Cracks are pathologies whose appearance in ceramic tiles can cause various damages due to the coating system losing water tightness and impermeability functions. Besides, the detachment of a ceramic plate, exposing the building structure, can still reach people who move around the building. Manual inspection is the most common method for addressing this problem. However, it depends on the knowledge and experience of those who perform the analysis and demands a long time and a high cost to map the entire area. This work focuses on automated optical inspection to find faults in ceramic tiles performing the segmentation of cracks in ceramic images using deep learning to segment these defects. We propose an architecture for segmenting cracks in facades with Deep Learning that includes an image pre-processing step. We also propose the Ceramic Crack Database, a set of images to segment defects in ceramic tiles. The proposed model can adequately identify the crack even when it is close to or within the grout.

Reinforcement learning refers to a machine learning paradigm in which an agent interacts with the environment to learn how to perform a task. The characteristics of the environment may change over time or be affected by disturbances not controlled, avoiding the agent finding a proper policy. Some approaches attempt to address these problems, as interactive reinforcement learning, where an external entity helps the agent learn through advice. Other approaches, such as robust reinforcement learning, allow the agent to learn the task, acting in a disturbed environment. In this paper, we propose an approach that addresses interactive reinforcement learning problems in a dynamic environment, where advice provides information on the task and the dynamics of the environment. Thus, an agent learns a policy in a disturbed environment while receiving advice. We implement our approach in the dynamic version of the cart-pole balancing task and a simulated robotic arm dynamic environment to organize objects. Our results show that the proposed approach allows an agent to complete the task satisfactorily in a dynamic, continuous state-action domain. Moreover, experimental results suggest agents trained with our approach are less sensitive to changes in the characteristics of the environment than interactive reinforcement learning agents.

Human interaction starts with a person approaching another one, respecting their personal space to prevent uncomfortable feelings. Spatial behavior, called proxemics, allows defining an acceptable distance so that the interaction process begins appropriately. In recent decades, human-agent interaction has been an area of interest for researchers, where it is proposed that artificial agents naturally interact with people. Thus, new alternatives are needed to allow optimal communication, avoiding humans feeling uncomfortable. Several works consider proxemic behavior with cognitive agents, where human-robot interaction techniques and machine learning are implemented. However, it is assumed that the personal space is fixed and known in advance, and the agent is only expected to make an optimal trajectory toward the person. In this work, we focus on studying the behavior of a reinforcement learning agent in a proxemic-based environment. Experiments were carried out implementing a grid-world problem and a continuous simulated robotic approaching environment. These environments assume that there is an issuer agent that provides non-conformity information. Our results suggest that the agent can identify regions where the issuer feels uncomfortable and find the best path to approach the issuer. The results obtained highlight the usefulness of reinforcement learning in order to identify proxemic regions.

Interactive reinforcement learning is an approach in which an external trainer helps an agent to learn through advice. A trainer is useful in large or continuous scenarios; however, when the characteristics of the environment change over time, it can affect the learning. Robust reinforcement learning is a reliable approach that allows an agent to learn a task, regardless of disturbances in the environment. In this work, we present an approach that addresses interactive reinforcement learning problems in a dynamic environment with continuous states and actions. Our results show that the proposed approach allows an agent to complete the cart-pole balancing task satisfactorily in a dynamic, continuous action-state domain.

Conveyor belts are widely used tools in the industry. In them, different types of elements and materials are transported and being in constant and arduous work. The constant contact of the materials can compromise the integrity of the conveyor, even more so when it is used in mining to transport heavy minerals. In detecting anomalies in conveyor belts, an expert is necessary to inspect the conveyor, which leads to high costs and a danger to the worker. In recent years, the study of anomaly detection and deep learning has been increasing, so an automatic inspection of the conveyor is necessary. In this work, we implement a deep learning anomaly detection model to identify defects on the surface of a conveyor. We use the HALCON software to carry out an image acquisition process and the training of an anomaly detection model. This model has the advantage of using images with similar features and without anomalies for its training. These features are to classify those images with the same characteristics of the training set. Our results show that the model can identify anomalies with a precision and recall of 89% and 88%, respectively.