Research Papers
Here are the academic papers that I have published over the years. Recently I am researching about Simultaneous Localization and Mapping (SLAM) and Mobile Robotics. In order to read the full paper, just click the "Read more" button and you'll be sent to my research gate where you can download it.
PEOPLE FOLLOWING SYSTEM FOR HOLONOMIC ROBOTS USING AN RGB-D SENSOR - 2021
People following is an important task in mobile robotics, with applications in several areas, such as industry, hospitals and home services. Recent advances on deep learning techniques and the availability of RGB-D sensors resulted in a higher robustness in identifying the target during these tasks. This paper presents a system for people following using an RGB-D sensor. The proposed method uses object tracking, combined with a vision-based controller that exploits the advantages of the high maneuverability of holonomic robots. Experimental tests are performed with a mecanum-wheeled
robot equipped with an RGB-D camera to evaluate the effectiveness of the proposed approach.
Autonomous Navigation System for a Wall-painting Robot based on Map Corners - 2020
Wall-painting is an important task in construction that has an increasing necessity for automation. This paper presents a navigation system for a wall-painting robot based on map corners. Using an occupancy grid map as input of the system, the proposed method is able to generate a path following the walls of the environment. The main advantage of the proposed methodology is the ability to work in non-convex and open maps. The system is implemented as a ROS package and integrated with the ROS navigation stack. The method is tested in a simulator developed using ROS and Gazebo, a virtual environment that simulates the physics and dynamics of robotic systems.
Project and Development of a Mecanum-wheeled Robot for Au-tonomous Navigation Tasks - 2019
This paper presents the project and development of a Mecanum-wheeled robot for autonomous navigation tasks. The robot is equipped with odometry and a laser sensor for range scans. A Monte Carlo Localization algorithm is used to estimate the pose of the robot in a global coordinate system and, simultaneously, a Grid Map is generated with the range scans to enable navigation. Once the map is constructed, the robot is able to perform autonomous navigation, given a desired goal. The Robot Operating System (ROS), an open-source framework for writing robot software, is used as middleware.