检索结果-内蒙古大学图书馆

RSI/ISM International Conference on robotics and Mechatronics (ICROM)

作者： Nima Maghooli Omid Mahdizadeh Mohammad Bajelani S. Ali A. Moosavian Department of Mechanical Engineering Center of Excellence in Robotics and Control Advanced Robotics and Automated Systems (ARAS) K. N. Toosi University of Technology Tehran Iran

ISBN: (数字)9798331529734

ISBN: (纸本)9798331529741

Continuum robots, while versatile for handling complex tasks, present significant challenges in control system design. This paper introduces a novel framework that integrates position and orientation control laws to address shape constraints effectively. Specifically, a Deep Reinforcement Learning (DRL) strategy is proposed to facilitate trajectory tracking within the desired orientation. To ensure safety, the framework directly controls the end-effector's position and orientation in the workspace, avoiding unsafe zones. A centralized control law, the Modified Transpose Jacobian (MTJ), is employed to resolve the robot's redundancy without relying on inverse kinematics. The proposed approach is validated through simulations on a Tendon-Driven Continuum Robot (TDCR), demonstrating superior performance compared to similar learning-based controllers.

关键词： Meters Mechatronics Shape Trajectory tracking Termination of employment Position control Kinematics Deep reinforcement learning Safety Continuum robots

来源：评论

学校读者我要写书评

暂无评论

A new approach for orientation determination

A new approach for orientation determination

引用

RSI/ISM International Conference on robotics and Mechatronics (ICROM)

作者： Mohammad Dehghani S. Ali A. Moosavian Center of Excellence in Robotics and Control Advanced Robotics and Automated Systems Laboratory Department of Mechanical Engineering K. N. Toosi University of Technology Tehran Iran

In some modeling and control problems, especially in robotics, determination of orientation of a rotating body or frame requires slow and time taking numerical calculations. In some cases, such as for continuum robots, these time-taking calculations are an impediment to real-time control. The common approaches for orientation determination, such as Euler angles or Euler parameters, are beneficial when generalized coordinates are needed. Otherwise, these approaches require some time-taking equations for calculation of the rotation matrix (direction cosine matrix). Another method is to calculate the rotation matrix directly, based on the angular velocity. Although this method is very fast, it is numerically unstable, because of accumulation of some numerical errors. In this paper, an approach is introduced that cancels these errors with the least numerical efforts, and provides high accuracies. The application and importance of this approach is studied and discussed in the case of modeling and control of continuum robotic arms, as an instance. The proposed methods are used to model a spring, as a case study. The obtained results are validated by analytic data, and are compared to the results obtained by other methods.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

A Stable Nonlinear in Parameter Neural Network controller for a Class of Saturated Nonlinear Systems

引用

IFAC Proceedings Volumes 2014年第3期47卷 2533-2538页

作者： K. Esfandiari F. Abdollahi H.A. Talebi The Center of Excellence on Control and Robotics Department of Electrical Engineering Amirkabir University of Technology Tehran Iran Department of Electrical and Computer Engineering Concordia University Montreal QC Canada

This paper deals with the tracking problem for a class of uncertain nonlinear systems subjected to actuator saturation constraint. Despite most of proposed control schemes for saturated systems which employed linear in parameter neural networks (LPNNs), in the present work nonlinear in parameter neural network (NLPNN) is introduced to support global approximation property. To compensate the effect of the input saturation constraint an auxiliary system is introduced and the error dynamics are modified based on the auxiliary states. Then, learning rules are achieved based on the back propagation (BP) algorithm and by adding two robustifying terms to the standard BP learning rules the stability of the overall system is ensured via Lyapunov direct method. Finally simulations performed on a “generalized pendulum” nonlinear system to illustrate the effectiveness of the proposed tracking control scheme.

关键词： Adaptive tracking control Back propagation algorithm Input saturation Neural networks Nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

Modified Jacobian Transpose control of a Quadruped Robot

Modified Jacobian Transpose Control of a Quadruped Robot

引用

RSI/ISM International Conference on robotics and Mechatronics

作者： Mahdi Khorram S. Ali A. Moosavian Center of Excellence in Robotics and Control Advanced Robotics and Automated Systems Lab Dept of Mech Eng K. N. Toosi Univ of Tech Tehran Iran

ISBN: (纸本)9781467372350

Quadruped robots have many advantages over other robots. Their excellent potentials to traverse different terrains are one of main advantages which distinguish these robots from wheeled mobile robot. In this article, the gait planning problem and also the design of an appropriate controller for a quadruped robot will be investigated. To this end, an explicit dynamics model of an 18-DOF quadruped robot will be derived. Then, a constraint elimination method is proposed to cancel the contact forces from dynamics equations and also express the dynamics equations in terms of the independent variables of the motion. In the walking gait, these DOFs are the position and the orientation of main body and also the joint angles of the swing leg. A stable COG trajectory generation algorithm based on the ZMP approach will be proposed. The path of swing legs is planned to prevent any impact between the swing legs and the ground. To apply the generated path on the robot, Modified Transpose Jacobian (MTJ) controller is used. This controller is based on the feedback linearization approach. It uses the command controller in the previous time step to increase the controller performance. The simulation is conducted to evaluate the performance of the gait planning algorithm and also the controller. Obtained results verify the merits of the proposed algorithms.

关键词： Quadruped robots Walking gait stable gait planning control MTJ Algorithm

来源：评论

学校读者我要写书评

暂无评论

State prediction approach for master-slave agents in presence of communication delay

State prediction approach for master-slave agents in presenc...

引用

2013 1st RSI/ISM International Conference on robotics and Mechatronics, ICRoM 2013

作者： Ghahremani, Sona Nili Ahmadabadi, Majid Mirian, Maryam S. Araabi, Babak N. Cognitive Robotics Lab. Dept. of Elect. and Comp. Eng. University of Tehran Iran Control and Intelligent Processing Center of Excellence Dept. of Elect. and Comp. Eng. University of Tehran Iran Robotics and Machine Intelligence Dept. of Elect. and Comp. Eng. University of Tehran Iran

ISBN: (纸本)9781467358118

Teleoperation is a mechanism that makes it possible to accomplish a task in an environment where the presence of the master at the slave site is either undesirable or hardly possible The communication delay is a challenge with undesirable effects, jeopardizing the teleoperated systems the most. When the salve agent is performing in a dynamically changing environment, communication delay can be very harmful since the environment is changing continuously even though the agent has stopped operating because of the delay. Many studies have been conducted to overcome time delay effects. © 2013 IEEE.

关键词： Remote control

来源：评论

学校读者我要写书评

暂无评论

Modeling of continuum robots with twisted tendon actuation systems

Modeling of continuum robots with twisted tendon actuation s...

引用

RSI/ISM International Conference on robotics and Mechatronics (ICROM)

In contrast to traditional articulated robots, continuum robots do not have any joints. The backbone of these robots can be bent, twisted and stretched by environmental and actuation forces. A group of continuum robotic arms use tendon-driven actuation systems. In this group, the shape of robot backbone can be controlled by pulling the tendons. Generally, exact modeling of the forces and moments produced by tendon-driven systems has no closed form solution. However, for a simplified case where the backbone shape is a planar curve with a constant curvature, some closed-form solutions have been introduced. Such solutions are valuable, especially in control applications where Jacobian matrices must be calculated. For exact modeling of elastic rods in spatial deformations, constant curvature models are not accurate. In such cases, the theory of Cosserat rod can be used for backbone modeling. Continuum robots usually consist of an elastic rod as the backbone and an actuation system. The effects of the actuation systems must be included to the model of Cosserat rod. The effects of the actuation systems are more complicated, when the tendon passages are not parallel to the backbone. In this paper, a model for continuum robotic arms is presented, which considers both, the elastic backbone and the effects of the actuation system. Furthermore, the tendons can twist around the backbone, in an arbitrary passage. The presented model is more compact than other solutions, and will be validated in a case study, by comparison with numerical results obtained from existing models.

关键词： Robots Vectors

来源：评论

学校读者我要写书评

暂无评论

RoboWalk Multiple-Sensor and Multipolar Data Fusion

RoboWalk Multiple-Sensor and Multipolar Data Fusion

引用

RSI/ISM International Conference on robotics and Mechatronics (ICROM)

作者： Omid Mahdizadeh Vahid Akbari S. Ali A. Moosavian Center of Excellence in Robotics and Control Advanced Robotics and Automated Systems (ARAS) Lab. K. N. Toosi University of Technology. Tehran Iran

ISBN: (数字)9781728166049

ISBN: (纸本)9781728166056

RoboWalk is a two-legged rehabilitation assisting robot, which helps users by carrying a portion of the weight. In this paper, we propose an algorithm to correct the attitude and position error by means of an Adaptive Root Square Unscented Kalman Filter. To this end, the IMU and encoders are used to determine the robot kinematic configuration, but since there is no solid connection between the ground and the feet, the sensor's data may not lead to exact positioning configuration. Therefore, a new approach for estimating the position of the feet and the seat is presented. The method is based on using the standing foot IMU, and related encoders to obtain the seat position. Then, the obtained result is compared to the seat IMU and correcting the position. Next, the corrected position and the swing leg encoders are used to obtain the swing foot position, which is compared to the corresponding IMU, to modify and yield all corrected positions. Describing the proposed method, it is then implemented, and the results will be discussed.

关键词： Mathematical model Robot sensing systems Estimation Robot kinematics Foot

来源：评论

学校读者我要写书评

暂无评论

Real-Time Face-Tracking control of a 4 DOF Manipulator Using Deep Learning Detection

Real-Time Face-Tracking Control of a 4 DOF Manipulator Using...

引用

RSI/ISM International Conference on robotics and Mechatronics (ICROM)

作者： Ali Asadi Amirreza Hassan Nejad S. Ali A. Moosavian Department of Mechanical Engineering Center of Excellence in Robotics and Control Advanced Robotics and Automated Systems (ARAS) K. N. Toosi University of Technology Tehran Iran

ISBN: (数字)9798331529734

ISBN: (纸本)9798331529741

This paper has presented the design, simulation, and real-time implementation of a four-degree-of-freedom (4-DOF) robotic system for face detection and tracking. The system has combined kinematic control with deep learning. It has used the Xception network for high-accuracy facial detection. A Fuzzy PID-MIJ control algorithm has optimized the trajectory planning. This has ensured smooth and precise target tracking. Both simulations and physical experiments have validated the system's real-time performance. The results have shown that the system can reliably track faces with minimal error. This approach has demonstrated significant potential for dynamic, human-interactive applications.

关键词： Deep learning Target tracking Trajectory planning Target recognition Face recognition Kinematics Real-time systems Robustness Planning Face detection

来源：评论

学校读者我要写书评

暂无评论

Comparing effects of rigid, flexible, and actuated series-elastic spines on bounding gait of quadruped robots

Comparing effects of rigid, flexible, and actuated series-el...

引用

RSI/ISM International Conference on robotics and Mechatronics (ICROM)

作者： Mohammad Hasan H. Kani Majid Nili Ahmadabadi Control and Intelligent Processing Center of Excellence Cognitive Robotics Laboratory School of ECE College of Engineering University of Tehran Tehran Iran

Spinal actuation is necessary for quadruped robots to achieve rapid leg locomotion. In this paper, effect of flexible spinal actuation on the bounding gait is investigated. By defining a performance criterion for the bounding gait, a quadruped robot (Ghostdog) is tested in four different case studies; namely rigid spine, flexible passive spine, actuated spine, and series elastic actuated spine. We show that the robot with a series elastic actuator in its spinal joint has the best performance criterion and is the best robot in terms of bounding power consumption. On the other hand, it is shown that by using spinal actuation not only the speed of locomotion increases considerably, but also the pattern of bounding becomes more similar to real fast felines.

关键词： Robots Oscillators Equations Hip

来源：评论

学校读者我要写书评

暂无评论

Modeling and Model-free Fuzzy control of a Continuum Robotic Arm

Modeling and Model-free Fuzzy Control of a Continuum Robotic...

引用

RSI/ISM International Conference on robotics and Mechatronics (ICROM)

作者： Aida Parvaresh S. Ali A. Moosavian Center of Excellence in Robotics & Control Faculty of Mechanical Engineering K. N. Toosi University of Technology Tehran Iran

ISBN: (纸本)9781728101286;9781728101279

Continuum robotic arms have many advantages compared to traditional manipulators, which motivate further researches in this field. Dynamics modeling and controlling these systems are challenging areas due to the complicated nonlinearities and uncertainties. In this paper, a three-dimensional dynamics model of such manipulators is developed through appropriate system identification method that is validated by experimental data, and then it is used to design a PID-fuzzy controller. This is a model-free controller and does not require the exact model of the system for controlling the position of the end-effector. Next, the performance in reaching different positions of the workspace is investigated. Obtained results show the merits of the proposed controller.

关键词： Analytical models Robot sensing systems Mathematical model End effectors Kinematics

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：