This work describes our efforts to provide a holistic hardware RISC-V virtualization SoC based on the CVA6 core. At the core level, we implemented hardware support for virtualization through the ratified Hypervisor instruction set architecture (ISA) extension version 1.0. At the system level, we are working on providing reference open-source IPs for two non-ISA components needed to build a virtualization-aware platform: (i) the advanced interrupt architecture (AIA) to enable hardware support for interrupt virtualization; (ii) the input/output memory management unit (IOMMU) to protect memory accesses from direct memory access (DMA) devices. All these IPs will be open and freely available to the RISC-V community under permissive open-source licenses.

This paper presents a case study of Copelia, an augmented reality application targeted for smart glasses. Copelia was developed to optimize the workflow of COPEL (Companhia Paranaense de Energia), a major Brazilian electricity company. The application assists its users in the maintenance of reclosers with features such as object recognition, augmented reality (AR), and remote calls. These features allow generalist electricians to perform tasks that would otherwise be exclusively executed by skilled professionals. Copelia was evaluated in laboratory and field tests. Results show that users resisted the application due to its novel interaction paradigm. Most of the reported issues were related to the usability of smart glasses or the graphics interface. A list of good practices was derived from the discussion of these issues. The features themselves proved to be useful, especially the guided instructions. Despite an initial negative reaction, Copelia gained appraisal by its users over time, who highlighted its usefulness for training and maintenance.

Brazilian energy distribution companies are investing in automatic circuit reclosers (ACRs) to optimize their energy grids. These devices often require specialists to maintain. Training electricians can be problematic, as there are very similar models and provide different commands for the same tasks. Based on this problem, an application was developed in this work that allows generalists to carry out maintenance on reclosers and make training less confusing. This paper describes the object detection module of this application, which employs Deep Learning to identify four different recloser models. Were tested some state of art neural networks implementations in object detection field in the recognition of the ACRs supported models and in the tests was reached the best neural network obtained approximately 89% in Mean Average Precision (mAP). This work aim apply the object detection in energy area, focused in maintenance and training scenarios, showing in effective to detect and differentiate ACRs similar models, thus helping general electricians to provide a more accurate service and reducing company costs.

This paper proposes a solution using Deep Learning to increase efficiency in operation and maintenance of automatic circuit reclosers (ACRs). After the automatic detection of an ACR, the solution presents documentation and maintenance procedures in the format of checklists. Each step of those checklists is illustrated in augmented reality with 3D animated models of the detected ACR. The best neural network obtained a Mean Average Precision (mAP) of approximately 91.2% in tests. The solution will aid operators and maintenance professionals in decision making, providing them information and instructions compatible with each of the supported ACR models.

This paper presents a platform-agnostic distributed navigation architecture for autonomous mobile robots operating in intra-factory logistics. Communication, control, navigation, diagnosis and hardware are layered in a hierarchical approach increasing robustness, modularity and flexibility. This architecture promotes several key features, such as dynamic selection of navigation profiles, semantic mapping and human-aware navigation. The approach allowed multiple autonomous mobile robots, cooperating through a fleet management system, to adapt to a wide range of situations, alternating their path planning between high-speed free-space strategies, and high precision low-speed for tight passageways and docking to assembly stations. The benefits of the proposed architecture were validated through a set of experiments in a mockup shopfloor environment. During these tests 3 robots operated continuously for several hours, self-charging without any human intervention.

The proposed telemetry system consists of a graphical user interface with reconfigurable multiple widgets whose transmission is prioritised based on the user's gaze. The proposed approach encompasses a novel framework for telemetry of remote machines, based on ROS (Robot Operating System). It includes a modular ensemble of GUI, gaze device interoperability, and a ROS sensory topic modulator, which alternates different strategies to optimise all displayed information transmission quality, in a way that best suits the user. The approach was validated on a teleoperation scenario having multiple users control a robot in a designed course.

This paper presents an incremental learning mechanism for context-aware switching between localisation methods which are available to the robots control system (e.g., GPS-based, map-based). The goal is to avoid the cumbersome and error prone manual mapping between localisation methods and environmental contexts. At each moment, the system determines which localisation method is performing best by comparison with the motion estimates produced by an odometer, assumed as accurate in the short-time. Then, the best performing method is associated to the current environmental context, which is defined by a novel descriptor built from the local occupancy grid. The result of this instance-based learning process is used online to estimate which localisation method performs the best in the current environmental context. The switching process is facilitated by the use of the de facto standard Robot Operating System (ROS) framework. The system was instantiated in a differential-wheeled robot equipped with a short-range 2-D laser scanner, and successfully validated on a set of field trials.

The trends of manufacturing have now begun to call for a more adaptive and dynamic shop floor in the automation industry. The advancements in mobile robotics of recent decades have inspired and cemented a belief that multiple autonomous mobile robotic agents, often cooperatively sharing the workspace with humans, will significantly contribute to a truly flexible shop floor of the future. This article reports on the design specifications for one such robotic agent, the Intra-factory Mobile Assistant Unit (IMAU), able to carry material boxes between supermarkets and assembly stations, dynamically avoiding obstacles, throughout the shop floor. The solution will make shop floor logistics more flexible, reduce the allocated space for buffers, and, also, ease the human workload. The article will cover the sensing, actuation, communication, software architecture, and the seamless integration into the plant's execution system, which shape the autonomous logistics robot to be deployed into a working automotive shop floor during the ROBO-PARTNER project.

Testing and debugging real hardware is a time consuming task, in particular for the case of aquatic robots, for which it is necessary to transport and deploy the robots on the water. Performing waterborne and airborne field experiments with expensive hardware embedded in not yet fully functional prototypes is a highly risky endeavour. In this sense, physics-based 3D simulators are key for a fast paced and affordable development of such robotic systems. This paper contributes with a modular, open-source, and soon to be freely online available, ROS-based multi-robot simulator specially focused for aerial and water surface vehicles. This simulator is being developed as part of the RIVERWATCH experiment in the ECHORD european FP7 project. This experiment aims at demonstrating a multi-robot system for remote monitoring of riverine environments.

This paper presents ARES-III, a multi-purpose service robot for robust operation in all-terrain outdoor environments. Currently in pre-production phase, ARES-III is aimed to fulfil the requirements of a robotic platform that is able to support the development of real world applications in surveillance, agriculture, environmental monitoring, and other related domains. These demanding scenarios motivate a design focused on the reliability of the mechanical platform, the scalability of the control system, and the flexibility of its self-diagnosis and error recovery mechanisms. These are key features of ARES-III often disregarded in current commercial and research platforms. First, a comprehensive set of field trials demonstrated the ability of the ARES-III chassis, made of durable materials and with no-slip quasi-omnidirectional kinematic characteristics, to perform robustly in rough terrain. Second, supported by a control system fully compliant with the wide spread Robot Operating System (ROS), the scalability of ARES-III is enforced. Finally, the integration of active self-diagnosis and error recovery mechanisms in ARES-III control system fosters long lasting operation.