Technical Program

Day 1 — Monday 20 August 2018

8:30AM-9:00AM Coffee and Light Refreshments
9:00AM-9:30AM Welcome and Introduction
Alexander M. Wyglinski & Raghvendra V. Cowlagi, WPI
9:30AM-11:30AM Lecture 1
“Impact of Environmental Information on the Control of Self-Driving Cars”
R. V. Cowlagi, A. M. Wyglinski, R. Du, N. Kanthasamy (WPI)
11:30AM-12:30PM Lecture 2 (Part 1)
“Security and Privacy of Connected and Automated Vehicles”
J. Petit (OnBoard Security)
12:30PM-1:30PM Lunch (on your own)
1:30PM-2:30PM Lecture 2 (Part 2)
Security and Privacy of Connected and Automated Vehicles”
J. Petit (OnBoard Security)
2:30PM-3:15PM Networking Session / Coffee Break
3:15PM-5:15PM Lecture 3
“Visual Inertial Odometry using Neural Networks”
E. Yilmaz (Analog Devices)
5:15PM-5:30PM Day 1 Closing Remarks

 

Day 2 — Tuesday 21 August 2018

8:30AM-9:00AM Coffee and Light Refreshments
9:00AM-11:00AM Lecture 4
“Understanding Vehicular Wireless Access Using Bumblebee Behavioral Models”
A. M. Wyglinski, R. J. Gegear, E. F. Ryder, K. S. Gill, K. N. Heath
11:00AM-12:00PM Lecture 5 (Part 1)
“Vision Systems for Self-Driving Cars”
J. Nafziger (The MITRE Corporation)
12:00PM-1:00PM Lunch (on your own)
1:0PM-2:00PM Lecture 5 (Part 2)
“Vision Systems for Self-Driving Cars”
J. Nafziger (The MITRE Corporation)
2:00PM-4:00PM Lecture 6
“Multi-Sensor Data Fusion for Self-Driving Cars”
T. Wickramarathne (UMass Lowell)
4:00PM-4:30PM Networking Session / Coffee Break
4:30PM-5:30PM Presentation
“Optimus Ride – A Self-Driving Vehicle Company Based in Boston”
Ryan Chin (Optimus Ride), Sertac Karaman (Optimus Ride)
5:30PM-5:45PM Day 2 Closing Remarks

 


 

Lecture 1

Impact of Environmental Information on the Control of Self-Driving Cars

Vehicular autonomony, ranging from driver assistance to full self-driving autonomy, and vehicle-to-everything (V2X) wireless connectivity promises to revolutionize the safety, reliability, and energy-efficiency of future automotive transportation. Connected autonomous vehicles (CAVs) are cyber-physical systems with increasingly complex software algorithms in control of a physical vehicle moving in uncertain real-world environments. Planned connectivity regulations and recent advances in vehicular autonomy by leading manufacturers imply that CAVs will be ubiquitous in the near future. Roads will be data-rich environments where a large number of wireless devices attached to vehicles, infrastructure, personal electronics, and wearable gadgets will transmit multimodal data. Consequently, it is important to understand the de facto upper bound on the number of data sources that can be accommodated by the autonomy algorithms as well as the limitations of the surrounding wireless environment to support the multiple communication links between vehicles and nearby road-side infrastructure.  In this lecture, we will explore the intricate bidirectional interactions between the technologies of autonomy and of wireless connectivity in cyber-physical systems. Specifically, we will study how estimation and control algorithms affect – and are affected by – software-defined radio communications in spectrum-scarce, data-rich environments. In particular, we will study how to perform dynamic information selection and how it evolves with the trajectory plan.  This is based on the so-called method of lifted graphs, which promises to bridge the gap between fast geometric path planning algorithms and slower control-theoretic techniques that incorporate vehicle dynamical constraints. Furthermore, trajectory planning approaches presented in this lecture will be extended to other formulations and solutions of different application-specific planning problems.

Speaker Biographies

rvc-photoRaghvendra Cowlagi is an assistant professor in the Aerospace Engineering Program at Worcester Polytechnic Institute, Worcester, MA since 2013. Previously, he obtained a Ph.D. in Aerospace Engineering from Georgia Tech in 2011 (advisor: P. Tsiotras); worked as a postdoctoral researcher at MIT (sponsor: E. Frazzoli); and worked as a researcher at Aurora Flight Sciences Corp., Cambridge, MA. He is a recipient of the AFOSR Young Investigator award (2016), and the Student Best Paper award at the American Control Conference (2009). He serves as an associate editor on the IEEE Control Systems Society Conference Editorial Board, as an associate editor for the Aerospace Science & Technology journal, and is a member of the AIAA Guidance, Navigation, & Control Technical Committee.

awygAlexander M. Wyglinski received the B.Eng. degree from McGill University in 1999, the M.Sc. (Eng.) degree from Queen’s University, Kingston, Canada, in 2000, and the Ph.D. degree from McGill University in 2005, all in electrical engineering. He is currently a Professor of Electrical and Computer Engineering with the Worcester Polytechnic Institute, Worcester, MA, USA, where he was the Director of the Wireless Innovation Laboratory. He has authored over 40 journal papers, over 80 conference papers, nine book chapters, and three textbooks. His current research activities include wireless communications, cognitive radio, software-defined radio, dynamic spectrum access, spectrum measurement and characterization, electromagnetic security, wireless system optimization and adaptation, and cyber physical systems. He is currently being or has been sponsored by organizations, such as the Defense Advanced Research Projects Agency, the Naval Research Laboratory, the Office of Naval Research, the Air Force Research Laboratory-Space Vehicles Directorate, The MathWorks, the Toyota InfoTechnology Center U.S.A, Raytheon, the MITRE Corporation, the National Aeronautics and Space Administration, and the National Science Foundation. He was a member of Sigma Xi, Eta Kappa Nu, and the ASEE. He is currently the President of the IEEE Vehicular Technology Society.

duRuixiang Du is a PhD candidate in Mechanical Engineering at Worcester Polytechnic Institute (WPI) and working in the Autonomy, Control, and Estimation Laboratory (ACEL) under supervision of Professor Raghvendra V. Cowlagi. His general interests are in robotics, as well as real-time and embedded systems. His current research focus is on the sensing and motion planning of self-driving cars. Mr. Du received his Master’s degree in Robotics Engineering from WPI in May 2013. Mr. Du spent about one and a half years working on the DARPA Robotics Challenge as part of Team WPI-CMU, which ultimately ranked 7th out of 23 competing teams in the DRC Finals.

Nivetha Kanthasamy is a PhD candidate in Electrical and Computer Engineering at Worcester Polytechnic Institute (WPI) and working in the Wireless Innovation Laboratory (WILab) under supervision of Professor Alexander M. Wyglinski. She received her MS degree from California State University Fullerton, and her BS degree from Anna University in India. Her research interests are in software defined radio, signal processing for wireless communications, and cognitive radio.


Lecture 2

Security and Privacy of Connected and Automated Vehicles

Automated vehicles will be connected to other vehicles and infrastructure, offering numerous attack surfaces. In this talk, I will give an overview of the current solutions for security and privacy of connected and automated vehicles. Then, I will present some research results on pseudonym change, safety, sensor security, misbehavior detection. I will conclude the talk with a list of open research challenges, not only for the vehicle but also for the entire ecosystem.

Speaker Biography

petitJonathan Petit is the Senior Director of Research for OnBoard Security. He is in charge of leading projects in security and privacy of automated and connected vehicles. He has conducted extensive research in detecting security vulnerabilities in automotive systems. He published the first work on potential cyber attacks on automated vehicles and has supported communications security design and cybersecurity analysis through OEM and NHTSA-sponsored projects. He received his PhD in 2011 from Paul Sabatier University, Toulouse, France.

 


Lecture 3

Visual Inertial Odometry using Deep Learning

Accurately estimating the motion of an autonomous system is possible by fusing information from inertial, vision and ranging sensors. Traditional approaches using monocular camera suffer from scale ambiguity and drift, which can be remedied by addition of inertial information using standard filtering methods, thereby forming a visual inertial odometry (VIO) system. These systems require careful synchronization and calibration of sensors. Recent research employs deep learning for sensor fusion and demonstrates improvements over filtering methods. We discuss addition of ranging sensors like lidars and radars to further improve these results.

Speaker Biography

erdal2Erdal Yilmaz is a Systems Architect in Perception Ecosystem Team, part of Autonomous Transportation & Safety Business Unit at Analog Devices. He holds B.S. degrees in Electrical and Electronics Engineering and Physics from Bogazici University in Istanbul, Turkey, as well as M.S. and Ph.D. degrees in Applied Physics from Cornell University, and is currently studying Software Engineering at Harvard University. He has previous experience in robotics, experimental physics, and computational science and engineering. At Analog Devices, he worked on inertial micro-electro-mechanical systems design, simulation and optimization for automotive and industrial applications. He participated twice and is a silver medalist in International Physics Olympiads.


Lecture 4

Understanding Vehicular Wireless Access Using Bumblebee Behavioral Models

In this lecture, we explore how intelligent wireless medium access control can be used in order to support connected vehicle networks operating in dynamic environments. Vehicles forming connected communication networks are often challenged with the complex decision problem of either staying with the same wireless channel or moving to a different wireless channel when experiencing highly variable channel quality conditions. Consequently, approaches based on cognitive or intelligent decision-making algorithms, such as bumblebee behavioral models, can be leveraged in order to enable vehicles to adapt to these time-varying channel conditions.  Specifically, we will study how a bumblebee-inspired decision-making algorithm can be used to assess channel quality in vehicular communication environments, including how this environmental information is stored in memory.  We will also show how this information is used to estimate qualities of channel options and then weighed against switch costs to determine optimal channel selection. In order to highlight the benefits of intelligent wireless medium access control in vehicular communication networks, we will demonstrate the bumblebee behavioral model-based algorithm in a vehicular dynamic spectrum access (VDSA)-based vehicular ad hoc network (VANET) environment using the GEMV 2 Vehicle-to-Vehicle (V2V) propagation simulator across a range of different memory parameters and existing models.

Speaker Biographies

awygAlexander M. Wyglinski received the B.Eng. degree from McGill University in 1999, the M.Sc. (Eng.) degree from Queen’s University, Kingston, Canada, in 2000, and the Ph.D. degree from McGill University in 2005, all in electrical engineering. He is currently a Professor of Electrical and Computer Engineering with the Worcester Polytechnic Institute, Worcester, MA, USA, where he was the Director of the Wireless Innovation Laboratory. He has authored over 40 journal papers, over 80 conference papers, nine book chapters, and three textbooks. His current research activities include wireless communications, cognitive radio, software-defined radio, dynamic spectrum access, spectrum measurement and characterization, electromagnetic security, wireless system optimization and adaptation, and cyber physical systems. He is currently being or has been sponsored by organizations, such as the Defense Advanced Research Projects Agency, the Naval Research Laboratory, the Office of Naval Research, the Air Force Research Laboratory-Space Vehicles Directorate, The MathWorks, the Toyota InfoTechnology Center U.S.A, Raytheon, the MITRE Corporation, the National Aeronautics and Space Administration, and the National Science Foundation. He was a member of Sigma Xi, Eta Kappa Nu, and the ASEE. He is currently the President of the IEEE Vehicular Technology Society.

gegearRobert J. Gegear received the Ph.D. degree from the University of Western Ontario, London, ON, Canada, in 2002. After completing his Ph.D., he was an NSERC Post-Doctoral Fellow with the University of Toronto, and then a Research Assistant Professor with the University of Massachusetts Medical School, Worcester, MA, USA. Since 2010, he has been an Assistant Professor with the Department of Biology and Biotechnology, Worcester Polytechnic Institute, Worcester, MA, USA. His work is currently supported by two grants from the National Science Foundation. His current research interests include bumblebee neuroecology and conservation, multi-modal communication systems, animal navigational systems, and pollinator-driven floral diversification.

ryderElizabeth F. Ryder received the A.B. degree in statistics from Princeton University in 1980, the M.S. degree in biostatistics from the Harvard T.H. Chan School of Public Health in 1985, and the Ph.D. degree in genetics from Harvard University in 1993. She was with the Worcester Polytechnic Institute (WPI), Worcester, MA, USA, in 1996, and was a Post-Doctoral Fellowship with the Massachusetts General Hospital, Boston, MA, USA. He is currently an Associate Professor of Biology and Biotechnology and an Associate Director of the Bioinformatics and Computational Biology Program with WPI, Worcester, MA, USA. Her work is currently supported by the National Science Foundation. His research interests include the simulation of biological systems using agent-based computational modeling, with both research and educational goals.

gillKuldeep S. Gill received the B.S. degree in electrical engineering with emphasis on electronics and telecommunications from the S. B. Jain Institute of Technology, Management and Research, India, in 2014, and the M.S degree from the Worcester Polytechnic Institute, MA, USA, in 2017. He is currently pursuing the Ph.D. degree with the Wireless Innovation Laboratory, Department of Electrical and Computer Engineering, Worcester Polytechnic Institute, Worcester, MA, USA. His research interests include software-defined radios, dynamic spectrum access, vehicular ad-hoc networks, signal processing, and channel modeling.

heathKevin N. Heath received the B.S. degree in mathematical and computational biology from Harvey Mudd College, Claremont, CA, USA. He is currently pursuing the Ph.D. degree with the Department of Biology and Biotechnology, Worcester Polytechnic Institute, Worcester, MA, USA.

 

 

 


Lecture 5

Vision Systems for Self-Driving Cars

Abstract to be posted

Speaker Biographies

JohnNafzigerJohn S, Nafziger is a principal engineer at the MITRE corporation, a not-for-profit Federally Funded Research and Development Company in McLean, VA, and an Adjunct Professor in the Robotics Engineering Program at Worcester Polytechnic Institute, Worcester, MA.  Previously, he was an Associate Professor in Aerospace and Mechanical at Embry-Riddle Aeronautical University, where he developed the curriculum for the Robotics Program and served as the director of the Robotics and Mechatronics Laboratory.  John was a Member of the Technical Staff in the Vision Technologies Division at the Sarnoff Corporation in Princeton, NJ, where his group won a Technical Emmy Award for work in video image quality.  John obtained a BS and MS in Mechanical Engineering in the area of  Dynamics and Controls, and a PhD in Neuroscience from the University of Pennsylvania in the area of biologically based models of early visual processing and extracellular recordings from visual cortex.  His current research focuses on autonomous navigation of small unmanned aerial systems for the Department of Homeland Security and the Department of Defense.


Lecture 6

Multi-Sensor Data Fusion for Self-Driving Cars

In this lecture, we explore the notions of multi-sensor data fusion that are applicable to autonomous vehicles operating in dynamic environments. The lecture will begin with a brief introduction to data fusion covering data fusion-levels and architectures for autonomous vehicles; environment perception data and their representation; objects, grids and raw data oriented data fusion problems; and, some other details that play a vital role in real-life sensor fusion applications. Then we will introduce sensor fusion, target tracking and situational awareness techniques with a special focus on self-driving technologies ranging from simple Kalman filters to advanced interacting multi-modal tracking techniques. In addition, we will also present some of the algorithms that are available in the literature along with some ongoing work on multiple-hypothesis tracking with speakers research group in collaboration with local industry.

Speaker Biography

thanuka_bioThanuka Wickramarathne is currently a tenure-track assistant professor with the Department of Electrical & Computer Engineering at University of Massachusetts Lowell. Previously, he was a Research Assistant Professor in the Departments of Electrical Engineering and Computer Science & Engineering at the University of Notre Dame, Engineering intern with the DSP group at Motorola Solutions (Plantation, FL) and RNP Engineer (short stint) at Celltell Lanka pvt ltd (now Etiselat, in Sri Lanka). He received his B.Sc. in Electronics and Telecommunication Engineering from University of Moratuwa, Sri Lanka and both of his MS and PhD degrees in Electrical & Computer Engineering from University of Miami, Coral Gables, FL. He is a senior member of IEEE.