Inconsistency of distributions in human actions and camera viewpoints can lead to significant deviations when the pre-trained 3D pose estimators are tested on cross-datasets. In practical applications, the estimators usually follow the standard full fine-tuning paradigm on the target dataset, which requires updating and saving a complete set of training parameters for different tasks, resulting in a large waste of resources and distorting pre-trained features. Taking inspiration from the widely used prompt learning in NLP, we explore the parameter-efficient fine-tuning solution of 3D pose estimators for the first time and propose the Adaptive Skeleton Prompt Tuning (ASP-Tuning) method, which freezes the backbone of the pre-trained model and generates a series of pose generic promptings as well as adaptive promptings specific to the input skeleton features to learn distribution transformation. Extensive experiments on multiple estimator backbones and datasets show that our method is superior to other fine-tuning methods and achieves state-of-the-art performance.

Although human pose estimation in video has achieved significant advancements, challenges such as occlusions often result in pronounced jitters and substantial errors. Addressing these challenges is critical for the further development of this field. In this study, we propose a multi-branch network designed for trajectory and pose refinement to mitigate these issues. The network comprises four branches, with three branches focus on capturing structural and motion features of human skeletal sequences, while one branch focuses on analyzing frequency features. More specifically, the first three branches model joint, bone vector, and motion data respectively to capture the structural and dynamic motion characteristics of human skeletal sequences. The frequency branch extracts frequency features to distinguish jitter from normal motion. Furthermore, the network incorporates a spatio-temporal residual block to capture both long-range temporal dependencies of individual joints and the spatial interrelationships among joints. Our method demonstrates competitive performance across three challenging datasets involving 2D, 3D, and SMPL pose representations.

Human motion prediction is crucial for applications ranging from robotics to human-computer interaction. This paper introduces a novel, multi-scale, spatiotemporal cross-attention-based algorithm for human motion prediction, which effectively models long-term dependencies in motion sequences. The proposed method leverages a dual-stream spatio-temporal Transformer framework that decouples temporal and spatial features, allowing each to independently capture dynamic temporal dependencies and spatial correlations. A key innovation is the introduction of a cross-attention mechanism, which ensures consistent information exchange between the temporal and spatial streams. Additionally, a multi-scale cross-attention mechanism is employed to capture relationships across different scales. Extensive experiments on benchmark datasets such as Human3.6M, CMU-MoCap, AMASS, and 3DPW demonstrate that the proposed model outperforms state-of-the-art methods in both short-term and long-term prediction accuracy. Metrics including MPJPE, MAE, PSEnt, and PSKLD validate the model's ability to generate accurate and smooth motion trajectories. Ablation studies further confirm the critical contributions of each component, highlighting the algorithm's robustness and efficiency. This research represents a significant advancement in human motion prediction, offering precise and reliable solutions for understanding and forecasting complex motion patterns.

Scene flow estimation using 4D millimeter-wave radar has emerged as a prominent research focus for 3D dynamic perception. However, compared to LiDAR point clouds, the drastic sparsity of radar point clouds poses challenges in enforcing local rigidity constraints, which are crucial for accurate 3D motion estimation. To address this issue, we propose a novel Gaussian-based pseudo-point generation method that fully leverages two distinct yet complementary data modalities, 3D coordinates and Doppler velocity, to support multi-body rigidity assumptions, effectively capturing fine-grained and structured motion patterns from highly sparse radar point clouds. Furthermore, a velocity calibration mechanism is designed to improve the reliability of fine-grained rigid motion velocity estimation. In addition, a progressive fusion strategy is introduced to systematically integrate fine-grained rigid motion priors at multiple levels, enhancing the robustness of matching costs and motion features while effectively compensating for coarse flows. Experimental results on real-world radar scans from the View-of-Delft (VoD) dataset demonstrate the promising performance of our FGRFlow compared to other leading 4D radar-based approaches, validating the advantages of our design choices.

This paper investigates the fixed-time control issue for the post-capture space tethered robot system in the presence of uncertainty and external disturbances. A new form of fixed-time nonsingular terminal sliding mode surface (FNTSMS) is constructed by introducing the power function to traditional terminal sliding mode surface (TSM), thus the system fast response and singularity circumvention are ensured gracefully. With the aid of FNTSMS, a new fixed-time control scheme is proposed for post-capture space tethered robot, which can achieve the high-precision tracking performance and fast response rate after the space targets are captured. Moreover, the proposed scheme is compared with the traditional boundary layer sliding mode control method. The simulation results verify the effectiveness of the proposed control scheme.

This paper describles an experiment of a binocular vision-based system for positioning the thruster nozzle on the satellite mockup. Images of the thruster are obtained using two cameras in order to determine the thruster's 3D position. At the beginning the thruster is selected manually, and then a local image region is extracted from the raw image. Subsequently, a Canny detector algorithm is used in the local image region to acquire the edge roadmap, and a Hough Transform algorithm is performed to detect the features with circles. Then, a curving fitting method is employed to determine the position of the center of the thruster nozzle., The end effector keeps tracking the target thruster to the distance of 0.1 meter and grasps the target by prodicting its trajectory. The experiment has shown that the system is robust to camera/target relative motions and performs approaching and grappling procedures on satellite mockup successfully.