Ken Goldberg, a renowned academic and leading expert in networked telerobotics and Cloud Robotics, will share his insights at the workshop, offering a valuable perspective from an academic authority in the field.

Abstract— Mobility, power, and price points often dictate that automation systems do not have sufficient computing power on board to run contemporary algorithms at desired rates. Cloud computing providers such as AWS, GCP, and Azure offer immense computing power on demand, but tapping into that power is non-trivial. We present FogROS2, an open-source platform to facilitate cloud and fog computing that is compatible with the emerging Robot Operating System 2 (ROS 2) standard.

FogROS2 is completely redesigned and distinct from its predecessor FogROS1 in 9 ways, and has lower latency, overhead, and startup times; improved usability, and additional automation, such as region and computer type selection. Additionally, FogROS2 was added to the official distribution of ROS 2, gaining performance, timing, and additional improvements associated with ROS 2.

In examples, FogROS2 reduces SLAM latency by 50 %, reduces grasp planning time from 14 s to 1.2 s, and speeds up motion planning 28x. When compared to FogROS1, FogROS2 reduces network utilization by up to 3.8x, improves startup time by 63 %, and network round-trip latency by 97 % for images using video compression.

Prachi Sachdeva is a researcher at TNO (Netherlands Organization for Applied Scientific Research) with expertise spanning 6G networks, European Union policy frameworks, and cloud computing architectures. Her research focuses on the intersection of next-generation communication technologies and autonomous systems.

The talk shares perspectives on the realities of using mobile networks in robotics and autonomous systems, the gaps between standardization and deployment, and lessons learned from 5G in industrial applications.

It also looks ahead to future roadmaps and what next-generation mobile networks could mean for robotics.

Florian Pokorny is an Associate Professor at KTH Royal Institute of Technology, Stockholm. His group is working on data-driven methods for robotic manipulation and cloud robotics. He is currently coordinating the Horizon Europe project SoftEnable (softenable.eu) and the WASP-NEST project "Intelligent Cloud Robotics for Real-Time Manipulation at Scale" funded by the Wallenberg AI, Autonomous Systems & Software Program (wasp-sweden.org). He obtained his PhD in mathematics at the University of Edinburgh and holds a BSc in mathematics from the University of Edinburgh and a Master of Advanced Study in Mathematics (Part III) from the University of Cambridge.

Abstract—Data-Driven methods in Robotics, and Foundation Models in particular, are currently among the most exciting areas of progress within robotic manipulation, but core challenges such as rigorous reasoning about data requirements and reliability, remain. In this presentation, I will discuss some of our recent work on leveraging cloud robotics as a paradigm for training machine learning models for robotics and how the CloudGripper (cloudgripper.org) cloud robotics test-bed at KTH enables data-driven validation and benchmarking at scale using a set of remotely accessible robot arm cells.

Yoshinori Kitatsuji is a Senior Research Engineer at KDDI, where he focuses on developing advanced technologies for telecommunications networks. He has extensive experience in network engineering and telecommunications systems.

This talk explores the role of communication in robotics applications and the network requirements needed to support it. This begins with an overview of advancements in robotics and their diverse applications, followed by an explanation of how communication technologies enhance robot functionality.

Next, The talk delves into the importance of real-time communication and key network requirements such as bandwidth, latency, and reliability. Discussions include the potential of 5G, edge computing, and cloud processing in transforming robotics.

Additionally, the talk addresses challenges like security concerns, measures to handle communication failures, and the design of network topologies. Finally, the talk examines the impact of next-generation communication technologies, such as 6G and quantum communication, on the future of robotics.