In this paper, a novel Vision-Based Measurement (VBM) approach is proposed to estimate the contact force and classify materials in a single grasp. This approach is the first event-based tactile sensor which utilizes the recent technology of neuromorphic cameras. This novel approach provides a higher sensitivity, a lower latency, and less computational and power consumption compared to other conventional visionbased techniques. Moreover, Dynamic Vision Sensor (DVS) has a higher dynamic range which increases the sensor sensitivity and performance in poor lighting conditions. Two time-series machine learning methods, namely, Time Delay Neural Network (TDNN) and Gaussian Process (GP) are developed to estimate the contact force in a grasp. A Deep Neural Network (DNN) is proposed to classify the object materials. Forty-eight experiments are conducted for four different materials to validate the proposed methods and compare them against a piezoresistive force sensor measurements. A leave-one-out cross-validation technique is implemented to evaluate and analyze the performance of the proposed machine learning methods. The contact force is successfully estimated with a mean squared error of 0.16 N and 0.17 N for TDNN and GP respectively. Four materials are classified with an average accuracy of 79.17% using unseen experimental data. The results show the applicability of eventbased sensors for grasping applications.

Achieving precise state estimation is needed for the unmanned aerial vehicle to perform a successful flight with a high degree of stability. Nonetheless, obtaining accurate state estimation is considered challenging due to the inaccuracies associated with the measurements of the onboard commercial-offthe-shelf (COTS) Inertial Measurement Unit (IMU). The immense vibration of the vehicle's rotors makes these measurements suffer from issues like; large drifts, biases and immense unpredictable noise sequences. These issues cannot be significantly tackled using classical estimators and an accurate sensor fusion technique needs to be developed. In this paper, a deep learning framework is developed to enhance the performance of the state estimator. A deep neural network (DNN) is trained using a deep-learning-based technique to identify the associated measurement noise models and filter them out. Dropout technique is adopted for training the DNN to avoid overfitting and reduce the complexity of nets computations. Compared to the classical estimation results, the proposed deep learning technique demonstrates capabilities in identifying the measurement's noise characteristics. As an example, an enhancement in estimating the attitude states at near hover is proved using this approach. Furthermore, an actual hover flight was performed to validate the proposed estimation enhancement method.

The positional inaccuracies associated with the GPS/INS measurements make the terminal phase of the normal GPS/INS landing system imprecise. To solve this problem, an adaptive fuzzy data fusion algorithm is developed to obtain more accurate state estimates while the vehicle approaches the landing surface. This algorithm takes the translational displacements in x and y from the mounted Optical Flow (OF) sensor and fuses them with the INS attitude measurements and the altimeter measurements. This low cost adaptive algorithm can be used for vertical landings in areas where GPS outages might happen or in GPS denied areas. The adaptation is governed by imposing appropriate assumptions under which the filter measurement noise matrix R is predicted. The R matrix is continuously adjusted through a fuzzy inference system (FIS) based on the Kalman innovative sequence and the applied covariance-matching technique. This adaptive fuzzy Kalman fusion algorithm (AFKF) is used to estimate the vehicle's states while landing is being commanded. AFKF results are compared with these obtained using a classical Kalman estimation technique. The AFKF algorithm shows better states estimates than its conventional counterpart does. Compared to prior landing systems, the proposed low cost AFKF has achieved a precision landing with less than 10 cm maximum estimated position error. Real precision landing flights were conducted to demonstrate the validity of the proposed intelligent estimation method.

In today's modern electric Vehicles, enhancing the Safety-Critical Cyber-Physical (CPS) system's performance is necessary for the safe maneuverability of the vehicle. As a typical CPS system, the braking system is crucial for the vehicle design and safe control. However, precise state estimation of the brake pressure is desired to perform safe driving with a high degree of autonomy. In this paper, a sensorless state estimation technique of the vehicle's brake pressure is developed using a deep-learning approach. A Deep Neural Network (DNN) is structured and trained using special deep-learning training techniques, such as, dropout and rectified units. These techniques are utilized to obtain more accurate model for brake pressure state estimation applications. The proposed model is trained using real experimental training data which were collected via conducting real vehicle testing. The vehicle was attached to a chassis dynamometer while the brake pressure data were collected under random driving cycles. Based on these experimental data, the DNN is trained and the performance of the proposed state estimation approach is validated accordingly. The results demonstrate highaccuracy brake pressure state estimation with RMSE of 0.048 MPa.

Unmanned aerial helicopters are essential for use in environments that are inaccessible for fixed wing aerial vehicles. Flybarless helicopters are famous for their high agility and maneuverability, which makes them suitable platforms in many challenging applications. This paper is concerned with the problem of estimating attitude and flapping angles of a flybarless, small-scale, single-rotor helicopter. The study utilizes a nonlinear model for the Maxi Joker 3 helicopter. A dynamic model-based Kalman filter is designed and implemented to estimate both the attitude and the flapping angles of the helicopter. Results of a simulation scenario are shown to validate the performance of the proposed approach. The results demonstrate high-accuracy flapping angles estimation with errors not exceeding,│Δ max │,0.3° in longitudinal flapping angles and 0.1° in lateral flapping angles. An experimental test is also conducted to demonstrate the performance of the method.