This paper introduces a novel high-certainty visual servo algorithm for a space manipulator with flexible joints, which consists of a kinematic motion planner and a Lyapunov dynamics model reference adaptive controller. To enhance kinematic certainty, a three-stage motion planner is proposed in Cartesian space to control the intermediate states and minimize the relative position error between the manipulator and the target. Moreover, a planner in joint space based on the fast gradient descent algorithm is proposed to optimize the joint’s deviation from the centrality. To improve dynamic certainty, an adaptive control algorithm based on Lyapunov stability analysis is used to enhance the system’s anti-disturbance capability. As to the basic PBVS (position-based visual servo methods) algorithm, the proposed method aims to increase the certainty of the intermediate states to avoid collision. A physical experiment is designed to validate the effectiveness of the algorithm. The experiment shows that the visual servo motion state in Cartesian space is basically consistent with the planned three-stage motion state, the average joint deviation index from the centrality is less than 40%, and the motion trajectory consistency exceeds 90% under different inertial load disturbances. Overall, this method reduces the risk of collision by enhancing the certainty of the basic PBVS algorithm.

Object detection in remote sensing images is an important research topic in the field of remote sensing intelligent interpretation. Although modern object detectors have made good progress, high-precision oriented object detection still faces severe challenges due to the large-scale variation, strong directional diversity and complex background interference of objects in remote sensing images. Currently, most remote sensing object detectors focus on modeling object characteristics in the spatial domain while ignoring the frequency domain information of the object. Recent studies have shown that frequency domain learning has brought substantial benefits in many visual fields. To this end, we proposed an adaptive dual-domain dynamic interaction network (AD³I-Net) for oriented object detection tasks in remote sensing images. The network has three important components: a spatial adaptive selection (SAS) module, a frequency adaptive selection (FAS) module, and a dual-domain feature interaction (DDFI) module. The SAS module adaptively models spatial context information and dynamically adjusts the feature receptive field to construct more accurate spatial position features for objects of different scales. The FAS module uses the transformation from the spatial domain to the frequency domain to adaptively learn the frequency information of the object, to model direction features, and to make up for the lack of spatial domain information. Finally, through the DDFI module, the features extracted from the two domains are interactively fused, thereby bridging the complementary information to enhance the feature expression of the object and give it rich spatial position and direction information. The AD³I-Net we proposed fully exploits the interaction between the different domains and improves the model’s ability to capture subtle object features. Our method has been extensively experimentally verified on two mainstream datasets, HRSC2016 and DIOR-R. The experimental results demonstrate that this method performs competitively in oriented object detection tasks.

In-orbit docking technology of microsatellites to realize combined reconfiguration has a wide application prospect, such as large antennas and space telescopes. In order to reduce collision impact and improve docking accuracy, a new deployable docking mechanism is proposed based on the slider-crank principle, which has the advantages of smaller volume and larger posture tolerance. To achieve large capture tolerance and increase the success rate of docking, the posture error is analyzed by considering the specific boundary of the position and pose. And a step-by-step cooperative capture strategy is proposed to complete the velocity selection and action matching among multiple capture arms. The reliable docking of posture correction in the docking process is realized by designing the action path of the docking mechanism. The effects of tolerance capture under different initial posture conditions are analyzed by dynamic simulation. The effectiveness and superiority of the step-by-step cooperative capture strategy are valid by comparison with the synchronized capture strategy. The comparison results show that the impact force is reduced by 8% than the synchronized strategy. The capture experiments are carried out to verify the docking performance. The results show the proposed configuration with a step-by-step cooperative capture strategy achieves successfully reliable capture, weak impact, and large posture tolerance under eight extreme initial pose conditions.

This paper presents a novel control strategy for transferring large inertia loads using flexible space manipulators in orbit. The proposed strategy employs a Luenberger state observer and damping-stiffness controller to address issues of large tracking error and vibration. A comprehensive joint dynamics model is developed to identify the main sources of disturbance, and a Luenberger state observer is designed to estimate unmeasurable transmission deformation. Transmission stiffness and load inertia perturbations are identified based on the estimated results. By adjusting velocity damping and the gain of the forward channel, perturbations are suppressed to maintain optimal system damping and stiffness. Simulation and physical experiments demonstrate the effectiveness of the algorithm, with simulation experiments showing smoother joint output characteristics and minimal vibration under large load inertia changes, and a 97% reduction in internal deformation. Physical experiments demonstrate improved joint dynamic command tracking performance, with an 88% reduction in position tracking error. The algorithm provides a practical and efficient approach for transferring large inertia scientific payloads in space.

The addition of telescopic joints will enhance the manipulator’s motion dexterity but increase the motion complexity, thereby potentially reducing the efficiency of motion planning. To address the issue, a manipulability priority principle is used to reduce the computational dimension, aiming to enhance computational efficiency. Firstly, an improved Monte Carlo algorithm combined with Weighted Ensemble Learning is proposed to rapidly obtain a well-distributed and information-complete reachable workspace under small-sample conditions. Then, all dexterous points are computed by the manipulability formula and the least squares algorithm is applied to obtain the boundary of the reachable workspace. Based on the boundary, a spatial quadratic surface-based segmentation algorithm is proposed to obtain the dexterous workspace corresponding to all dexterous points. Subsequently, the Telescopic Motion Computation (TMC) method is designed to transform the kinematics problem of a 9-DOF manipulator into a 7-DOF problem by precomputing the telescopic joint lengths, effectively reducing the computational time for inverse kinematics. Finally, simulations are performed to verify the effectiveness, dexterity, and efficiency of the TMC method. The results indicate that applying the TMC method to PInv, DLS, and PSO algorithms enhances the efficiency by 3.43, 3.53, and 3.64 times while maintaining the motion dexterity.

Monocular depth estimation is critical for endoscopists to perform spatial perception and 3D navigation of surgical sites. However, most of the existing methods ignore the important geometric structural consistency, which inevitably leads to performance degradation and distortion of 3D reconstruction. To address this issue, we introduce a gradient loss to penalize edge fluctuations ambiguous around stepped edge structures and a normal loss to explicitly express the sensitivity to frequently small structures, and propose a geometric consistency loss to spreads the spatial information across the sample grids to constrain the global geometric anatomy structures. In addition, we develop a synthetic RGB-Depth dataset that captures the anatomical structures under reflections and illumination variations. The proposed method is extensively validated across different datasets and clinical images and achieves mean RMSE values of 0.066 (stomach), 0.029 (small intestine), and 0.139 (colon) on the EndoSLAM dataset. The generalizability of the proposed method achieves mean RMSE values of 12.604 (T1-L1), 9.930 (T2-L2), and 13.893 (T3-L3) on the ColonDepth dataset. The experimental results show that our method exceeds previous state-of-the-art competitors and generates more consistent depth maps and reasonable anatomical structures. The quality of intraoperative 3D structure perception from endoscopic videos of the proposed method meets the accuracy requirements of video-CT registration algorithms for endoscopic navigation. The dataset and the source code will be available at https://github.com/YYM-SIA/LINGMI-MR.