Biped robots have gained much attention for decades. A variety of researches has been conducted to make them able to assist or even substitute for humans in performing special tasks. In addition, studying biped robots is important in order to understand the human locomotion and to develop and improve control strategies for prosthetic and orthotic limbs. Some challenges encountered in the design of biped robots are: (1) biped robots have unstable structures due to the passive joint located at the unilateral foot-ground contact. (2) They have different configuration when switching from walking phase to another. During the singlesupport phase, the robot is under-actuated, while turning into an over-actuated system during the double-support phase. (3) Biped robots have many degrees of freedom (DOFs). (4) Biped robots interact with different unknown environments. Therefore, this work attempts to investigate and resolve different issues encountered in dynamics, walking pattern generators and control of biped robots; the details as follows: • Dynamics Two walking patterns have been modeled using two well-known formulations: Lagrangian and the modified recursive Newton-Euler (N-E) formulations. The first walking pattern moves with 6 DOFs during the single support phase (SSP) changing its configuration with 7 DOFs during the double support phase (DSP) (the stance foot will move directly during the DSP). Whereas the other walking pattern has 6 DOFs during all walking phases (the SSP and the two sub-phases of the DSP); the stance foot will be fixed during the first sub-phase of the DSP. These two walking pattern are different in configuration and number of phases during the DSP. To resolve the problem of over-actuation, a linear transition function is proposed to ensure smooth transition for the biped from the SSP to the DSP and vice versa. If we assume ideal dynamic response, this strategy can resolve the discontinuity in input control torque and ground reaction forces. • Walking pattern generators Two methods have been used to generate walking patterns of biped mechanism which are (1) optimal control theory and (2) center of gravity (COG)-based model. Computational optimal control has been performed to investigate the effects of some imposed constraints on biped locomotion, such as enforcing swing foot to move level to the ground, hip motion with constant height etc. finite difference approach has been used to transcribe infinite dimensional optimal control problem into finite dimensional suboptimal control problem. Then parameter optimization has been used to get suboptimal trajectory of the biped with the imposing different constraints. In general, any artificially imposed constraint to biped locomotion can lead to increase in value of input control torques. On the other hand, suboptimal trajectory of biped robot during complete gait cycle had been accomplished with different cases such that continuous dynamic response occurs. Enforcing the biped locomotion to move with linear transition of zero-moment point (ZMP) during the DSP can lead to more energy consumption. Using the simple COG-based model, a comparative study has been conducted to generate continuous motion for COG of the biped; all these methods depend on linear pendulum model. It has been shown all these methods are equivalent. On the other hand, the effect of foot configuration has been investigated. Foot rotation can improve biped configuration at heel strike by controlling foot angle. In addition, foot motion with impact can give some freedom and uniform biped configuration compared with motion without impact. To compensate for the deviation of ZMP trajectory due to approximate model of the COG, a novel strategy has been proposed to satisfy kinematic and dynamic constraints, as well as singularity condition. A stable motion has been obtained for the target walking patterns. • Low-level control Two control schemes have been proposed based on dynamics formulations which are conventional adaptive control based on local approximation technique and Lagrangian formulation, and virtual decomposition control (VDC) based on local approximation technique and recursive N-E formulation. In the first approach (conventional control), a new representation of dynamic matrices has been coined which is computationally efficient than other representation (sparse-base representation, Kronecker product etc.). Controller structures for the SSP and the DSP have been designed in details. Since adaptive control assumes no prior knowledge of estimated weighting matrices; therefore, zero input control torques could be result in at the beginning of each phase. Consequently, discontinuous dynamic response could result. The VDC is an efficient tool for complex robotic system such as biped robot. Therefore each subsystem (link, joint) has been controlled using adaptive approximation–based VDC. A novel optimization technique has been used to deal with continuous dynamic response; however, using zero initial weighting matrices for estimation dynamic matrices and vectors could result in zero input control at beginning of each walking phases.
A new Differential Evolution (ARDE) algorithm is introduced that automatically adapt a repository of DE strategies and parameters adaptation schemes of the mutation factor and the crossover rate to avoid the problems of stagnation and make DE responds to a wide range of function characteristics at different stages of the evolution. ARDE algorithm makes use of JADE strategy and the MDE_pBX parameters adaptive schemes as frameworks. Then a new adaptive procedure called adaptive repository (AR) has been developed to select the appropriate combinations of the JADE strategies and the parameter control schemes of the MDE_pBX to generate the next population based on their fitness values. Experimental results have been presented to confirm the reli
... Show More
(1)
Hand gestures are currently considered one of the most accurate ways to communicate in many applications, such as sign language, controlling robots, the virtual world, smart homes, and the field of video games. Several techniques are used to detect and classify hand gestures, for instance using gloves that contain several sensors or depending on computer vision. In this work, computer vision is utilized instead of using gloves to control the robot's movement. That is because gloves need complicated electrical connections that limit user mobility, sensors may be costly to replace, and gloves can spread skin illnesses between users. Based on computer vision, the MediaPipe (MP) method is used. This method is a modern method that is discover
... Show More
(6)
(6)
This paper presents a modified training method for Recurrent Neural Networks. This method depends on the Non linear Auto Regressive (NARX) model with Modified Wavelet Function as activation function (MSLOG) in the hidden layer. The modified model is known as Modified Recurrent Neural (MRN). It is used for identification Forward dynamics of four Degrees of Freedom (4-DOF) Selective Compliance Assembly Robot Arm (SCARA) manipulator robot. This model is also used in the design of Direct Inverse Control (DIC). This method is compared with Recurrent Neural Networks that used Sigmoid activation function (RS) in the hidden layer and Recurrent Neural Networks with Wavelet activation function (RW). Simulation results shows that the MRN model is bett
... Show MoreAerial Robot Arms (ARAs) enable aerial drones to interact and influence objects in various environments. Traditional ARA controllers need the availability of a high-precision model to avoid high control chattering. Furthermore, in practical applications of aerial object manipulation, the payloads that ARAs can handle vary, depending on the nature of the task. The high uncertainties due to modeling errors and an unknown payload are inversely proportional to the stability of ARAs. To address the issue of stability, a new adaptive robust controller, based on the Radial Basis Function (RBF) neural network, is proposed. A three-tier approach is also followed. Firstly, a detailed new model for the ARA is derived using the Lagrange–d’A
... Show More
(42)
(39)
This paper discusses an optimal path planning algorithm based on an Adaptive Multi-Objective Particle Swarm Optimization Algorithm (AMOPSO) for two case studies. First case, single robot wants to reach a goal in the static environment that contain two obstacles and two danger source. The second one, is improving the ability for five robots to reach the shortest way. The proposed algorithm solves the optimization problems for the first case by finding the minimum distance from initial to goal position and also ensuring that the generated path has a maximum distance from the danger zones. And for the second case, finding the shortest path for every robot and without any collision between them with the shortest time. In ord
... Show MoreElectromyogram (EMG)-based Pattern Recognition (PR) systems for upper-limb prosthesis control provide promising ways to enable an intuitive control of the prostheses with multiple degrees of freedom and fast reaction times. However, the lack of robustness of the PR systems may limit their usability. In this paper, a novel adaptive time windowing framework is proposed to enhance the performance of the PR systems by focusing on their windowing and classification steps. The proposed framework estimates the output probabilities of each class and outputs a movement only if a decision with a probability above a certain threshold is achieved. Otherwise (i.e., all probability values are below the threshold), the window size of the EMG signa
... Show More
(26)
This paper includes an experimental study of hydrogen mass flow rate and inlet hydrogen pressure effect on the fuel cell performance. Depending on the experimental results, a model of fuel cell based on artificial neural networks is proposed. A back propagation learning rule with the log-sigmoid activation function is adopted to construct neural networks model. Experimental data resulting from 36 fuel cell tests are used as a learning data. The hydrogen mass flow rate, applied load and inlet hydrogen pressure are inputs to fuel cell model, while the current and voltage are outputs. Proposed model could successfully predict the fuel cell performance in good agreement with actual data. This work is extended to developed fuel cell feedback
... Show More
(4)
(1)