Explore the vast range of titles available.

Multi-agent perceptual map construction and long-term maintenance constitute an important paradigm for improving adaptability and real-world applicability. With the outstanding capability of 3D Gaussian Splatting in preserving fine-grained texture details, a number of 3DGS-based real-time mapping approaches have recently emerged. However, these methods often struggle to cope with complex dynamics in real-world environments and lack the generalization needed to scale to multi-agent systems. Existing solutions typically rely on direct parameter concatenation or locally confined optimization, which are unable to explicitly model cross-agent observation reliability under temporal asynchrony and dynamic inconsistency, and therefore tend to amplify conflicting updates rather than resolve them. To address these limitations, we propose DGOMapping, an online system for multi-agent dynamic perceptual mapping. DGOMapping leverages an uncertainty-coupled 4DGS scene representation and a collaborative interaction mechanism via Gaussian perception-score exchange, enabling both real-time 4DGS construction and long-term map memory adjustment. Experiments on multiple real-world datasets demonstrate that DGOMapping effectively suppresses dynamic interference and exploits multi-agent collaboration, achieving state-of-the-art performance in both tracking and reconstruction. The proposed system therefore provides a practical sensing-oriented solution for collaborative perception and real-time dynamic environment mapping.

Non-cooperative target capturing is a great challenge for space robots among space tasks, because of the difficulty of target detumbling and base stability maintaining, which increasing the requirements for the control performances of the attitude control systems. In this paper, a contact force model combining an optimized Hertz’s model and the LuGre friction model is established, to estimate the contact force without additional sensors. And a novel control methodology for stabilization control of space robot based on an adaptive backstepping nonsingular fast integral terminal sliding mode control (ABNFITSMC) is developed, which significantly improve the convergence speed and satisfied the requirements of robustness of the complex system after capturing. First, the fully controllable dynamic model of the free-flying (no position control) space robot is established by using the Lagrange method. Then, the contact force between the end effector (gripper) and the target is analyzed by combining modified Hertz model and the LuGre friction model. Finally, a novel nonsingular fast integral terminal sliding mode (NFITSM) surface is proposed, so a finite-time convergence, non-singularity, fast transient response, precise trajectory tracking, robustness with uncertainties and disturbances is achieved. Then, an adaptive control law is used to approximate the upper bound value of the disturbance and uncertainties, and a backstepping control method is employed to guaranty the global asymptotic stability of the control system. The numerical simulation results show that the proposed algorithm can stable the attitude of the space robot in a quick limited time, and reduce the chattering significantly compared to the traditional sliding surface, the results demonstrates the superior performance of the proposed approach., and proves the feasibility of its application in non-cooperative target capturing task.

Electric field reconstruction at interfaces plays a crucial role in device performances controlling, for example, Schottky potential barrier and interfacial Rashba effect. Here, scanning transmission electron microscopy (STEM) and ab‐initio calculation are used to estimate the atomic‐scale and large‐scale potential reconstruction at the interface between a metallic oxide SrRuO3 (SRO) thin film and an insulating DyScO3 (DSO) substrate. The intensity and the symmetry of the large‐scale electrostatic reconstruction at the interface is probed by 4D‐STEM discussing the center‐of‐mass shift for different angular ranges detection. Numerical simulations indicate that thermal diffuse scattered (TDS) electrons can be sensitive to large‐scale electric field and experiments based on these diffused electrons near the interface confirm that the electric field extends more in the insulating DyScO3 (DSO) side. The magnitude of the electrostatic drop at the interface estimated by the 4D‐STEM experiment is in accordance with the ab‐initio values for a p‐type reconstruction of the interface plane. Furthermore, an atomically resolved TDS potential asymmetry is observed in real‐space at the SRO/DSO interface by 4D‐STEM. This asymmetry is associated with the formation of a local ferroelectric type dipole at the interfacial unit‐cell revealing unambiguously the balance evolution between antiferrodistortive and ferroelectric instabilities at the interface between a metallic SRO and an insulating DSO. Scanning transmission electron microscopy (STEM) and ab‐initio calculations estimate the atomic‐scale and large‐scale potential reconstruction at the interface between a metallic oxide SrRuO3 (SRO) thin film and an insulating DyScO3 (DSO) substrate. The 4D‐STEM experiments and calculations take into account the thermal diffuse scattered electrons in order to estimate the large‐scale electrostatic potential discontinuity at the SRO/DSO interface.

Redundant manipulators are widely used in fields such as human-robot collaboration due to their good flexibility. To ensure efficiency and safety, the manipulator is required to avoid obstacles while tracking a desired trajectory in many tasks. Conventional methods for obstacle avoidance of redundant manipulators may encounter joint singularity or exceed joint position limits while tracking the desired trajectory. By integrating deep reinforcement learning into the gradient projection method, a reactive obstacle avoidance method for redundant manipulators is proposed. We establish a general DRL framework for obstacle avoidance, and then a reinforcement learning agent is applied to learn motion in the null space of the redundant manipulator Jacobian matrix. The reward function of reinforcement learning is redesigned to handle multiple constraints automatically. Specifically, the manipulability index is introduced into the reward function, and thus the manipulator can maintain high manipulability to avoid joint singularity while executing tasks. To show the effectiveness of the proposed method, the simulation of 4 degrees of planar manipulator freedom is given. Compared with the gradient projection method, the proposed method outperforms in a success rate of obstacles avoidance, average manipulability, and time efficiency.

Emotion recognition based on facial expression is a challenging research topic and has attracted a great deal of attention in the past few years. This paper presents a novel method, utilizing multi-modal strategy to extract emotion features from facial expression images. The basic idea is to combine the low-level empirical feature and the high-level self-learning feature into a multi-modal feature. The 2-dimensional coordinate of facial key points are extracted as low-level empirical feature and the high-level self-learning feature are extracted by the Convolutional Neural Networks (CNNs). To reduce the number of free parameters of CNNs, small filters are utilized for all convolutional layers. Owing to multiple small filters are equivalent of a large filter, which can reduce the number of parameters to learn effectively. And label-preserving transformation is used to enlarge the dataset artificially, in order to address the over-fitting and data imbalance of deep neural networks. Then, two kinds of modal features are fused linearly to form the facial expression feature. Extensive experiments are evaluated on the extended Cohn–Kanade (CK+) Dataset. For comparison, three kinds of feature vectors are adopted: low-level facial key point feature vector, high-level self-learning feature vector and multi-modal feature vector. The experiment results show that the multi-modal strategy can achieve encouraging recognition results compared to the single modal strategy.

Autonomous indoor service robots are affected by multiple factors when they are directly involved in manipulation tasks in daily life, such as scenes, objects, and actions. It is of self-evident importance to properly parse these factors and interpret intentions according to human cognition and semantics. In this study, the design of a semantic representation framework based on a knowledge graph is presented, including (1) a multi-layer knowledge-representation model, (2) a multi-module knowledge-representation system, and (3) a method to extract manipulation knowledge from multiple sources of information. Moreover, with the aim of generating semantic representations of entities and relations in the knowledge base, a knowledge-graph-embedding method based on graph convolutional neural networks is proposed in order to provide high-precision predictions of factors in manipulation tasks. Through the prediction of action sequences via this embedding method, robots in real-world environments can be effectively guided by the knowledge framework to complete task planning and object-oriented transfer.

Visual servoing is widely used in the peg-in-hole assembly due to the uncertainty of pose. Humans can easily align the peg with the hole according to key visual points/edges. By imitating human behavior, we propose P2HNet, a learning-based neural network that can directly extract desired landmarks for visual servoing. To avoid collecting and annotating a large number of real images for training, we built a virtual assembly scene to generate many synthetic data for transfer learning. A multi-modal peg-in-hole strategy is then introduced to combine image-based search-and-force-based insertion. P2HNet-based visual servoing and spiral search are used to align the peg with the hole from coarse to fine. Force control is then used to complete the insertion. The strategy exploits the flexibility of neural networks and the stability of traditional methods. The effectiveness of the method was experimentally verified in the D-sub connector assembly with sub-millimeter clearance. The results show that the proposed method can achieve a higher success rate and efficiency than the baseline method in the high-precision peg-in-hole assembly.

In the quest for intelligent robots, it is essential to enable them to understand tasks beyond mere manipulation. Achieving this requires a robust parsing mode that can be used to understand human cognition and semantics. However, the existing methods for task and motion planning lack generalization and interpretability, while robotic knowledge bases primarily focus on static manipulation objects, neglecting the dynamic tasks and skills. To address these limitations, we present a knowledge-based framework for hierarchically understanding various factors and knowledge types in robotic manipulation. Using this framework as a foundation, we collect a knowledge graph dataset describing manipulation tasks from text datasets and an external knowledge base with the assistance of large language models and construct the knowledge base. The reasoning tasks of entity alignment and link prediction are accomplished using a graph embedding method. A robot in real-world environments can infer new task execution plans based on experience and knowledge, thereby achieving manipulation skill transfer.

Emotion recognition with weighted feature based on facial expression is a challenging research topic and has attracted great attention in the past few years. This paper presents a novel method, utilizing subregion recognition rate to weight kernel function. First, we divide the facial expression image into some uniform subregions and calculate corresponding recognition rate and weight. Then, we get a weighted feature Gaussian kernel function and construct a classifier based on Support Vector Machine (SVM). At last, the experimental results suggest that the approach based on weighted feature Gaussian kernel function has good performance on the correct rate in emotion recognition. The experiments on the extended Cohn-Kanade (CK+) dataset show that our method has achieved encouraging recognition results compared to the state-of-the-art methods.

Compliant capture of the space non-cooperative targets is a key technology in on-orbit services. A great challenge is that the multi-dimensional contact force generated by the tumbling space target can destabilize the spacecraft-manipulator system (SMS), which may eventually cause failure of the capture task. A full-dimensional controllable damping mechanism (FDCDM) with gyroscopic structure is introduced into the joint of the SMS to buffer the multi-dimensional contact forces during capture. The six-dimensional damping force outputs by the FDCDM can be equivalent to the actuator outputs in the end joint, which could form a coordinated control system with the torque of base flywheel and active joints. The whole-body dynamic model of SMS with FDCDM is established using the Kane method. Furthermore, a backstepping non-singular sliding mode control is proposed to optimize the momentum distribution and impact absorption. The characteristics of collision process for the above SMS-FDCDM system is analyzed in the ADAMS workspace, and the experiments performed in MATLAB demonstrate that the full-dimensional damping mechanism and coordinated control can greatly reduce the vibration caused by the impact force, and the attitude of SMS is quickly stabilized after capture, which proves the feasibility of its application in non-cooperative target capturing tasks.