ahmadreza khoogar

The Reinforcement Learning Approach (RL) is used to solve the path-planning problem of an autonomous mobile robot in unknown environments. Despite that RL is a recent and powerful tool, it requires a lot of training processes because there are so many parameters in the agent’s training process. Some of these parameters have a larger effect on the convergence of the learning process than others, so, knowing these parameters and their suitable values makes the training process more efficient, saves time, and consequently makes the trained agent execute the required task successfully. No analytical equations are available to determine the best values for these parameters, therefore, in this paper, a statistical analysis is made using the design and analysis of experiment (DoE) methods to determine the parameters that have the largest effect on the training process. After that, analysis is done to determine the values of the most effective parameters. Results show that the determined parameters lead to a successful autonomous path planning in different unknown environments

The method is presented for object assembling via a manipulator robot. This method was designed to track the pieces based on image feedback for pick and placement tasks. The depth of the pieces is calculated by stereo triangulation. Vision-guided robotics is most often based on the training steps, therefore it is a time-consuming process. For this reason, we have proposed a modified stereo vision method to predict the movement of the part in the image space. The linear and angular velocities of moving objects predict by a state estimator. The object velocity components predicted by estimation algorithms such as Kalman filter, Recursive least square and Extended Kalman Filter. Results show that in the case of, Extended Kalman filter estimator shows better tracking and convergence behavior. This method does not need to know the three-dimensional model of the parts, and it can be used on pick and place robots if the physical limitations of the joints are considered. The proposed method was experimentally tested in a laboratory environment. The cameras were installed parallel and non-parallel to determine the effect of the field of view on the precision and speed detection. A comparison of the simulation and experimental results showed that the use of the parallel stereo Image-based visual servoing with the Extended Kalman Filter method could be smoother and more accurate than the other methods.

In this paper, an eye-in-hand stereo image-based visual serving controller for industrial 6 degrees of freedom manipulator robots is presented. The visual control algorithms mostly use the relationship between camera speed and changes in image features, to determine the end-effector movement path.  One of the main problems of the classical IBVS method is the inability to estimate the distance of the object related to the camera, which requires peripheral equipment such as a laser rangefinder to estimate the depth. In this study, two cameras were mounted on the end-effector of a 6 DOF manipulator robot. The distance of the object to the camera is estimated by the equations associated with the epipolar plane, and the interaction matrix is updated at any time. For increasing response speed, the image interaction matrix was divided into two separate parts related to translational and rotational motion, and it was found that only the translational motion part is affected by distance. The control method separates the camera motion into three-stage based on pure rotation, pure translation, and hybrid motion, which has a better time response compared to the classical IBVS control methods. Additionally, a method for position prediction and trajectory estimation of the moving target in order to use in a real-time grasping task is proposed and developed using Recursive Least Square as the trajectory estimators in the image plane.  The simulation results show that the proposed method increases the system response speed and improves the tracking performance.

The method is presented for object assembling via a manipulator robot. This method was designed to track the pieces based on image feedback for pick and placement tasks. The depth of the pieces is calculated by stereo triangulation. Vision-guided robotics is most often based on the training steps, therefore it is a time-consuming process. For this reason, we have proposed a modified stereo vision method to predict the movement of the part in the image space. The linear and angular velocities of moving objects predict by a state estimator. The object velocity components predicted by estimation algorithms such as Kalman filter, Recursive least square and Extended Kalman Filter. Results show that in the case of, Extended Kalman filter estimator shows better tracking and convergence behavior. This method does not need to know the three-dimensional model of the parts, and it can be used on pick and place robots if the physical limitations of the joints are considered. The proposed method was experimentally tested in a laboratory environment. The cameras were installed parallel and non-parallel to determine the effect of the field of view on the precision and speed detection. A comparison of the simulation and experimental results showed that the use of the parallel stereo Image-based visual servoing with the Extended Kalman Filter method could be smoother and more accurate than the other methods.

In order to evaluate and improve the accuracy of the distance traveled by the laser beam with a fixed distance, first the relation of the pulsed laser reflection signal reflected from the surface of the objects should be calculated and analyzed. Then, the broadening angle of the reflection signal and the relative broadening factor should be determined. In this research, an analytical relationship for distance measurement and detection for pulsed laser and statistical distance measurement has been designed, in which the minimum measurable distance and the necessary calculations for its quantitative estimation are presented. In this regard, the relationship between the broadening coefficient and relevant parameters such as detection distance, radiation angle to the target surface, and radiation reflection signal have been determined and evaluated. Simulation results and experimental results show that the maximum laser range for reliable distance measurement is 36.5 m, which is associated with a statistical error of 0.24 to 0.48 m. As the measurement threshold increases, the distance measurement error and the reliable range decrease. As the laser radiation angle increases, the divergence angle and the broadening coefficient increase, and as the laser pulse width decreases, the broadening coefficient decreases. Since increasing the angle of the target surface increases the divergence of the reflection signal, the mean values ​​and variance of the reflection signal will also increase.

The most common types of mechanical arms are robots that are used as palletizing robots to transport light and heavy loads. In robots that are used to move heavy loads, increasing the carrying capacity of the robot while maintaining dexterously, accuracy, repeatability and lightness has always been one of the issues studied by researchers. With this approach, in the present paper, the kinematic design and dimensional optimization of the geometry of a four-degree robotic robotic arm have been performed. The primary geometry is designed using parallel parallelograms to allow horizontal load carrying. After the initial design of the geometry dimensions of the robot, using the finite element method, the geometric optimization of the structure has been done in such a way that changes in the geometric dimensions of the arms as design parameters result in receiving the best results for the objective function. Deformation of the arms and proper distribution of load force among all arms. Using the optimization results of this paper and achieving a set of parametric relationships for the geometry of the robot structure, a shorter path can be taken to design these robots and With optimal geometry, parameters such as not increasing the dimensions of the arm sections to overcome stress and deformation, not increasing the overall weight of the structure, followed by increasing accuracy, repeatability, more load carrying capacity, robot dexterously and not enlarging the overall dimensions of the robot Improve.

A Spherical Parallel Mechanism (SPM) is used to rotate a body around a fixed point. Using type synthesis, different kinematic arrangements can be obtained for the robot with three degrees of rotational freedom. The most commonly used structure for this robot is the 3-RRR kinematic architecture which is an overconstrained parallel mechanism and causes several problems of mounting the mechanism, but has the advantage of having high rigidity thus a good accuracy. In this paper two non-overconstrained architectures 3-RRS and 3-RSR that are extracted from the type synthesis are compared with overconstrained one from accuracy point of view based on joint clearance. First, a method to obtain a model of moving platform pose (position and orientation) error based on joint clearance is introduced which leads to a standard convex optimization problem. Then maximum values of six components of the pose error are computed in more than 1000 different configurations within their workspace. It is shown that this displacement is configuration dependent. The obtained results revealed that the 3-RRR SPM has better position accuracy while in the case of orientation, the 3-RRS SPM has lowest maximum error between SPMs under study in the prescribed workspace. It can be concluded that non-overconstrained structures can be used instead of the overconstrained structure. Finally, a comparison was made between the performance indices and the method presented in this paper and results showed that the kinematic sensitivity index is most consistent with the accuracy of the robot.

In design of defense structures, concrete are often used to provide protection against incidental dynamic loadings such as the impact of a steel projectile. In the present study, a new analytical model is proposed to predict penetration depth into concrete targets by ogive nose projectile. Hence, to develop the model and simulate penetration of high velocity ogive-shape nose steel projectiles into concrete targets, several tests has been simulated numerically with the Ls-Dyna finite element code. The results show good agreement with the analytical analyses and experimental results from other researchers.