Space robots play a significant role in on‐orbit servicing (OOS) missions, such as inspecting, capturing, refueling, and repairing satellites, assembling and maintaining large space infrastructure, and removing orbital debris. Over the past four decades, many space robot engineering applications and technology verifications for OOS have been accomplished. This article comprehensively reviews the advances by representative space robotic programs on space shuttles, outside/inside the International Space Station and the China Space Station, as well as on satellites, and the development trends of space robots are summarized. In addition, the primary key technologies and challenges are explored, including the following: 1) visual perception for noncooperative targets; 2) motion planning and control with a free‐floating base and flexibility; 3) multifunctional end‐effectors; 4) ground teleoperation with long time delays; and 5) high‐fidelity ground verification. Finally, the prospects for space robot future research are presented.

Edge detection is one of the most fundamental operations in the field of image analysis and computer vision as a critical preprocessing step for high-level tasks. It is difficult to give a generic threshold that works well on all images as the image contents are totally different. This paper presents an adaptive, robust and effective edge detector for real-time applications. According to the 2D entropy, the images can be clarified into three groups, each attached with a reference percentage value based on the edge proportion statistics. Compared with the attached points along the gradient direction, anchor points were extracted with high probability to be edge pixels. Taking the segment direction into account, these points were then jointed into different edge segments, each of which was a clean, contiguous, 1-pixel wide chain of pixels. Experimental results indicate that the proposed edge detector outperforms the traditional edge following methods in terms of detection accuracy. Besides, the detection results can be used as the input information for post-processing applications in real-time.

We propose NEDS-SLAM, a dense semantic SLAM system based on 3D Gaussian representation, that enables robust 3D semantic mapping, accurate camera tracking, and high-quality rendering in real-time. In the system, we propose a Spatially Consistent Feature Fusion model to reduce the effect of erroneous estimates from pre-trained segmentation head on semantic reconstruction, achieving robust 3D semantic Gaussian mapping. Additionally, we employ a lightweight encoder-decoder to compress the high-dimensional semantic features into a compact 3D Gaussian representation, mitigating the burden of excessive memory consumption. Furthermore, we leverage the advantage of 3D Gaussian splatting, which enables efficient and differentiable novel view rendering, and propose a Virtual Camera View Pruning method to eliminate outlier gaussians, thereby effectively enhancing the quality of scene representations. Our NEDS-SLAM method demonstrates competitive performance over existing dense semantic SLAM methods in terms of mapping and tracking accuracy on Replica and ScanNet datasets, while also showing excellent capabilities in 3D dense semantic mapping.

From the optimization perspective, this article proposes a novel actual shape-based obstacle avoidance synthesized by velocity–acceleration minimization (ASOA-VAM) scheme that performs operational tasks safely in a complex environment utilizing redundant manipulators. Concretely, an actual shape-based obstacle avoidance (ASOA) strategy with a variable magnitude escape acceleration using the Gilbert–Johnson–Keerthi distance algorithm is presented. Trajectory tracking, the end-effector’s errors feedback, and the joint multilevel physical limits (joint angle, -velocity, and -acceleration limits) avoidance are also incorporated into this optimization scheme. Meanwhile, the velocity–acceleration minimization (VAM) measure is developed. Combining the ASOA strategy with the VAM measure, the ASOA-VAM scheme is formed and further reformulated as a quadratic program (QP). Moreover, a recurrent neural network with theoretically provable convergence is designed to solve the QP online. Finally, simulations, comparisons, and experiments of a 7-degree-of-freedom manipulator with engineering applications illustrate the ASOA-VAM scheme’s effectiveness, accuracy, superiority, and physical realizability.

This research presents the design, modeling, and control for a bio-inspired robotic hand with antagonistic variable stiffness (AVS). A key design character is the integrated modular finger unit. The modular finger unit is developed based on the variable stiffness actuation principle and has physical impact absorption and stiffness adjustment capabilities to achieve safer grasping and manipulation in interactions and adjustable system bandwidth. Compared with the design of the previous version, the finger unit is optimized in terms of mechanism, cable path, transmission gap, and manufacturing process, and specially designed torque sensors are added to achieve the force perception of the fingertip in three dimensions. A modularized finger unit integrating mechanical parts, sensors, and electronic devices with more compact size, higher precision, and low friction is developed, which eventually lead to the implementation of the fully actuated AVS hand with three fingers and eight degrees of freedom (DOF). The hand controller hardware developed based on a field programmable gate array (FPGA) chip is integrated in the palm. These have guaranteed the real-time and stable grasping and manipulation performance of the hand.