Abstract
Teleoperation of autonomous mobile robots (AMR) is relevant in logistics operations to automate repetitive tasks that often result in injuries to the operator. This paper presents an overview of the systems involved in the current teleoperation scheme where these AMRs are present as well as some works and advances that have been done in the high-level teleoperation field.

Abstract
In the manufacturing domain, the digital twin has become an emerging concept for decision-making through the integration of what-if simulation capabilities. In such systems, the processing of the entire space of alternative solutions is very time-consuming; recommendation systems are used to solve this; however, these suffer from several problems, namely data sparsity and cold-start. The application of trust-based models can mitigate these problems, particularly the cold-start problems, by providing valuable background for the recommendation system. This paper presents the implementation and experimental validation of a trust-based model for improving the digital twin based what-if simulation recommendation system, addressing the cold-start problems. The proposed trust model was applied in an assembly line case study to recommend the best configurations for the optimal number of AGVs (Autonomous Guided Vehicles). The results show that applying the trust-based model with similarity metrics improved the mitigation of the cold-start problem. © 2022 IEEE.

Abstract
Purpose The purpose of this paper is to present a programming by demonstration (PbD) system based on 3D stereoscopic vision and inertial sensing that provides a cost-effective pose tracking system, even during error-prone situations, such as camera occlusions. Design/methodology/approach The proposed PbD system is based on the 6D Mimic innovative solution, whose six degrees of freedom marker hardware had to be revised and restructured to accommodate an IMU sensor. Additionally, a new software pipeline was designed to include this new sensing device, seeking the improvement of the overall system's robustness in stereoscopic vision occlusion situations. Findings The IMU component and the new software pipeline allow the 6D Mimic system to successfully maintain the pose tracking when the main tracking tool, i.e. the stereoscopic vision, fails. Therefore, the system improves in terms of reliability, robustness, and accuracy which were verified by real experiments. Practical implications Based on this proposal, the 6D Mimic system reaches a reliable and low-cost PbD methodology. Therefore, the robot can accurately replicate, on an industrial scale, the artisan level performance of highly skilled shop-floor operators. Originality/value To the best of the authors' knowledge, the sensor fusion between stereoscopic images and IMU applied to robot PbD is a novel approach. The system is entirely designed aiming to reduce costs and taking advantage of an offline processing step for data analysis, filtering and fusion, enhancing the reliability of the PbD system.

Abstract

Abstract
Robotics will play an essential role in agriculture. Deploying agricultural robots on the farm is still a challenging task due to the terrain's irregularity and size. Optimal path planning solutions may fail in larger terrains due to memory requirements as the search space increases. This work presents a novel open-source solution called AgRob Topologic Path Planner, which is capable of performing path planning operations using a hybrid map with topological and metric representations. A local A* algorithm pre-plans and saves local paths in local metric maps, saving them into the topological structure. Then, a graph-based A* performs a global search in the topological map, using the saved local paths to provide the full trajectory. Our results demonstrate that this solution could handle large maps (5 hectares) using just 0.002 % of the search space required by a previous solution.

Abstract
Bin picking is a highly researched topic, due to the need for automated procedures in industrial environments. A general bin picking system requires a highly structured process, starting with data acquisition, and ending with pose estimation and grasping. A high number of bin picking problems are being presently solved, through deep learning networks, combined with distinct procedures. This study provides a comprehensive review of deep learning approaches, implemented in bin picking problems. Throughout the review are described several approaches and learning methods based on specific domains, such as gripper oriented and object oriented, as well as summarized several methodologies, in order to solve bin picking issues. Furthermore, are introduced current strategies used to simplify particular cases and at last, are presented peculiar means of detecting object poses.