Advantage of a GPU powered trajectory planning for autonomous driving using NVidia DrivePX. GPU Technology Conference 2017

Size: px
Start display at page:

Download "Advantage of a GPU powered trajectory planning for autonomous driving using NVidia DrivePX. GPU Technology Conference 2017"

Transcription

1 Advantage of a GPU powered trajectory planning for autonomous driving using NVidia DrivePX GPU Technology Conference 2017 GTC Munich, 12 th October 2017 Dipl.-Ing. Jörg Küfen - Senior Manager Engineer Marius Stärk, M.Sc. - Development Engineer Forschungsgesellschaft Kraftfahrwesen mbh Aachen

2 To Start With E/E Systems of Vehicles System Layers Architecture and Software ECU Hardware, Communication Depending Interdisciplinary Perspective On the E/E System Power Systems, Infrastructure Slide No. 2

3 Introduction Disruptive Technologies Potentials of Disruptive Technologies Manhatten Manhatten years Slide No. 3

4 Introduction Disruptive Technologies Potentials of Disruptive Technologies Mobile Phone Mobile Phone less than 10 years Slide No. 4

5 Introduction Automated Driving (AD) Systems Impact on the Future of Mobility 1 Zero Emission Optimize traffic and traffic flow Reduce of fuel consumption and CO2 emission 2 Demographic Change Support unconfident drivers Guarantee mobility for elderly people 3 Vision Zero Avoidance of human driving errors 4 Increase traffic density Optimize traffic and traffic flow Convenient, time efficient 5 Economy Attractive products, by technology leadership Time efficient and comfortable mobility redefine tomorrows mobility Slide No. 5

6 Introduction Automated Driving (AD) Systems Slide No. 6

7 Introduction Automated Driving (AD) Systems Decomposition of an Autonomous Driving (AD) System Goal Strategy Tactic Execution Map Sense Localize Plan Control Perceive Sense Interpret Plan Arbitrate Act Slide No. 7

8 Introduction Automated Driving (AD) Systems Decomposition of an Autonomous Driving (AD) System min complex objects plans Knowledge Based Reasoning (respecting system capabilities) s objects abstract actions High-Level Perception Reflex B reactions Arbiter ms actions Base Perception Reflex A fast reactions Actuator Command µs signals S S S S S S A A A A A A actuations Slide No. 8

9 Trajectory Planner Essential Element of the Functional Network Hierarchy Levels Decision Layer Trajectory Planner Dynamic Controllers Slide No. 9

10 Trajectory Planner Requirements From Acceptance and Technology 1 Trajectories need to feel human to the passengers 2 Trajectory calculation must be stable 3 Trajectory calculation must always provide a safe result 4 Trajectory calculation must be fast Slide No. 10

11 Trajectory Planner Characterisation Different planner characteristics Characteristic Calculation Method Optimization Value Range State Transition Degrees of Freedom Alternatives Direct / Sampling / Numerical Optimization Global Optimum / Local Optimum Discrecte / Continuous Primitives / Vehicle Model Spatial / Spatial & Temporal Slide No. 11

12 Trajectory Planner Characterisation fka s GPU based Trajectory Planner Characteristic Calculation Method Optimization Value Range State Transition Degrees of Freedom fka s Planner Numerical Optimization Local Optimum Continuous Vehicle Model Spatial Slide No. 12

13 Trajectory Planner Cost Function Relevant Aspects for Planning Trajectory planner uses a discrete set of intermediate steps to generate a solution Intermediate state cost depends on factors like Distance to borders Reference trajectory distance Reference trajectory relative orientation and more The overall cost of a trajectory is defined as the sum of all costs of each intermediate states Intermediate States Cost factor terms can be integrated or removed easily Facilitates model adaption based on driving situation Slide No. 13

14 Trajectory Planner Functional Interface Input and Output Input for the planner consists of a reference trajectory road data obstacles defined as polygons Road Boundary Output is a trajectory spline Static Obstacles Reference Trajectory Slide No. 14

15 Trajectory Planner Structure Draft Workflow Core Loop Sample Track / Create Reference Trajectory Evaluate Cost Function and Derivatives Vehicle Data (Position, Velocity, ) Solve NLP Solution found or max iterations reached Output Trajectory Simulation Update Vehicle Data According to Trajectory Real Vehicle Send commands Read odometry Slide No. 15

16 Trajectory Planner Structure Optimization Potentials Question from a point of System Architecture: where are optimization potentials, which can be addressed by new technologies? Cost function solved by NLP solver NLP solver requires 1st and 2nd partial derivatives of cost function Core Loop Evaluate Cost Function and Derivatives The fka GPU based planner utilizes the massive parallel computing power of GPUs Solve NLP GPU is used for function evaluation and derivative calculation Derivatives are calculated implicitly using automatic differentiation (hyperdual numbers) Afterwards the NLP solver operates upon the calculated cost function Slide No. 16

17 Trajectory Planner Capabilities of the Planner fka's Planner Capabilities Capabilites of the Trajectory Planner Realtime usabilty Constraints and conditions Customizable dynamic models Prediction horizon adaptabe Robust solutions not given any prior assumptions Static obstacles Slide No. 17

18 Performance Analysis Evaluation Planning Performance - Slide No. 18

19 Performance Analysis Evaluation Planning Performance Planning performance depends on several factors: Number of intermediate steps Scenario and cost function complexity Parallel computing capability Platform CPU-Only x86 Drive PX 2 dgpu Drive PX 2 igpu Runtime (approx.) 200ms 21ms 35ms Speed-Up (vs CPU) 1x 9.52x 5.71x Slide No. 19

20 Performance Analysis Evaluation The Driver as a Reference Sense Interpret Plan Arbitrate Act Driver reaction time depends on various factors physical and mental condition degree of experience in order to characterize situation Traffic situation complexity Driver: Typically ms can be assumed corresponds to 8 to 100km/h Planner: average planning time of 25ms corresponds to 100km/h Slide No. 20

21 Outlook Further Roadmap Planner and GPU as Component for AD Next steps on fka s GPU based planner Extend functionality and further enhance computation efficiency Natively integrate aspect of situation dependent, adaptive granularity selection and adaptive selection of cost function influencing factors Perform functional safety analysis Integrate complete planner into driving environment Slide No. 21

22 Contact Dipl.-Ing. Jörg Küfen Senior Manager Electronics Department Marius Stärk, M.Sc. Development Engineer Electronics Department fka Forschungsgesellschaft Kraftfahrwesen mbh Aachen Steinbachstr Aachen Germany Phone Fax Internet kuefen@fka.de Slide No. 22

23 Engineering for the Future of Automotive

Automated Driving Necessary Infrastructure Shift

Automated Driving Necessary Infrastructure Shift DEVELOPMENT DRIVER ASSISTANCE SYSTEMS Automated Driving Necessary Infrastructure Shift The current driver assistance functions such as automated parking or traffic jam assistants and lane departure warning

More information

Designing a software framework for automated driving. Dr.-Ing. Sebastian Ohl, 2017 October 12 th

Designing a software framework for automated driving. Dr.-Ing. Sebastian Ohl, 2017 October 12 th Designing a software framework for automated driving Dr.-Ing. Sebastian Ohl, 2017 October 12 th Challenges Functional software architecture with open interfaces and a set of well-defined software components

More information

Towards Fully-automated Driving. tue-mps.org. Challenges and Potential Solutions. Dr. Gijs Dubbelman Mobile Perception Systems EE-SPS/VCA

Towards Fully-automated Driving. tue-mps.org. Challenges and Potential Solutions. Dr. Gijs Dubbelman Mobile Perception Systems EE-SPS/VCA Towards Fully-automated Driving Challenges and Potential Solutions Dr. Gijs Dubbelman Mobile Perception Systems EE-SPS/VCA Mobile Perception Systems 6 PhDs, 1 postdoc, 1 project manager, 2 software engineers

More information

Securing Automated Driving - The Database Approach in PEGASUS

Securing Automated Driving - The Database Approach in PEGASUS Day 1, Session: Vehicle Validation/Certification Roadworthiness Testing Securing Automated Driving - The Database Approach in PEGASUS Dr.-Ing. Adrian Zlocki Senior Manager Driver Assistance fka, Germany

More information

Arccore AB 2017, all rights reserved. Accelerating innovation

Arccore AB 2017, all rights reserved. Accelerating innovation 2017-03-02 Arccore AB 2017, all rights reserved Accelerating innovation ARCCORE in brief Independent vendor of automotive-sw with focus on AUTOSAR Integration, adaptation and service Incorporated 2009

More information

How Microcontrollers help GPUs in Autonomous Drive

How Microcontrollers help GPUs in Autonomous Drive How Microcontrollers help GPUs in Autonomous Drive GTC 2017 Munich, 2017-10-12 Hans Adlkofer, VP Automotive System department Outline 1 Main Safety concepts 2 Sensor Fusion architecture and functionalities

More information

W4. Perception & Situation Awareness & Decision making

W4. Perception & Situation Awareness & Decision making W4. Perception & Situation Awareness & Decision making Robot Perception for Dynamic environments: Outline & DP-Grids concept Dynamic Probabilistic Grids Bayesian Occupancy Filter concept Dynamic Probabilistic

More information

5GIC update 5G Test Beds & Trials event 21 st June 2017 NE LEP

5GIC update 5G Test Beds & Trials event 21 st June 2017 NE LEP 5G INNOVATION CENTRE The 5G Innovation Centre (5GIC) at the University of Surrey is now the largest UK academic research centre dedicated to the development of the next generation of mobile and wireless

More information

Failure Diagnosis and Prognosis for Automotive Systems. Tom Fuhrman General Motors R&D IFIP Workshop June 25-27, 2010

Failure Diagnosis and Prognosis for Automotive Systems. Tom Fuhrman General Motors R&D IFIP Workshop June 25-27, 2010 Failure Diagnosis and Prognosis for Automotive Systems Tom Fuhrman General Motors R&D IFIP Workshop June 25-27, 2010 Automotive Challenges and Goals Driver Challenges Goals Energy Rising cost of petroleum

More information

Developing Algorithms for Robotics and Autonomous Systems

Developing Algorithms for Robotics and Autonomous Systems Developing Algorithms for Robotics and Autonomous Systems Jorik Caljouw 2015 The MathWorks, Inc. 1 Key Takeaway of this Talk Success in developing an autonomous robotics system requires: 1. Multi-domain

More information

Driving virtual Prototyping of Automotive Electronics

Driving virtual Prototyping of Automotive Electronics Driving virtual Prototyping of Electronics B. Hellenthal, AUDI AG, Competence Center Electronics & Semiconductor, DVCon, Munich, October 17 th, 2017 Project Idea More space for passengers enabled by decreasing

More information

Mobile Robots: An Introduction.

Mobile Robots: An Introduction. Mobile Robots: An Introduction Amirkabir University of Technology Computer Engineering & Information Technology Department http://ce.aut.ac.ir/~shiry/lecture/robotics-2004/robotics04.html Introduction

More information

Autonomous Driving From Fail-Safe to Fail-Operational Systems

Autonomous Driving From Fail-Safe to Fail-Operational Systems Autonomous Driving From Fail-Safe to Fail-Operational Systems Rudolf Grave December 3, 2015 Agenda About EB Automotive Autonomous Driving Requirements for a future car infrastructure Concepts for fail-operational

More information

Realtime Object Detection and Segmentation for HD Mapping

Realtime Object Detection and Segmentation for HD Mapping Realtime Object Detection and Segmentation for HD Mapping William Raveane Lead AI Engineer Bahram Yoosefizonooz Technical Director NavInfo Europe Advanced Research Lab Presented at GTC Europe 2018 AI in

More information

Design your autonomous vehicle applications with NVIDIA DriveWorks components on RTMaps

Design your autonomous vehicle applications with NVIDIA DriveWorks components on RTMaps SAN JOSE MAY 8-11, 2017 Design your autonomous vehicle applications with NVIDIA DriveWorks components on RTMaps Nicolas du Lac CEO, Intempora Brief introduction about Intempora Intempora Software editor

More information

Software Architecture. Lecture 4

Software Architecture. Lecture 4 Software Architecture Lecture 4 Last time We discussed tactics to achieve architecture qualities We briefly surveyed architectural styles 23-Jan-08 http://www.users.abo.fi/lpetre/sa08/ 2 Today We check

More information

Final Exam Practice Fall Semester, 2012

Final Exam Practice Fall Semester, 2012 COS 495 - Autonomous Robot Navigation Final Exam Practice Fall Semester, 2012 Duration: Total Marks: 70 Closed Book 2 hours Start Time: End Time: By signing this exam, I agree to the honor code Name: Signature:

More information

Robotic Behaviors. Potential Field Methods

Robotic Behaviors. Potential Field Methods Robotic Behaviors Potential field techniques - trajectory generation - closed feedback-loop control Design of variety of behaviors - motivated by potential field based approach steering behaviors Closed

More information

Spring 2010: Lecture 9. Ashutosh Saxena. Ashutosh Saxena

Spring 2010: Lecture 9. Ashutosh Saxena. Ashutosh Saxena CS 4758/6758: Robot Learning Spring 2010: Lecture 9 Why planning and control? Video Typical Architecture Planning 0.1 Hz Control 50 Hz Does it apply to all robots and all scenarios? Previous Lecture: Potential

More information

Handling Challenges of Multi-Core Technology in Automotive Software Engineering

Handling Challenges of Multi-Core Technology in Automotive Software Engineering Model Based Development Tools for Embedded Multi-Core Systems Handling Challenges of Multi-Core Technology in Automotive Software Engineering VECTOR INDIA CONFERENCE 2017 Timing-Architects Embedded Systems

More information

DEEP NEURAL NETWORKS CHANGING THE AUTONOMOUS VEHICLE LANDSCAPE. Dennis Lui August 2017

DEEP NEURAL NETWORKS CHANGING THE AUTONOMOUS VEHICLE LANDSCAPE. Dennis Lui August 2017 DEEP NEURAL NETWORKS CHANGING THE AUTONOMOUS VEHICLE LANDSCAPE Dennis Lui August 2017 THE RISE OF GPU COMPUTING APPLICATIONS 10 7 10 6 GPU-Computing perf 1.5X per year 1000X by 2025 ALGORITHMS 10 5 1.1X

More information

Path Planning. Marcello Restelli. Dipartimento di Elettronica e Informazione Politecnico di Milano tel:

Path Planning. Marcello Restelli. Dipartimento di Elettronica e Informazione Politecnico di Milano   tel: Marcello Restelli Dipartimento di Elettronica e Informazione Politecnico di Milano email: restelli@elet.polimi.it tel: 02 2399 3470 Path Planning Robotica for Computer Engineering students A.A. 2006/2007

More information

Modelling and verification of cyber-physical system

Modelling and verification of cyber-physical system Modelling and verification of cyber-physical system Michal Pluska, David Sinclair LERO @ DCU Dublin City University School of Computing Dublin 9, Ireland michal.pluska@computing.dcu.ie Abstract * Embedded

More information

Turning an Automated System into an Autonomous system using Model-Based Design Autonomous Tech Conference 2018

Turning an Automated System into an Autonomous system using Model-Based Design Autonomous Tech Conference 2018 Turning an Automated System into an Autonomous system using Model-Based Design Autonomous Tech Conference 2018 Asaf Moses Systematics Ltd., Technical Product Manager aviasafm@systematics.co.il 1 Autonomous

More information

The Safe State: Design Patterns and Degradation Mechanisms for Fail- Operational Systems

The Safe State: Design Patterns and Degradation Mechanisms for Fail- Operational Systems The Safe State: Design Patterns and Degradation Mechanisms for Fail- Operational Systems Alexander Much 2015-11-11 Agenda About EB Automotive Motivation Comparison of different architectures Concept for

More information

CSE 490R P3 - Model Learning and MPPI Due date: Sunday, Feb 28-11:59 PM

CSE 490R P3 - Model Learning and MPPI Due date: Sunday, Feb 28-11:59 PM CSE 490R P3 - Model Learning and MPPI Due date: Sunday, Feb 28-11:59 PM 1 Introduction In this homework, we revisit the concept of local control for robot navigation, as well as integrate our local controller

More information

Architecting for autonomy

Architecting for autonomy Architecting for autonomy Exploring the landscape Sagar Behere 14 January 2014 Kungliga Tekniska Högskolan Architecting for autonomy 1 / 29 Contents 1 Background: Intelligence and autonomy 2 Architecture

More information

Automated Driving Development

Automated Driving Development Automated Driving Development with MATLAB and Simulink MANOHAR REDDY M 2015 The MathWorks, Inc. 1 Using Model-Based Design to develop high quality and reliable Active Safety & Automated Driving Systems

More information

Taking the Right Turn with Safe and Modular Solutions for the Automotive Industry

Taking the Right Turn with Safe and Modular Solutions for the Automotive Industry Taking the Right Turn with Safe and Modular Solutions for the Automotive Industry A Time-Triggered Middleware for Safety- Critical Automotive Applications Ayhan Mehmet, Maximilian Rosenblattl, Wilfried

More information

Parametric Sensitivity Analysis of NLP Problems and its Applications to Real-Time Controller Design

Parametric Sensitivity Analysis of NLP Problems and its Applications to Real-Time Controller Design SADCO - Sensitivity Analysis for Deterministic Controller Design Parametric Sensitivity Analysis of NLP Problems and its Applications to Real-Time Controller Design Part 1: Nonlinear Real-Time Optimization

More information

Advanced Driver Assistance: Modular Image Sensor Concept

Advanced Driver Assistance: Modular Image Sensor Concept Vision Advanced Driver Assistance: Modular Image Sensor Concept Supplying value. Integrated Passive and Active Safety Systems Active Safety Passive Safety Scope Reduction of accident probability Get ready

More information

High-Performance Real-Time Lab (HiPeRT) Marko Bertogna University of Modena, Italy

High-Performance Real-Time Lab (HiPeRT) Marko Bertogna University of Modena, Italy High-Performance Real-Time Lab (HiPeRT) Marko Bertogna University of Modena, Italy marko.bertogna@unimore.it http://hipert.unimore.it/ HiPeRT Lab Research on High-Performance Real-Time Systems ~20 people

More information

Autonomous Driving Solutions

Autonomous Driving Solutions Autonomous Driving Solutions Oct, 2017 DrivePX2 & DriveWorks Marcus Oh (moh@nvidia.com) Sr. Solution Architect, NVIDIA This work is licensed under a Creative Commons Attribution-Share Alike 4.0 (CC BY-SA

More information

Industry 4.0 & Transport for Digital Infrastructure

Industry 4.0 & Transport for Digital Infrastructure Industry 4.0 for Digital Infrastructure u Vehicle to Anything Connectivity (V2X) ICT changes Transport Automotive World IT World V2I IVN-Sensor X-by-Wire, MOST, CDMA, DSRC, WLAN,.. RSU Distance Sens. Multi

More information

On Board 6D Visual Sensors for Intersection Driving Assistance Systems

On Board 6D Visual Sensors for Intersection Driving Assistance Systems On Board 6D Visual Sensors for Intersection Driving Assistance Systems S. Nedevschi, T. Marita, R. Danescu, F. Oniga, S. Bota, I. Haller, C. Pantilie, M. Drulea, C. Golban Sergiu.Nedevschi@cs.utcluj.ro

More information

A Pattern-supported Parallelization Approach

A Pattern-supported Parallelization Approach A Pattern-supported Parallelization Approach Ralf Jahr, Mike Gerdes, Theo Ungerer University of Augsburg, Germany The 2013 International Workshop on Programming Models and Applications for Multicores and

More information

Advanced Robotics Path Planning & Navigation

Advanced Robotics Path Planning & Navigation Advanced Robotics Path Planning & Navigation 1 Agenda Motivation Basic Definitions Configuration Space Global Planning Local Planning Obstacle Avoidance ROS Navigation Stack 2 Literature Choset, Lynch,

More information

T6: Position-Based Simulation Methods in Computer Graphics. Jan Bender Miles Macklin Matthias Müller

T6: Position-Based Simulation Methods in Computer Graphics. Jan Bender Miles Macklin Matthias Müller T6: Position-Based Simulation Methods in Computer Graphics Jan Bender Miles Macklin Matthias Müller Jan Bender Organizer Professor at the Visual Computing Institute at Aachen University Research topics

More information

10 th AUTOSAR Open Conference

10 th AUTOSAR Open Conference 10 th AUTOSAR Open Conference Nadym Salem, Jan Hegewald Carmeq GmbH Dealing with the Challenges for Future Software Systems in the Automotive Industry with the AUTOSAR Standards AUTOSAR Nov-2017 Dealing

More information

Learning Driving Styles for Autonomous Vehicles for Demonstration

Learning Driving Styles for Autonomous Vehicles for Demonstration Learning Driving Styles for Autonomous Vehicles for Demonstration Markus Kuderer, Shilpa Gulati, Wolfram Burgard Presented by: Marko Ilievski Agenda 1. Problem definition 2. Background a. Important vocabulary

More information

PREEvision Technical Article

PREEvision Technical Article PREEvision Technical Article E/E Development for Future Vehicle Innovations: An Integrated, Model-based Approach The development of modern electric/electronic (E/E) architectures is a challenge today more

More information

MESO & HYBRID MODELING IN

MESO & HYBRID MODELING IN MESO & HYBRID MODELING IN www.ptvgroup.com JONGSUN WON, P.E. www.ptvgroup.com I Slide 1 SOMETHING NEW WITH PTV NORTH AMERICA Portland, OR Arlington, VA www.ptvgroup.com I Slide 2 MULTIRESOLUTION MODELING

More information

Figure Potential 5G applications

Figure Potential 5G applications 6. 5G Key Concept 6.1 Key Concepts of 5G End-to-end (E2E) quality required by applications and/or users will be far more diversified in the 5G era than what we have seen in the preceding generations. For

More information

Robotics: Science and Systems

Robotics: Science and Systems Robotics: Science and Systems Model Predictive Control (MPC) Zhibin Li School of Informatics University of Edinburgh Content Concepts of MPC MPC formulation Objective function and constraints Solving the

More information

Communication Patterns in Safety Critical Systems for ADAS & Autonomous Vehicles Thorsten Wilmer Tech AD Berlin, 5. March 2018

Communication Patterns in Safety Critical Systems for ADAS & Autonomous Vehicles Thorsten Wilmer Tech AD Berlin, 5. March 2018 Communication Patterns in Safety Critical Systems for ADAS & Autonomous Vehicles Thorsten Wilmer Tech AD Berlin, 5. March 2018 Agenda Motivation Introduction of Safety Components Introduction to ARMv8

More information

Designing GPU-accelerated applications with RTMaps (Real-Time Multisensor Applications) Framework and NVIDIA DriveWorks

Designing GPU-accelerated applications with RTMaps (Real-Time Multisensor Applications) Framework and NVIDIA DriveWorks MUNICH OCT 10-12, 2017 Designing GPU-accelerated applications with RTMaps (Real-Time Multisensor Applications) Framework and NVIDIA DriveWorks Xavier Rouah Lead Software Engineer Brief introduction about

More information

Agent controlled traffic lights

Agent controlled traffic lights Agent controlled traffic lights Danko A. Roozemond *, Jan L.H. Rogier ** * Delft University of Technology, Civil Engineering and Geosciences Stevinweg 1, 2628 CN, Delft, The Netherlands Phone: +31(0)15

More information

Creating Affordable and Reliable Autonomous Vehicle Systems

Creating Affordable and Reliable Autonomous Vehicle Systems Creating Affordable and Reliable Autonomous Vehicle Systems Shaoshan Liu shaoshan.liu@perceptin.io Autonomous Driving Localization Most crucial task of autonomous driving Solutions: GNSS but withvariations,

More information

What s inside: What is deep learning Why is deep learning taking off now? Multiple applications How to implement a system.

What s inside: What is deep learning Why is deep learning taking off now? Multiple applications How to implement a system. Point Grey White Paper Series What s inside: What is deep learning Why is deep learning taking off now? Multiple applications How to implement a system More and more, machine vision systems are expected

More information

Can We Improve Autonomous Driving With IoT and Cloud?

Can We Improve Autonomous Driving With IoT and Cloud? Data Center Modernization Title Slide Can We Improve Autonomous Driving With IoT and Cloud?! Subtitle! Name! Title, Department! Date Subrata Kundu, Ph.D. Senior Researcher & Team Leader R&D Division, Hitachi

More information

This project has received funding from the European Union s Horizon 2020 research and innovation programme under grant agreement No

This project has received funding from the European Union s Horizon 2020 research and innovation programme under grant agreement No This project has received funding from the European Union s Horizon 2020 research and innovation programme under grant agreement No 643921. TOOLS INTEGRATION UnCoVerCPS toolchain Goran Frehse, UGA Xavier

More information

Approximating Maximum Speed on Road from Curvature Information of Bezier Curve

Approximating Maximum Speed on Road from Curvature Information of Bezier Curve Approximating Maximum Speed on Road from Curvature Information of Bezier Curve M. Y. Misro, A. Ramli, J. M. Ali Abstract Bezier curves have useful properties for path generation problem, for instance,

More information

Computational Fluid Dynamics and Interactive Visualisation

Computational Fluid Dynamics and Interactive Visualisation Computational Fluid Dynamics and Interactive Visualisation Ralf-Peter Mundani 1, Jérôme Frisch 2 1 Computation in Engineering, TUM 2 E3D, RWTH Aachen University Interdisciplinary Cluster Workshop on Visualization

More information

PULSE Indoor Pass-by and Exterior Noise Contribution Analysis System

PULSE Indoor Pass-by and Exterior Noise Contribution Analysis System APPLICATION NOTE PULSE Indoor Pass-by and Exterior Noise Contribution Analysis System A pass-by noise measurement is defined as the method of measuring the noise emission of a road vehicle under acceleration

More information

Combining Deep Reinforcement Learning and Safety Based Control for Autonomous Driving

Combining Deep Reinforcement Learning and Safety Based Control for Autonomous Driving Combining Deep Reinforcement Learning and Safety Based Control for Autonomous Driving Xi Xiong Jianqiang Wang Fang Zhang Keqiang Li State Key Laboratory of Automotive Safety and Energy, Tsinghua University

More information

Robot Motion Planning

Robot Motion Planning Robot Motion Planning James Bruce Computer Science Department Carnegie Mellon University April 7, 2004 Agent Planning An agent is a situated entity which can choose and execute actions within in an environment.

More information

Safety and Security for Automotive using Microkernel Technology

Safety and Security for Automotive using Microkernel Technology Informationstag "Das Automobil als IT-Sicherheitsfall" Berlin, 11.05.2012 Safety and Security for Automotive using Microkernel Technology Dr.-Ing. Matthias Gerlach OpenSynergy TwoBirds withonestone Safety

More information

5G As A User-Centric Network. Xiao-Feng Qi

5G As A User-Centric Network. Xiao-Feng Qi 5G As A User-Centric Network Xiao-Feng Qi Contents 5G at Huawei 5G Vision and Viewpoints A User-Centric View Huawei Began 5G Research since 2009 $600m For 5G Research 300+ Experts 9 Research Centers 2013~2018

More information

Three-Dimensional Off-Line Path Planning for Unmanned Aerial Vehicle Using Modified Particle Swarm Optimization

Three-Dimensional Off-Line Path Planning for Unmanned Aerial Vehicle Using Modified Particle Swarm Optimization Three-Dimensional Off-Line Path Planning for Unmanned Aerial Vehicle Using Modified Particle Swarm Optimization Lana Dalawr Jalal Abstract This paper addresses the problem of offline path planning for

More information

Visual Perception for Autonomous Driving on the NVIDIA DrivePX2 and using SYNTHIA

Visual Perception for Autonomous Driving on the NVIDIA DrivePX2 and using SYNTHIA Visual Perception for Autonomous Driving on the NVIDIA DrivePX2 and using SYNTHIA Dr. Juan C. Moure Dr. Antonio Espinosa http://grupsderecerca.uab.cat/hpca4se/en/content/gpu http://adas.cvc.uab.es/elektra/

More information

PRISMA Lab. Napoli, 24 October 2008

PRISMA Lab.     Napoli, 24 October 2008 First workshop for young researchers on Human-friendly robotics Modelling and control for Human-Robot Interaction ti Agostino DE SANTIS PRISMA Lab Università degli Studi di Napoli Federico II agodesa@unina.it

More information

Dynamic facial expression recognition using a behavioural model

Dynamic facial expression recognition using a behavioural model Dynamic facial expression recognition using a behavioural model Thomas Robin Michel Bierlaire Javier Cruz STRC 2009 10th september The context Recent interest for emotion recognition in transportation

More information

Applying AI to Mapping

Applying AI to Mapping Applying AI to Mapping Dr. Ryan Wolcott Manager, Simultaneous Localization and Mapping (SLAM) 1 TRI: Who We Are Our mission is to improve the quality of human life through advances in artificial intelligence,

More information

PREEvision Technical Article

PREEvision Technical Article PREEvision Technical Article AUTOSAR-Conformant Vehicle Diagnostics over : Developing Diagnostic Communications for E/E Systems The electronically controlled systems of modern vehicles are networked with

More information

Functional Safety on Multicore Microcontrollers for Industrial Applications. Thomas Barth (h-da) Prof. Dr.-Ing. Peter Fromm (h-da)

Functional Safety on Multicore Microcontrollers for Industrial Applications. Thomas Barth (h-da) Prof. Dr.-Ing. Peter Fromm (h-da) Functional Safety on Multicore Microcontrollers for Industrial Applications Thomas Barth (h-da) Prof. Dr.-Ing. Peter Fromm (h-da) Contents Functional Safety Multicore Motivation ISO13849 Implemented Software

More information

Intel and Mobileye Autonomous Driving Solutions

Intel and Mobileye Autonomous Driving Solutions Product Brief Autonomous Driving Intel and Mobileye Autonomous Driving Solutions Together, Mobileye and Intel deliver scalable and versatile solutions using purpose-built software and efficient, powerful

More information

elektronik Security for Software and IT ECU ENERGY STORAGE TESTING COVER STORY Gasoline Direct Injection in-the-loop

elektronik Security for Software and IT ECU ENERGY STORAGE TESTING COVER STORY Gasoline Direct Injection in-the-loop www.atzonline.com 03 May 2015 Volume 10 elektronik W O R L D W I D E COVER STORY Security for Software and IT ECU Gasoline Direct Injection in-the-loop TESTING Tablets in Mobile Measurement Technique ENERGY

More information

Autonomous Mobile Robots, Chapter 6 Planning and Navigation Where am I going? How do I get there? Localization. Cognition. Real World Environment

Autonomous Mobile Robots, Chapter 6 Planning and Navigation Where am I going? How do I get there? Localization. Cognition. Real World Environment Planning and Navigation Where am I going? How do I get there?? Localization "Position" Global Map Cognition Environment Model Local Map Perception Real World Environment Path Motion Control Competencies

More information

Accurate Thermo-Fluid Simulation in Real Time Environments. Silvia Poles, Alberto Deponti, EnginSoft S.p.A. Frank Rhodes, Mentor Graphics

Accurate Thermo-Fluid Simulation in Real Time Environments. Silvia Poles, Alberto Deponti, EnginSoft S.p.A. Frank Rhodes, Mentor Graphics Accurate Thermo-Fluid Simulation in Real Time Environments Silvia Poles, Alberto Deponti, EnginSoft S.p.A. Frank Rhodes, Mentor Graphics M e c h a n i c a l a n a l y s i s W h i t e P a p e r w w w. m

More information

Riccardo Mariani, Intel Fellow, IOTG SEG, Chief Functional Safety Technologist

Riccardo Mariani, Intel Fellow, IOTG SEG, Chief Functional Safety Technologist Riccardo Mariani, Intel Fellow, IOTG SEG, Chief Functional Safety Technologist Internet of Things Group 2 Internet of Things Group 3 Autonomous systems: computing platform Intelligent eyes Vision. Intelligent

More information

Partially Observable Markov Decision Processes. Mausam (slides by Dieter Fox)

Partially Observable Markov Decision Processes. Mausam (slides by Dieter Fox) Partially Observable Markov Decision Processes Mausam (slides by Dieter Fox) Stochastic Planning: MDPs Static Environment Fully Observable Perfect What action next? Stochastic Instantaneous Percepts Actions

More information

Ingress Policing in Automotive Systems. Soheil Samii, General Motors R&D Johannes Specht, Univ. of Duisburg-Essen

Ingress Policing in Automotive Systems. Soheil Samii, General Motors R&D Johannes Specht, Univ. of Duisburg-Essen Ingress Policing in Automotive ystems oheil amii, General Motors R&D Johannes pecht, Univ. of Duisburg-Essen Ethernet in Automotive ystems Automotive Ethernet will grow Advanced Driver Assistance ystems

More information

A Tutorial on Runtime Verification and Assurance. Ankush Desai EECS 219C

A Tutorial on Runtime Verification and Assurance. Ankush Desai EECS 219C A Tutorial on Runtime Verification and Assurance Ankush Desai EECS 219C Outline 1. Background on Runtime Verification 2. Challenges in Programming Robotics System Drona). 3. Solution 1: Combining Model

More information

Alma Mater Studiorum University of Bologna CdS Laurea Magistrale (MSc) in Computer Science Engineering

Alma Mater Studiorum University of Bologna CdS Laurea Magistrale (MSc) in Computer Science Engineering Mobile Systems M Alma Mater Studiorum University of Bologna CdS Laurea Magistrale (MSc) in Computer Science Engineering Mobile Systems M course (8 ECTS) II Term Academic Year 2016/2017 08 Application Domains

More information

Deutsche Bahn AG Digital Rail (IDX)

Deutsche Bahn AG Digital Rail (IDX) Deutsche Bahn s Digital Rail Vision and its Implications on the Future Radio for Rail Transport Dr. Patrick Marsch ETSI Workshop on Developing the Future Radio for Rail Transport, July 5th, 2018 The Envisioned

More information

EE631 Cooperating Autonomous Mobile Robots

EE631 Cooperating Autonomous Mobile Robots EE631 Cooperating Autonomous Mobile Robots Lecture 3: Path Planning Algorithm Prof. Yi Guo ECE Dept. Plan Representing the Space Path Planning Methods A* Search Algorithm D* Search Algorithm Representing

More information

Timing Analysis on Complex Real-Time Automotive Multicore Architectures

Timing Analysis on Complex Real-Time Automotive Multicore Architectures 2 nd Workshop on Mapping Applications to MPSoCs St. Goar, June 2009 Timing Analysis on Complex Real-Time Automotive Multicore Architectures Mircea Negrean Simon Schliecker Rolf Ernst Technische Universität

More information

Customized Switches for the Harshest Conditions

Customized Switches for the Harshest Conditions Customized Switches for the Harshest Conditions The extremely robust design of IP67/54 OCTOPUS switches from Hirschmann ensures fail-safe data communication even under severe stress in the most demanding

More information

S CUDA on Xavier

S CUDA on Xavier S8868 - CUDA on Xavier Anshuman Bhat CUDA Product Manager Saikat Dasadhikari CUDA Engineering 29 th March 2018 1 CUDA ECOSYSTEM 2018 CUDA DOWNLOADS IN 2017 3,500,000 CUDA REGISTERED DEVELOPERS 800,000

More information

NVIDIA AI BRAIN OF SELF DRIVING AND HD MAPPING. September 13, 2016

NVIDIA AI BRAIN OF SELF DRIVING AND HD MAPPING. September 13, 2016 NVIDIA AI BRAIN OF SELF DRIVING AND HD MAPPING September 13, 2016 AI FOR AUTONOMOUS DRIVING MAPPING KALDI LOCALIZATION DRIVENET Training on DGX-1 NVIDIA DGX-1 NVIDIA DRIVE PX 2 Driving with DriveWorks

More information

An Encapsulated Communication System for Integrated Architectures

An Encapsulated Communication System for Integrated Architectures An Encapsulated Communication System for Integrated Architectures Architectural Support for Temporal Composability Roman Obermaisser Overview Introduction Federated and Integrated Architectures DECOS Architecture

More information

Networked Cyber-Physical Systems

Networked Cyber-Physical Systems Networked Cyber-Physical Systems Dr.ir. Tamás Keviczky Delft Center for Systems and Control Delft University of Technology The Netherlands t.keviczky@tudelft.nl http://www.dcsc.tudelft.nl/~tkeviczky/ September

More information

Humanoid Robotics. Path Planning and Walking. Maren Bennewitz

Humanoid Robotics. Path Planning and Walking. Maren Bennewitz Humanoid Robotics Path Planning and Walking Maren Bennewitz 1 Introduction Given the robot s pose in a model of the environment Compute a path to a target location First: 2D path in a 2D grid map representation

More information

Aerial Robotic Autonomous Exploration & Mapping in Degraded Visual Environments. Kostas Alexis Autonomous Robots Lab, University of Nevada, Reno

Aerial Robotic Autonomous Exploration & Mapping in Degraded Visual Environments. Kostas Alexis Autonomous Robots Lab, University of Nevada, Reno Aerial Robotic Autonomous Exploration & Mapping in Degraded Visual Environments Kostas Alexis Autonomous Robots Lab, University of Nevada, Reno Motivation Aerial robotic operation in GPS-denied Degraded

More information

Vision based autonomous driving - A survey of recent methods. -Tejus Gupta

Vision based autonomous driving - A survey of recent methods. -Tejus Gupta Vision based autonomous driving - A survey of recent methods -Tejus Gupta Presently, there are three major paradigms for vision based autonomous driving: Directly map input image to driving action using

More information

Vehicle Trust Management for Connected Vehicles

Vehicle Trust Management for Connected Vehicles Vehicle Trust Management for Connected Vehicles FINAL RESEARCH REPORT Insup Lee (PI), Nicola Bezzo, Jian Chang Contract No. DTRT12GUTG11 DISCLAIMER The contents of this report reflect the views of the

More information

Future Grid Initiative Technology Challenges in Designing the Future Grid to Enable Sustainable Energy Systems

Future Grid Initiative Technology Challenges in Designing the Future Grid to Enable Sustainable Energy Systems Future Grid Initiative Technology Challenges in Designing the Future Grid to Enable Sustainable Energy Systems Vijay Vittal Director, Power Systems Engineering Research Center Ira A. Fulton Chair Professor,

More information

SHRP 2 Safety Research Symposium July 27, Site-Based Video System Design and Development: Research Plans and Issues

SHRP 2 Safety Research Symposium July 27, Site-Based Video System Design and Development: Research Plans and Issues SHRP 2 Safety Research Symposium July 27, 2007 Site-Based Video System Design and Development: Research Plans and Issues S09 Objectives Support SHRP2 program research questions: Establish crash surrogates

More information

Roadmaps. Vertex Visibility Graph. Reduced visibility graph, i.e., not including segments that extend into obstacles on either side.

Roadmaps. Vertex Visibility Graph. Reduced visibility graph, i.e., not including segments that extend into obstacles on either side. Roadmaps Vertex Visibility Graph Full visibility graph Reduced visibility graph, i.e., not including segments that extend into obstacles on either side. (but keeping endpoints roads) what else might we

More information

AUTONOMOUS NAVIGATION: MUNIN UNMANNED VESSEL TEST-BED

AUTONOMOUS NAVIGATION: MUNIN UNMANNED VESSEL TEST-BED AUTONOMOUS NAVIGATION: MUNIN UNMANNED VESSEL TEST-BED Dipl.-Wirtsch.-Ing. Univ. Hans-Christoph Burmeister 25.09.2015 The Nautical Insitute, Maritime Excellence Programme AGENDA 1. MUNIN Overview 2. MUNIN

More information

Automotive and Aerospace Synergies

Automotive and Aerospace Synergies Corporate Technical Office Automotive and Aerospace Synergies Potential for common activities Denis Chapuis, EADS Corporate Technical Office, Electronics denis.chapuis@eads.net Seite 1 Presentation title

More information

Energy Aware Dynamic Data Driven Distributed Traffic Simulations

Energy Aware Dynamic Data Driven Distributed Traffic Simulations Energy Aware Dynamic Data Driven Distributed Traffic Simulations Michael Hunter, Bhargava Chilukuri, Randall Guensler, Haobing Liu, Michael Rodgers School of Civil & Environmental Engineering Richard Fujimoto,

More information

ECE276B: Planning & Learning in Robotics Lecture 5: Configuration Space

ECE276B: Planning & Learning in Robotics Lecture 5: Configuration Space ECE276B: Planning & Learning in Robotics Lecture 5: Configuration Space Lecturer: Nikolay Atanasov: natanasov@ucsd.edu Teaching Assistants: Tianyu Wang: tiw161@eng.ucsd.edu Yongxi Lu: yol070@eng.ucsd.edu

More information

!"#$"%"& When can a UAV get smart with its operator, and say 'NO!'? Jerry Ding**, Jonathan Sprinkle*, Claire J. Tomlin**, S.

!#$%& When can a UAV get smart with its operator, and say 'NO!'? Jerry Ding**, Jonathan Sprinkle*, Claire J. Tomlin**, S. Arizona s First University. When can a UAV get smart with its operator, and say 'NO!'? Jerry Ding**, Jonathan Sprinkle*, Claire J. Tomlin**, S. Shankar Sastry**!"#$"%"&!"#"$"%"&"'"("$")"*""+",""-"."/"$","+"'"#"$".!"#"$"%"&"'"("$")"*""+",""-"."/"$","+"'"#"$".

More information

REINFORCEMENT LEARNING: MDP APPLIED TO AUTONOMOUS NAVIGATION

REINFORCEMENT LEARNING: MDP APPLIED TO AUTONOMOUS NAVIGATION REINFORCEMENT LEARNING: MDP APPLIED TO AUTONOMOUS NAVIGATION ABSTRACT Mark A. Mueller Georgia Institute of Technology, Computer Science, Atlanta, GA USA The problem of autonomous vehicle navigation between

More information

Cooperation in the field of Automated and connected driving. In view of the Dutch presidency of the European Union

Cooperation in the field of Automated and connected driving. In view of the Dutch presidency of the European Union Cooperation in the field of Automated and connected driving In view of the Dutch presidency of the European Union 15 September2015 Frans op de Beek Ministry of Infrastructure and the Environment Rijkswaterstaat

More information

Systems Architecting Approach for Complex Ecosystems

Systems Architecting Approach for Complex Ecosystems Architecting a complex world Systems Architecting Approach for Complex Ecosystems Daniel KROB CESAMES & Ecole Polytechnique INCOSE Fellow CSD&M ASIA 016 February 016 0 CESAMES at a glance Issued from :

More information

A Longitudinal Control Algorithm for Smart Cruise Control with Virtual Parameters

A Longitudinal Control Algorithm for Smart Cruise Control with Virtual Parameters ISSN (e): 2250 3005 Volume, 06 Issue, 12 December 2016 International Journal of Computational Engineering Research (IJCER) A Longitudinal Control Algorithm for Smart Cruise Control with Virtual Parameters

More information

EE631 Cooperating Autonomous Mobile Robots

EE631 Cooperating Autonomous Mobile Robots EE631 Cooperating Autonomous Mobile Robots Lecture: Multi-Robot Motion Planning Prof. Yi Guo ECE Department Plan Introduction Premises and Problem Statement A Multi-Robot Motion Planning Algorithm Implementation

More information

GTC Interaction Simplified. Gesture Recognition Everywhere: Gesture Solutions on Tegra

GTC Interaction Simplified. Gesture Recognition Everywhere: Gesture Solutions on Tegra GTC 2013 Interaction Simplified Gesture Recognition Everywhere: Gesture Solutions on Tegra eyesight at a Glance Touch-free technology providing an enhanced user experience. Easy and intuitive control

More information