Search

Purpose The grasping task of robots in dense cluttered scenes from a single-view has not been solved perfectly, and there is still a problem of low grasping success rate. This study aims to propose an end-to-end grasp generation method to solve this problem. Design/methodology/approach A new grasp representation method is proposed, which cleverly uses the normal vector of the table surface to derive the grasp baseline vectors, and maps the grasps to the pointed points (PP), so that there is no need to add orthogonal constraints between vectors when using a neural network to predict rotation matrixes of grasps. Findings Experimental results show that the proposed method is beneficial to the training of the neural network, and the model trained on synthetic data set can also have high grasping success rate and completion rate in real-world tasks. Originality/value The main contribution of this paper is that the authors propose a new grasp representation method, which maps the 6-DoF grasps to a PP and an angle related to the tabletop normal vector, thereby eliminating the need to add orthogonal constraints between vectors when directly predicting grasps using neural networks. The proposed method can generate hundreds of grasps covering the whole surface in about 0.3 s. The experimental results show that the proposed method has obvious superiority compared with other methods.

Purpose This paper aims to propose a method to solve the problem of localization and mapping of a two-wheeled inverted pendulum (TWIP) robot on the ground using the Stereo–inertial measurement unit (IMU) system. This method reparametrizes the pose according to the motion characteristics of TWIP and considers the impact of uneven ground on vision and IMU, which is more adaptable to the real environment. Design/methodology/approach When TWIP moves, it is constrained by the ground and swings back and forth to maintain balance. Therefore, the authors parameterize the robot pose as SE(2) pose plus pitch according to the motion characteristics of TWIP. However, the authors do not omit disturbances in other directions but perform error modeling, which is integrated into the visual constraints and IMU pre-integration constraints as an error term. Finally, the authors analyze the influence of the error term on the vision and IMU constraints during the optimization process. Compared to traditional algorithms, the algorithm is simpler and better adapt to the real environment. Findings The results of indoor and outdoor experiments show that, for the TWIP robot, the method has better positioning accuracy and robustness compared with the state-of-the-art. Originality/value The algorithm in this paper is proposed for the localization and mapping of a TWIP robot. Different from the traditional positioning method on SE(3), this paper parameterizes the robot pose as SE(2) pose plus pitch according to the motion of TWIP and the motion disturbances in other directions are integrated into visual constraints and IMU pre-integration constraints as error terms, which simplifies the optimization parameters, better adapts to the real environment and improves the accuracy of positioning.

Purpose This paper aims to present a pipeline to progressively deal with the online external parameter calibration and estimator initialization of the Stereo-inertial measurement unit (IMU) system, which does not require any prior information and is suitable for system initialization in a variety of environments. Design/methodology/approach Before calibration and initialization, a modified stereo tracking method is adopted to obtain a motion pose, which provides prerequisites for the next three steps. Firstly, the authors align the pose obtained with the IMU measurements and linearly calculate the rough external parameters and gravity vector to provide initial values for the next optimization. Secondly, the authors fix the pose obtained by the vision and restore the external and inertial parameters of the system by optimizing the pre-integration of the IMU. Thirdly, the result of the previous step is used to perform visual-inertial joint optimization to further refine the external and inertial parameters. Findings The results of public data set experiments and actual experiments show that this method has better accuracy and robustness compared with the state of-the-art. Originality/value This method improves the accuracy of external parameters calibration and initialization and prevents the system from falling into a local minimum. Different from the traditional method of solving inertial navigation parameters separately, in this paper, all inertial navigation parameters are solved at one time, and the results of the previous step are used as the seed for the next optimization, and gradually solve the external inertial navigation parameters from coarse to fine, which avoids falling into a local minimum, reduces the number of iterations during optimization and improves the efficiency of the system.

Purpose The purpose of this paper is to improve control performance and safety of a real two-wheeled inverted pendulum (TWIP) robot by dealing with model uncertainty and motion restriction simultaneously, which can be extended to other TWIP robotic systems. Design/methodology/approach The inequality of lumped model uncertainty boundary is derived from original TWIP dynamics. Several motion restriction conditions are derived considering zero dynamics, centripedal force, ground friction condition, posture stability, control torque limitation and so on. Sliding-mode control (SMC) and model predictive control (MPC) are separately adopted to design controllers for longitudinal and rotational motion, while taking model uncertainty into account. The reference value of the moving velocity and acceleration, delivered to the designed controller, should be restricted in a specified range, limited by motion restrictions, to keep safe. Findings The cancelation of model uncertainty commonly existing in real system can improve control performance. The motion commands play an important role in maintaining safety and reliability of TWIP, which can be ensured by the proposed motion restriction to avoid potential movement failure, such as slipping, lateral tipping over because of turning and large fluctuation of body. Originality/value An inequation of lumped model uncertainty boundary incorporating comprehensive errors and uncertainties of system is derived and elaborately calculated to determine the switching coefficients of SMC. The motion restrictions for TWIP robot moving in 3D are derived and used to impose constraints on reference trajectory to avoid possible instability or failure of movement.

Purpose One of the development trends of robots is to enable robots to have the ability of anthropomorphic manipulation. Grasping is the first step of manipulation. For mobile manipulator robots, grasping a target during the movement process is extremely challenging, which requires the robots to make rapid motion planning for arms under uncertain dynamic disturbances. However, there are many situations require robots to grasp a target quickly while they move, such as emergency rescue. The purpose of this paper is to propose a method for target dynamic grasping during the movement of a robot. Design/methodology/approach An off-line learning from demonstrations method is applied to learn a basic reach model for arm and a motion model for fingers. An on-line dynamic adjustment method of arm speed for active and passive grasping mode is designed. Findings The experimental results of the robot movement on flat, slope and speed bumps ground show that the proposed method can effectively solve the problem of fast planning under uncertain disturbances caused by robot movement. The method performs well in the task of target dynamic grasping during the robot movement. Originality/value The main contribution of this paper is to propose a method to solve the problem of rapid motion planning of the robot arm under uncertain disturbances while the robot is grasping a target in the process of robot movement. The proposed method significantly improves the grasping efficiency of the robot in emergency situations. Experimental results show that the proposed method can effectively solve the problem.