Autonomous navigation and localization of Aerial Vehicles in indoor environments is a major problem due to the difficulty of reliable control. Sliding Mode Control, Model Predictive Control, Back-stepping Control and Fuzzy Logic Control are proposed to stabilize and trajectory tracking for Unmanned Aerial Vehicles. Two trajectories were validated on the four controllers to determine the most efficient controller to maintain the optimal results.

In this paper, a novel technique using an ultra-sensitive optical resonator based on whispering gallery modes (WGM) is proposed to detect the diffusion of organic solvents. The sensor configuration is a micro-cavity made of polymeric material. When the solvent starts to diffuse, the polymer of the cavity starts to swallow that solvent. A swollen elastomer is in fact a solution, except that its mechanical response is now elastic rather than viscous. As solvents fill the network, chains are extended. In turn, that leads to the change of the morphology and mechanical properties of the sensing element. These changes could be measured by tracking the WGM shifts. Several experiments were carried out to measure that swelling force. Ethanol and methanol are used in this paper as candidates to study their driving force of diffusion (concentration gradient) on the cavity. Additionally, this sensing design can be used for biological sensing application. Breath diagnosis can use this configuration in diabetes diagnosis since a solvent like acetone concentration in human breath leads to a quick, convenient, accurate, and painless breath diagnosis of diabetes. The optical resonator results are verified through two different analyses: theoretical and experimental modeling. These micro-optical cavities have been examined using preliminary experiments to fully investigate their response and to verify the numerical analysis. Results show that the proposed sensor yields sensitivity for the driving force of diffusion (concentration gradient) (9.405 × 10¹³ pm/N) with a measurement precision of ~3.6 fN.

This paper extends the traditional single vehicle trajectory tracking problem to develop a control approach for a group of N-vehicles which are capable of converging to a desired formation while moving on a predefined trajectory. A novel hybrid control algorithm is introduced to handle the two aforementioned problems separately. The proposed controller integrates three different techniques; graph theory, Lyapunov stability and leader-follower approach. The controller structure consists of two main subsystems. In the first subsystem, a leader virtual robot is responsible for the trajectory tracking problem, actuated via a Lyapunov-based controller. Simultaneously, a graph-based controller is used to guarantee the convergence of the follower mobile robots to the desired formation using local positioning information; thus, ensuring the stability of the formation of the follower robots with respect to the moving leader. This new hybrid approach handles the problem of impractical velocities providing control inputs within acceptable ranges that can be practically implemented. Furthermore, it eliminates the oscillations in the motor inputs. Several scenarios are implemented to verify the proposed hybrid control algorithm. The simulations show significant and promising results which prove the effectiveness of this hybrid approach.

Reinforcement learning is recently widely used in the field of Autonomous Vehicles as it became a powerful algorithm in the artificial intelligence field. In this paper, Reinforcement learning is further extended to be implemented on Multi-Vehicle Systems. The purpose of this paper is to design a multi-layer architecture for formation control of multi-vehicles. The main target is to plan the motion of a group of vehicles to achieve a specific pattern predefined by the user. The multi-layer is divided into two tasks. The first task is to plan the vehicle configuration using the traditional Q-learning algorithm due to the low computational time and the cost in terms of consumption of computing resources. For the second layer, the deep reinforcement policy- gradient algorithm is adopted for planning a collision free path for the vehicles as it has the ability to train on completely new environments and discover it with trial and error. The two different layers are tested separately and the numerical analysis shows promising results in terms of achieving the aforementioned problems.

In this work, the problem of predicting a pedestrian’s intention to cross the road is addressed using visual data from a camera. The proposed ROS-based modular architecture consists of four modules: Visual-Perception, Intention Prediction, and Planning and Control Modules. The Visual Perception module is divided into three sub-modules. The pedestrian detection is responsible for detecting the pedestrian and analyzing his motion and looking states. The lane detection is responsible for analyzing the structured environment which helps in the road state classifiers. The third sub-module aims to extract some curvilinear localization states that are essential for the vehicle’s motion planning and control. The intention prediction module captures the pedestrian’s intention to cross the road. A comparative study is conducted between three different data-driven sequential models. Each model is trained on the JAAD dataset and different extracted features from the visual perception module. The proposed GRU model obtained an $86\%$ average f1-score, anticipating the pedestrian’s intention two seconds in advance when the pedestrian is standing, and three seconds in advance when the pedestrian is walking to the crossing area. To control the maneuver of the vehicle, longitudinal velocity and lateral controllers are implemented to control the motion of the vehicle while avoid collision with the pedestrian based on the intention prediction. Finally, this work is verified on a 1:4 scaled real vehicle to ensure the applicability of implementing this work in real hardware.