Abstract
Reliable operation of production lines without unscheduled disruptions is of paramount importance for ensuring the proper operation of automated working cells involving robotic systems. This article addresses the issue of preventing disruptions to an automotive production line that can arise from incorrect placement of aluminum car parts by a human operator in a feeding container with 4 indexing pins for each part. The detection of the misplaced parts is critical for avoiding collisions between the containers and a high pressure washing machine and also to avoid collisions between the parts and a robotic arm that is feeding parts to a air leakage inspection machine. The proposed inspection system relies on a 3D sensor for scanning the parts inside a container and then estimates the 6 DoF pose of the container followed by an analysis of the overlap percentage between each part reference point cloud and the 3D sensor data. When the overlap percentage is below a given threshold, the part is considered as misplaced and the operator is alerted to fix the part placement in the container. The deployment of the inspection system on an automotive production line for 22 weeks has shown promising results by avoiding 18 hours of disruptions, since it detected 407 containers having misplaced parts in 4524 inspections, from which 12 were false negatives, while no false positives were reported, which allowed the elimination of disruptions to the production line at the cost of manual reinspection of 0.27% of false negative containers by the operator. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Abstract
Intelligent wheelchairs aim to improve mobility limitations by providing ingenious mechanisms to control and move the chair. This paper aims to enhance the autonomy level of intelligent wheelchair navigation by applying reinforcement learning algorithms to move the chair to the desired location. Also, as a second objective, add one more chair and move both chairs in pairs to promote group social activities. The experimental setup is based on a simulated environment using gazebo and ROS where a leader chair moves towards a goal, and the follower chair should navigate near the leader chair. The collected metrics (time to complete the task and the trajectories of the chairs) demonstrated that Deep Q-Network (DQN) achieved better results than the Q-Learning algorithm by being the unique algorithm to accomplish the pair navigation behaviour between two chairs.

Abstract
Robotics is an ever-growing field, used in countless applications, from domestic to industrial, and taught in advanced courses of multiple higher education institutions. Robot Operating System (ROS), the most prominent robotics architecture, integrates several of these, and has recently moved to a new iteration in the form of ROS2. This project aims to design a complete educational package meant for teaching intelligent robotics in ROS1 and ROS2. A foundation for the package was constructed, using a small differential drive robot equipped with camera-based virtual sensors, a representation in the Flatland simulator, and introductory lessons to both ROS versions and Reinforcement Learning (RL) in robotics. To evaluate the package's pertinence, expected learning outcomes were set and the lessons were tested with users from varying backgrounds and levels of robotics experience. Encouraging results were obtained, especially in the ROS1 and ROS2 lessons, while the feedback from the RL lesson provided clear indications for future improvements. Therefore, this work provides solid groundwork for a more comprehensive educational package on robotics and ROS.

Abstract
To tackle wildfires and improve forest biomass management, cost effective and reliable mowing and pruning robots are required. However, the development of visual perception systems for forestry robotics needs to be researched and explored to achieve safe solutions. This paper presents two main contributions: an annotated dataset and a benchmark between edge-computing hardware and deep learning models. The dataset is composed by nearly 5,400 annotated images. This dataset enabled to train nine object detectors: four SSD MobileNets, one EfficientDet, three YOLO-based detectors and YOLOR. These detectors were deployed and tested on three edge-computing hardware (TPU, CPU and GPU), and evaluated in terms of detection precision and inference time. The results showed that YOLOR was the best trunk detector achieving nearly 90% F1 score and an inference average time of 13.7ms on GPU. This work will favour the development of advanced vision perception systems for robotics in forestry operations.

Abstract
Bin picking is a challenging problem that involves using a robotic manipulator to remove, one-by-one, a set of objects randomly stacked in a container. When the objects are prone to entanglement, having an estimation of their pose and shape is highly valuable for more reliable grasp and motion planning. This paper focuses on modeling entangled tubes with varying degrees of curvature. An unconventional machine learning technique, Inductive Logic Programming (ILP), is used to construct sets of rules (theories) capable of modeling multiple tubes when given the cylinders that constitute them. Datasets of entangled tubes are created via simulation in Gazebo. Experiments using Aleph and SWI-Prolog illustrate how ILP can build explainable theories with a high performance, using a relatively small dataset and low amount of time for training. Therefore, this work serves as a proof-of-concept that ILP is a valuable method to acquire knowledge and validate heuristics for pose and shape estimation in complex bin picking scenarios.