Search results

It is quite universal for high-speed turnouts to be exposed to the wear of the stock rail of the switch rail during the service process. The wear will cause the change of railhead profile and the relative positions of the switch rail and the stock rail, which will directly affect the wheel–rail contact state and wheel load transition when a train passes the turnout and will further impose serious impacts on the safety and stability of train operation. The purpose of this paper is to provide suggestions for wear management of high-speed turnout.

The actual wear characteristics of switch rails of high-speed turnouts in different guiding directions were studied based on the monitoring results on site; the authorized wear limits for the switch rails of high-speed turnout were studied through derailment risk analysis and switch rail strength analysis.

The results show that: the major factor for the service life of a curved switch rail is the lateral wear. The wear characteristics of the curved switch rail of a facing turnout are significantly different from those of a trailing turnout. To be specific, the lateral wear of the curved switch rail mainly occurs in the narrower section at its front end for a trailing turnout, but in the wider section at its rear end when for a facing turnout. The maximum lateral wear of a dismounted switch rail from a trailing turnout is found on the 15-mm wide section and is 3.9 mm, which does not reach the specified limit of 6 mm. For comparison, the lateral wear of a dismounted switch rail from a facing turnout is found from the 35-mm wide section to the full-width section and is greater than 7.5 mm, which exceeds the specified limit. Based on this, in addition to meeting the requirements of maintenance rules, the allowed wear of switch rails of high-speed turnout shall be so that the dangerous area with a tangent angle of wheel profile smaller than 43.6° will not contact the switch rail when the wheel is lifted by 2 mm. Accordingly, the lateral wear limit at the 5-mm wide section of the curved switch rail shall be reduced from 6 mm (as specified) to 3.5 mm.

The work in this paper is of reference significance to the research on the development law of rail wear in high-speed turnout area and the formulation of relevant standards.

The purpose of this paper is to propose an error model for serial robot kinematic calibration based on dual quaternions.

The dual quaternions are the combination of dual-number theory and quaternion algebra, which means that they can represent spatial transformation. The dual quaternions can represent the screw displacement in a compact and efficient way, so that they are used for the kinematic analysis of serial robot. The error model proposed in this paper is derived from the forward kinematic equations via using dual quaternion algebra. The full pose measurements are considered to apply the error model to the serial robot by using Leica Geosystems Absolute Tracker (AT960) and tracker machine control (T-MAC) probe.

Two kinematic-parameter identification algorithms are derived from the proposed error model based on dual quaternions, and they can be used for serial robot calibration. The error model uses Denavit–Hartenberg (DH) notation in the kinematic analysis, so that it gives the intuitive geometrical meaning of the kinematic parameters. The absolute tracker system can measure the position and orientation of the end-effector (EE) simultaneously via using T-MAC.

The error model formulated by dual quaternion algebra contains all the basic geometrical parameters of serial robot during the kinematic calibration process. The vector of dual quaternion error can be used as an indicator to represent the trend of error change of robot’s EE between the nominal value and the actual value. The accuracy of the EE is improved after nearly 20 measurements in the experiment conduct on robot SDA5F. The simulation and experiment verify the effectiveness of the error model and the calibration algorithms.

This paper aims to design a deep neural network for object instance segmentation and six-dimensional (6D) pose estimation in cluttered scenes and apply the proposed method in real-world robotic autonomous grasping of household objects.

A novel deep learning method is proposed for instance segmentation and 6D pose estimation in cluttered scenes. An iterative pose refinement network is integrated with the main network to obtain more robust final pose estimation results for robotic applications. To train the network, a technique is presented to generate abundant annotated synthetic data consisting of RGB-D images and object masks in a fast manner without any hand-labeling. For robotic grasping, the offline grasp planning based on eigengrasp planner is performed and combined with the online object pose estimation.

The experiments on the standard pose benchmarking data sets showed that the method achieves better pose estimation and time efficiency performance than state-of-art methods with depth-based ICP refinement. The proposed method is also evaluated on a seven DOFs Kinova Jaco robot with an Intel Realsense RGB-D camera, the grasping results illustrated that the method is accurate and robust enough for real-world robotic applications.

A novel 6D pose estimation network based on the instance segmentation framework is proposed and a neural work-based iterative pose refinement module is integrated into the method. The proposed method exhibits satisfactory pose estimation and time efficiency for the robotic grasping.

The purpose of this paper is to propose a robust iterative LIDAR-based pose tracking method assisted by modified visual odometer to resist initial value disturbance and locate a robot in the environments with certain occlusion.

At first, an iterative LIDAR-based pose tracking method is proposed. The LIDAR information is filtered and occupancy grid map is pre-processed. The sample generation and scoring are iterated so that the result is converged to the stable value. To improve the efficiency of sample processing, the integer-valued map indices of rotational samples are preserved and translated. All generated samples are analyzed to determine the maximum error direction. Then, a modified visual odometer is introduced for error compensation. The oriented fast and rotated brief (ORB) features are uniformly sampled in the image. A local map which contains key frames for reference is maintained. These two measures ensure that the modified visual odometer is able to return robust result which compensates the error of LIDAR-based pose tracking method in the maximum error direction.

Three experiments are conducted to prove the advantages of the proposed method. The proposed method can resist initial value disturbance with high computational efficiency, give back credible real-time result in the environment with abundant features and locate a robot in the environment with certain occlusion.

The proposed method is able to give back real-time pose tracking results with robustness. The iterative sample generation enables the robot to resist initial value disturbance. In each iteration, rotational and translational samples are separately generated to enhance computational efficiency. The maximum error direction of LIDAR-based pose tracking method is determined by principle component analysis and compensated by the result of modified visual odometer to give back correct pose in the environment with certain occlusion.

Robot-assisted system for minimally invasive surgery (MIS) has been attracting more and more attentions. Compared with a traditional MIS, the robot-assisted system for MIS is able to overcome or reduce defects, such as poor hand-eye coordination, heavy labour intensity and limited motion of the instrument. The purpose of this paper is to design a novel robotic system for MIS applications.

A robotic system with three separate slave arms for MIS has been designed. In the proposed robot, a new mechanism was designed as the remote centre motion (RCM) mechanism to restrain the movement of instrument or laparoscope around the incision. Moreover, an improved instrument without coupling motion between wrist and grippers was developed to enhance its manipulability. A control system architecture was also developed, and an intuitive control method was applied to realize hand-eye coordination of the operator.

For the RCM mechanism, the workspace was analyzed and the positioning accuracy of the remote centre point was tested. The results show that the RCM mechanism can be applied to MIS. Furthermore, the master-slave trajectory tracking experiments reveal that slave robots are able to follow the movement of the master manipulators well. Finally, the feasibility of the robot-assisted system for MIS is proved by performing animal experiments successfully.

This paper offers a novel robotic system for MIS. It can accomplish the anticipated results.

This paper aims to use fully convolutional network (FCN) to predict pixel-wise antipodal grasp affordances for unknown objects and improve the grasp detection performance through multi-scale feature fusion.

A modified FCN network is used as the backbone to extract pixel-wise features from the input image, which are further fused with multi-scale context information gathered by a three-level pyramid pooling module to make more robust predictions. Based on the proposed unify feature embedding framework, two head networks are designed to implement different grasp rotation prediction strategies (regression and classification), and their performances are evaluated and compared with a defined point metric. The regression network is further extended to predict the grasp rectangles for comparisons with previous methods and real-world robotic grasping of unknown objects.

The ablation study of the pyramid pooling module shows that the multi-scale information fusion significantly improves the model performance. The regression approach outperforms the classification approach based on same feature embedding framework on two data sets. The regression network achieves a state-of-the-art accuracy (up to 98.9%) and speed (4 ms per image) and high success rate (97% for household objects, 94.4% for adversarial objects and 95.3% for objects in clutter) in the unknown object grasping experiment.

A novel pixel-wise grasp affordance prediction network based on multi-scale feature fusion is proposed to improve the grasp detection performance. Two prediction approaches are formulated and compared based on the proposed framework. The proposed method achieves excellent performances on three benchmark data sets and real-world robotic grasping experiment.

This paper aims to develop a novel miniature 3-axis force sensor which can detect the interaction forces during tissue palpation in MIS (minimally invasive surgery). MIS offers many significant merits compared with traditional open surgery, the wound to the patients and the postoperative pains are alleviated and reduced dramatically. However, the inherent drawback due to lack of force feedback still exists while conducting some operation procedures. For example, tissue palpation performed easily during open surgery could not be realized in an MIS manner.

The force sensor is based on the resistive-based sensing method that utilizes strain gauges to measure the strain when the external loads are acting on the tip of the sensor. A novel flexible tripod structure with bending and compression deformations is designed to discriminate the magnitudes and directions of the three orthogonal force components. A linear characteristic matrix is derived to disclose the relationship between the sensitivity and the geometric parameters of the structure, and a straightforward geometric parameterized optimization method considering the sensitivity isotropy is proposed to provide the sensor structure with high sensitivity and adequate stiffness.

The sensor prototype can perform force measurement with sensing ranges of ± 3.0 N in axial direction and ± 1.5 N in radial direction, and the resolutions are 5 per cent and 1 per cent, respectively. It is concluded that this force sensor is compatible with MIS instruments and the ex-vivo experiment shows that the sensor can be used to perform tissue palpation during MIS procedures.

This paper is intended to address the significant role of force sensing and force feedback during MIS operations, and presents a new application of the resistive-based sensing method in MIS. A tripod structure is designed and a straightforward optimization method considering the sensitivity isotropy of the sensor is proposed to determine geometric parameters suited for the given external loads.

The purpose of this paper is to review the state of the art of laser powder deposition (LPD), a solid freeform fabrication technique capable of fabricating fully dense functional items from a wide range of common engineering materials, such as aluminum alloys, steels, titanium alloys, nickel superalloys and refractory materials.

The main R&D efforts and the major issues related to LPD are revisited.

During recent years, a worldwide series of R&D efforts have been undertaken to develop and explore the capabilities of LPD and to tap into the possible cost and time savings and many potential applications that this technology offers.

These R&D efforts have produced a wealth of knowledge, the main points of which are highlighted herein.

To solve the problem that the traditional received signal strength indicator real-time location method does not test the attenuation characteristics of the electromagnetic wave transmission in the location area, which cannot guarantee the accuracy of the location, resulting in a large location error.

At present, the compressed sensing (CS) reconstruction algorithm can be roughly divided into the following two categories (Zhouzhou and Fubao, 2014; Lagunas et al., 2016): one is the greedy iterative algorithm proposed for combinatorial optimization problems, which includes matching pursuit algorithm (MP), positive cross matching tracking algorithm (OMP), greedy matching tracking algorithm, segmented orthogonal matching tracking algorithm (StOMP) and so on. The second kind is the convex optimization algorithm, which also called the optimization approximation method. The common method is the basic tracking algorithm, which uses the norm instead of the norm to solve the optimization problem. In this paper, based on the piecewise orthogonal MP algorithm, the improved StOMP reconstruction algorithm is obtained.

In this paper, the MP algorithm (OMP), the StOMP and the improved StOMP algorithm are used as simulation reconstruction algorithms to achieve the comparison of location performance. It can be seen that the estimated position of the target is very close to the original position of the target. It is concluded that the CS grid-based target stepwise location method in underground tunnel can accurately locate the target in such specific region.

In this paper, the offline fingerprint database in offline phase of location method is established and the measurement of the electromagnetic noise distribution in different localization areas is considered. Furthermore, the offline phase shares the work of the location process, which greatly reduces the algorithm complexity of the online phase location process and the power consumption of the reference node, meanwhile is easy to implement under the same conditions, as well as conforms to the location environment.

The purpose of this paper is to design a multifingered dexterous hand grasping planning method that can efficiently perform grasping tasks on multiple dexterous hand platforms.

The grasping process is divided into two stages: offline and online. In the offline stage, the grasping solution form is improved based on the forward kinematic model of the dexterous hand. A comprehensive evaluation method of grasping quality is designed to obtain the optimal grasping solution offline data set. In the online stage, a safe and efficient selection strategy of the optimal grasping solution is proposed, which can quickly obtain the optimal grasping solution without collision.

The experiments verified that the method can be applied to different multifingered dexterous hands, and the average grasping success rate for objects with different structures is 91.7%, indicating a good grasping effect.

Using a forward kinematic model to generate initial grasping points can improve the generality of grasping planning methods and the quality of initial grasping solutions. The offline data set of optimized grasping solutions can be generated faster by the comprehensive evaluation method of grasping quality. Through the simple and fast obstacle avoidance strategy, the safe optimal grasping solution can be quickly obtained when performing a grasping task. The proposed method can be applied to automatic assembly scenarios where the end effector is a multifingered dexterous hand, which provides a technical solution for the promotion of multifingered dexterous hands in industrial scenarios.