Showing papers by "Rogelio Lozano published in 2018"

Towards automatic inspection: crack recognition based on Quadrotor UAV-taken images

Abstract: Building inspection searching for superficial defects, such as cracks, is a vital task because such damages cause economic losses or put at risk the integrity of people For this reason, different ways to reduce the costs and risks through the use of robotic systems that allow make inspections have been studied Among these robotic systems, we have the unmanned aerial vehicles (UAV) that allow reaching difficult access places permitting better inspection In this work, we propose using convolutional neuronal networks for crack recognition from images captured by an UAV To carry out the training task of the network, a database of cracks in walls was built from images collected from the Internet The training of the network prompted encouraging results with a 95% accuracy over the training set Experimental results of crack recognition in images were carried out validating the application of the proposal

Robust controls for upper limb exoskeleton, real-time results:

Abstract: This article shows the development of an exoskeleton for human joint. The exoskeleton proposed was developed for rehabilitating individuals who have suffered injuries at their shoulders, by rehabil...

Fixed-Wing MAV Adaptive PD Control Based on a Modified MIT Rule with Sliding-Mode Control

Abstract: This paper presents an adaptive PD control law by using a modified MIT rule. The adaptation of the controller gains is based on the adjustment mechanism of the MIT rule by the gradient method with three types of sliding-mode control, i.e., first order sliding-mode control, second order sliding-mode (2SM), and high order sliding-mode control (HOSM). The proposed adjustment mechanism with the PD controller have been designed for the altitude movement, directional and lateral dynamics of a fixed-wing miniture aerial autonomous vehicle (MAV). Several simulations have been carried out in order to analyze the response of the modified MIT rule.

Design and Control of an Autonomous Underwater Vehicle (AUV-UMI)

Abstract: This paper outlines the conception, modeling and control of a rover type modular mini submarine. The development and implementation of the mechanical structure as well as the embedded electronics is described. The onboard instrumentation and sensors required to collect data on the environment and on its own position and orientation are also described. The mathematical representation to describe the movement of an underwater vehicle is analyzed considering the characteristics and limitations of the underwater robot. Furthermore, a control algorithm is implemented based on Lyapunov theory and Backstepping Integral Adaptive (BIA). This control strategy stabilizes the vehicle in position and orientation. The proposed control algorithm is validated in numerical simulations as well as in experimental tests which confirm the good performance of the prototype and the controller.

Robust control scheme for trajectory generation and tracking for quadcopters vehicles: Experimental results *

Abstract: A robust control scheme for aerial path generation and tracking is proposed in this paper. The control structure is based on the MPC - Model Predictive Control- and the UDE -Uncertainty and Disturbance Estimator - approaches. Both algorithms can be used with simple controllers for becoming more robust with respect to nonlinear uncertainties and external disturbances. The proposed scheme is applied to a quadcopter vehicle. Experimental results confirm the well performance of the closed-loop system when tracking trajectories, even in the presence of perturbations.

Flight Phases With Tests of a Projectile-Drone Hybrid System

Abstract: A fully functional prototype of a gun-launched micro air vehicle system (GLMAV) is developed for long-distance observation capabilities. A subsonic projectile is launched from an ad hoc tube and transforms into a micro air vehicle (MAV) once arrived over the site to be observed. The ballistic, transient, and operational flight phases of the GLMAV are studied theoretically and experimentally in this paper. Ballistic flight tests prove the stability of the platform in projectile mode and the availability of the inertial measurement unit and GPS measurements for the autopilot. Based on wind-tunnel measurements, a model of the transient phase is built, allowing the design and simulation of control laws for this phase. Indoor and outdoor tests of the system are successfully achieved highlighting the hovering and maneuvering flight capabilities of the GLMAV.

Low Level Control Architecture for Automatic Takeoff and Landing of Fixed Wing UAV

Abstract: This work presents a low level control architecture that allows to handle an aircraft with focus on takeoff and landing maneuvers for fixed wing UAV. The architecture consists of an attitude and angle rate control, on ground course angle control, airspeed control as well as auxiliar stages that allow to determine the required attitude to track the desired course and path angle to follow a desired vertical velocity. These controllers are combined in different forms depending on the phase of takeoff or landing maneuver. By means of simulation the performance of this architecture was illustrated during takeoff and landing maneuvers.

Sliding mode collision-free navigation for quadrotors using monocular vision

Abstract: Safe and accurate navigation for autonomous trajectory tracking of quadrotors using monocular vision is addressed in this paper. A second order Sliding Mode (2-SM) control algorithm is used to track desired trajectories, providing robustness against model uncertainties and external perturbations. The time-scale separation of the translational and rotational dynamics allows to design position controllers by giving a desired reference in roll and pitch angles, which is suitable for practical validation in quad-rotors equipped with an internal attitude controller. A Lyapunov based analysis proved the closed-loop stability of the system despite the presence of unknown external perturbations. Monocular vision fused with inertial measurements are used to estimate the vehicle's pose with respect to unstructured scenes. In addition, the distance to potential collisions is detected and computed using the sparse depth map coming also from the vision algorithm. The proposed strategy is successfully tested in real-time experiments, using a low-cost commercial quadrotor.

Enhanced UAV pose estimation using a KF: experimental validation

Abstract: An experimental validation for improving pose estimation using a linear Kalman Filter (KF) is presented in this paper The procedure is designed to lead with localization data degraded or lost The methodology is focused on determination, tuning and dynamics changes in the covariance matrices in the KF algorithm Several simulations are carried out in order to validate the methodology Similarly several flights tests are conducted in real time for validating the observer scheme A localization system is used and modified for emulating the GPS performance Main results show the good behavior of the proposed methodology and a video of them is available for showing the capabilities of the algorithm

Super-twisting control in a Solar Unmanned Aerial Vehicle: Application to Solar Tracking

Abstract: Renewable energies have been used more commonly over time, mainly used as source of energy for cities or like a main or auxiliary power sources for cars. Moreover the technology needed to produced and used this kind of energy, has reached enough efficiency and weight to be incorporated into the Unmanned Aerial Vehicle(UAV), especially the solar energy. However, it is necessary to solve some challenges to integrate the technology needed to used the solar energy, with the final objective of increasing the autonomy in this vehicle. Most of the problems has been solve, with some special constructions techniques or electronic boards designed for this purpose, in order to add the less weight possible but giving the UAV more energy and consequently more autonomy. Nevertheless, it can still do some research to increase the total energy produced along a day, one of them is taking into account the solar tracking procedure used in the solar panel fixed to the ground. The present paper show the design of a robust control over the roll angle, used to imitate the solar tracking procedure mentioned above, with a solar panel placed on the wing of a Solar Unmanned Aerial Vehicle(SUAV), with the main objective of generated the largest amount of solar energy, to continue with the effort to make more efficient systems. The control will set an appropriate roll angle to ensure the highest energy production depending on the position of the sun, using a control technique based on super-twisting, to ensures the convergence in finite time to a desired position under bounded external perturbations such as wind gusts. Only the design of the control and the results of the simulation are shown to evaluate the effectiveness of the proposed control algorithm.

Autonomous Ground Vehicle Navigation Using a Novel Visual Positioning System

Abstract: In this paper a novel visual positioning system for slip correction of vehicles in GPS-denied environments based on Kalman filter is presented. Kalman filter fuses 2 sources of data; the first source of data is obtained from odometry, while a computer vision algorithm is used to obtain the second source of data. Using a plane-based pose estimation algorithm that employs four reference points and the Consensus-based Tracking and Matching algorithm (CMT) we were able to obtain pose estimation with centimeter accuracy. The four reference points correspond to the pixel coordinates of the corners of a rectangle closing a region in the roof where the camera should be pointing. Since the employed camera is mounted into the vehicle and it has eye fish lens, an image distortion correction method is used. As the CMT algorithm is robust to scale and rotations, position and orientation (POSE) estimation using computer vision is obtained even if the roof is not completely visible. Autonomous navigation of a ground wheeled vehicle was achieved using the proposed algorithm performing different courses on long period of time and no big slip was observed.

A Kinect-based natural interface for formation flight of quadrotors

Abstract: This paper focuses on the implementation of algorithms for formation flight of quadrotors via teleoperation system These algorithms of navigation are based on the human gestures using a Kinect sensor The human gestures act as reference signals in the control loop during the real-time flights In order to test the performance and feasibility of the developed platform, experimental tests are carried out for indoor of multiple quadrotors with manual movements and with waypoints based on SE(3) geometric navigation for autonomous flights Real-time experiments of the flights present an acceptable performance of the proposed algorithms

Robustness Margin for Leader-based Multi-agent Consensus Systems in Presence of Parametric Uncertainty

Abstract: In this paper, the use of a class of robust control technique as a tool to compute the robustness margin for a closed loop multi-agent system is discussed. Our approach is based on a leader/follower structure of the multiple robot systems. It is shown that, for multiple agent system with cyclic, chain and balanced topology of information exchange, the result is achieved. A Lyapunov based robust control design for coordination and trajectory tracking of multiple agent systems with parametric uncertainty is presented. The results are illustrated with examples and simulations.