Visual Collaborative Simultaneous Localization and Mapping (SLAM) uses multiple mobile devices to capture images of their surroundings and map their environment collectively while simultaneously determining their position. In centralized approaches, a single server merges visual features from these devices to build a shared map. Offloading computationally intensive tasks benefits resource-limited mobile devices. However, due to unpredictable and heterogeneous communication links, maps at the server and on the devices can become asynchronous, potentially leading to real-time localization failures. To address these issues, we present Reliable Agents in Centralized Visual Collaborative SLAM (RAVIC), which employs an optimised server-to-agent communication strategy. This includes a novel keyframe selection method that exploits the server’s global map to improve tracking under high agent mobility and network latency. In addition, adjustments to agent-to-server communication and agent tracking algorithm reduce the computational demands on mobile devices, leading to a reduction in average tracking processing time of up to 27.2 ms. Our evaluation using benchmark datasets and different network conditions shows a drastic reduction in track loss probability from 61.4% to only 1.0% utilising merged map data in collaborative scenarios, demonstrating that collaboration increases the reliability of individual agents.

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.

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.

Simultaneous Localization and Mapping (SLAM), among other critical functions of mobile robots, such as navigation, are computationally expensive. When deployed at the robot, those functions demand high energy consumption and result in shorter operation time. Offloading SLAM to an Edge Cloud (EC) can significantly reduce the robot’s computing demand and resources, subsequently reducing energy consumption. We offload intelligence of mobile robot control functionality, i.e., navigation, localization, and control to an EC. The EC processes sensor data and sends the robot the directional velocities. Meanwhile, a 5G wireless connection ensures the necessary low latencies and high throughputs. We demonstrate the feasibility of offloading SLAM and navigation in an EC based on a use case in automotive production. Additionally, we developed a digital twin of the robot and visualized its current sensor data.

Edge Simultaneous Localization and Mapping (SLAM) retains only the tracking on the mobile device, while offloading the compute-intensive local mapping and loop close to edge computing. Existing Edge SLAM approaches incur relatively high delays for offloading, resulting in high failure probabilities, i.e., low reliability, for commonly used public SLAM datasets. We discovered that two parameters which had not previously been studied in detail, namely the number of features and the number of keyframes that are bundled for a local map update, play a critical role in the offloading delay. Also, previous approaches updated the local map in the mobile device in a serial manner, incurring map update latencies. We study the numbers of features and bundled keyframes in detail and we parallelize the local map update. We find that judicious parameter settings, namely relatively small numbers of features (750 per frame) and bundled keyframes (1, i.e., effectively no bundling), reduce the map update latency to less than half compared to the previously common settings (1000 features per frame and 6 keyframes used for a map update). For a low network latency of 20ms, these judicious parameter settings in conjunction with our parallelized local map updating, reduce the 79% failure rate of the previous Edge SLAM systems down to 2%.

Mobile robots are an essential part of the vision of flexible production in a smart factory. To monitor and connect the robots, reliable and low latency communication is necessary. In this work, we conduct packet-based active measurements to evaluate the performance of a state-of-the-art 5G standalone system in a production environment. The focus is on whether 5G connections can meet the requirements specified by 3G PP in terms of delay and reliability. The results indicate that without cross-traffic, the requirement of a delay of less than 10 ms for 99.9 % of the packets can be met for the remote control and fleet management of mobile robots. However, as soon as cross-traffic is injected, especially in the uplink, the upper percentiles of the delay increase significantly, thus failing to hold the reliability requirements.

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).

The Simultaneous Localization and Mapping (SLAM) method is becoming more and more established for the localization of mobile robots in indoor environments. Due to the high complexity of SLAM, high computing resources are necessary, which leads to a shorter runtime. By using edge computing and higher bandwidths of new wireless technologies, the computing can be outsourced. In this work, the SLAM process is offloaded from a mobile robot to an edge cloud and the impact of more computing power is investigated. We show that outsourcing has performance advantages in terms of the update rate of the map generation as well as the localization.