Title: Human Interactive Driving: Amplify People for a Safer, More Enjoyable Driving Experience

Abstract: Despite the benefits of autonomous vehicles, their many challenges have made their wide scale deployment and adoption slower than hoped for. This has created a growing need for intelligent interaction and collaboration between increasingly, but not fully, automated vehicles and humans. Such a collaborative system promises to potentially unlock new driving experiences where an AI amplifies, supports and empowers the driver to not only be more safe but to also have a more engaging and enjoyable driving experience. Toyota Research Institute (TRI) calls this new collaborative driving paradigm Human Interactive Driving (HID) which includes research thrusts in building better learned models of human behavior, building expert level AI driving skills and sharing autonomy between an AI and human. This talk will introduce both TRI's core research in this area as well as potential ways this research can create a safer and more enjoyable driving experience.

Bio: Dr. Avinash Balachandran is the director of the Human Interactive Driving (HID) division at Toyota Research Institute (TRI). The goal of the HID division is to create AI-driven capabilities and tools empowering humans and increasingly automated vehicles to interact more effectively and naturally. The department blends competencies in machine learning, human-machine interaction and robotics to create novel and innovative technologies for the intelligent vehicles of the future.

Prior to TRI, Dr. Balachandran was one of the early engineers on Uber's self-driving program and was instrumental in developing their first autonomous service in Pittsburgh, PA (2016). He also led engineering teams focused on autonomous driving development at EV startup Faraday Future. He is passionate about bringing cutting-edge research closer to commercialization. He is also a noted public speaker, expert and adviser on topics around autonomy and human-centric research.

Dr. Balachandran holds a B.S. in mechanical engineering and a minor in computer science from Cornell University. He also holds M.S. and Ph.D. degrees in mechanical engineering from Stanford University focusing on autonomous technologies, performance driving and human interaction. He is also a recipient of the prestigious Stanford Graduate Fellowship.

Title: How to Act as Team - Multi-Robot Coordination

Abstract: Now that robots have evolved from bulky platforms to agile devices, a challenge is to combine multiple robots into an integrated autonomous system, offering functionality that individual robots cannot achieve. A key building block for this integration is coordination, which is concerned with sharing knowledge, joint decision making, and allocation of computation tasks to processing nodes. Different levels of coordination exist—ranging from high-level functions, like the assignment of system-wide tasks and resources, down to low-level control, like collision avoidance, flight formations, and joint sensor usage for state estimation. In this talk, I will present different coordination techniques for multi-robot systems, discuss their usage in prototypical multi-robot applications such as path planning, swarming and surveillance, and demonstrate deployments in unmanned aerial vehicles.

Bio: Bernhard Rinner is professor at the University of Klagenfurt, Austria where he is heading the Pervasive Computing group. He is deputy head of the Institute of Networked and Embedded Systems and serves as vice dean of the Faculty of Technical Sciences. Before joining Klagenfurt he was with Graz University of Technology and held research positions at the Department of Computer Sciences at the University of Texas at Austin in 1995 and 1998/99.  His current research interests include embedded computing, sensor networks multi-robot systems and pervasive computing. Together with partners from four European universities, he has jointly initiated the Erasmus Mundus Joint Doctorate Program on Interactive and Cognitive Environments (ICE). He is senior member of IEEE and member of the board of the Austrian Science Fund.

Title: Vehicle-to-Everything-Communication-Aided Perception in Autonomous Driving 

Abstract: When observing the world, each individual has a certain bias due to the limited field of view. The observation would be more holistic and robust when a group of individuals could collaborate and share information. With decades of efforts on machine learning and computer vision, single-agent perception has made remarkable success in 2D/3D object detection, tracking and segmentation; however, it still suffers from a number of inevitable limitations due to an individual perspective, such as occlusion and long-range issues. Fortunately, with the fast development of communication technologies, agents are able to share more information with each other, leading to an emerging field of collaborative perception. In this talk, we will present collaborative perception, which enables multiple agents to share complementary perceptual information with each other, promoting more holistic perception. It provides a new direction to fundamentally overcome a number of inevitable limitations of single-agent perception, such as occlusion and long-range issues.

Bio: Siheng Chen is a tenure-track associate professor of Shanghai Jiao Tong University and research scientist at Shanghai AI Laboratory. Before this, he was a research scientist at Mitsubishi Electric Research Laboratories (MERL), and an autonomy engineer at Uber Advanced Technologies Group, working on the perception and prediction systems of self-driving cars. Dr. Chen received his doctorate from Carnegie Mellon University. Dr. Chen's work on sampling theory of graph data received the 2018 IEEE Signal Processing Society Young Author Best Paper Award. His co-authored paper on structural health monitoring received ASME SHM/NDE 2020 Best Journal Paper Runner-Up Award and another paper on 3D point cloud processing received the Best Student Paper Award at 2018 IEEE Global Conference on Signal and Information Processing. Dr. Chen contributed to the project of scene-aware interaction, winning MERL President's Award. His research interests focuses on collective intelligence and autonomous driving.

Title: Recent Advances in the Automotive Radar Research

Abstract: Automated driving needs accurate perception of the vehicle's surroundings. Radar is a key sensing modality for robust environment perception. As the automation level in cars increases from advanced driver assistance systems (ADAS) to highly automated driving, and ultimately, to self-driving cars, demands on radar imaging performance grow. Particularly, resolution as well as dynamic range in all four radar dimensions are to be improved. For radar performance to meet the requirements of self-driving cars, straightforward scaling of the radar parameters (e.g. bandwidth, sampling rate, aperture) is not sufficient. Rather, fundamentally different approaches are required, among others conceptually new system designs and advanced algorithms. 

The talk gives an overview of the challenges that arise for automotive radar from its development as a sensor for ADAS to a core component of self-driving cars. It summarizes the relevant research and discusses topics related to high-performance automotive radar systems, such as novel signal processing algorithms, multiple-input multiple-output (MIMO) radar, synthetic aperture radar, radar AI.

Bio: Dr. Gor Hakobyan is the CTO of Waveye Inc, Palo Alto, California, a technology startup developing high-resolution imaging radars for automotive and robotics. Previously he was a research scientist at Bosch working on future radar sensors for self-driving cars. His research focuses on signal processing algorithms and system design for automotive radar sensors. He holds a PhD in radar signal processing from University of Stuttgart, is recipient of multiple awards on radar conferences, author of several IEEE journal and magazine papers, and inventor in >100 patent filings. He is a lecturer at the University of Stuttgart for the lecture "Automotive Radar Systems for Autonomous Driving".

Title: AI Meets the Streets: Building Accurate HD Maps with Crowdsourced Road Images

Abstract: The ability to build large-scale HD maps is increasingly important for the development of advanced driving assistance systems (ADAS), self-driving cars and other autonomous systems. Current approaches to mapping rely on expensive hardware such as LIDAR, dedicated fleets and time-consuming surveying techniques, which limit their scalability and usefulness. In this talk, we will introduce a new approach that combines edge AI and crowdsourced road images to enable more efficient and cost-effective HD map creation. By aggregating detections and visual evidence from hundreds of thousands of vehicle cameras, our real-time mapping platform is able to generate HD maps at scale with minimum cost. Beyond reviewing the underlying technology, we will highlight numerous use cases where these maps can benefit future mobility and autonomous systems, ranging from improved localisation to detailed behavioural maps.

Bio: An award-winning wireless engineer, academic leader and passionate entrepreneur, João loves to turn complex theorems and algorithms into products and services that can make a real difference in people’s lives.

During the 23 years he spent developing new wireless networking and intelligent transportation technologies, João Barros held appointments at Technische Universitaet Muenchen, Universidade do Porto, MIT, Carnegie Mellon and Stanford, while founding two venture-backed startups, Streambolico and Veniam, where he served as CEO until the acquisition by Nexar Inc in 2022.  His work has led to one book, 180 science and technology papers, 22 International patents, and feature articles by NPR, BBC, MIT Technology Review, The Atlantic, and TechCrunch, among others.

Prof. Barros is an IEEE Fellow, was awarded two Fulbright scholarships, and served as principal investigator for several national and European projects and has received numerous awards, including the 2010 IEEE Communications Society Young Researcher Award for the Europe, Middle East and Africa region, the 2011 IEEE ComSoC and Information Theory Society Joint Paper Award, CableLabs, Wireless broadband alliance, TU Automotive, and a state-wide best teaching award by the Bavarian State Ministry of Sciences, Research and the Arts. He has a Ph.D. degree in Electrical Engineering and Information Technology from the Technische Universitaet Muenchen (Germany), his undergraduate education in Electrical and Computer Engineering from the Universidade do Porto, Portugal and Universitaet Karlsruhe, Germany, and a performing arts degree in flute from the Music Conservatory of Porto, Portugal.