Visual Simultaneous Localization and Mapping (SLAM) systems have their numerous applications in robotics and autonomous driving. Computational offloading enables the computationally demanding Visual SLAM systems to run on hardware-constrained mobile devices, such as Unmanned Aerial Vehicles (UAVs) and Automated Guided Vehicles (AGVs). The offloading of SLAM modules to a central server also enables cooperative collaboration between multiple mobile devices. In this paper, we investigate the process of map synchronization between the edge and mobile devices in edge assisted SLAM systems. Due to the condition of uninterrupted execution, it is necessary that the map synchronization can be executed in the running process without losing the localization on the mobile device. Using a state-of-the-art edge assisted SLAM system, we investigate the influences of the movement speed as well as the network latency on the map synchronization and the resulting success ratio of the tracking continuation. By introducing a frame buffer on the mobile device, we have managed to compensate for the negative effect of the synchronization delay and thus increase reliability by up to 37%.

Traffic congestion in dense urban centers presents an economical and environmental burden. In recent years, the availability of vehicle- to-anything communication allows for the transmission of detailed vehicle states to the infrastructure that can be used for intelligent traffic light control. The other way around, the infrastructure can provide vehicles with advice on driving behavior, such as appropriate velocities, which can improve the efficacy of the traffic system. Several research works applied deep reinforcement learning to either traffic light control or vehicle speed advice. In this work, we propose a first attempt to jointly learn the control of both. We show this to improve the efficacy of traffic systems. In our experiments, the joint control approach reduces average vehicle trip delays, w.r.t. controlling only traffic lights, in eight out of eleven benchmark scenarios. Analyzing the qualitative behavior of the vehicle speed advice policy, we observe that this is achieved by smoothing out the velocity profile of vehicles nearby a traffic light. Learning joint control of traffic signaling and speed advice in the real world could help to reduce congestion and mitigate the economical and environmental repercussions of today's traffic systems.

The evolution of wireless communications into 6G and beyond is expected to rely on new machine learning (ML)-based capabilities. These can enable proactive decisions and actions from wireless-network components to sustain quality-of-service (QoS) and user experience. Moreover, new use cases in the area of vehicular and industrial communications will emerge. Specifically in the area of vehicle communication, vehicle-to-everything (V2X) schemes will benefit strongly from such advances. With this in mind, we have conducted a detailed measurement campaign that paves the way to a plethora of diverse ML-based studies. The resulting datasets offer GPS-located wireless measurements across diverse urban environments for both cellular (with two different operators) and sidelink radio access technologies, thus enabling a variety of different studies towards V2X. The datasets are labeled and sampled with a high time resolution. Furthermore, we make the data publicly available with all the necessary information to support the on-boarding of new researchers. We provide an initial analysis of the data showing some of the challenges that ML needs to overcome and the features that ML can leverage, as well as some hints at potential research studies.

Forward Error Correction (FEC) has become an integral part of communication technology to address expected losses during transfer of data. Among various layer three block codes, Random Linear Network Coding (RLNC) has emerged as an adaptable, powerful approach. However, its most straightforward implementation, Full Vector Coding (FVC), introduces too much delay for widespread adoption. Handcrafted schemes were introduced to optimise coding delay, while keeping resilience reasonably high. These works have resulted in tailRLNC and PACE. For the first time we analyse their respective behaviours in a fair and comparable manner, as non-recovered packets were statistically ignored previously. We then introduce an environment that uses a consistent, unbiased simulator and interface it with a Deep Reinforcement Learning (DRL) agent. This is the first time RLNC is joined with DRL. Our deep Q-network (DQN) based agent effectively uses an optimisation loop and utilises a customisable, expressive and extendable parametric loss function to learn a protocol. We demonstrate our agent recovers hand-tailored schemes and achieves state of the art.

New generations of mobile networks are opening up novel possibilities for controlling robots remotely in real-time. With 5G’s requirement to support use cases that demand low latencies at a high reliability from the communication network, wireless control applications become feasible. A remote operator typically uses a handheld device with buttons or joysticks to control a mobile robot. Joysticks are widely used today. The limitations of two-dimensional controlling and displaying of camera data can cause difficulties. Augmented Reality (AR)-based control provides the ability to control in three dimensional space. Therefore, new user-friendly Human Machine Interfaces (HMIs) can improve the interaction with these robots. In this demonstration, we present a human-in-the-loop application with a novel HMI. With our HMI a remote operator controls a four-legged Boston Dynamics Spot robot with gestures while wearing the AR-Headset Microsoft HoloLens 2. The remote operator receives feedback from the robot in the form of live camera streams visualised on holographic screens.

The trade-offs between storage and repair traffic for replacing failed storage nodes with new nodes (newcomers) in data centers with an omniscient controller are well understood. However, in edge storage settings, newcomers are not readily available, necessitating resilient data storage (caching) without newcomers. Edge storage nodes can often communicate via a broadcast wireless medium, which can be exploited to reduce the transmitted repair traffic via network coding. Repairs for resilient distributed caching without newcomers over a broadcast medium with Random Linear Network Coding (RLNC), which does not require an omniscient controller, have not been previously studied. We develop an information-theoretic model to characterize the theoretically achievable trade-offs between stored data and transmitted repair data in the RLNC broadcast setting without newcomers. Specifically, we formulate an Information Flow Graph (FG) model and identify all cuts in the resulting FG. We validate the theoretical FG model with simulations that demonstrate that the practically achievable trade-offs are close to the theoretical trade-offs.

5G campus networks, whose advantages include flexible deployment, can be a promising candidate for production plants to complement existing Wifi-based networks. Toward that goal, 5G has to satisfy strict requirements about real-time communication to facilitate novel use cases. However, the realtime-capability of 5G is not well understood yet. In this work, we deliver insights into the functioning of 5G NR RAN Release 15, which includes actual one-way delay and Round-Trip Time (RTT) measurements for Downlink and Uplink in a private 5G Standalone campus network. The extensive measurement results reveal that these delays are correlated, and the corresponding RTT, i.e. the sum of Downlink and Uplink delays, is discreetly clustered, ranging between 12ms and 40ms. The measurements also show that the distribution of RTTs is mainly dependent on the packet rates and their inter-arrival times. Our study helps expand the current understanding of 5G used for latency-critical applications. We make the code and the measurement data traces publicly available as the IEEE DataPort 5G Campus Networks: Measurement Traces dataset (DOI 10.21227/xe3c-e968).

In the future, mobility use cases will depend on precise predictions, with Quality of Service (QoS) prediction being a prominent example. This paper presents realistic measurements from today’s vehicles to support robust QoS prediction in the future. Based on a dedicated and controlled measurement campaign, we highlight aspects of the wireless environment and the device characteristics, like the sampling rates, that influence the collected datasets. If not properly handled, such characteristics might hinder the performance of Artificial Intelligence-based algorithms for QoS prediction. Therefore, we also provide insights on dataset characteristics that should be further used to enable easier adoption of AI-based algorithms. New AI-based algorithms should be able to operate in very diverse radio environments with data captured from different devices. We provide several examples that highlight the importance of thoroughly understanding the datasets and their dynamics.

Present-day and future network protocols that include and implement Forward Error Correction are configurable by internal parameters, typically incorporating expert knowledge to set up.We introduce a framework to systematically, objectively and efficiently determine parameters for Random Linear Network Codes (RLNC). Our approach uses an unbiased, consistent simulator in an optimization loop and utilizes a customizable, powerful and extendable parametric loss function. This allows to tailor existing protocols to various use cases, including ultra reliable, low latency communication (URLLC) codes. Successful configurations exploring the search space are under evolutionary pressure and written into a database for instant retrieval. We demonstrate three examples, Full Vector Coding, tail RLNC, and PACE with different focus for each.