Search results

Soft robotics, regarded as a new research branch of robotics, has generated increasing interests in this decade and has demonstrated its outperformance in addressing safety issues when cooperating with human beings. However, there is still lack of accurate close-loop control because of the difficulty in acquiring feedback information and accurately modeling the system, especially in interactive environments. To this end, this paper aims to improve the controllability of the soft robot working in specific underwater environment. The system dynamics, which takes complicated hydrodynamics into account, is solved using Kane’s method. The dynamics-based adaptive visual servoing controller is proposed to realize accurate sensorimotor control.

This paper presents an image-based visual servoing control scheme for a cable-driven soft robot with a fixed camera observing the motions. The intrinsic and extrinsic parameters of the camera can be adapted online so that tedious camera calibration work can be eliminated. It is acknowledged that kinematics-based control can be only applied into tasks in the free space and has limitation in accelerating the motion speed of robot arms. That is, one must consider the unneglectable interaction effects generated from the environment and objectives when operating soft robots in such interactive control tasks. To extend the application of soft robots into underwater environment, the study models system dynamics considering complicated hydrodynamic effects. With the pre-knowledge of the external effects, the performance of the robot can be further improved by adding the compensation term into the controller.

The proposed controller has theoretically proved its convergence of image error, adaptive estimation error and the stability of the dynamical system based on Lyapunov’s analysis. The authors also validate the performance of the controller in positioning control task in an underwater environment. The controller shows its capacity of rapid convergence to and accurate tracking performance of a static image target in a physical experiment.

To the best of the authors’ knowledge, there is no such research before that has developed dynamics-based visual servoing controller which takes into account the environment interactions. This work can thus improve the control accuracy and enhance the applicability of soft robotics when operating in complicated environments.

In the running of multiple automated guided vehicles (AGVs) in warehouses, delay problems in motions happen unavoidably as there might exist some disabled components of robots, the instability of networks and the interference of people walking. Under this case, robots would not follow the designed paths and the coupled relationship between temporal and space domain for paths is broken. And there is no doubt that other robots are disturbed by the ones where delays happen. Finally, this brings about chaos or even breakdown of the whole system. Therefore, taking the delay disturbance into consideration in the path planning of multiple robots is an issue worthy of attention and research.

This paper proposes a prioritized path planning algorithm based on time windows to solve the delay problems of multiple AGVs. The architecture is a unity consisting of three components which are focused on scheduling AGVs under normal operations, delays of AGVs, and recovery of AGVs. In the components of scheduling AGVs under normal operations and recovery, this paper adopts a dynamic routing method based on time windows to ensure the coordination of multiple AGVs and efficient completion of tasks. In the component for scheduling AGVs under delays, a dynamical prioritized local path planning algorithm based on time windows is designed to solve delay problems. The introduced planning principle of time windows would enable the algorithm to plan new solutions of trajectories for multiple AGVs, which could lower the makespan. At the same time, the real-time performance is acceptable based on the planning principle which stipulates the parameters of local time windows to ensure that the computation of the designed algorithm would not be too large.

The simulation results demonstrate that the proposed algorithm is more efficient than the state-of-the-art method based on homotopy classes, which aims at solving the delay problems. What is more, it is validated that the proposed algorithm can achieve the acceptable real-time performance for the scheduling in warehousing applications.

By introducing the planning principle and generating delay space and local adjustable paths, the proposed algorithm in this paper can not only solve the delay problems in real time, but also lower the makespan compared with the previous method. The designed algorithm guarantees the scheduling of multiple AGVs with delay disturbance and enhances the robustness of the scheduling algorithm in multi-AGV system.

The purpose of this paper is to propose a localizability-based particle filtering localization algorithm for mobile robots to maintain localization accuracy in the high-occluded and dynamic environments with moving people.

First, the localizability of mobile robots is defined to evaluate the influences of both the dynamic obstacles and prior-map on localization. Second, based on the classical two-sensor track fusion algorithm, the odometer-based proposal distribution function (PDF) is corrected, taking account of the localizability. Then, the corrected PDF is introduced into the classical PF with “roulette” re-sampling. Finally, the robot pose is estimated according to all the particles.

The experimental results show that, first, it is necessary to consider the influence of the prior-map during the localization in the high-occluded and dynamic environments. Second, the proposed algorithm can maintain an accurate and robust robot pose in the high-occluded and dynamic environments. Third, its real timing is acceptable.

When the odometer error and occlusion caused by the dynamic obstacles are both serious, the proposed algorithm also has a probability evolving into the kidnap problem. But fortunately, such serious situations are not common in practice.

To check the ability of real application, we have implemented the proposed algorithm in the campus cafeteria and metro station using an intelligent wheelchair. To better help the elderly and disabled people during their daily lives, the proposed algorithm will be tested in a social welfare home in the future.

The localizability of mobile robots is defined to evaluate the influences of both the dynamic obstacles and prior-map on localization. Based on the localizability, the odometer-based PDF is corrected properly.

The purpose of this study is to propose extended potentials and investigate the applicability of extended Finnis–Sinclair (FS) potential to Cr with the unit cell structure of body-centered cubic (BCC Cr).

The parameters of each potential are determined by fitting the elastic constants, cohesive energy and mono-vacancy formation energy. Furthermore, the ability of the extended FS potential to describe the crystal defect properties is tested. Finally, the applicability of reproducing the thermal properties of Cr is discussed.

The internal relationship between physical properties and potential function is revealed. The mathematical relationship between physical properties and potential function is derived in detail. The extended FS potential performs well in reproducing physical properties of BCC Cr, such as elastic constants, cohesive energy, surface energy and the properties of vacancy et al. Moreover, good agreement is obtained with the experimental data for predicting the melting point, specific heat and coefficient of thermal expansion.

In this study, new extended potentials are proposed. The extended FS potential is able to reproduce the physical and thermal properties of BCC Cr. Therefore, the new extended potential can be used to describe the crystal defect properties of BCC Cr.

Getting high-quality data by removing the noisy data from the user-generated content (UGC) is the first step toward data mining and effective decision-making based on ubiquitous and unstructured social media data. This paper aims to design a framework for revoking noisy data from UGC.

In this paper, the authors consider a classification-based framework to remove the noise from the unstructured UGC in social media community. They treat the noise as the concerned topic non-relevant messages and apply a text classification-based approach to remove the noise. They introduce a domain lexicon to help identify the concerned topic from noise and compare the performance of several classification algorithms combined with different feature selection methods.

Experimental results based on a Chinese stock forum show that 84.9 per cent of all the noise data from the UGC could be removed with little valuable information loss. The support vector machines classifier combined with information gain feature extraction model is the best choice for this system. With longer messages getting better classification performance, it has been found that the length of messages affects the system performance.

The proposed method could be used for preprocessing in text mining and new knowledge discovery from the big data.

Existing Simultaneous Localization and Mapping (SLAM) algorithms have been relatively well developed. However, when in complex dynamic environments, the movement of the dynamic points on the dynamic objects in the image in the mapping can have an impact on the observation of the system, and thus there will be biases and errors in the position estimation and the creation of map points. The aim of this paper is to achieve more accurate accuracy in SLAM algorithms compared to traditional methods through semantic approaches.

In this paper, the semantic segmentation of dynamic objects is realized based on U-Net semantic segmentation network, followed by motion consistency detection through motion detection method to determine whether the segmented objects are moving in the current scene or not, and combined with the motion compensation method to eliminate dynamic points and compensate for the current local image, so as to make the system robust.

Experiments comparing the effect of detecting dynamic points and removing outliers are conducted on a dynamic data set of Technische Universität München, and the results show that the absolute trajectory accuracy of this paper's method is significantly improved compared with ORB-SLAM3 and DS-SLAM.

In this paper, in the semantic segmentation network part, the segmentation mask is combined with the method of dynamic point detection, elimination and compensation, which reduces the influence of dynamic objects, thus effectively improving the accuracy of localization in dynamic environments.