Simultaneous localization and mapping responds to the problem of building a map of the environment without any prior information and based on the data obtained from one or more sensors. In most situations, the robot is driven by a human operator, but some systems are capable of navigating autonomously while mapping, which is called active simultaneous localization and mapping. This strategy focuses on actively calculating the trajectories to explore the environment while building a map with a minimum error. In this paper, a comprehensive review of the research work developed in this field is provided, targeting the most relevant contributions in indoor mobile robotics.

This work focuses on the operation of picking an object on a table with a mobile manipulator. We use deep reinforcement learning (DRL) to learn a positioning policy for the robot’s base by considering the reachability constraints of the arm. This work extends our first proof-of-concept with the ultimate goal of validating the method on a real robot. Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm is used to model the base controller, and is optimised using the feedback from the MoveIt! based arm planner. The idea is to encourage the base controller to position itself in areas where the arm reaches the object. Following a simulation-to-reality approach, first we create a realistic simulation of the robotic environment in Unity, and integrate it in Robot Operating System (ROS). The drivers for both the base and the arm are also implemented. The DRL-based agent is trained in simulation and, both the robot and target poses are randomised to make the learnt base controller robust to uncertainties. We propose a task-specific setup for TD3, which includes state/action spaces, reward function and neural architectures. We compare the proposed method with the baseline work and show that the combination of TD3 and the proposed setup leads to a $$11\%$$11% higher success rate than with the baseline, with an overall success rate of $$97\%$$97% . Finally, the learnt agent is deployed and validated in the real robotic system where we obtain a promising success rate of $$75\%$$75% .

Surface defect identification based on computer vision algorithms often leads to inadequate generalization ability due to large intraclass variation. Diversity in lighting conditions, noise components, defect size, shape, and position make the problem challenging. To solve the problem, this paper develops a pixel-level image augmentation method that is based on image-to-image translation with generative adversarial neural networks (GANs) conditioned on fine-grained labels. The GAN model proposed in this work, referred to as Magna-Defect-GAN, is capable of taking control of the image generation process and producing image samples that are highly realistic in terms of variations. Firstly, the surface defect dataset based on the magnetic particle inspection (MPI) method is acquired in a controlled environment. Then, the Magna-Defect-GAN model is trained, and new synthetic image samples with large intraclass variations are generated. These synthetic image samples artificially inflate the training dataset size in terms of intraclass diversity. Finally, the enlarged dataset is used to train a defect identification model. Experimental results demonstrate that the Magna-Defect-GAN model can generate realistic and high-resolution surface defect images up to the resolution of 512 × 512 in a controlled manner. We also show that this augmentation method can boost accuracy and be easily adapted to any other surface defect identification models.

Computer vision based visual inspection systems are gaining enormous importance for manufacturing quality control in recent years due to the advent of Convolutional neural networks (CNN) and transformer-based (vision) models. CNN based models attempt to extract global features by gradually increasing the receptive field, while long-range dependencies are ignored. Therefore, CNN recognizes objects based on the texture instead of the shape. Transformer models, on the other hand, enable modeling long range dependencies using self-attention mechanism. But learning ability of spatial information inside each patch is limited, which means it can disregard a significant spatial local pattern, such as texture. In this work, we propose to combine transformer-based and CNN-based models to take advantage of the strengths of both methods. To meet inference time constraints of real time defect classification tasks, we exploit knowledge distillation method (KD) using softened logits of ensemble model as supervision to train a lightweight CNN model (Resnet18). The study showed that the proposed vision transformer-based KD approach overcome the requirements of limited computational resources and can be deployed on low-power and resource limited devices. The experimental results also showed that proposed framework outperforms in terms of mean accuracy on the test datasets compared to stand-alone CNN methods.

Industrial wireless communications will be an important technology enabler for the Industry 4.0 paradigm. However, the pervasive introduction of wireless communications in factories requires improving their reliability and capacity to support low latency communications. An approach to do so is through the introduction of redundancy. Several studies have analytically and through simulations demonstrated the benefits of exploiting redundancy in industrial wireless communications. This paper progresses the current state of the art by experimentally analyzing for the first time the benefits that redundancy in industrial wireless communications can provide to support mobile industrial applications. The analysis has been conducted in a collaborative robotics experimental facility under the framework of the H2020 AUTOW ARE project.

The use of autonomous robots for certain tasks within agriculture applications can bring many advantages. The H2020-funded GreenPatrol project has developed an autonomous system for pest detection and treatment within commercial greenhouses. In this system the robot will navigate autonomously and regularly inspect crops using an array of cameras and algorithms to detect and treat pests at an early stage in order to improve yield, reduce pesticide use and improve worker conditions. A key enabler for this application is the localization and navigation function of the robot platform. In order to operate independently and autonomously, the robot must know in real-time its precise location and direction of pointing, it must be able to plan a route through the greenhouse from its current location to where it needs to go, it must be able to control its movements to reach its required destination, and it must be able to identify and avoid obstacles that may obstruct its route. In order to achieve these goals the robot sub-systems include an absolute localization function, to provide precise absolute position and heading in a global reference frame in real-time, a relative localization function, to provide more fidelity of the exact location and orientation of the robot with respect to its surroundings in the greenhouse, and a navigation function, to plan the route through the greenhouse and provide movement instructions to the robot platform. This paper describes the localization system of the GreenPatrol robot and presents results of testing for each of the functions. The tests include simulations as well as data collections and tests of the real-time system using the robot platform. The results show the high performance of the positioning capability and heading information for the individual systems.