RT Dissertation/Thesis
T1 Towards edge robotics: the progress from cloud-based robotic systems to intelligent and context-aware robotic services
A1 Groshev, Milan
AB Current robotic systems handle a different range of applications such as video surveillance, deliveryof goods, cleaning, material handling, assembly, painting, or pick and place services. These systemshave been embraced not only by the general population but also by the vertical industries tohelp them in performing daily activities. Traditionally, the robotic systems have been deployed instandalone robots that were exclusively dedicated to performing a specific task such as cleaning thefloor in indoor environments. In recent years, cloud providers started to offer their infrastructuresto robotic systems for offloading some of the robot’s functions. This ultimate form of the distributedrobotic system was first introduced 10 years ago as cloud robotics and nowadays a lot of robotic solutionsare appearing in this form. As a result, standalone robots became software-enhanced objectswith increased reconfigurability as well as decreased complexity and cost. Moreover, by offloadingthe heavy processing from the robot to the cloud, it is easier to share services and information fromvarious robots or agents to achieve better cooperation and coordination.Cloud robotics is suitable for human-scale responsive and delay-tolerant robotic functionalities(e.g., monitoring, predictive maintenance). However, there is a whole set of real-time robotic applications(e.g., remote control, motion planning, autonomous navigation) that can not be executed withcloud robotics solutions, mainly because cloud facilities traditionally reside far away from the robots.While the cloud providers can ensure certain performance in their infrastructure, very little can beensured in the network between the robots and the cloud, especially in the last hop where wirelessradio access networks are involved. Over the last years advances in edge computing, fog computing,5G NR, network slicing, Network Function Virtualization (NFV), and network orchestration are stimulatingthe interest of the industrial sector to satisfy the stringent and real-time requirements of theirapplications. Robotic systems are a key piece in the industrial digital transformation and their benefitsare very well studied in the literature. However, designing and implementing a robotic systemthat integrates all the emerging technologies and meets the connectivity requirements (e.g., latency,reliability) is an ambitious task.This thesis studies the integration of modern Information andCommunication Technologies (ICTs)in robotic systems and proposes some robotic enhancements that tackle the real-time constraints ofrobotic services. To evaluate the performance of the proposed enhancements, this thesis departsfrom the design and prototype implementation of an edge native robotic system that embodies the concepts of edge computing, fog computing, orchestration, and virtualization. The proposed edgerobotics system serves to represent two exemplary robotic applications. In particular, autonomousnavigation of mobile robots and remote-control of robot manipulator where the end-to-end roboticsystem is distributed between the robots and the edge server. The open-source prototype implementationof the designed edge native robotic system resulted in the creation of two real-world testbedsthat are used in this thesis as a baseline scenario for the evaluation of new innovative solutions inrobotic systems.After detailing the design and prototype implementation of the end-to-end edge native roboticsystem, this thesis proposes several enhancements that can be offered to robotic systems by adaptingthe concept of edge computing via the Multi-Access Edge Computing (MEC) framework. First, itproposes exemplary network context-aware enhancements in which the real-time information aboutrobot connectivity and location can be used to dynamically adapt the end-to-end system behavior tothe actual status of the communication (e.g., radio channel). Three different exemplary context-awareenhancements are proposed that aim to optimize the end-to-end edge native robotic system. Later,the thesis studies the capability of the edge native robotic system to offer potential savings by means ofcomputation offloading for robot manipulators in different deployment configurations. Further, theimpact of different wireless channels (e.g., 5G, 4G andWi-Fi) to support the data exchange between arobot manipulator and its remote controller are assessed.In the following part of the thesis, the focus is set on how orchestration solutions can supportmobile robot systems to make high quality decisions. The application of OKpi as an orchestration algorithmand DLT-based federation are studied to meet the KPIs that autonomously controlledmobilerobots have in order to provide uninterrupted connectivity over the radio access network. The elaboratedsolutions present high compatibility with the designed edge robotics system where the robotdriving range is extended without any interruption of the end-to-end edge robotics service. While theDLT-based federation extends the robot driving range by deploying access point extension on top ofexternal domain infrastructure, OKpi selects the most suitable access point and computing resourcein the cloud-to-thing continuum in order to fulfill the latency requirements of autonomously controlledmobile robots.To conclude the thesis the focus is set on how robotic systems can improve their performance byleveraging Artificial Intelligence (AI) and Machine Learning (ML) algorithms to generate smart decisions.To do so, the edge native robotic system is presented as a true embodiment of a Cyber-PhysicalSystem (CPS) in Industry 4.0, showing the mission of AI in such concept. It presents the key enablingtechnologies of the edge robotic system such as edge, fog, and 5G, where the physical processes areintegrated with computing and network domains. The role of AI in each technology domain is identifiedby analyzing a set of AI agents at the application and infrastructure level. In the last part of thethesis, the movement prediction is selected to study the feasibility of applying a forecast-based recoverymechanism for real-time remote control of robotic manipulators (FoReCo) that uses ML to inferlost commands caused by interference in the wireless channel. The obtained results are showcasingthe its potential in simulation and real-world experimentation.
YR 2022
FD 2022-09
LK https://hdl.handle.net/10016/36018
UL https://hdl.handle.net/10016/36018
LA eng
DS e-Archivo
RD 27 jul. 2024