Zhen Jiang

Low Cost Hand Gesture Learning and Recognition System Based on Hidden Markov Model

Focusing on recognizing some typical gestures based on 3-axis MEMS accelerometer to interact with an application of human-machine interactive game, the hand gesture problem is analyzed firstly, then theory basis of HMM is introduced. In order to obtain training gesture data for HMM, and also to provide a hardware basis for gesture recognition, a low cost data acquisition system hardware is researched and designed. The system can get the acceleration data of user’s gesture and transmit them wirelessly to a personal computer. In the hand gesture recognition approach, k-mean algorithms are applied to cluster and abstract the vector data from sensor. And then the quantized vectors are put into a hidden Markov model to learn and recognize user’s gestures. Finally the gesture recognition library is implemented in C# development environment, and is utilized in a human-machine interactive game application. The results show that the typical gesture emerging in the game can be identified in a high rate, and the user can experience more interest and interaction.

GA-Based Flight Motion Model Parameter Identification of a Subminiature Fixed-Wing Unmanned Aerial Vehicle

Subminiature fixed-wing unmanned aerial vehicles (SUAVs) present an enormous potential for low-altitude exploration applications. In order to develop a robotic SUAV and realize high level of autonomy, the flight motion model of the platform with wingspan of 1.8 m is studied thoroughly. Based on the rectilinear trim flight and small perturbation theory, the linear parametric model is investigated. The flight experiments are designed, and the flight data measurement system is developed to collect the input and output data. Through outliers processing, data smoothing, data fusion, etc, all the required data for parameter identification are figured out. As the estimation method, improvements of GA are detailed, and the comparison of model verification indicates that improved GA has prominent effects in flight motion model parameter identification of SUAV.

Flight control system of a robotic portable unmanned aerial vehicle

Portable fixed-wing Unmanned Aerial Vehicles (PUAV) present enormous potential. In order to develop a robotic PUAV with significant levels of autonomy, the flight control system is studied. The platform is introduced and dynamics model is studied firstly. Then the infrastructure hardware and the architecture of the flight control system are detailed. As the core of the flight control system, the attitude controller using variable fuzzy controller is investigated, and a bilinear interpolation approach is presented to realize quick inference with low computation cost of the embedded micro processor. The flight simulation and experiment validates the performance of the flight control system of PUAV.

Online Fuzzy Self-Adaptive PID Attitude Control of a Sub Mini Fixed-Wing Air Vehicle

An online fuzzy self-adaptive Proportional Integral Derivative (PID) controller is proposed to control the attitude of a sub miniature fixed-wing unmanned air vehicle (SUAV). The vehicle is a complex dynamic system with three rotational DOFs (degrees of freedom) and three translational DOFs. It is the three rotational DOFs that determine the air vehicle attitude in the air. The attitude control is based on the conventional PID control combined with an online fuzzy self-adaptive PID gains regulator which regulates three PID gains according to input error and the change in error, and the controller is realized on MCU system. Simulation and test flights show that the proposed controller enhanced the attitude control performance of the SUAV, such as rapidity, stability, and anti-disturbance.

Aero-robotic vehicles for low-altitude remote-detecting on disaster scene

In this paper, two kinds of subminiature unmanned aero-robotic vehicles (SUAV) including sub-mini fixed-wing aerial vehicles and sub-mini helicopters are presented mainly. The characteristic sizes of these aero-robotic vehicles that are integrated with various micro and mini elements are less than traditional mini unmanned aerial vehicles. The key technologies concerned are aerodynamics for low-Reynolds number, configuration and structure design, dynamic modeling and flight control, navigation and so on, which are briefly introduced in the paper. Trial flights indicated that the two kinds of SUAVs can stably and clearly transmit the real-time image from the air to ground, when the cruising velocity in the air is equal or more than 10 m/s. Especially, the sub-mini helicopters have a detecting ability hanging in the air under wind scale 3-4.

Position and Attitude Information Fusion for Portable Unmanned Aerial Vehicles

Portable Unmanned Aerial Vehicles (PUAVs) present an enormous application potential, and the real time accurate position and attitude information is the basis of autonomous flight of PUAVs. In order to obtain comprehensive and accurate position and attitude data of PUAVs in flight, focusing on the common sensors configuration of PUAVs, each type of sensor’s characteristic is analyzed, and the data fusion problem of SINS/GPS/Compass combination is presented and studied in this paper. Firstly, the error expressions of MEMS inertia sensors, attitude, velocity and position are researched and derived, and the state equation and observation equation are built, and the discrete equations are derived for computer implementation, so the data fusion model for Kalman Filter fusion algorithms is presented. Then, the data fusion system and algorithms are implemented in software, and the flight data obtained in flight experiment is fed to the software for data fusion. The comparison between original data and fusional data shows that SINS/GPS/Compass data fusion system can promote accuracy of position and attitude markedly.

A Control Method of Four-Legged Robot Stable Walking with Diagonal Gait

This paper proposes a kind of control method used to solve the stability problem of the trotted robot. Propose the concept of inside flip design four-footed robot and build a double inverted pendulum model. Establish dynamic equation to analyze the factors of affecting the motion stability. During walking, the center of gravity can maintain a proper vibration and have a maximum safety region of flip angle. Finally, use Adams to verify the control method.

Portable Ground Control and Test Station Design for Robotic Subminiature Unmanned Aerial Vehicles

Subminiature fixed-wing Unmanned Aerial Vehicles (SUAVs) present enormous potential. In order to develop a robotic SUAV with significant levels of autonomy, a portable ground control and test station (GCTS) is studied and developed. The requirements of GCTS are analyzed and the overview of GCTS is given firstly. Then the main operation modes of digital data link module are detailed. As the core of the portable GCTS, a set of software tools, including embedded map and trajectory visualization, 3-dimention attitude viewer, avionics panel, plotting utility, mission and control configuring, flight data and mission video storage and playback, etc., are researched and developed. The flight experiments application validate that the portable GCTS satisfy most of the requirements, and mitigates the difficulties and cost of development of the robotic SUAV remarkably.

Flight Control System Onboard Embedded Software for Small Unmanned Aerial Vehicles

The onboard software of the flight control system (FCS) plays important role for small unmanned aerial vehicles’ performance. In this paper, the characteristics difficulties of the FCS software are analyzed firstly, then the compositions of the software are introduced using HIPO method. A genetic architecture of onboard software is presented to coordinate and organize the software and function modules, and an unique task scheduling strategy is designed and applied to realize multi-task processing. Finally, on the basis of the elementary operation procedure of the software, the flight experiment is implemented, and the feasibility and reliability of the onboard software is validated.

Hybrid ANNs-GAs Strategy Based Constrained Optimization and Application in Sheet Metal Flanging Forming

In order to provide a general purpose method to search optimum solution for complex constrained engineering problems without explicit system model, a hybrid optimization strategy based on artificial neural networks (ANNs) and genetic algorithms (GAs) is proposed in this paper. This strategy combines the strong nonlinearity mapping abilities of ANNs and effective and robust evolutionary searching ability of GAs. Firstly, ANNs are utilized to model the un-known system using inputs and outputs of system. Then the direct comparison approach based improved GAs are employed to search optimal solution in the constrained design space, using the trained ANNs as the function generator of system outputs. This strategy is implemented in optimization of design variables for sheet metal flanging process. The verification results of numerical simulation and the experiments demonstrate the feasibility and effectiveness of the strategy.