Search results

The purpose of this paper is the research of a novel gesture-based dual-robot collaborative interaction interface, which achieves the gesture recognition when both hands overlap. This paper designs a hybrid-sensor gesture recognition platform to detect the both-hand data for dual-robot control.

This paper uses a combination of Leap Motion and PrimeSense in the vertical direction, which detects both-hand data in real time. When there is occlusion between hands, each hand is detected by one of the sensors, and a quaternion-based algorithm is used to realize the conversion of two sensors corresponding to different coordinate systems. When there is no occlusion, the data are fused by a self-adaptive weight fusion algorithm. Then the collision detection algorithm is used to detect the collision between robots to ensure safety. Finally, the data are transmitted to the dual robots.

This interface is implemented on a dual-robot system consisting of two 6-DOF robots. The dual-robot cooperative experiment indicates that the proposed interface is feasible and effective, and it takes less time to operate and has higher interaction efficiency.

A novel gesture-based dual-robot collaborative interface is proposed. It overcomes the problem of gesture occlusion in two-hand interaction with low computational complexity and low equipment cost. The proposed interface can perform a long-term stable tracking of the two-hand gestures even if there is occlusion between the hands. Meanwhile, it reduces the number of hand reset to reduce the operation time. The proposed interface achieves a natural and safe interaction between the human and the dual robot.

The purpose of this paper is to provide a novel training-responding controlling approach for human–robot interaction. The approach is inspired by the processes of muscle memory and conditioned reflex. The approach is significant for dealing with the problems of robot’s redundant movements and operator’s fatigue in human–robot interaction system.

This paper presented a directional double clustering algorithm (DDCA) to achieve the training process. The DDCA ensured that the initial clustering centers uniformly distributed in every desired cluster. A minimal resource allocation network was used to construct a memory responding algorithm (MRA). When the human–robot interaction system needed to carry out a task for more than one time, the desired movements of the robot were given by the MRA without repeated training. Experimentally demonstrated results showed the proposed training-responding controlling approach could successfully accomplish human–robot interaction tasks.

The training-responding controlling approach improved the robustness and reliability of the human–robot interaction system, which presented a novel controlling method for the operator.

This approach has significant commercial applications, as a means of controlling for human–robot interaction could serve to point to the desired target and arrive at the appointed positions in industrial and household environment.

This work presented a novel training-responding human-robot controlling method. The human-robot controlling method dealt with the problems of robot’s redundant movements and operator’s fatigue. To the authors’ knowledge, the working processes of muscle memory and conditioned reflex have not been reported to apply to human-robot controlling.

The aim of this paper is to propose a grasping method based on intelligent perception for implementing a grasp task with human conduct.

First, the authors leverage Kinect to collect the environment information including both image and voice. The target object is located and segmented by gesture recognition and speech analysis and finally grasped through path teaching. To obtain the posture of the human gesture accurately, the authors use the Kalman filtering (KF) algorithm to calibrate the posture use the Gaussian mixture model (GMM) for human motion modeling, and then use Gaussian mixed regression (GMR) to predict human motion posture.

In the point-cloud information, many of which are useless, the authors combined human’s gesture to remove irrelevant objects in the environment as much as possible, which can help to reduce the computation while dividing and recognizing objects; at the same time to reduce the computation, the authors used the sampling algorithm based on the voxel grid.

The authors used the down-sampling algorithm, kd-tree algorithm and viewpoint feature histogram algorithm to remove the impact of unrelated objects and to get a better grasp of the state.

The purpose of this paper is to provide a novel methodology based on two-level protection for ensuring safety of the moving human who enters the robot’s workspace, which is significant for dealing with the problem of human security in a human-robot coexisting environment.

In this system, anyone who enters the robot’s working space is detected by using the Kinect and their skeletons are calculated by the interval Kalman filter in real time. The first-level protection is mainly based on the prediction of the human motion, which used Gaussian mixture model and Gaussian Mixture Regression. However, even in cases where the prediction of human motion is incorrect, the system can still safeguard the human by enlarging the initial bounding volume of the human as the second-level early warning areas. Finally, an artificial potential field with some additional avoidance strategies is used to plan a path for a robot manipulator.

Experimental studies on the GOOGOL GRB3016 robot show that the robot manipulator can accomplish the predetermined tasks by circumventing the human, and the human does not feel dangerous.

This study presented a new framework for ensuring human security in a human-robot coexisting environment, and thus can improve the reliability of human-robot cooperation.

The purpose of this paper is to present a markerless human–manipulators interface which maps the position and orientation of human end-effector (EE, the center of the palm) to those of robot EE so that the robot could copy the movement of the operator hand.

The tracking system of this human–manipulators interface comprises five Leap Motions (LMs) which not only makes up the narrow workspace drawback of one LM but also provides redundancies to improve the data precision. However, because of the native noises and tracking errors of the LMs, the measurement errors increase over time. To address this problem, two filter tools are integrated to obtain the relatively accurate estimation of the human EE, that is, Particle Filter for position estimation and Kalman Filter for orientation estimation. Because the operator has inherent perceptive limitations, the motions of the manipulator may be out of sync with the hand motions, so that it is hard to complete with the high performance manipulation. Therefore, in this paper, an over-damping method is adopted to improve reliability and accuracy.

A series of human–manipulators interaction experiments were carried out to verify the proposed system. Compared with the markerless and contactless methods(Kofman et al., 2007; Du and Zhang, 2015), the method described in this study is more accurate and efficient.

The proposed method would not hinder most natural human limb motion and allows the operator to concentrate on his/her own task, making it perform high-precision manipulations efficiently.

This paper aims to develop a wearable-based human-manipulator interface which integrates the interval Kalman filter (IKF), unscented Kalman filter (UKF), over damping method (ODM) and adaptive multispace transformation (AMT) to perform immersive human-manipulator interaction by interacting the natural and continuous motion of the human operator’s hand with the robot manipulator.

The interface requires that a wearable watch is tightly worn on the operator’s hand to track the continuous movements of the operator’s hand. Nevertheless, the measurement errors generated by the sensor error and tracking failure signicantly occur several times, which means that the measurement is not determined with sufficient accuracy. Due to this fact, IKF and UKF are used to compensate for the noisy and incomplete measurements, and ODM is established to eliminate the influence of the error signals like data jitter. Furthermore, to be subject to the inherent perceptive limitations of the human operator and the motor, AMT that focuses on a secondary treatment is also introduced.

Experimental studies on the GOOGOL GRB3016 robot show that such a wearable-based interface that incorporates the feedback mechanism and hybrid filters can operate the robot manipulator more flexibly and advantageously even if the operator is nonprofessional; the feedback mechanism introduced here can successfully assist in improving the performance of the interface.

The interface uses one wearable watch to simultaneously track the orientation and position of the operator’s hand; it is not only avoids problems of occlusion, identification and limited operating space, but also realizes a kind of two-way human-manipulator interaction, a feedback mechanism can be triggered in the watch to reflect the system states in real time. Furthermore, the interface gets rid of the synchronization question in posture estimation, as hybrid filters work independently to compensate the noisy measurements respectively.

The aim of this paper is to present a novel methodology which incorporates Camshift, Kalman filter (KFs) and adaptive multi-space transformation (AMT) for a human-robot interface, which perfects human intelligence and teleoperation.

In the proposed method, an inertial measurement unit is used to measure the orientation of the human hand, and a Camshift algorithm is used to track the human hand using a three-dimensional camera. Although the location and the orientation of the human can be obtained from the two sensors, the measurement error increases over time due to the noise of the devices and the tracking errors. KFs are used to estimate the location and the orientation of the human hand. Moreover, to be subject to the perceptive limitations and the motor limitations, human operator is hard to carry out the high precision operation. An AMT method is proposed to assist the operator to improve accuracy and reliability in determining the pose of the robot.

The experimental results show that this method would not hinder most natural human-limb motion and allows the operator to concentrate on his/her own task. Compared with the non-contacting marker-less method (Kofman et al., 2007), this method proves more accurate and stable.

The human-robot interface system was experimentally verified in a laboratory environment, and the results indicate that such a system can complete high-precision manipulation efficiently.

The purpose of this paper is to provide a hybrid adaptive impedance-leader-follower control algorithm for multi-arm coordination manipulators, which is significant for dealing with the problems of kinematics inconsistency and error accumulation of interactive force in multi-arm system.

This paper utilized a motion mapping theory in Cartesian space to establish a centralized dynamic leader-follower control algorithm which helped to reduce the possibility of kinematics inconsistency for multiple manipulators. A virtual linear spring model (VLSM) was presented based on a recognition approach of characteristic marker. This paper accomplished an adaptive impedance control algorithm based on the VLSM, which took into account the non-rigid contact characteristic. Experimentally demonstrated results showed the proposed algorithm guarantees that the motion and interactive forces asymptotically converge to the prescribed values.

The hybrid control method improves the accuracy and reliability of multi-arm coordination system, which presents a new control framework for multiple manipulators.

This algorithm has significant commercial applications, as a means of controlling multi-arm coordination manipulators that could serve to handle large objects and assemble complicated objects in industrial and hazardous environment.

This work presented a new control framework for multiple coordination manipulators, which can ensure consistent kinematics and reduce the influence of error accumulation, and thus can improve the accuracy and reliability of multi-arm coordination system.