Contrôle
Permanent URI for this collectionhttps://dspace.univ-boumerdes.dz/handle/123456789/3081
Browse
3 results
Search Results
Item End-to-End learning-based navigation of autonoumous mobile robot(2020) Mehrab, Anis Abdeldjalil; Guernane, Reda (supervisor)In this work we present an end-to-end learning approach that is able to perform target- oriented navigation and collision avoidance using Deep Neural Network. This approach can be defined as learning a model that maps sensory inputs, such as raw 2D-laser range findings and a target position, to navigation actions for controlling the mobile robot such as steering commands. Compared to the traditional autonomous navigation systems, which often require perception, localization, mapping, and path planning, the end-to-end learning approach offers a more efficient method. which utilize large set of expert navigation demonstrations to learn the desired navigation policy. The end-to-end learning approach has gained considerable interests in autonomous navigation in academic and industrial fields. Researches have already used different artificial neural networks to predict steering commands. However, most of the existing end-to-end methods are used for lane keeping for self-driving cars. therefore, we propose an end-to-end navigation model for mobile robots that is based on a Convolutional Neural Network (CNN). The network was trained using expert demonstration data which was generated in virtual simulation environments. The learned model was test in real time simulation and gave an acceptable result, however, it suffered when it encounters situations that requires hard maneuvers. Therefore, in order to overcome some of these difficulties, we proposed an improved model which incorporates the temporal information in the prediction process using the Long Short-Term Memory (LSTM) network. basically, this model aims to include the motion history of the robot in the steering prediction model. The improved model showed its ability to predict steering commands with high performance compared to the expert operator. However, this model imposed some limitations which will be further discussed in this remaining parts of this thesis.Item Control design and visual autonomous navigation of quadrotor(2018) Boughellaba, Mouaad; Rabah hazila, Ramzi; Rabah hazila, Ramzi; Boushaki, Razika (Supervisor); Boushaki, Razika (Supervisor)Starting from the fact that quadrotors are nonlinear MIMO system that operates in 3D space, the task of stabilizing and generating suitable control commands have been the interest of many researches. Another challenging task is the autonomous navigation as both the weight and the computation capacity are limited which constrains the type of sensors and algorithms. In this project, an autonomous navigation and obstacle avoidance system based on monocular camera has been implemented which enables the quadrotor navigates in previously unknown GPS-denied environment. Moreover, four controllers have been designed and their performance were compared.The mathematical model of a quadrotor has been derived using Newton’s and Euler’s laws, where a linear and nonlinear version of the model are presented, based on that various control strategies such as LQR, PID, Feedback Linearization with pole placement and Sliding Mode control Have been implemented in MATLAB/Simulink and discussed. Sensor data and the camera video stream have been used by a Keyframe visual SLAM system to compute the location of the drone and generate the 3D map of the environment in the form of point cloud. This point cloud data is clustered and used for obstacle detection. Moreover a PRM algorithm has been used to generate a collision-free path that will be followed by the drone based on the PID controller designed. We implemented our approach on a real Parrot ARDrone2.0, and our approach has been validated with experiments. All computations are performed on a ground station, which isconnected to the drone via wireless LAN.Item Control design and visual autonomous navigation of quadrotor(2018) Boughellaba, Mouaad; Rabah hazila, Ramzi; Boushaki, Razika (supervisor)Starting from the fact that quadrotors are nonlinear MIMO system that operates in 3D space, the task of stabilizing and generating suitable control commands have been the interest of many researches. Another challenging task is the autonomous navigation as both the weight and the computation capacity are limited which constrains the type of sensors and algorithms. In this project, an autonomous navigation and obstacle avoidance system based on monocular camera has been implemented which enables the quadrotor navigates in previously unknown GPS-denied environment. Moreover, four controllers have been designed and their performance were compared.The mathematical model of a