Fernando Tello Gamarra - Academia.edu (original) (raw)

Papers by Fernando Tello Gamarra

arXiv (Cornell University), Aug 13, 2022

Robotics simulation has been an integral part of research and development in the robotics area. T... more Robotics simulation has been an integral part of research and development in the robotics area. The simulation eliminates the possibility of harm to sensors, motors, and the physical structure of a real robot by enabling robotics application testing to be carried out quickly and affordably without being subjected to mechanical or electronic errors. Simulation through virtual reality (VR) offers a more immersive experience by providing better visual cues of environments, making it an appealing alternative for interacting with simulated robots. This immersion is crucial, particularly when discussing sociable robots, a subarea of the human-robot interaction (HRI) field. The widespread use of robots in daily life depends on HRI. In the future, robots will be able to interact effectively with people to perform a variety of tasks in human civilization. It is crucial to develop simple and understandable interfaces for robots as they begin to proliferate in the personal workspace. Due to this, in this study, we implement a VR robotic framework with readyto-use tools and packages to enhance research and application development in social HRI. Since the entire VR interface is an open-source project, the tests can be conducted in an immersive environment without needing a physical robot.

Lecture notes in networks and systems, 2023

In this work, we present two Deep Reinforcement Learning (Deep-RL) approaches to enhance the prob... more In this work, we present two Deep Reinforcement Learning (Deep-RL) approaches to enhance the problem of mapless navigation for a terrestrial mobile robot. Our methodology focus on comparing a Deep-RL technique based on the Deep Q-Network (DQN) algorithm with a second one based on the Double Deep Q-Network (DDQN) algorithm. We use 24 laser measurement samples and the relative position and angle of the agent to the target as information for our agents, which provide the actions as velocities for our robot. By using a low-dimensional sensing structure of learning, we show that it is possible to train an agent to perform navigation-related tasks and obstacle avoidance without using complex sensing information. The proposed methodology was successfully used in three distinct simulated environments. Overall, it was shown that Double Deep structures further enhance the problem for the navigation of mobile robots when compared to the ones with simple Q structures.

arXiv (Cornell University), Jan 26, 2023

In this work, we present two Deep Reinforcement Learning (Deep-RL) approaches to enhance the prob... more In this work, we present two Deep Reinforcement Learning (Deep-RL) approaches to enhance the problem of mapless navigation for a terrestrial mobile robot. Our methodology focus on comparing a Deep-RL technique based on the Deep Q-Network (DQN) algorithm with a second one based on the Double Deep Q-Network (DDQN) algorithm. We use 24 laser measurement samples and the relative position and angle of the agent to the target as information for our agents, which provide the actions as velocities for our robot. By using a low-dimensional sensing structure of learning, we show that it is possible to train an agent to perform navigation-related tasks and obstacle avoidance without using complex sensing information. The proposed methodology was successfully used in three distinct simulated environments. Overall, it was shown that Double Deep structures further enhance the problem for the navigation of mobile robots when compared to the ones with simple Q structures.

2022 Latin American Robotics Symposium (LARS), 2022 Brazilian Symposium on Robotics (SBR), and 2022 Workshop on Robotics in Education (WRE)

arXiv (Cornell University), Sep 27, 2022

Human-robot interaction (HRI) is essential to the widespread use of robots in daily life. Robots ... more Human-robot interaction (HRI) is essential to the widespread use of robots in daily life. Robots will eventually be able to carry out a variety of duties in human civilization through effective social interaction. Creating straightforward and understandable interfaces to engage with robots as they start to proliferate in the personal workspace is essential. Typically, interactions with simulated robots are displayed on screens. A more appealing alternative is virtual reality (VR), which gives visual cues more like those seen in the real world. In this study, we introduce Jubileo, a robotic animatronic face with various tools for research and application development in human-robot social interaction field. Jubileo project offers more than just a fully functional open-source physical robot; it also gives a comprehensive framework to operate with a VR interface, enabling an immersive environment for HRI application tests and noticeably better deployment speed.

IEEE Latin America Transactions, 2022

The goal of this work is to analyze and compare trajectory planners for a mobile robot in Robot O... more The goal of this work is to analyze and compare trajectory planners for a mobile robot in Robot Operating System (ROS), focusing on the performance of local planners on symmetric and asymmetric environments. In addition, two global planners, Dijkstra and A-star, are implemented in order to have a complete analysis and comprehension of the navigation architecture. Two local planning algorithms, Dynamic Window Approach and Timed Elastic Bands, are analyzed and compared more in depth using the mobile robot TurtleBot 3 Burger, an open-source and low-cost platform. The analyzed criteria were geometric and angular precision of the final position and orientation, time and distance of the complete trajectory, and usage of computational power. Experiments were carried out in two environments with different spatial arrangement of obstacles, with the intention of analyzing the behavior both in simulation with the Gazebo software and in the real robot. Both local planning algorithms enabled the robot to reach the target destination without any collisions, presenting the main difference in the usage of processing power.

Anais do 14º Simpósio Brasileiro de Automação Inteligente

In this paper the construction and structure for the implementation of linear and angular velocit... more In this paper the construction and structure for the implementation of linear and angular velocity controllers of a selfbalanced differential robot using the NI myRIO embedded system and the LabVIEW software are presented. Each of the two wheels of the robot has a PID speed controller, and a low-resolution encoder, so this makes the speed measurement have abrupt variations, consequently compromising the quality of the action of the controllers in the process. To solve such problem, we used the one-dimensional Kalman filter. In addition to the implementation of the linear and angular velocity controllers and the wheel speed controllers of the robot, the control system must act in self-balancing. At the end, practical results, conclusions and recommendations are presented. Resumo: Neste artigo são apresentadas a construção e uma estrutura para a implementação de controladores de velocidade linear e angular de um robô diferencial auto equilibrado utilizando o sistema embarcado NI myRIO e o software LabVIEW. Cada uma das duas rodas do robô possui um controlador de velocidade PID, e um encoder de baixa resolução, portanto, isto faz que a medição da velocidade tenha variações bruscas, consequentemente, comprometendo a qualidade da ação dos controladores no processo. Para resolver tal problema, utilizou-se o Filtro de Kalman de uma dimensão. Além da implementação dos controladores de velocidade linear, angular e das velocidades das rodas; o sistema de controle deve também atuar nas rodas para manter o equilíbrio. Ao final, são apresentados resultados práticos, conclusões e recomendações.

Advances in Intelligent Systems and Computing

Compared to other traditional imaging exams, computed tomography (CT) is more efficient, where a ... more Compared to other traditional imaging exams, computed tomography (CT) is more efficient, where a digital geometry processing is used to generate a 3D image of an internal structure of an object, or patient, from a series of 2D images obtained during various rotations of the CT scan around the scanned object. Also taking in consideration traditional imaging exams such as MRI or ultrasound, for example, the CT technique uses higher radiation doses than these exams, providing high quality images. However, in order to prevent constant exposures to high radiation doses, low-dose computed tomography (LDCT) scans are often recommended. Nevertheless, the images acquired in LDCT scans are degraded by undesirable artifacts, known as noise, which affects negatively the image quality. In this study, a two-stage filter based on morphological operators and Block-Matching 3D (BM3D) is proposed to remove noise in low-dose dental CT images. The quantitative results obtained by our proposed method demonstrated superior performance when compared to several state of the art techniques. Also, our proposed method obtained better visual performance, removing the noise and preserving details more efficiently than the compared filters.

Advances in Intelligent Systems and Computing

Advances in Intelligent Systems and Computing

In this paper, we use data from the Microsoft Kinect sensor that processes the captured image of ... more In this paper, we use data from the Microsoft Kinect sensor that processes the captured image of a person, thus, reducing the number of data in just joints on each frame. Then, we propose a creation of an image from all the frames removed from the movement, which facilitates training in a convolutional neural network. Finally, we trained a CNN using two different forms of training: combined training and individual training using the MSRC-12 dataset. Thus, the trained network obtained an accuracy rate of 86.67% in combined training and 90.78% of accuracy rate in the individual training, which is a very good performance compared to related works. This demonstrates that networks based on convolutional networks can be effective for the recognition of human actions using joints.

Advances in Intelligent Systems and Computing

This work aims to compare the application of two controllers for a mobile robot in a trajectory t... more This work aims to compare the application of two controllers for a mobile robot in a trajectory tracking task. The first method uses a heuristic approach based on the prior knowledge of the designer, while the second method uses a mathematical model based on the robot kinematics. Both systems employ the estimated robot position derived from an image processing algorithm. The paper shows experimental results with a real robot following a predefined path to explore the use of these techniques.

Journal of Intelligent & Fuzzy Systems

This article describes the use of the Deep Deterministic Policy Gradient network, a deep reinforc... more This article describes the use of the Deep Deterministic Policy Gradient network, a deep reinforcement learning algorithm, for mobile robot navigation. The neural network structure has as inputs laser range findings, angular and linear velocities of the robot, and position and orientation of the mobile robot with respect to a goal position. The outputs of the network will be the angular and linear velocities used as control signals for the robot. The experiments demonstrated that deep reinforcement learning’s techniques that uses continuous actions, are efficient for decision-making in a mobile robot. Nevertheless, the design of the reward functions constitutes an important issue in the performance of deep reinforcement learning algorithms. In order to show the performance of the Deep Reinforcement Learning algorithm, we have applied successfully the proposed architecture in simulated environments and in experiments with a real robot.

Studies in health technology and informatics, 2019

During the acquisition on a low-dose radiation computed tomography (CT) scan, images are usually ... more During the acquisition on a low-dose radiation computed tomography (CT) scan, images are usually marked by heavy noise and undesired artifacts, which dramatically reduce its applicability in the image processing workflow. A noise reduction and detail preservation filter based on mathematical morphology is presented in this paper. The filter is geared to allow control of an opening operator followed by a systematic contrast limited adaptive histogram equalization (CLAHE) in conjunction with a reconstruction by dilation in last stage. A quantitative metric built on peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and mean-squared error (MSE) were applied to check noise reduction, detail preservation, and performance. The results obtained by the proposed filter were compared with those obtained in the literature, showing very good results: compared with the best-tested filter, the filter had a gain of 7.91% on PSNR, 7.57% on SSIM and 37.8% on MSE.

2019 32nd SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), 2019

The impact in reducing the radiation dose in computed tomography (CT) exams is directly related t... more The impact in reducing the radiation dose in computed tomography (CT) exams is directly related to the quality of the images obtained in these exams. Such images are degraded by undesirable artifacts, known as noise. In order to improve the quality of these images and provide an accurate medical diagnosis, it is necessary to apply noise reduction techniques. In this study, a method based on structural segmentation and filtering through morphological operators along with a BM3D filtering is proposed to reduce noise and preserve details in low-dose CT dental images. Experimental results of the proposed method were compared with several existing methods and validated using the PSNR, SSIM, MSE and EPI metrics. Our method demonstrated superior performance among the evaluated filters. In comparison to the filter that obtained the best results, our method had a gain of 12.46% on PSNR, 11.11% on SSIM, 14.5% on MSE and 9.63% on EPI metrics.

This work aims to compare the application of two tracking controllers for a mobile robot in a tra... more This work aims to compare the application of two tracking controllers for a mobile robot in a trajectory tracking task. The first method uses a heuristic approach based on the prior knowledge of the designer, while the second method uses mathematical model based on the robot kinematics. Both systems employ the estimated robot position derived from the encoder sensors using the dead reckoning method. The paper shows experimental results with a real robot following a predefined path to explore the use of these techniques.

This work aims to compare the application of two controllers for a mobile robot in a trajectory t... more This work aims to compare the application of two controllers for a mobile robot in a trajectory tracking task. The first method uses a heuristic approach based on the prior knowledge of the designer, while the second method uses a mathematical model based on the robot kinematics. Both systems employ the estimated robot position derived from an image processing algorithm. The paper shows experimental results with a real robot following a predefined path to explore the use of these techniques.

This work proposes a system to detect visual defects in an optical fiber. Fibers of different typ... more This work proposes a system to detect visual defects in an optical fiber. Fibers of different types and with different simulated deformations were used, looking for an approximation of a real case of defect in an optical fiber. Some continuous fiber patterns were detected in images captured with a microscopic camera. The identification of these patterns was searched using different image processing techniques, such as edge detection, line detection and feature descriptors. In order to classify images of the fibers in good and defective ones, a fuzzy classifier was used. Experimental results of the algorithm are shown and is demonstrated that the proposed method helps to detect defects and classify optical fibers.

arXiv (Cornell University), Aug 13, 2022

Robotics simulation has been an integral part of research and development in the robotics area. T... more Robotics simulation has been an integral part of research and development in the robotics area. The simulation eliminates the possibility of harm to sensors, motors, and the physical structure of a real robot by enabling robotics application testing to be carried out quickly and affordably without being subjected to mechanical or electronic errors. Simulation through virtual reality (VR) offers a more immersive experience by providing better visual cues of environments, making it an appealing alternative for interacting with simulated robots. This immersion is crucial, particularly when discussing sociable robots, a subarea of the human-robot interaction (HRI) field. The widespread use of robots in daily life depends on HRI. In the future, robots will be able to interact effectively with people to perform a variety of tasks in human civilization. It is crucial to develop simple and understandable interfaces for robots as they begin to proliferate in the personal workspace. Due to this, in this study, we implement a VR robotic framework with readyto-use tools and packages to enhance research and application development in social HRI. Since the entire VR interface is an open-source project, the tests can be conducted in an immersive environment without needing a physical robot.

Lecture notes in networks and systems, 2023

In this work, we present two Deep Reinforcement Learning (Deep-RL) approaches to enhance the prob... more In this work, we present two Deep Reinforcement Learning (Deep-RL) approaches to enhance the problem of mapless navigation for a terrestrial mobile robot. Our methodology focus on comparing a Deep-RL technique based on the Deep Q-Network (DQN) algorithm with a second one based on the Double Deep Q-Network (DDQN) algorithm. We use 24 laser measurement samples and the relative position and angle of the agent to the target as information for our agents, which provide the actions as velocities for our robot. By using a low-dimensional sensing structure of learning, we show that it is possible to train an agent to perform navigation-related tasks and obstacle avoidance without using complex sensing information. The proposed methodology was successfully used in three distinct simulated environments. Overall, it was shown that Double Deep structures further enhance the problem for the navigation of mobile robots when compared to the ones with simple Q structures.

arXiv (Cornell University), Jan 26, 2023

In this work, we present two Deep Reinforcement Learning (Deep-RL) approaches to enhance the prob... more In this work, we present two Deep Reinforcement Learning (Deep-RL) approaches to enhance the problem of mapless navigation for a terrestrial mobile robot. Our methodology focus on comparing a Deep-RL technique based on the Deep Q-Network (DQN) algorithm with a second one based on the Double Deep Q-Network (DDQN) algorithm. We use 24 laser measurement samples and the relative position and angle of the agent to the target as information for our agents, which provide the actions as velocities for our robot. By using a low-dimensional sensing structure of learning, we show that it is possible to train an agent to perform navigation-related tasks and obstacle avoidance without using complex sensing information. The proposed methodology was successfully used in three distinct simulated environments. Overall, it was shown that Double Deep structures further enhance the problem for the navigation of mobile robots when compared to the ones with simple Q structures.

2022 Latin American Robotics Symposium (LARS), 2022 Brazilian Symposium on Robotics (SBR), and 2022 Workshop on Robotics in Education (WRE)

arXiv (Cornell University), Sep 27, 2022

Human-robot interaction (HRI) is essential to the widespread use of robots in daily life. Robots ... more Human-robot interaction (HRI) is essential to the widespread use of robots in daily life. Robots will eventually be able to carry out a variety of duties in human civilization through effective social interaction. Creating straightforward and understandable interfaces to engage with robots as they start to proliferate in the personal workspace is essential. Typically, interactions with simulated robots are displayed on screens. A more appealing alternative is virtual reality (VR), which gives visual cues more like those seen in the real world. In this study, we introduce Jubileo, a robotic animatronic face with various tools for research and application development in human-robot social interaction field. Jubileo project offers more than just a fully functional open-source physical robot; it also gives a comprehensive framework to operate with a VR interface, enabling an immersive environment for HRI application tests and noticeably better deployment speed.

IEEE Latin America Transactions, 2022

The goal of this work is to analyze and compare trajectory planners for a mobile robot in Robot O... more The goal of this work is to analyze and compare trajectory planners for a mobile robot in Robot Operating System (ROS), focusing on the performance of local planners on symmetric and asymmetric environments. In addition, two global planners, Dijkstra and A-star, are implemented in order to have a complete analysis and comprehension of the navigation architecture. Two local planning algorithms, Dynamic Window Approach and Timed Elastic Bands, are analyzed and compared more in depth using the mobile robot TurtleBot 3 Burger, an open-source and low-cost platform. The analyzed criteria were geometric and angular precision of the final position and orientation, time and distance of the complete trajectory, and usage of computational power. Experiments were carried out in two environments with different spatial arrangement of obstacles, with the intention of analyzing the behavior both in simulation with the Gazebo software and in the real robot. Both local planning algorithms enabled the robot to reach the target destination without any collisions, presenting the main difference in the usage of processing power.

Anais do 14º Simpósio Brasileiro de Automação Inteligente

In this paper the construction and structure for the implementation of linear and angular velocit... more In this paper the construction and structure for the implementation of linear and angular velocity controllers of a selfbalanced differential robot using the NI myRIO embedded system and the LabVIEW software are presented. Each of the two wheels of the robot has a PID speed controller, and a low-resolution encoder, so this makes the speed measurement have abrupt variations, consequently compromising the quality of the action of the controllers in the process. To solve such problem, we used the one-dimensional Kalman filter. In addition to the implementation of the linear and angular velocity controllers and the wheel speed controllers of the robot, the control system must act in self-balancing. At the end, practical results, conclusions and recommendations are presented. Resumo: Neste artigo são apresentadas a construção e uma estrutura para a implementação de controladores de velocidade linear e angular de um robô diferencial auto equilibrado utilizando o sistema embarcado NI myRIO e o software LabVIEW. Cada uma das duas rodas do robô possui um controlador de velocidade PID, e um encoder de baixa resolução, portanto, isto faz que a medição da velocidade tenha variações bruscas, consequentemente, comprometendo a qualidade da ação dos controladores no processo. Para resolver tal problema, utilizou-se o Filtro de Kalman de uma dimensão. Além da implementação dos controladores de velocidade linear, angular e das velocidades das rodas; o sistema de controle deve também atuar nas rodas para manter o equilíbrio. Ao final, são apresentados resultados práticos, conclusões e recomendações.

Advances in Intelligent Systems and Computing

Compared to other traditional imaging exams, computed tomography (CT) is more efficient, where a ... more Compared to other traditional imaging exams, computed tomography (CT) is more efficient, where a digital geometry processing is used to generate a 3D image of an internal structure of an object, or patient, from a series of 2D images obtained during various rotations of the CT scan around the scanned object. Also taking in consideration traditional imaging exams such as MRI or ultrasound, for example, the CT technique uses higher radiation doses than these exams, providing high quality images. However, in order to prevent constant exposures to high radiation doses, low-dose computed tomography (LDCT) scans are often recommended. Nevertheless, the images acquired in LDCT scans are degraded by undesirable artifacts, known as noise, which affects negatively the image quality. In this study, a two-stage filter based on morphological operators and Block-Matching 3D (BM3D) is proposed to remove noise in low-dose dental CT images. The quantitative results obtained by our proposed method demonstrated superior performance when compared to several state of the art techniques. Also, our proposed method obtained better visual performance, removing the noise and preserving details more efficiently than the compared filters.

Advances in Intelligent Systems and Computing

Advances in Intelligent Systems and Computing

In this paper, we use data from the Microsoft Kinect sensor that processes the captured image of ... more In this paper, we use data from the Microsoft Kinect sensor that processes the captured image of a person, thus, reducing the number of data in just joints on each frame. Then, we propose a creation of an image from all the frames removed from the movement, which facilitates training in a convolutional neural network. Finally, we trained a CNN using two different forms of training: combined training and individual training using the MSRC-12 dataset. Thus, the trained network obtained an accuracy rate of 86.67% in combined training and 90.78% of accuracy rate in the individual training, which is a very good performance compared to related works. This demonstrates that networks based on convolutional networks can be effective for the recognition of human actions using joints.

Advances in Intelligent Systems and Computing

This work aims to compare the application of two controllers for a mobile robot in a trajectory t... more This work aims to compare the application of two controllers for a mobile robot in a trajectory tracking task. The first method uses a heuristic approach based on the prior knowledge of the designer, while the second method uses a mathematical model based on the robot kinematics. Both systems employ the estimated robot position derived from an image processing algorithm. The paper shows experimental results with a real robot following a predefined path to explore the use of these techniques.

Journal of Intelligent & Fuzzy Systems

This article describes the use of the Deep Deterministic Policy Gradient network, a deep reinforc... more This article describes the use of the Deep Deterministic Policy Gradient network, a deep reinforcement learning algorithm, for mobile robot navigation. The neural network structure has as inputs laser range findings, angular and linear velocities of the robot, and position and orientation of the mobile robot with respect to a goal position. The outputs of the network will be the angular and linear velocities used as control signals for the robot. The experiments demonstrated that deep reinforcement learning’s techniques that uses continuous actions, are efficient for decision-making in a mobile robot. Nevertheless, the design of the reward functions constitutes an important issue in the performance of deep reinforcement learning algorithms. In order to show the performance of the Deep Reinforcement Learning algorithm, we have applied successfully the proposed architecture in simulated environments and in experiments with a real robot.

Studies in health technology and informatics, 2019

During the acquisition on a low-dose radiation computed tomography (CT) scan, images are usually ... more During the acquisition on a low-dose radiation computed tomography (CT) scan, images are usually marked by heavy noise and undesired artifacts, which dramatically reduce its applicability in the image processing workflow. A noise reduction and detail preservation filter based on mathematical morphology is presented in this paper. The filter is geared to allow control of an opening operator followed by a systematic contrast limited adaptive histogram equalization (CLAHE) in conjunction with a reconstruction by dilation in last stage. A quantitative metric built on peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and mean-squared error (MSE) were applied to check noise reduction, detail preservation, and performance. The results obtained by the proposed filter were compared with those obtained in the literature, showing very good results: compared with the best-tested filter, the filter had a gain of 7.91% on PSNR, 7.57% on SSIM and 37.8% on MSE.

2019 32nd SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), 2019

The impact in reducing the radiation dose in computed tomography (CT) exams is directly related t... more The impact in reducing the radiation dose in computed tomography (CT) exams is directly related to the quality of the images obtained in these exams. Such images are degraded by undesirable artifacts, known as noise. In order to improve the quality of these images and provide an accurate medical diagnosis, it is necessary to apply noise reduction techniques. In this study, a method based on structural segmentation and filtering through morphological operators along with a BM3D filtering is proposed to reduce noise and preserve details in low-dose CT dental images. Experimental results of the proposed method were compared with several existing methods and validated using the PSNR, SSIM, MSE and EPI metrics. Our method demonstrated superior performance among the evaluated filters. In comparison to the filter that obtained the best results, our method had a gain of 12.46% on PSNR, 11.11% on SSIM, 14.5% on MSE and 9.63% on EPI metrics.

This work aims to compare the application of two tracking controllers for a mobile robot in a tra... more This work aims to compare the application of two tracking controllers for a mobile robot in a trajectory tracking task. The first method uses a heuristic approach based on the prior knowledge of the designer, while the second method uses mathematical model based on the robot kinematics. Both systems employ the estimated robot position derived from the encoder sensors using the dead reckoning method. The paper shows experimental results with a real robot following a predefined path to explore the use of these techniques.

This work aims to compare the application of two controllers for a mobile robot in a trajectory t... more This work aims to compare the application of two controllers for a mobile robot in a trajectory tracking task. The first method uses a heuristic approach based on the prior knowledge of the designer, while the second method uses a mathematical model based on the robot kinematics. Both systems employ the estimated robot position derived from an image processing algorithm. The paper shows experimental results with a real robot following a predefined path to explore the use of these techniques.

This work proposes a system to detect visual defects in an optical fiber. Fibers of different typ... more This work proposes a system to detect visual defects in an optical fiber. Fibers of different types and with different simulated deformations were used, looking for an approximation of a real case of defect in an optical fiber. Some continuous fiber patterns were detected in images captured with a microscopic camera. The identification of these patterns was searched using different image processing techniques, such as edge detection, line detection and feature descriptors. In order to classify images of the fibers in good and defective ones, a fuzzy classifier was used. Experimental results of the algorithm are shown and is demonstrated that the proposed method helps to detect defects and classify optical fibers.