Search results
1 – 10 of over 2000Haoqiang Yang, Xinliang Li, Deshan Meng, Xueqian Wang and Bin Liang
The purpose of this paper is using a model-free reinforcement learning (RL) algorithm to optimize manipulability which can overcome difficulties of dilemmas of matrix inversion…
Abstract
Purpose
The purpose of this paper is using a model-free reinforcement learning (RL) algorithm to optimize manipulability which can overcome difficulties of dilemmas of matrix inversion, complicated formula transformation and expensive calculation time.
Design/methodology/approach
Manipulability optimization is an effective way to solve the singularity problem arising in manipulator control. Some control schemes are proposed to optimize the manipulability during trajectory tracking, but they involve the dilemmas of matrix inversion, complicated formula transformation and expensive calculation time.
Findings
The redundant manipulator trained by RL can adjust its configuration in real-time to optimize the manipulability in an inverse-free manner while tracking the desired trajectory. Computer simulations and physics experiments demonstrate that compared with the existing methods, the average manipulability is increased by 58.9%, and the calculation time is reduced to 17.9%. Therefore, the proposed method effectively optimizes the manipulability, and the calculation time is significantly shortened.
Originality/value
To the best of the authors’ knowledge, this is the first method to optimize manipulability using RL during trajectory tracking. The authors compare their approach to existing singularity avoidance and manipulability maximization techniques, and prove that their method has better optimization effects and less computing time.
Details
Keywords
Ling-Jie Gai, Xiaofeng Zong and Jie Huang
The aim of the paper is to propose a global, automated and continuous curvature calibration strategy for bending sensors, which is used for the angle feedback control of soft…
Abstract
Purpose
The aim of the paper is to propose a global, automated and continuous curvature calibration strategy for bending sensors, which is used for the angle feedback control of soft fingers.
Design/methodology/approach
In this work, the proposed curvature calibration strategy for bending sensors is based on the constant curvature bending properties of soft fingers. The strategy is to install the bending sensor on the soft finger and use the laser distance sensor to assist calibration, then calculate the relationship between the curvature and the voltage of the bending sensor through geometric conversion. In addition, this work also develops a full set of standard calibration systems and collection procedures for the bending sensor curvature calibration and uses machine learning algorithms to fit the collected data.
Findings
First, compared with the traditional calibration methods, the proposed curvature calibration strategy can achieve constant curvature measurement with the advantages of better continuity. Second, using the sensor data obtained by the proposed calibration method as the feedback signal for the soft finger bending angle control, the control effect is better than that of the traditional method.
Originality/value
This work proposes and verifies a global, automated and continuous curvature calibration strategy for bending sensors and is used for the angle feedback control of soft fingers. In addition, this work also develops a full set of standard calibration systems and collection procedures, which can be applied to a variety of flexible bending sensors with a good adaptability.
Details
Keywords
Yue Qiao, Wang Wei, Yunxiang Li, Shengzui Xu, Lang Wei, Xu Hao and Re Xia
The purpose of this paper is to introduce a motion control method for WFF-AmphiRobot, which can effectively realize the flexible motion of the robot on land, underwater and in the…
Abstract
Purpose
The purpose of this paper is to introduce a motion control method for WFF-AmphiRobot, which can effectively realize the flexible motion of the robot on land, underwater and in the transition zone between land and water.
Design/methodology/approach
Based on the dynamics model, the authors selected the appropriate state variables to construct the state space model of the robot and estimated the feedback state of the robot through the maximum a posteriori probability estimation. The nonlinear predictive model controller of the robot is constructed by local linearization of the model to perform closed-loop control on the overall motion of the robot. For the control problem of the terminal trajectory, using the neural rhythmic movement theory in bionics to construct a robot central pattern generator (CPG) for real-time generation of terminal trajectory.
Findings
In this paper, the motion state of WFF-AmphiRobot is estimated, and a model-based overall motion controller for the robot and an end-effector controller based on neural rhythm control are constructed. The effectiveness of the controller and motion control algorithm is verified by simulation and physical prototype motion experiments on land and underwater, and the robot can ideally complete the desired behavior.
Originality/value
The paper designed a controller for WFF-AmphiRobot. First, when constructing the robot state estimator in this paper, the robot dynamics model is introduced as the a priori estimation model, and the error compensation of the a priori model is performed by the method of maximum a posteriori probability estimation, which improves the accuracy of the state estimator. Second, for the underwater oscillation motion characteristics of the flipper, the Hopf oscillator is used as the basis, and the flipper fluctuation equation is modified and improved by the CPG signal is adapted to the flipper oscillation demand. The controller effectively controls the position error and heading angle error within the desired range during the movement of the WFF-AmphiRobot.
Details
Keywords
Yuze Shang, Fei Liu, Ping Qin, Zhizhong Guo and Zhe Li
The goal of this research is to develop a dynamic step path planning algorithm based on the rapidly exploring random tree (RRT) algorithm that combines Q-learning with the…
Abstract
Purpose
The goal of this research is to develop a dynamic step path planning algorithm based on the rapidly exploring random tree (RRT) algorithm that combines Q-learning with the Gaussian distribution of obstacles. A route for autonomous vehicles may be swiftly created using this algorithm.
Design/methodology/approach
The path planning issue is divided into three key steps by the authors. First, the tree expansion is sped up by the dynamic step size using a combination of Q-learning and the Gaussian distribution of obstacles. The invalid nodes are then removed from the initially created pathways using bidirectional pruning. B-splines are then employed to smooth the predicted pathways.
Findings
The algorithm is validated using simulations on straight and curved highways, respectively. The results show that the approach can provide a smooth, safe route that complies with vehicle motion laws.
Originality/value
An improved RRT algorithm based on Q-learning and obstacle Gaussian distribution (QGD-RRT) is proposed for the path planning of self-driving vehicles. Unlike previous methods, the authors use Q-learning to steer the tree's development direction. After that, the step size is dynamically altered following the density of the obstacle distribution to produce the initial path rapidly and cut down on planning time even further. In the aim to provide a smooth and secure path that complies with the vehicle kinematic and dynamical restrictions, the path is lastly optimized using an enhanced bidirectional pruning technique.
Details
Keywords
Hakan F. Oztop, Burak Kiyak and Ishak Gökhan Aksoy
This study aims to focus on understanding how different jet angles and Reynolds numbers influence the phase change materials’ (PCMs) melting process and their capacity to store…
Abstract
Purpose
This study aims to focus on understanding how different jet angles and Reynolds numbers influence the phase change materials’ (PCMs) melting process and their capacity to store energy. This approach is intended to offer novel insights into enhancing thermal energy storage systems, particularly for applications where heat transfer efficiency and energy storage are critical.
Design/methodology/approach
The research involved an experimental and numerical analysis of PCM with a melting temperature range of 22 °C–26°C under various conditions. Three different jet angles (45°, 90° and 135°) and two container angles (45° and 90°) were tested. Additionally, two different Reynolds numbers (2,235 and 4,470) were used to explore the effects of jet outlet velocities on PCM melting behaviour. The study used a circular container and analysed the melting process using the hot air inclined jet impingement (HAIJI) method.
Findings
The obtained results showed that the average temperature for the last time step at Ф = 90° and Re = 4,470 is 6.26% higher for Ф = 135° and 14.23% higher for Ф = 90° compared with the 45° jet angle. It is also observed that the jet angle, especially for Ф = 90°, is a much more important factor in energy storage than the Reynolds number. In other words, the jet angle can be used as a passive control parameter for energy storage.
Originality/value
This study offers a novel perspective on the effective storage of waste heat transferred with air, such as exhaust gases. It provides valuable insights into the role of jet inclination angles and Reynolds numbers in optimizing the melting and energy storage performance of PCMs, which can be crucial for enhancing the efficiency of thermal energy storage systems.
Details
Keywords
Florian Zellmer, Markus Löffler, Markus Schneider and Christian Kreischer
The purpose of this paper is to investigate a novel approach toward electromagnetic launch.
Abstract
Purpose
The purpose of this paper is to investigate a novel approach toward electromagnetic launch.
Design/methodology/approach
The field of linear electromagnetic acceleration aims at accelerating macroscopic masses (up to several kg) to speeds in excess of 2 km/s. This can be achieved using accelerators of the railgun type. The innovation of this work lies in the use of multiphase current instead of the classically used quasi-direct current (DC). The approach taken is to work out in a first step the potential performance of such a configuration, for example, by showing that a constant propulsive force can be realized. Next, the necessary changes for the system setup were carefully analyzed. Both the accelerator and the power supply have to be considerably modified with regard to the classical approach.
Findings
Thorough analysis of the electromagnetic behavior of the launcher including nonlinear effects lead to an innovative system design which is considered to be the main finding of the work presented here. Moreover, a prototype was build. The preliminary experimental results obtained are in very good agreement with corresponding simulations validating the underlying modeling approach.
Research limitations/implications
For the purpose of this paper, power levels of only 450 kVA are considered. However, this research can be used to design more powerful devices in the future.
Originality/value
While DC powered railguns are modeled very well in a variety of papers, the use of multiphase alternating current is not very well discussed yet. It could be of value for launch scenarios, for which very high speeds are required such as the launch of micro satellites to space.
Details
Keywords
Zhen Sun, Takahiro Sato and Kota Watanabe
Topology optimization (TO) methods have shown their unique advantage in the innovative design of electric machines. However, when introducing the TO method to the rotor design of…
Abstract
Purpose
Topology optimization (TO) methods have shown their unique advantage in the innovative design of electric machines. However, when introducing the TO method to the rotor design of interior permanent magnet (PM) synchronous machines (IPMSMs), the layout parameters of the magnet cannot be synchronously optimized with the topology of the air barrier; the full design potential, thus, cannot be unlocked. The purpose of this paper is to develop a novel method in which the layout parameters PMs and the topology of air barriers can be optimized simultaneously for aiding the innovative design of IPMSMs.
Design/methodology/approach
This paper presents a simultaneous TO and parameter optimization (PO) method that is applicable to the innovative design of IPMSMs. In this method, the mesh deformation technique is introduced to make it possible to make a connection between the TO and PO, and the multimodal optimization problem can thereby be solved more efficiently because good topological features are inherited during iterative optimization.
Findings
The numerical results of two case studies show that the proposed method can find better Pareto fronts than the traditional TO method within comparable time-consuming. As the optimal design result, novel rotor structures with better torque profiles and higher reluctance torque are respectively found.
Originality/value
A method that can simultaneously optimize the topology and parameter variables for the design of IPMSMs is proposed. The numerical results show that the proposed method is useful and practical for the conceptual and innovative design of IPMSMs because it can automatically explore optimal rotor structures from the full design space without relying on the experience and knowledge of the engineer.
Details
Keywords
Qinghua Huang, Yingchen Wang, Hao Luo and Jianyi Li
This paper aims to develop a new robotic ultrasound system for spine imaging with more anthropomorphic scanning manipulation in comparison with previously reported techniques.
Abstract
Purpose
This paper aims to develop a new robotic ultrasound system for spine imaging with more anthropomorphic scanning manipulation in comparison with previously reported techniques.
Design/methodology/approach
The system evaluates the imaging quality of ultrasound (US) B-scans by detecting vertebral landmarks and groups the images with relatively low quality into several sub-optimal types. By imitating the scanning skills of sonographers, the authors defined a set of adjustment strategies for certain sub-optimal types. In this way, the robot can recollect the US images with high quality by adaptively adjusting the pose of the probe like a sonographer.
Findings
The results from phantom experiments and in vivo experiments showed that the proposed method could improve the quality of B-scans during the scanning. The 3 D US volume reconstruction has also verified the feasibility of the proposed method.
Originality/value
This paper demonstrates how to adapt a robotic spinal ultrasound scanning using a preliminary anthropomorphic approach.
Details
Keywords
Yumei Song, Jianzhang Hao, Changhao Dong, Xizheng Guo and Li Wang
This paper aims to study a multi-level reinjection current source converter (MLR-CSC) that adds attracting properties such as the self-commutation and pulse multiplication to the…
Abstract
Purpose
This paper aims to study a multi-level reinjection current source converter (MLR-CSC) that adds attracting properties such as the self-commutation and pulse multiplication to the thyristor converter, which is of great significance for increasing the device capacity and reducing current harmonics on the grid side. Particularly, designing advantageous driving methods of the reinjection circuit is a critical issue that impacts the harmonic reduction and operation reliability of the MLR-CSC.
Design/methodology/approach
To deal with the mentioned issue, this paper takes the five-level reinjection current source converter (FLR-CSC), which is a type of the MLR-CSC, as the research object. Then, a method that can fully use combinations of five-level reinjection switching functions based on the concept of decomposition and recombination is proposed. It is worthy to mention that the proposed method can be easily extended to other multi-level reinjection circuits. Moreover, the working principle of the three-phase bridge circuit based on semi-controlled thyristors in the FLR-CSC that can achieve the four-quadrant power conversion is analyzed in detail.
Findings
Finally, the simulation and experimental results of FLR-CSC verify the effectiveness of the proposed reinjection circuit driving method and the operating principle of four-quadrant power conversion in this paper.
Originality/value
The outstanding features of the proposed driving method for FLR-CSC in this paper include combinations of reinjection switching functions that are fully exploited through three simple steps and can be conveniently extended to other multi-level reinjection circuits.
Details
Keywords
Jiazhong Zhang, Shuai Wang and Xiaojun Tan
The light detection and ranging sensor has been widely deployed in the area of simultaneous localization and mapping (SLAM) for its remarkable accuracy, but obvious drift…
Abstract
Purpose
The light detection and ranging sensor has been widely deployed in the area of simultaneous localization and mapping (SLAM) for its remarkable accuracy, but obvious drift phenomenon and large accumulated error are inevitable when using SLAM. The purpose of this study is to alleviate the accumulated error and drift phenomenon in the process of mapping.
Design/methodology/approach
A novel light detection and ranging SLAM system is introduced based on Normal Distributions Transform and dynamic Scan Context with switch. The pose-graph optimization is used as back-end optimization module. The loop closure detection is only operated in the scenario, while the path satisfies conditions of loop-closed.
Findings
The proposed algorithm exhibits competitiveness compared with current approaches in terms of the accumulated error and drift distance. Further, supplementary to the place recognition process that is usually performed for loop detection, the authors introduce a novel dynamic constraint that takes into account the change in the direction of the robot throughout the total path trajectory between corresponding frames, which contributes to avoiding potential misidentifications and improving the efficiency.
Originality/value
The proposed system is based on Normal Distributions Transform and dynamic Scan Context with switch. The pose-graph optimization is used as back-end optimization module. The loop closure detection is only operated in the scenario, while the path satisfies condition of loop-closed.
Details