检索结果-内蒙古大学图书馆

Deep reinforcement learning-based trajectory planning for double pendulum cranes: Design and experiments

Mechanical systems and Signal Processing 2025年 234卷

作者： Ding, Weili Zhang, Heng Hua, Changchun Lu, Biao Engineering Research Center of Intelligent Control System and Intelligent Equipment Ministry of Education Laboratory of Intelligent Rehabilitation and Neuromodulation of Hebei Province Institute of Electrical Engineering Yanshan University Qinhuangdao066004 China Institute of Robotics and Automatic Information System College of Artificial Intelligence Nankai University Tianjin300353 China Institute of Intelligence Technology and Robotic Systems Shenzhen Research Institute of Nankai University Shenzhen518083 China

Since cranes usually possess double pendulum dynamics, the mass of the payload often changes and there are frequently lifting/lowering operations simultaneously. Moreover, most crane systems are driven by motors, whose velocities and accelerations are often limited. To solve the above problems, this paper proposes a deep reinforcement learning (DRL) reference trajectory generation method based on virtual–physical joint training. Firstly, a DRL module based on deep deterministic policy gradient (DDPG), along with a double pendulum crane dynamic model and an adaptive controller, are established within the virtual environment for training the reference trajectory. When the reward reaches the threshold, the training is switched to the physical environment to further optimize the reference trajectory, realizing the swing suppression of the hook and the payload. In addition, to satisfy the performance of the drive motors, velocity and acceleration thresholds are set to constrain the performance of the drive motors. Finally, in view of the fact that the operation process of the double pendulum crane is divided into payload transportation and payload loading/unloading, an event-triggering mechanism is designed to switch different control policies in accordance with different operation processes, thus reducing the consumption of computing resources. Through experiments on the actual double pendulum crane and comparison with the existing reference trajectories and input shapers, the superiority of this method is demonstrated. © 2025 Elsevier Ltd

关键词： Model reference adaptive control

来源：评论

学校读者我要写书评

暂无评论

Modeling and Tracking Control of Micropipette Oocyte Enucleation Based on Fractional Calculus

引用

IEEE Transactions on Industrial Electronics 2025年

作者： Zhang, Yujie Li, Bingxin Liu, Yaowei Zhao, Xin Tianjin300350 China Shenzhen Research Institute of Nankai University Institute of Intelligence Technology and Robotic Systems Shenzhen518083 China

The protocol of somatic cell nuclear transfer technology requires oocyte enucleation with a micropipette. This operation is destructive and critical to the further development of reconstructed oocytes. As an aspiration control problem, the viscoelastic property of extracted material, complicated dynamics, great uncertainty, and disturbance bring about difficulties on the subject. To address this issue, this article models the enucleation process with fractional-order calculus. With the same number of parameters, it is shown that the fractional-order models have better fitting performance than integer-order models. In addition, more terms and more parameters can be added to fractional-order models, which strengthens the modeling ability. Based on the identified incommensurate fractional-order model, an adaptive sliding mode controller is proposed to deal with the unknown system parameters and disturbance. In the numerical simulation, the fractional-order controller gets a small overshoot (25%) and fast oscillation. Experiments on the micromanipulation system compare the fractional-order, integer-order and traditional PID controllers. The results show that the proposed fractional-order controller has shorter arrival time, less arrival velocity, less root mean square error (RMSE), higher success rate and higher cleavage rate. The higher cleavage rate of the proposed fractional-order controller means lower damage to oocytes, which is meaningful for the completion of somatic cell nuclear transfer. © 1982-2012 IEEE.

关键词： Differentiation (calculus)

来源：评论

学校读者我要写书评

暂无评论

Optimal Trajectory-Based Control of 3-D Dual Rotary Cranes for Payload Dynamic Regulation in Complex Environments

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial intelligence 2024年第11期5卷 5452-5464页

作者： Liu, Zhuoqing Yang, Tong Fang, Yongchun Sun, Ning Shenzhen Research Institute Nankai University Institute of Intelligence Technology and Robotic Systems Shenzhen518083 China College of Artificial Intelligence and the TBI Center Tianjin300350 China

With flexible payload adjustment ability and large load capacity, dual rotary cranes (DRCs) provide effective solutions for various complex hoisting tasks. At present, the control research for DRCs mostly focuses on two-dimensional space (restricting workspace and efficiency), or lacks the consideration of DRC dynamic characteristics and the practical demands for the dynamic regulation of payload positions and attitudes, which makes it difficult to handle hoisting tasks in complex environments. To tackle these issues, this article proposes an optimal trajectory-based motion control method for three-dimensional (3-D) DRCs in complex environments, effectively tackling key challenges encountered by DRCs operating in 3-D space. The proposed method achieves dynamic regulation of payload position and attitude by DRCs in 3-D space for the first time, constraining payload velocity and acceleration within reasonable ranges while avoiding obstacles, which represents an advancement in enhancing the efficiency and safety of 3-D DRC operations in complex environments. Specifically, the coupling relationship between the actuated boom motions and the non-actuated payload motions in 3-D space is mathematically solved, which provides the foundation of indirect payload regulation through boom control. Moreover, by introducing multiple performance indicators during optimization, the proposed method ensures satisfactory payload transient performance while maintaining a safe distance from obstacles. Additionally, by the analysis of steady-state equilibrium conditions and the reasonable passing time allocation of virtual via-points, coordinated boom motions with payload swing suppression are realized, ensuring transportation smoothness. Finally, hardware experiments are conducted considering collision-free payload transportation through reciprocating boom pitch/rotation motions, which verifies the effectiveness and practical performance of the proposed method. © 2024 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Data-Based Dual-Loop Learning Control of Underactuated systems With Disturbance Prediction and Input-Output Constraints

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial intelligence 2024年第7期5卷 3419-3430页

作者： Yang, Tong Sun, Ning Zhai, Meng Fang, Yongchun Wu, Qingxiang College of Artificial Intelligence and the TBI center Tianjin300350 China Shenzhen Research Institute of Nankai University Institute of Intelligence Technology and Robotic Systems Shenzhen518083 China

In practice, many mechanical systems have fewer actuators than degrees of freedom (DOFs), such as transportation robots, aerial vehicles, and flexible structures. These systems are underactuated with high flexibility and low energy consumption. However, unexpected input/output constraints, unmeasurable nonlinear dynamics/disturbances, and complicated gain selections bring about more challenges in real operations. To this end, this article presents a dual-loop learning control framework for a class of multiinput-multioutput (MIMO) underactuated systems. The model-independent inner-loop controller accelerates error convergence and is derived from Lyapunov-based stability analysis. Moreover, the inner-loop controller and the underactuated system are integrated into an optimal reference model by a data-based learning method. The parameters and control gains are optimized online. The outer-loop prediction controller directly adapts the optimized reference model as a prediction model. Also, the reference trajectories and disturbance estimates are generated and transmitted to the inner-loop structure. Hence, the real-time performance of the proposed controller is not affected by model accuracy. As far as we know, this article designs the first controller for MIMO underactuated systems to simultaneously restrict actuated/unactuated motions and actual inputs, predict unknown disturbances, and optimize control gains. The closed-loop stability is theoretically guaranteed. Some hardware experiments provide performance verification. © 2020 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Modeling and precise tracking control of spatial bending pneumatic softactuators

引用

Biomimetic intelligence & robotics 2024年第4期4卷 92-98页

作者： Yize Ma Qingxiang Wu Zehao Qiu Yongchun Fang Ning Sun Institute of Robotics and Automatic Information Systems(IRAIS) College of Artificial IntelligenceNankai UniversityTianjin 300350China Institute of Intelligence Technology and Robotic Systems Shenzhen Research Institute of Nankai UniversityShenzhen 518083China

In recent years,a variety of pneumatic soft actuators(PSAs)have been proposed due to the develop-ment of soft robots in biomimetic robots,medical devices,*** the same time,the modeling and control of PSAs remains an open *** this paper,a spatial bending pneumatic soft actuator(SBPSA)modeling method based on the Prandtl-Ishlinskii(PI)model is proposed,and the inverse model is designed to compensate for hysteresis ***,an adaptive feedback controller combined with a hysteresis compensator is proposed for the precise control and tracking of ***,an experimental platform is built,and experimental results demonstrate the effectiveness of the proposed method for precise tracking.

关键词： Spatial bending Hysteresis compensation Prandtl-Ishlinskii modeling Adaptive feedback control

来源：评论

学校读者我要写书评

暂无评论

LQR-based Balance Control of Two-wheeled Legged Robot 41

LQR-based Balance Control of Two-wheeled Legged Robot

引用

第41届中国控制会议

作者： Jinyang Dong Rui Liu Biao Lu Xian Guo Huawang Liu Institute of Robotics and Automatic Information Systems College of Artificial IntelligenceNankai University Institute of Intelligence Technology and Robotic Systems Shenzhen Research Institute of Nankai University

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Recently,the research of wheel-legged robot(WLR) has become a hot *** has fast speed,high efficiency and strong adaptability to terrain,which makes full use of the advantages of wheeled robots and leg *** paper presents a successful case of balance control applied to an actual WLR *** mechanical structure is firstly introduced in this ***,the simplified dynamic model of the robot is *** on the linear quadratic regulator(LQR),the balance controller is constructed according to the established dynamic *** simulation and experiments are carried out,which sufficiently demonstrate the efficiency of the designed LQR controller.

关键词： LQR balance control underactuated robotics optimizion two-wheeled legged robot

来源：评论

学校读者我要写书评

暂无评论

Fully-Actuated System Approach-Based Neuroadaptive Control for Underactuated Robots With State Estimation and Delay

引用

IEEE Transactions on Cybernetics 2025年 PP卷 PP页

作者： Yang, Tong Zhang, Menghua Sun, Wei Sun, Ning Nankai University Institute of Robotics and Automatic Information Systems College of Artificial Intelligence TBI center Tianjin300350 China Shenzhen Research Institute of Nankai University Institute of Intelligence Technology and Robotic Systems Shenzhen518083 China University of Jinan School of Electrical Engineering Jinan250022 China Liaocheng University School of Mathematics Science Liaocheng252000 China

In practice, many mechanical systems are underactuated, such as naval vessels, cranes, and helicopters, to reduce energy consumption and enhance flexibility. However, compounded by strong nonlinearity arising from state coupling, the underactuated nature and high-order unavailable states pose great challenges to motion control (particularly for unactuated states lacking independent actuators or kinematic constraints). In this article, an adaptive controller based on fully-actuated system methods is proposed, together with a general and extensible analysis method. First, a group of high-order auxiliary variables, consisting of actuated/unactuated states, their derivatives, and proportional-differential terms, are designed to rearrange the nonlinear underactuated system as a high-order linear fully-actuated system without any linearization operations. The asymptotic convergence of auxiliary variables theoretically eliminates the steady-state errors of actuated/unactuated states together. For high-order unmeasurable variables, they are recovered by the constructed neural network observer to estimate high-order dynamics, which avoids discontinuous robust terms and improves the accuracy of compensation/positioning. Motivated by the inherent features and advantages of fully-actuated systems, this article proposes the first fully-actuated system-based continuous adaptive controller for a class of underactuated robots. Moreover, it is convenient to extend the proposed controller to handle more practical problems, such as state delay, without the need to reconduct Lyapunov-based analysis. In addition to complete theoretical frames, this article also provides several experimental validation. © 2013 IEEE.

关键词： State estimation

来源：评论

学校读者我要写书评

暂无评论

Modeling and MPC-based balance control for a wheeled bipedal robot 41

Modeling and MPC-based balance control for a wheeled bipedal...

引用

第41届中国控制会议

作者： Haixin Cao Biao Lu Huawang Liu Rui Liu Xian Guo Institute of Robotics and Automatic Information System Nankai University Institute of Intelligence Technology and Robotic Systems Shenzhen Research Institute of Nankai University

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

In recent years,wheeled bipedal robots have been widely researched as its flexible structures and superior *** the utilization of wheels,wheeled bipedal robots have the ability to move quickly on flat *** addition to this,they can cope with some complicated terrains by motors mounted on *** tasks have been achieved by wheeled bipedal robots such as trajectory tracking,carrying objects and leaping over *** whether the task is,the balance control is the basis of the subsequent *** this article,we established the dynamic equations of a wheeled bipedal robot on an inclined surface *** linearization and discretization around the equilibrium point,a model predictive controller(MPC) with input constraints is constructed to keep the balance of the *** order to deal with unmodeled dynamics and external disturbances,an extended state observer(ESO) is designed to enhance the robustness of the *** simulation results prove that the proposed control method can ensure the balance of the robot and has a satisfactory adaptability to external interference.

关键词： Wheeled Bipedal Robot Balance Control Model Predictive Control Extended State Observer

来源：评论

学校读者我要写书评

暂无评论

Kinematics and Dynamics Modeling of Bionic Variable Structure UAVs

Kinematics and Dynamics Modeling of Bionic Variable Structur...

引用

2024 IEEE International Conference on Real-Time Computing and robotics, RCAR 2024

作者： Lou, Huanhuan Wu, Qingxiang Wang, Hai Yang, Tong Liu, Huawang Sun, Ning College of Artificial Intelligence Tianjin300350 China Shenzhen Research Institute of Nankai University Institute of Intelligence Technology and Robotic Systems Shenzhen518083 China

ISBN: (纸本)9798350372601

In recent years, quadrotors have been widely used in many fields, and the requirements for rescue and exploration in narrow and limited environments have gradually increased. In order to improve the adaptability of quadrotors for limited environments, this paper establishes the kinematics and dynamics of bionic variable structure unmanned aerial vehicle (BVS-UAVs). Specifically, the four arms of BVS-UAVs can rotate independently around the central body frame to realize the configuration change during flight, which enhances the adaptation for limited environments and complex tasks, such as narrow space and close scanning vertical surfaces. However, compared with fixed-wing UAVs, the control of variable structure and asymmetric for BVS-UAV is full of challenges, and the modeling of kinematics and dynamics is intuitively important. Therefore, kinematics and dynamics for BVS-UAVs considering the change of center of gravity (CoG) and the moment of inertia (MoI) are established. We also calculated the control allocation matrix. Besides, the prototype of BVS-UAVs is built and the hover performance is fully verified. © 2024 IEEE.

关键词： Fixed wings

来源：评论

学校读者我要写书评

暂无评论

robotic dual-arm patch clamp for neuron excitability research under mechanical stimulation 43

Robotic dual-arm patch clamp for neuron excitability researc...

引用

43rd Chinese Control Conference, CCC 2024

作者： Ma, Biting Cui, Chaoyu Li, Ruimin Li, Minghui Qiu, Jinyu Li, Ke Sun, Mingzhu Zhao, Xin Zhao, Qili Tianjin300350 China Shenzhen Research Institute of Nankai University Institute of Intelligence Technology and Robotic Systems Shenzhen518083 China

ISBN: (纸本)9789887581581

The dual-arm patch clamp technique, using one micropipette electrode to patch the target cell to record its electric signals with the other micropipette mechanically stimulating the target cell, is a significant technique in neuroscience for studying neuron excitability under mechanical stimulation. A key step for dual-arm patch clamp operation is to coordinate two micropipettes to reach the target cells in the narrow brain tissue environment. The traditional manual operations face issues such as inaccurate workspace estimation, clumsy movements, and collision risks of the two micropipettes, resulting in low operational efficiency. Addressing the above issues, a robotic dual-arm patch clamp method was developed for neuron excitability research under mechanical stimulation in this paper. First, the reachable workspace of the dual-arm was calculated based on a kinematics model. Then, a robotic dual arm patch clamp operation procedure is proposed to approach, whole-cell patch, and mechanically stimulate the target cell. The experiment results on neurons in mouse brain slices show that the success rate of dual micropipette contacting cell surface reaches up to 90 %(18 / 20) at an average speed of 6 mins/cell, which are both significantly improved in comparison to manual operation. An increase in neuron excitability in the primary visual cortex (V1) was found under the mechanical stimulation, proving the feasibility of the proposed system for studying the impact of mechanical stimulation on ion channel activities. © 2024 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Neurons

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：