Search results

The purpose of this paper is to present a novel tactile sensor and a visual-tactile recognition framework to reduce the uncertainty of the visual recognition of transparent objects.

A multitask learning model is used to recognize intuitive appearance attributes except texture in the visual mode. Tactile mode adopts a novel vision-based tactile sensor via the level-regional feature extraction network (LRFE-Net) recognition framework to acquire high-resolution texture information and temperature information. Finally, the attribute results of the two modes are integrated based on integration rules.

The recognition accuracy of attributes, such as style, handle, transparency and temperature, is near 100%, and the texture recognition accuracy is 98.75%. The experimental results demonstrate that the proposed framework with a vision-based tactile sensor can improve attribute recognition.

Transparency and visual differences make the texture of transparent glass hard to recognize. Vision-based tactile sensors can improve the texture recognition effect and acquire additional attributes. Integrating visual and tactile information is beneficial to acquiring complete attribute features.

The purpose of the paper is to present a novel cross-modal sensor whose tactile is computed by the visual information. The proposed sensor can measure the forces of robotic grasping.

The proposed cross-modal tactile sensor consists of a transparent elastomer with markers, a camera, an LED circuit board and supporting structures. The model and performance of the elastomer are analyzed. Then marker recognition method is proposed to determine the movements of the marker on the surface, and the force calculation algorithm is presented to compute the three-dimension force.

Experimental results demonstrate that the proposed tactile sensor can accurately measure robotic grasping forces.

The proposed cross-modal tactile sensor determines the robotic grasping forces by the images of markers. It can give more information of the force than traditional tactile sensors. Meanwhile, the proposed algorithms for forces calculation determine the superior results.

The purpose of this paper is to present a novel data glove which can capture the motion of the arm and hand by inertial and magnetic sensors. The proposed data glove is used to provide the information of the gestures and teleoperate the robotic arm-hand.

The data glove comprises 18 low-cost inertial and magnetic measurement units (IMMUs) which not only make up the drawbacks of traditional data glove that only captures the incomplete gesture information but also provide a novel scheme of the robotic arm-hand teleoperation. The IMMUs are compact and small enough to wear on the upper arm, forearm, palm and fingers. The calibration method is proposed to improve the accuracy of measurements of units, and the orientations of each IMMU are estimated by a two-step optimal filter. The kinematic models of the arm, hand and fingers are integrated into the entire system to capture the motion gesture. A positon algorithm is also deduced to compute the positions of fingertips. With the proposed data glove, the robotic arm-hand can be teleoperated by the human arm, palm and fingers, thus establishing a novel robotic arm-hand teleoperation scheme.

Experimental results show that the proposed data glove can accurately and fully capture the fine gesture. Using the proposed data glove as the multiple input device has also proved to be a suitable teleoperating robotic arm-hand system.

Integrated with 18 low-cost and miniature IMMUs, the proposed data glove can give more information of the gesture than existing devices. Meanwhile, the proposed algorithms for motion capture determine the superior results. Furthermore, the accurately captured gestures can efficiently facilitate a novel teleoperation scheme to teleoperate the robotic arm-hand.

This paper aims to propose a novel active SLAM framework to realize avoid obstacles and finish the autonomous navigation in indoor environment.

The improved fuzzy optimized Q-Learning (FOQL) algorithm is used to solve the avoidance obstacles problem of the robot in the environment. To reduce the motion deviation of the robot, fractional controller is designed. The localization of the robot is based on FastSLAM algorithm.

Simulation results of avoiding obstacles using traditional Q-learning algorithm, optimized Q-learning algorithm and FOQL algorithm are compared. The simulation results show that the improved FOQL algorithm has a faster learning speed than other two algorithms. To verify the simulation result, the FOQL algorithm is implemented on a NAO robot and the experimental results demonstrate that the improved fuzzy optimized Q-Learning obstacle avoidance algorithm is feasible and effective.

The improved fuzzy optimized Q-Learning (FOQL) algorithm is used to solve the avoidance obstacles problem of the robot in the environment. To reduce the motion deviation of the robot, fractional controller is designed. To verify the simulation result, the FOQL algorithm is implemented on a NAO robot and the experimental results demonstrate that the improved fuzzy optimized Q-Learning obstacle avoidance algorithm is feasible and effective.

The (n‐1) attack is the most powerful attack against mix which is the basic building block of many modern anonymous systems. This paper aims to present a strategy that can be implemented in mix networks to detect and counter the active attacks, especially the (n‐1) attack and its variants.

Based on the analysis of the preconditions of a successful (n‐1) attack and the limitations of previous countermeasures, this paper presents Regroup‐And‐Go mix (RG mix) for detecting and foiling the (n‐1) attack. Messages are divided into groups by the sender, regrouped and forwarded at the intermediate mixes, and reordered and sent to the receiver at the last mix. The grouping information for each mix is encrypted with the public key of the corresponding mix. The messages are forwarded only when all the messages in the same group have arrived. When the regrouping of messages triggers a timeout alert, the mix detects the ongoing attack and takes countermeasures.

RG mix can help foil and detect the (n‐1) attacks from both internal and external attackers because the grouping information for the other mixes is unavailable for them. They can only guess which messages can constitute a group and randomly select some messages to have a try. Analysis and experiments show that the probability of successful attack is low.

RG mix uses the hidden correlations between messages for active attack prevention and detection. RG mix does not have unpractical requirements and can be used in the real‐world implementations.

This paper aims to propose a soft actuator that combines a sponge-based actuating structure and a layer-jamming-based stiffness-improving structure in a cavity.

The proposed soft actuator consists of film-constrained sponge units (FCSUs) and jamming layers. The FCSUs in the proposed soft actuator bend under vacuum pressure, causing bending deformation of the entire actuator. The jamming layers are strongly coupled through friction under vacuum pressure, increasing the stiffness of the entire actuator. The performance of the proposed soft actuator was examined by measuring its stiffness, bending deformation and response performance. A four-finger soft robotic gripper was proposed based on the proposed soft actuator.

Through experiments, it was shown that the proposed soft actuator exhibited acceptable bending deformation, stiffness and response. Moreover, the proposed four-finger soft gripper could effectively grasp objects in daily life.

In this study, the authors proposed a novel bending actuator (with a volume of approximately 43.2 cm³) based on FCSUs and jamming layers. To the best of the authors’ knowledge, this is the first study to combine a sponge-based actuating structure and a layer-jamming structure in a cavity to achieve simultaneous change in actuation and stiffness. The soft actuator exhibited good bending deformation and high stiffness simultaneously under vacuum pressure. Consequently, it could be used effectively to fabricate soft grippers.

This study aims to introduce the DoraHand, and the basic capability and performance have been verified in this paper. Besides the idea of sharing modular design and sensor design, the authors want to deliver an affordable and practical dexterous hand to the research area to contribute to the robotic manipulation area.

This paper introduced the DoraHand, a novel scalable and practical modular dexterous hand, which, adopting modular finger and palm design, fully actuated joint and tactile sensors, can improve the dexterity for robotic manipulation and lower the complexity of maintenance. A series of experiments are delivered to verify the performance of the hand and sensor module.

The parameters of the DoraHand are verified and suitable for the research of robotics manipulation area, the sensing capability has been tested with the static experiment and the slip prediction algorithm. And, the advantage of modular design and extensible interface have been verified by the real application.

The authors continue improving the DoraHand and extend it to more different applications. The authors want to make the DoraHand as a basic research platform in the robotic manipulation area.

The DoraHand has been sent to more than ten different research institutes for different research applications. The authors continue working on this hand for better performance, easier usage and more affordability.

This kind of dexterous hand can help researchers get rid of complex physical issues and pay more attention to the algorithm part; it can help to make robotic manipulation work more popular.

The key design in the DoraHand is the modular finger and sensing module. With the special design in mechanical and electrical parts, the authors build reliable hardware and can support the diversity requirement in the robotic manipulation area. The hand with tactile sensing capability can be used in more research and applications with its extensibility.

The purpose of this paper is to investigate the dynamic forming process of the micro dent fabricated by laser shock processing on 2024-T3 aluminum alloy. The effect of laser pluse energy on the deformation of micro dent was also discussed in detail.

It uses finite element analysis method and the corresponding laser shocking experiment.

The results demonstrate that the dynamic formation process of micro dent lasts longer in comparison with the shock wave loading time, and the depths of micro dents increase with the increasing laser energy. In addition, laser shocking with higher energy can result in more obvious pileup occurred at the outer edge of micro dent.

Surface micro dents can serve as fluid reservoirs and traps of the wear debris, which can decrease the effects of the wear and friction in rolling and sliding interfaces. The investigations can not only be propitious to comprehensively understand the forming mechanism of laser-shocked dent, but also be beneficial to get sight into the residual stress field induced by laser shocking.