., Ltd., July 2015 人工知能モジュール - 環境理解 - 判断 - 目標走行軌跡修正 修正 指示 修正 指示 道路地図 交通情報等 道路線形 障害物 位置等 車間 距離 白線距離
  • 4. 4 Autonomous Driving System Architecture Typical Architecture MAP MODULE - Road Map - Local Dynamic Map - Target Path Generation SPEED CONTROL MODULE - Adaptive Cruise Control - Pre-Crush System Engine, Break STEERING CONTROL MODULE - Lane Keep Control Steering HMI MODULE - Auto/Manual Mode SW Operation - System Operation Status Big Data, Road, Traffic Information etc Driving Environment Sensing and Obstacle Recognition - Front Obstacles Sensing (Mili-wave Radar, Laser Radar, Camera) - Lane Marker Sensing Position Sensing GPS AI MODULE - Environment Recognition - Decision Making - Target Path Tuning Adjusting Acceleration Adjusting Direction Road Map Traffic Information Road Structure Obstacle Location Car Distance Lane Distance 参考文献:「自動運転 システム構成と要素技術」、保坂明夫、青木啓二、津川定之 森北出版、2015年7月 Reference: “Automated Driving System and Technologies”, Akio Hosaka et al, Morikita Publishing Co., Ltd., July 2015
  • 5. 5 Autonomous Driving System Architecture MAP MODULE implementation by DRIVE PX/CUDA SPEED CONTROL MODULE - Adaptive Cruise Control - Pre-Crush System Engine, Break STEERING CONTROL MODULE - Lane Keep Control Steering HMI MODULE - Auto/Manual Mode SW Operation - System Operation Status Big Data, Road, Traffic Information etc Driving Environment Sensing and Obstacle Recognition - Front Obstacles Sensing (Mili-wave Radar, Laser Radar, Camera) - Lane Marker Sensing Position Sensing GPS AI MODULE - Environment Recognition - Decision Making - Target Path Tuning Adjusting Acceleration Adjusting Direction Road Map Traffic Information Road Structure Obstacle Location Car Distance Lane Distance DRIVE PX / CUDA MAP MODULE - Road Map - Local Dynamic Map - Target Path Generation 参考文献:「自動運転 システム構成と要素技術」、保坂明夫、青木啓二、津川定之 森北出版、2015年7月 Reference: “Automated Driving System and Technologies”, Akio Hosaka et al, Morikita Publishing Co., Ltd., July 2015
  • 6. 6 Autonomous Driving System Architecture + AI MODULE implementation by DRIVE PX/DL SPEED CONTROL MODULE - Adaptive Cruise Control - Pre-Crush System Engine, Break STEERING CONTROL MODULE - Lane Keep Control Steering HMI MODULE - Auto/Manual Mode SW Operation - System Operation Status Big Data, Road, Traffic Information etc Driving Environment Sensing and Obstacle Recognition - Front Obstacles Sensing (Mili-wave Radar, Laser Radar, Camera) - Lane Marker Sensing Position Sensing GPS Adjusting Direction Road Map Traffic Information Road Structure Obstacle Location Car Distance Lane Distance DRIVE PX / CUDA DRIVE PX / DL MAP MODULE - Road Map - Local Dynamic Map - Target Path Generation AI MODULE - Environment Recognition - Decision Making - Target Path Tuning Adjusting Acceleration 参考文献:「自動運転 システム構成と要素技術」、保坂明夫、青木啓二、津川定之 森北出版、2015年7月 Reference: “Automated Driving System and Technologies”, Akio Hosaka et al, Morikita Publishing Co., Ltd., July 2015
  • 7. 7 Autonomous Driving System Architecture + HMI MODULE Implementation by DRIVE CX/HMI SPEED CONTROL MODULE - Adaptive Cruise Control - Pre-Crush System Engine, Break STEERING CONTROL MODULE - Lane Keep Control Steering Big Data, Road, Traffic Information etc Driving Environment Sensing and Obstacle Recognition - Front Obstacles Sensing (Mili-wave Radar, Laser Radar, Camera) - Lane Marker Sensing Position Sensing GPS Adjusting Direction Road Map Traffic Information Road Structure Obstacle Location Car Distance Lane Distance DRIVE PX / CUDA DRIVE PX / DL DRIVE CX/HMI MAP MODULE - Road Map - Local Dynamic Map - Target Path Generation AI MODULE - Environment Recognition - Decision Making - Target Path Tuning HMI MODULE - Auto/Manual Mode SW Operation - System Operation Status Adjusting Acceleration 参考文献:「自動運転 システム構成と要素技術」、保坂明夫、青木啓二、津川定之 森北出版、2015年7月 Reference: “Automated Driving System and Technologies”, Akio Hosaka et al, Morikita Publishing Co., Ltd., July 2015
  • 8. 8 Autonomous Driving System Architecture + Computer Vision Processing by DRIVE PX/DL & CV -> Almost All Processings by Tegra SPEED CONTROL MODULE - Adaptive Cruise Control - Pre-Crush System Engine, Break STEERING CONTROL MODULE - Lane Keep Control Steering Big Data, Road, Traffic Information etc Position Sensing GPS Adjusting Direction Road Map Traffic Information Road Structure Obstacle Location Car Distance Lane Distance DRIVE PX / CUDA DRIVE PX / DL DRIVE CX/HMI MAP MODULE - Road Map - Local Dynamic Map - Target Path Generation AI MODULE - Environment Recognition - Decision Making - Target Path Tuning HMI MODULE - Auto/Manual Mode SW Operation - System Operation Status Computer Vision Deep Learning VisionWorks DRIVE PX / DL & CV Adjusting Acceleration 参考文献:「自動運転 システム構成と要素技術」、保坂明夫、青木啓二、津川定之 森北出版、2015年7月 Reference: “Automated Driving System and Technologies”, Akio Hosaka et al, Morikita Publishing Co., Ltd., July 2015
  • 9. 9
  • 10. 10 Audi zFAS Example as a Low-Speed Autonomous Driving: Obstacle Recognition, Target Path Generation by one Tegar K1 From GTC2015
  • 11. 11 Deep Learning Revolutionize 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….)
  • 12. 12 TEGRA X1 CLASSIFICATION Performance AlexNet 0 10 20 30 40 50 60 70 80 90 100 Tegra K1 Tegra X1 IMAGES/SECOND
  • 13. 13
  • 14. 14 Growing Performance of Automotive Tegra Products will allow further Integration in the Future Tegra 2 Tegra 3 Tegra 4 Tegra K1 0 200 400 600 800 1000 1200 GFLOPS FP16/INT16 Core i7 Tegra X1 CPU GPU GPU CPU Tegra X1 (FP16) Note: 4790K Core i7, CPU @ 4GHz, GPU @ 350 MHz TIME
  • 15. 15 DRIVE PX For Map Module, AI Module and Computer Vision
  • 16. 16 DRIVE PX An advanced computing platform based on NVIDIA Tegra processors for autonomous driving cars FEATURES The ability to capture and process multiple HD camera and sensor inputs A rich middleware for computer graphics, computer vision and deep learning A powerful and easy to develop platform for algorithm research and rapid prototyping NVIDIA CONFIDENTIAL — DRIVE PX DEVELOPMENT PLATFORM Preliminary information — Subject to change
  • 17. 17Proprietary & Confidential All Information Subject to Change DRIVE PX Camera & Display Interfaces Group A Group B Group C  12 simultaneous LVDS camera inputs • All cameras synchronized within each Group (3 groups)  2 LVDS display ports Display
  • 18. 18 Other Interfaces to Aurix CAN*, LIN*, FlexRay* and Ethernet 48-pin Automotive Grade Vehicle Harness CAN 2.0 (x6) FlexRay (x2) LIN (x4) UART (x1) Ethernet (x1) 1x Power
  • 19. 19 Hardware Specs PROCESSORS Dual Tegra X1 VCM; each VCM consists of: Tegra X1 processor DRAM: 4GB NOR FLASH: 64MB eMMC: 64GB Inter-Tegra X1 VCM Communication SPI and USB 3.0 for direct inter-Tegra communication and through Ethernet Switch ASIL-D MCU Camera and IO controls through ASIL-D MCU. NVIDIA CONFIDENTIAL — DRIVE PX DEVELOPMENT PLATFORM Preliminary information — Subject to change
  • 20. 20 Hardware Specs PERIPHERALS Sensors: Vision Sensors interface: 12x LVDS Cameras Sensor Interfaces for Radar, LIDAR, Vehicle Dynamics etc.: CAN 2.0; LIN; Ethernet; Flexray Displays: LVDS interface (x2) Power Management of ECU: System power monitor/control — ASIL-D MCU NVIDIA CONFIDENTIAL — DRIVE PX DEVELOPMENT PLATFORM Preliminary information — Subject to change
  • 21. 21 DRIVE PX software specs OS: NVIDIA Vibrante Linux 4.0 64-bit Kernel Linux, Quickboot, AutoSAR RunTimeEnvironment Graphics: Open GL ES 3.1 Development Tools/Samples: Delivered through Jetpack 2.x Graphics debugger, PerfKit, DNN Classifier Sample, Vision Works 1.0 (beta) Computer Vision libraries and Samples ASIL MCU Support for CAN, Ethernet, Flexray and LIN; AutoSAR framework External Storage for Video Recording USB3.0 interface for camera output in RAW or H.265/H.264 encoded formats Camera: NVMedia and Driver support for LVDS camera Open Source Collaboration initiatives/Compliance: Yocto 1.8 Genivi7 Compliant NVIDIA CONFIDENTIAL — DRIVE PX DEVELOPMENT PLATFORM Preliminary information — Subject to change
  • 22. 22 WORLD CLASS SOFTWARE TOOLS Faster debug and analysis reduces development costs Preliminary information — Subject to change TEGRA GRAPHICS DEBUGGER Visualize GPU performance metrics Automated analysis of GPU bottlenecks PERFKIT Performance monitoring Automated bottleneck analysis ECLIPSE IDE Standard Linux development environment
  • 23. 23 DRIVE PX LINUX SOFTWARE STACK Preliminary information — Subject to change Imaging (Camera) Pipeline Linux Performance Microprocessor A Graphics/ComputeNVMedia CUDA/EGL/ Open GL ES Tegra™ X1 Hardware (ARM, GPU & SoC Peripherals) Safety MCU Safety MCU MCA L Applications T1/OEM SW OS/3rd SW/HW NVIDIA Licensed SW Drive PX Hardware Elektrobit AUTOSAR BSW on Linux Linux Performance Microprocessor B Tegra™ X1 Hardware (ARM, GPU & SoC Peripherals) AUTOSAR BSW on Linux ApplicationsApplications Linux BSP/Drivers Filesystem(s) Linux BSP/Drivers Graphics/Compute CV/DL Libraries Imaging (Camera) Pipeline Graphics/Compute NVMedia CUDA/EGL/ Open GL ES Filesystem(s) Graphics/Compute CV/DL Libraries AUTOSAR on Safety MCU
  • 25. 25NVIDIA CONFIDENTIAL THE SOUL OF NVIDIA DRIVE™ CX DIGITAL COCKPIT CAR COMPUTER Natural Speech OTA updates Advanced Visuals Hypervisor – Cluster Cockpit
  • 26. 26 DRIVE CXTODAY ADVANCED VISUALS – Digital CLUSTER
  • 27. 27 DRIVE CX ADAS Also supported by DRIVE PX Best-in-Class Surround View
  • 28. 28 NVIDIA DRIVE Design Design Studio Professional artist environment Design Architect Integrated engineering environment NVIDIA’s HMI Platform version 8.0
  • 29. 29 Today (no internet connection) Google (with Internet Connection) DRIVE CX (no internet connection) ACCURACY LOW 1M parameters HIGH 30M parameters HIGH 30M parameters VOCABULARY SMALL 50k words LARGE 4M words LARGE 4M words SPEED SLOW 500+ ms latency FAST … or no response (lost internet connection) FAST … always Fail-safe NATURAL LANGUAGE SPEECH
  • 30. 30 SUMMARY 1. Autonomous Driving System Architecture consists of Sensing Module, Map Module, AI Module and HMI Module. DRIVE PX and CX can implement all functions with CUDA, Deep Learning , Computer Vision and HMI Frameworks. 2. DRIVE PX consists of two powerful Tegra X1 processors with the total performance of 2.3TFLOPS. It comes with a rich middleware for GPU Computing, Deep Learning and Computer Vision. 3. DRIVE CX powerful Tegra X1 processor enables the fail-safe Natural Speech Recognition, advanced visual quality which offers a safe, versatile and high- quality HMI. This is essential for the critical human-car interaction in the Autonomous Driving Cars. 4. Today, we might start with a few DRIVE PX and a DRIVE CX. However, the continuous performance and feature enhancement in the future will make it possible to implement the total system by a single DRIVE platform if required.