Keynote Lectures

Traffic Control Using Automated Vehicles: Distributed Sensing, Actuation, and Learning
Karl Henrik Johansson, KTH Royal Institute of Technology, Sweden, Sweden

Technologies Towards Automated Vehicles
Christoph Stiller, Karlsruhe Institute of Technology (KIT), Germany, Germany

Smart Shipping and Logistics: Perspectives & Challenges
Rudy R. Negenborn, Delft University of Technology, Netherlands, Netherlands

Abstract
While the long-term benefits of introducing connected and automated vehicles into road traffic are widely understood to be revolutionary, there is much debate about whether its early stages will cause an increase in congestion and issues related to human-driven vehicles. Notwithstanding, connected vehicles acting as mobile sensors and actuators could enable traffic predictions and control at a scale never before possible, and thereby a much more efficient use of the available and future road infrastructure. In this talk, we will present how new freight transport technology based on automated truck platoons can be the backbone for such a system. Some fundamental theoretical and experimental results on the control and coordination of truck platoons will be presented. How such platoons influence traffic flows by acting as a moving bottleneck will be discussed together with traffic models suitable for designing novel traffic control systems. It will also be argued that these models are possible to learn automatically from data gathered by platoons acting as traffic flow sensors. Experiments show that relatively few connected vehicles are enough to mitigate congestion and improve traffic conditions significantly. The presentation is based on joint work with many students and postdocs at KTH and researchers at Swedish automotive industry.

Abstract
Vehicle automation is among the most fascinating trends in automotive electronics and a huge challenge to the Intelligent Transportation Systems community. This talk with discuss the state-of-the-art and a potential evolution of automated vehicles. We discuss lessons learned from the autonomous Bertha Benz memorial tour from Mannheim to Pforzheim.

We investigate probabilistic and deep learning approaches to perception and planning methods for automated vehicles and elaborate on the potential and cooperative driving. Beyond the fascinating progress that we have witnessed in the past decades, the remaining challenges for achieving full autonomy for self-driving cars still require substantial research. Reliable perception, provable behavioral safety and safety validation are prominent examples for these. Furthermore, fail-safe requirement lead to novel vehicle architectures. Technical supervision and teleoperation may lower the hurdles for deployment. Last, not least, a societal consensus on an acceptable risk level is required and compliance with this consensus must be tracked in empirical safety analysis.

Abstract
To achieve sustainable and efficient transport, it is necessary to consider a more integrated perspective in which the operations of all modes of transport  (road, rail, and water) are synchronized, across geographical scopes (from equipment to network level), and across time scales (from operational to strategic), while making optimal use of real-time information processing and coordination.

In this talk we zoom in on recent advances in the ports and waterborne transport area, starting from the equipment level. New designs and applications for land-based transport using autonomous ground vehicles (AGVs) inside port areas and surroundings will first be presented. Then, we will shift focus towards the waterborne side, specifically addressing the growing interest in autonomous ships. We here highlight six open research gaps and discuss challenges and solution directions from an individual ship perspective, as well as from the perspective of multi-vessel systems with ship-2-ship and ship-2-infrastructure interaction.

We then make the link back the transport domain, presenting the approach taken by the European H2020 program NOVIMOVE. This program aims at solving inefficiencies specifically on the IWT Rhine-Alpine corridor via “condensing” of the logistics system by improving container load factors, by reducing waiting times in seaports, by improved river voyage planning and execution, and by facilitating smooth passages through bridges and locks. This can, with the right stakeholder involvement, ultimately lead to better aligned and sustainable operations, and improved use of transport capacity.