UAV Visual and Thermographic Power Line Detection Using Deep Learning.

Inspecting and maintaining power lines is essential for ensuring the safety, reliability, and efficiency of electrical infrastructure. This process involves regular assessment to identify hazards such as damaged wires, corrosion, or vegetation encroachment, followed by timely maintenance to prevent accidents and power outages. By conducting routine inspections and maintenance, utilities can comply with regulations, enhance operational efficiency, and extend the lifespan of power lines and equipment. Unmanned Aerial Vehicles (UAVs) can play a relevant role in this process by increasing efficiency through rapid coverage of large areas and access to difficult-to-reach locations, enhanced safety by minimizing risks to personnel in hazardous environments, and cost-effectiveness compared to traditional methods. UAVs equipped with sensors such as visual and thermographic cameras enable the accurate collection of high-resolution data, facilitating early detection of defects and other potential issues. To ensure the safety of the autonomous inspection process, UAVs must be capable of performing onboard processing, particularly for detection of power lines and obstacles. In this paper, we address the development of a deep learning approach with YOLOv8 for power line detection based on visual and thermographic images. The developed solution was validated with a UAV during a power line inspection mission, obtaining mAP@0.5 results of over 90.5% on visible images and over 96.9% on thermographic images.

Augmented Reality for Human-Robot Collaboration and Cooperation in Industrial Applications: A Systematic Literature Review.

With the continuously growing usage of collaborative robots in industry, the need for achieving a seamless human-robot interaction has also increased, considering that it is a key factor towards reaching a more flexible, effective, and efficient production line. As a prominent and prospective tool to support the human operator to understand and interact with robots, Augmented Reality (AR) has been employed in numerous human-robot collaborative and cooperative industrial applications. Therefore, this systematic literature review critically appraises 32 papers' published between 2016 and 2021 to identify the main employed AR technologies, outline the current state of the art of augmented reality for human-robot collaboration and cooperation, and point out future developments for this research field. Results suggest that this is still an expanding research field, especially with the advent of recent advancements regarding head-mounted displays (HMDs). Moreover, projector-based and HMDs developed approaches are showing promising positive influences over operator-related aspects such as performance, task awareness, and safety feeling, even though HMDs need further maturation in ergonomic aspects. Further research should focus on large-scale assessment of the proposed solutions in industrial environments, involving the solution's target audience, and on establishing standards and guidelines for developing AR assistance systems.

Programming Robots by Demonstration Using Augmented Reality.

The world is living the fourth industrial revolution, marked by the increasing intelligence and automation of manufacturing systems. Nevertheless, there are types of tasks that are too complex or too expensive to be fully automated, it would be more efficient if the machines were able to work with the human, not only by sharing the same workspace but also as useful collaborators. A possible solution to that problem is on human-robot interaction systems, understanding the applications where they can be helpful to implement and what are the challenges they face. This work proposes the development of an industrial prototype of a human-machine interaction system through Augmented Reality, in which the objective is to enable an industrial operator without any programming experience to program a robot. The system itself is divided into two different parts: the tracking system, which records the operator's hand movement, and the translator system, which writes the program to be sent to the robot that will execute the task. To demonstrate the concept, the user drew geometric figures, and the robot was able to replicate the operator's path recorded.

Evaluating the Single-Shot MultiBox Detector and YOLO Deep Learning Models for the Detection of Tomatoes in a Greenhouse.

The development of robotic solutions for agriculture requires advanced perception capabilities that can work reliably in any crop stage. For example, to automatise the tomato harvesting process in greenhouses, the visual perception system needs to detect the tomato in any life cycle stage (flower to the ripe tomato). The state-of-the-art for visual tomato detection focuses mainly on ripe tomato, which has a distinctive colour from the background. This paper contributes with an annotated visual dataset of green and reddish tomatoes. This kind of dataset is uncommon and not available for research purposes. This will enable further developments in edge artificial intelligence for in situ and in real-time visual tomato detection required for the development of harvesting robots. Considering this dataset, five deep learning models were selected, trained and benchmarked to detect green and reddish tomatoes grown in greenhouses. Considering our robotic platform specifications, only the Single-Shot MultiBox Detector (SSD) and YOLO architectures were considered. The results proved that the system can detect green and reddish tomatoes, even those occluded by leaves. SSD MobileNet v2 had the best performance when compared against SSD Inception v2, SSD ResNet 50, SSD ResNet 101 and YOLOv4 Tiny, reaching an F1-score of 66.15%, an mAP of 51.46% and an inference time of 16.44ms with the NVIDIA Turing Architecture platform, an NVIDIA Tesla T4, with 12 GB. YOLOv4 Tiny also had impressive results, mainly concerning inferring times of about 5 ms.

Autonomous wheelchair for patient's transportation on healthcare institutions.

The transport of patients from the inpatient service to the operating room is a recurrent task in a hospital routine. This task is repetitive, non-ergonomic, time consuming, and requires the labor of patient transporters. In this paper is presented a system, named Connected Driverless Wheelchair, that can receive transportation requests directly from the hospital information management system, pick up patients at their beds, navigate autonomously through different floors, avoid obstacles, communicate with elevators, and drop patients off at the designated operating room. As a result, a prototype capable of transporting patients autonomously in hospital environments was obtained. Although it was impossible to test the final developed system at the hospital as planned, due to the COVID-19 pandemic, the extensive tests conducted at the robotics laboratory facilities, and our previous experience in integrating mobile robots in hospitals, allowed to conclude that it is perfectly prepared for this integration to be carried out. The achieved results are relevant since this is a system that may be applied to support these types of tasks in the future, making the transport of patients more efficient (both from a cost and time perspective), without unpredictable delays and, in some cases, safer.

Persistently-exciting signal generation for Optimal Parameter Estimation of constrained nonlinear dynamical systems.

This work presents a novel methodology for Sub-Optimal Excitation Signal Generation and Optimal Parameter Estimation of constrained nonlinear systems. It is proposed that the evaluation of each signal must also account for the difference between real and estimated system parameters. However, this metric is not directly obtained once the real parameter values are not known. The alternative presented here is to adopt the hypothesis that, if a system can be approximated by a white box model, this model can be used as a benchmark to indicate the impact of a signal over the parametric estimation. In this way, the proposed method uses a dual layer optimization methodology: (i) Inner Level; For a given excitation signal a nonlinear optimization method searches for the optimal set of parameters that minimizes the error between the outputs of the optimized and benchmark models. (ii) At the outer level, a metaheuristic optimization method is responsible for constructing the best excitation signal, considering the fitness coming from the inner level, the quadratic difference between its parameters and the cost related to the time and space required to execute the experiment.

IntellWheels: modular development platform for intelligent wheelchairs.

Intelligent wheelchairs (IWs) can become an important solution to the challenge of assisting individuals who have disabilities and are thus unable to perform their daily activities using classic powered wheelchairs. This article describes the concept and design of IntellWheels, a modular platform to facilitate the development of IWs through a multiagent system paradigm. In fact, modularity is achieved not only in the software perspective, but also through a generic hardware framework that was designed to fit, in a straightforward manner, almost any commercial powered wheelchair. Experimental results demonstrate the successful integration of all modules in the platform, providing safe motion to the IW. Furthermore, the results achieved with a prototype running in autonomous mode in simulated and mixed-reality environments also demonstrate the potential of our approach. Although some future research is still necessary to fully accomplish our objectives, preliminary tests have shown that IntellWheels will effectively reduce users' limitations, offering them a much more independent life.