IN SPRINTS TOWARDS AUTONOMOUS DRIVING. BMW GROUP TECHNOLOGY WORKSHOPS. December 2017

Similar documents
BMW GROUP TECHNOLOGY WORKSHOPS AUTOMATED DRIVING-DIGITALIZATION MOBILITY SERVICES. December 2016

TECHNOLOGY WORKSHOPS December 2017

Citi's 2016 Car of the Future Symposium

The Imperative to Deploy. Automated Driving. CC MA-Info, 15th December 2016 Dr. Hans-Peter Hübner Kay (CC/EB4) Stepper

END TO END NEEDS FOR AUTONOMOUS VEHICLES NORM MARKS SEPT. 6, 2018

Deep Learning Will Make Truly Self-Driving Cars a Reality

Copyright 2016 by Innoviz All rights reserved. Innoviz

Driving simulation and Scenario Factory for Automated Vehicle validation

On the role of AI in autonomous driving: prospects and challenges

China Intelligent Connected Vehicle Technology Roadmap 1

NXP S32X AUTOMOTIVE PROCESSING PLATFORM

RENAULT and TOULOUSE : A long success story ready for the future

THE FAST LANE FROM SILICON VALLEY TO MUNICH. UWE HIGGEN, HEAD OF BMW GROUP TECHNOLOGY OFFICE USA.

Test & Validation Challenges Facing ADAS and CAV

MAX PLATFORM FOR AUTONOMOUS BEHAVIORS

REGULATORY APPROVAL OF AN AI-BASED AUTONOMOUS VEHICLE. Alex Haag Munich,

Financial Planning Association of Michigan 2018 Fall Symposium Autonomous Vehicles Presentation

DA to AD systems L3+: An evolutionary approach incorporating disruptive technologies

AUTONOMOUS DRIVING COLLABORATIVE APPROACH NEEDED FOR BIG BUSINESS. Innovation Bazaar, Vehicle ICT Arena ver 2. RISE Viktoria Kent Eric Lång

Autonomous Vehicles Transforming Vehicle Development André Rolfsmeier dspace Technology Conference 2017

Items to specify: 4. Motor Speed Control. Head Unit. Radar. Steering Wheel Angle. ego vehicle speed control

Using Virtualization to Accelerate the Development of ADAS & Automated Driving Functions

UNIFIED, SCALABLE AND REPLICABLE CONNECTED AND AUTOMATED DRIVING FOR A SMART CITY

PSA Peugeot Citroën Driving Automation and Connectivity

elektrobit.com Driver assistance software EB Assist solutions

Machine Learning & Active Safety Using Autonomous Driving and NVIDIA DRIVE PX. Dr. Jost Bernasch Virtual Vehicle Research Center Graz, Austria

The connected vehicle is the better vehicle!

Megatrends and their Impact on the Future of Mobility

Automated Driving is the declared goal of the automotive industry. Systems evolve from complicated to complex

WHITE PAPER Autonomous Driving A Bird s Eye View

Virtual Testing of the Full Vehicle System

ABB Journey to Digital New ways of Collaboration with Customers

Automated Driving - Object Perception at 120 KPH Chris Mansley

Our Market and Sales Outlook

Future mobility in a dynamic environment. Dr. Rolf Bulander

Advancing the TWV Fleet 10 May 2016

MEMS Sensors for automotive safety. Marc OSAJDA, NXP Semiconductors

Bitte decken Sie die schraffierte Fläche mit einem Bild ab. Please cover the shaded area with a picture. (24,4 x 7,6 cm)

Cooperative Autonomous Driving and Interaction with Vulnerable Road Users

University of Michigan s Work Toward Autonomous Cars

SAFETY ON EVERY CURVE

Automotive Electronics/Connectivity/IoT/Smart City Track

Enabling Technologies for Autonomous Vehicles

Deutsche Bank AutoTech Day

Simulation of the influence of road traffic on the operation of an electric city bus

AUTONOMOUS VEHICLES & HD MAP CREATION TEACHING A MACHINE HOW TO DRIVE ITSELF

LiDAR Teach-In OSRAM Licht AG June 20, 2018 Munich Light is OSRAM

H A R A L D W E S T E R C H I E F T E C H N I C A L O F F I C E R

Drive Security From The Inside Out... SIP-adus Workshop 2018 Tokyo Japan November Synopsys, Inc. 1

Our Businesses. Environment. Safety. Advanced Vehicle Control Systems

FLYING CAR NANODEGREE SYLLABUS

Crew integration & Automation Testbed and Robotic Follower Programs

LEADING THE TRANSFORMATION OF MOBILITY. Sergio Solero - CEO BMW Italia

VALET project: how connected and automated driving will change urban parking? Proposition technique

Siemens ADAS. Collision avoidance as the first step towards autonomous driving

AUTOPILOT presentation

THE FUTURE OF AUTONOMOUS CARS

THE WAY TO HIGHLY AUTOMATED DRIVING.

Transportation. Actuators, Pedals and Sensors

The Car manufacturer s challenge in a fast paced world of More Electric, Connected and Automated Vehicles

Tank-Automotive Research, Development, and Engineering Center

Powertrain and Chassis Hardware-in-the- Loop (HIL) Simulation of Ford s Autonomous Vehicle Platform

Our Approach to Automated Driving System Safety. February 2019

ZF Advances Key Technologies for Automated Driving

REAL AND VIRTUAL PROVING OF AUTOMATED DRIVING IN BERLIN'S MIXED TRAFFIC. Dr. Ilja Radusch,

Hardware-in-the-Loop Testing of Connected and Automated Vehicle Applications

More power to manufacturers. Improving electric vehicle production processes

Pushing the limits of automated driving with artificial intelligence and connectivity

AUTONOMOUS CARS: TECHNIQUES AND CHALLENGES

Integrated Architectures Management, Behavior models, Controls and Software

Intelligent Transportation Systems. Secure solutions for smart roads and connected highways. Brochure Intelligent Transportation Systems

Autnonomous Vehicles: Societal and Technological Evolution (Invited Contribution)

Towards Realizing Autonomous Driving Based on Distributed Decision Making for Complex Urban Environments

AUTONOMOUS VEHICLES: PAST, PRESENT, FUTURE. CEM U. SARAYDAR Director, Electrical and Controls Systems Research Lab GM Global Research & Development

Connected & Autonomous Vehicles: Developing the UK Supply Chain

AND CHANGES IN URBAN MOBILITY PATTERNS

State-of-the-Art and Future Trends in Testing of Active Safety Systems

ACTIVE SAFETY 3.0. Prof. Kompaß, VP Fahrzeugsicherheit, 14. April 2016

Smart Control for Electric/Autonomous Vehicles

IVECO DUAL ENERGY A TECHNOLOGY CONCEPT

Experience the Hybrid Drive

NavInfo HD maps make automated driving safer and more comfortable. Xiao Gong

On the road to automated vehicles Sensors pave the way!

Security for the Autonomous Vehicle Identifying the Challenges

Traffic Operations with Connected and Automated Vehicles

Intelligent Vehicle Systems

E-Mobility in Planning and Operation of future Distribution Grids. Michael Schneider I Head of Siemens PTI

Leading and shaping change Focus on technology

ADVANCES IN INTELLIGENT VEHICLES

VEDECOM. Institute for Energy Transition. Presentation

OPENSTEERING PLATFORM

Software Driving License

Car Technologies Stanford and CMU

Energy & Power Community of Interest March 21, 2018

Validation difficulties and testing challenges of connected and automated vehicles. Prof. Zsolt SZALAY

The Digital Future of Driving Dr. László Palkovics State Secretary for Education

Sustainable Intelligent Mining Systems. World Class Demonstrations. Morgan Rody

Jimi van der Woning. 30 November 2010

VIRTUAL VEHICLE Research Center

Cooperative brake technology

Transcription:

IN SPRINTS TOWARDS AUTONOMOUS DRIVING. BMW GROUP TECHNOLOGY WORKSHOPS. December 2017

AUTOMATED DRIVING OPENS NEW OPPORTUNITIES FOR CUSTOMERS AND COMMUNITY. MORE SAFETY MORE COMFORT MORE FLEXIBILITY MORE TIME LESS EMISSIONS LESS ACCIDENTS LESS TRAFFIC NEW MOBILITY CONCEPTS CAR AS EXTENDED LIVING SPACE In sprints towards Autonomous Driving December 2017. Page 2

THE DEVELOPMENT OF TODAY S ASSISTED FUNCTIONS TO TOMORROWS AUTONOMOUS DRIVING EQUALS A TECHNOLOGICAL QUANTUM LEAP. 0 1 2 3 4 5 Driver Feet off Hands off Eyes off Attention off Passenger No assistance Assistance Semi-automated Highly automated Fully automated Autonomous (L 0) (L 1) (L 2) (L 3) (L 4) (L 5) Individual Transfer of responsibility Transfer of responsibility Machine In sprints towards Autonomous Driving December 2017. Page 3

BMW HAS CREATED A STRONG SETTING FOR THE DEVELOPMENT OF AUTONOMOUS DRIVING TO SHAPE THE FUTURE OF MOBILITY. User Interface HAD/ FAD fleet Core cooperation Development partners PAD Backend / Data storage Autonomous driving Agile development agile Artificial Intelligence AI Sensors Autonomous Driving Campus

CROSS-INDUSTRIAL PARTNERSHIPS NEEDED FOR A SUCCESSFUL DEVELOPMENT OF THE AUTONOMOUS DRIVING. COOPERATION. HD-MAP. INFRASTRUCTURE 5G. SENSOR STANDARD. SENSORS: CAMERA, RADAR, LIDAR. OBJECT FUSION. ROAD MODEL. CENTIMETER PRECISION. REAL-TIME CAPABLE. HIGHLY AVAILABLE AND RELIABLE. ULTRA LOW LATENCY. ULTRA HIGH RELIABILITY. ULTRA HIGH DATA RATES. SENSORS: CAMERA, RADAR, LIDAR. COMPLEXITY REDUCTION. FLEXIBILITY. DRIVING STRATEGY/PLANNING. FUTURE-PROOF INTERFACE. AUTONOMOUS DRIVING. OEM- COOPERATION. 5G AUTOMOTIVE ASSOCIATION. INTERNATIONAL BOARDS & ASSOCIATIONS. OEMs In sprints towards Autonomous Driving December 2017. Page 5

FOR A FAST SUCCESS, BMW WILL DEVELOP A NON EXCLUSIVE PLATFORM FOR THE MARKET TOGETHER WITH ITS PARTNERS. Non exclusive platform Software Backend OEMs/ Tier 1 partners Core cooperation Platform Sensors Other cross-industrial partners In sprints towards Autonomous Driving December 2017. Page 6

THE WINNING FORMULA IS TO ADOPT A LEAN AND AGILE MIND-SET, BOTH ACROSS THE ORGANIZATION AND WITHIN COLLABORATIONS. Short distances, fast communication. Interdisciplinary teamwork for common targets. Central base for workshops, simulation and validation. Highly efficient agile product development. New organization models. Scalable and open for partners. In sprints towards Autonomous Driving December 2017. Page 7

C o m p onent re sp o n sibil ity C o m p onent re sp o n sibil ity C o m p onent re sp o n sibil ity C o m p onent re sp o n sibil ity C o m p onent re sp o n sibil ity C o m p onent re sp o n sibil ity C o m p onent re sp o n sibil ity C o m p onent re sp o n sibil ity C o m p onent re sp o n sibil ity THE CHANGE WE ARE DRIVING FORWARD IS NOT ONLY ABOUT TECHNOLOGY, IT S ALSO ABOUT WORKING MODELS. Today. Tomorrow. Component responsibility Component responsibility Component responsibility Component responsibility Component responsibility Component responsibility Component responsibility Component responsibility Focus on components and cascaded responsibility. Focus on features with end-to-end responsibility. In sprints towards Autonomous Driving December 2017. Page 8

CORE OF THE AUTONOMOUS DRIVING TECHNOLOGY IS THE END-TO-END ARCHITECTURE. In sprints towards Autonomous Driving December 2017. Page 9

BMW TAKES THE SENSOR SETUP TO A NEW LEVEL TO RELIABLY DETECT ALL RELEVANT OBJECTS IN URBAN ENVIRONMENTS TARGET SENSOR SETUP WILL CONTAIN 44 SENSORS. Front-Side Camera Tri-Focal Camera GPS Antenna Front-Side Camera Tri-Focal Camera Front-Side Camera Front-Side Camera Full-Range Radar Lidar Short Range Radar Rear-Facing Camera Short Range Radar Short Range Radar Lidar Lidar Lidar Full-Range Radar Lidar Not shown: 360 Surround-View Cameras, 360 Ultrasound Coverage, 1x Rear Camera, 2x Rear Lidar, 2x Full-Range Radar. In sprints towards Autonomous Driving December 2017. Page 10

ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING ARE INDISPENSABLE TO SUCCESSFULLY UNDERSTAND AND TRAIN THE RIGHT DRIVING BEHAVIOR. On-Board Off-Board ARTIFICIAL INTELLIGENCE Perception, Sensor fusion Scene Understanding FLEET DATA Labeling of Training Data 275/459 205/310 165/345 275/459 Evolution Through Training Plan Execution, Motion Control Mission and Trajectory Planning BACKEND Simulation and Sign-off MODEL UPDATE In sprints towards Autonomous Driving December 2017. Page 11

MACHINE LEARNING BY EXAMPLE PARKED VEHICLE CLASSIFICATION. Training Backend Labeled training-data Forward Pass Not Parked Parked Sensors 1000 x Backward Pass Execution On board Learned model Forward Pass Sensors??? Parked In sprints towards Autonomous Driving December 2017. Page 12

DATA DRIVEN DEVELOPMENT REQUIRES STATE OF THE ART DATA CENTERS. Data center End of 2017 70 PB data capacity at BMW, target capacity of 200 PB in 2019 compares with 770 km CDs. Storage capacity Ramp-up of capacity up to 200 PB until 2019, with flexibility of further capacity increase. > 200 PB 200 PB 70 PB 12/2017 07/2019 07/2025 INTEL Campeon Currently ~ 85 PB storage capacity 10x larger network gateways into INTEL than ever before. In sprints towards Autonomous Driving December 2017. Page 13

SAFETY FIRST: SEVERAL MILLION KILOMETERS WITHOUT ACCIDENTS TO BE COMPLETED SIMULATION AND HUGE DATA STORAGE IS REQUIRED. Driving simulation. Global Development Fleet. Driving Simulation Driving Test Hardware Testing. Several Million KM Prototype vehicle build up. 135 135 90 Test on Proofing Ground. Simulation 25 13 7 15 50 30 50 50 50 2016 2017 2018 2019 2020 2021 HAD FAD DATA CENTER FAD: 5 TB / h 40 TB / d - 8h / 5d running HAD: 2 TB / h 16 TB / d - 8h / 5d running In sprints towards Autonomous Driving December 2017. Page 14

SAFETY FIRST: SEVERAL MILLION KILOMETERS WITHOUT ACCIDENTS TO BE COMPLETED SIMULATION AND HUGE DATA STORAGE IS REQUIRED. SiL Software in the Loop. Performance of new Features Test safety-relevant Scenarios Fast Feedback for Developer HiL Hardware in the Loop. Real Hardware in simulated Environment Virtual Integration in the Lab-Car Evidence of Safety-Aspects WE PERFORM UP TO 2 MILLION SCENARIOS PER DAY! In sprints towards Autonomous Driving December 2017. Page 15

FOR DATA COLLECTION AND TEST DRIVES A MODERN TEST FLEET OF 40 VEHICLES IN 2017 ON BASIS OF 7 SERIES WAS BUILD, WORLD WIDE TEST DRIVES STARTED. Data Driven Development. Prototypes as critical to success developing tools. Mission: testing, developing and collecting data. In sprints towards Autonomous Driving December 2017. Page 16

MODERN VEHICLE INTEGRATION LAB FOR VEHICLE TEST FLEET AT THE AUTONOMOUS DRIVING CAMPUS. Perfect realization in Vehicle Integration Lab at AD Campus: Ingestion and flashing of the prototypes In sprints towards Autonomous Driving December 2017. Page 17

BMW WILL PAVE THE WAY TOWARDS AUTONOMOUS DRIVING WITH A GO LIVE OF THE HAD AND FAD FUNCTIONS STARTING WITH THE inext IN 2021. Tier 1 OEMs Integration of further partners Ca. 140 HAD/ FAD test vehicles ww HAD drives in US/ EU/ Asia FAD drives US/ EU/ Asia HAD/ FAD starting with inext HAD drives in US/ EU FAD drives MUC downtown 90 135 135 40 HAD/ FAD test vehicles 25 13 7 15 50 30 50 50 50 AD Campus Munich 2016 2017 2018 2019 2020 2021 HAD FAD 2017 2018 2019 2020 2021 In sprints towards Autonomous Driving December 2017. Page 18

IN SPRINTS TOWARDS AUTONOMOUS DRIVING. BMW GROUP TECHNOLOGY WORKSHOPS. December 2017