Long‐stroke hydraulic manipulators are utilized in various grasping‐handling tasks, and the flexible deformation of these manipulators is the primary obstacle that affects precise position control of the end‐effectors in Cartesian space. This deformation is manifested in the following three aspects: joint deformation, structural deformation and clearance variation. Due to deformation uncertainty, methods that model the hydraulic manipulator as a combination of flexible multibody systems and hydraulic actuators are unsuitable. In this article, we propose an incremental inverse kinematics model (IIKM) as a new approach to solving the above deformation difficulties. The projection method is used to obtain the inverse kinematic analytical solution of long‐stroke hydraulic manipulators, which is based on the manipulator deformation in the current configuration (current configuration refers to the arrangement of the manipulator links when the manipulator starts to move to the target position). The proposed method avoids complex flexible multibody modeling and parameter identification, allowing long‐stroke hydraulic manipulators to be accurately controlled within a certain neighborhood. An evaluation coefficient is proposed to analyze the calculation accuracy of the IIKM in combination with the success rate obtained from 190 grasping experiments. Through these experiments, we determine the optimal calculation height range of the IIKM in the vertical direction and the optimal calculation position area in the horizontal direction and prove that the IIKM result can guarantee the success of grasping‐handling tasks when the end‐effector is within the optimal calculation height range.

Space robot teleoperation is an important technology in the space human-robot interaction and collaboration. Hand-based visual teleoperation can make the operation more natural and convenient. The fast and accuracy hand detection is one of the most difficult and important problem in the hand-based space robot teleoperation. In this work, we propose a fast and accurate hand detection method by using a spatial-channel attention single shot multibox detector (SCA-SSD). The SSD framework is used and improved in our method by introducing spatial-channel attentions with feature fusion. To increase the restricted receptive field in shallow layers, two shallow layers are fused with deep layers by using feature fusion modules. And spatial attention and channel-wise attention are also used to extract more efficient features. This method can not only ease the computational burden but also bring more contextual information. To evaluate the effectiveness of the proposed method, experiments on some public datasets and a custom astronaut hand detection dataset (AHD) are conducted. The results show that our method can improve the hand detection accuracy by 2.7% compared with the original SSD with only 15 fps speed drops. In addition, the space robot teleoperation experiment proves that our hand detection method can be well utilized in the space robot teleoperation system.

No abstract