Previous 30 days30 days60 days90 days | Short FormatLong Format

using https://meetings.vtools.ieee.org/meetings/xml/0/30/asc/6/OREGON

39005 bytes

4 meetings

Title:
Robust depth estimation for robots with stereo cameras using bespoke DNNs
Date:
December 7th
6:30 PM (1.5 hours)
Abstract:

Autonomous robots depend on their perception systems to understand the world around them. These machines often leverage a host of sensors including cameras, lidars, radars, and ultrasonic sensors to create this environmental understanding. Stereo cameras play a big role in providing depth perception to robotic systems. This depth information can be estimated using classical computer vision techniques, like semi-global matching (SGM) or leverage deep neural networks (DNNs). Each individual algorithm may struggle in a particular set of operating conditions. But when multiple depth estimation algorithms are leveraged simultaneously, It is possible that more robust depth information can be calculated.

In this talk, we'll cover work at NVIDIA to train the ESS DNN model for determining stereo disparity using both synthetic and real-world data to perform well where SGM may not. We'll also introduce the Bi3D model which is trained on the simplified question of "is X closer than M meters?" rather than "how far away is X?", yielding improvements in both accuracy and speed. As every approach has deficiencies on its own, we'll touch upon how ensembling the responses of ESS and Bi3D, DNNs developed specifically for robotic perception with SGM could lead to robust obstacle detection. Finally, we'll discuss how we've tuned the performance of these models to run on embedded compute for the responsive stopping behavior required in autonomous mobile robots (AMRs).

Title:
Algorithms & protocols joint coms, localization, sensing by Dr. George Alexandropoulos
Date:
December 8th
7:00 AM (1.5 hours)
Abstract:

Title: Reconfigurable intelligent surfaces: Communications, sensing, and their integration

 

Abstract: The advent of the connected things paradigm within 5G wireless communications enabled various sophisticated applications, whose evolution paves the way for the notion of the connected intelligence of everything in 6G networks. Recent speculations for this upcoming new generation push the 5G performance indicators to unprecedented levels, envisioning THz frequency bands, devices with embedded sensing capabilities, and native AI. All these are expected to become a reality around 2030 and with a strong green footprint. In this talk, we will elaborate around the emerging technology of Reconfigurable Intelligent Surfaces (RISs) which is provisioned as the enabler of smart wireless environments, offering a highly scalable, low-cost, hardware-efficient, and almost energy-neutral solution for the dynamic control of the propagation of electromagnetic signals. We will discuss their evolution from programmable reflecting metamaterials to connected computational- and power-autonomous hybrid metasurfaces, emphasizing on the state-of-the-art approaches for RIS-empowered communications, localization, and sensing.

 

Short Biography: George C. Alexandropoulos received the Engineering Diploma, M.A.Sc., and Ph.D. degrees in Computer Engineering and Informatics from the School of Engineering, University of Patras, Greece in 2003, 2005, and 2010, respectively. He has held research positions at various Greek universities and research institutes, as well as at the Mathematical and Algorithmic Sciences Lab, Paris Research Center, Huawei Technologies France, and he is currently an Assistant Professor with the Department of Informatics and Telecommunications, School of Sciences, National and Kapodistrian University of Athens (NKUA), Greece. He also serves as a Principal Researcher for the Technology Innovation Institute, Abu Dhabi, United Arab Emirates. His research interests span the general areas of algorithmic design and performance analysis for wireless networks with emphasis on multi-antenna transceiver hardware architectures, active and passive Reconfigurable Intelligent Surfaces (RISs), integrated communications and sensing, millimeter wave and THz communications, as well as distributed machine learning algorithms. He currently serves as an Editor for IEEE Transactions on Communications, IEEE Wireless Communications Letters, ELSEVIER Computer Networks, Frontiers in Communications and Networks, and the ITU Journal on Future and Evolving Technologies. In the past, he has held various fixed-term and guest editorial positions for IEEE Transactions on Wireless Communications and IEEE Communications Letters, as well as for various special issues at IEEE journals. Prof. Alexandropoulos is a Senior Member of the IEEE Communications, Signal Processing, and Information Theory Societies, the vice-chair of the EURASIP Technical Area Committee on Signal Processing for Communications and Networking, as well as a registered Professional Engineer of the Technical Chamber of Greece. He is also a Distinguished Lecturer of the IEEE Communications Society. He has participated and/or technically managed more than 15 European Union (EU), international, and Greek research, innovation, and development projects. He is currently NKUA's principal investigator for the EU H2020 RISE‑6G and the SNS JU TERRAMETA projects dealing with RIS-empowered smart wireless environments and THz RISs, respectively. For the former project he also serves as the dissemination manager, whereas for the latter, he also serves as the project’s technical manager. Prof. Alexandropoulos has received the best Ph.D. thesis award 2010, the IEEE Communications Society Best Young Professional in Industry Award 2018, the EURASIP Best Paper Award of the Journal on Wireless Communications and Networking 2021, the IEEE Marconi Prize Paper Award in Wireless Communications 2021, and a Best Paper Award from the IEEE GLOBECOM 2021. More information is available at www.alexandropoulos.info.

 

  
Title:
Strategic Technology Management
Date:
December 8th
10:00 AM (1 hour)
Abstract:

Review of strategic technology management

Title:
V2X - The Cooperative Safety Revolution
Date:
December 15th
12:00 PM (1 hour)
Abstract:
V2X - The Cooperative Safety RevolutionDespite the development of automotive safety technologies in recent years, road fatalities keep going up. In order to change this reality we need a paradigm shift towards cooperative safety. V2X is the safety network that can protect all road users and bring on a true road safety revolution that will prevent road accidents and save lives. V2X is a wireless communication sensor and thus it is the only sensor able to provide life saving real time information regarding the other road users around us, without the need for line of sight and in any weather and light conditions.  Road safety organizations around the world have recognized the vital need for V2X and the technology is in various deployment stages, globally. EuroNCAP, the organization responsible for car safety rating in Europe, is set to include V2X in the safety grading starting from 2025.  

4 meetings. Generated Wednesday, November 30 2022, at 8:36:18 PM. All times America/Los_Angeles