Wheeled self-reconfigurable robots (WSRRs), a new type of multi-robot system with flexible configurations and task adaptability, have an extensive application prospects in unstructured mission environments. In this paper, based on the nonholonomic constraints and Lagrange method, the combinatorial modal kinematics and dynamics of WSRRs with arbitrary reconfiguration scale are established. At the kinematic level, based on the nonholonomic constraints, a smooth obstacle avoidance strategy based on the safety geofences is designed to ensure safety. At the dynamic level, an adaptive fault-tolerant mechanism is introduced to ensure reasonable torque distribution and avoid tracking performance degradation. Meanwhile, an improved extended state observer (IESO) is elaborated, through which the high-frequency ocsillation from measurement noises and peaking phenomenon from initial observer errors can be suppressed, and the robust velocity tracking control under unknown lumped disturbances is realized. Finally, a real-world WSRRs experiment is constructed to verify the proposed method's fault tolerance, robustness, and safety comparatively.

Achieving a real-time precise grasp of a specified target object in densely cluttered environments is an essential capability for autonomous robot operation. Recently, considerable investigations on planar and spatial grasp have been carried out, and significant results have been obtained. However, these point cloud-based grasp prediction methods often fail to ensure that the generated grasp configurations meet the precise requirements of the task. Additionally, some of the existing grasp pipelines are too time-consuming to meet the demand for real-time robot response. In more challenging cluttered scenes, the quality of pose and gripper jaw opening estimation in highdimensional space requires further improvement. Therefore, this paper introduces a data- and model-independent and efficient method to generate 7-DoF grasp configurations for arbitrary target objects from single-view point cloud data in dense cluttered scenes. In addition, this paper proposes a grasp framework that generates the grasp configuration for the target object while reducing the time consumed during the grasp process, to enable robots to efficiently grasp target objects for designated tasks. The grasp pipeline focuses on guided regions via target detection and rapidly adjusts grasp configurations through multi-region point cloud distribution perception. Extensive real-world robot experiments have demonstrated the effectiveness of the proposed method in grasping target objects in cluttered scenes, achieving higher success rates and reduced runtime compared to baseline methods. The realized code and video are available at https://github.com/L-tj/7DGCG.

In recent years, Vision-Language Models (VLMs) have exhibited powerful capacity of reasoning, decomposing long-horizon tasks and motion planning in robotic manipulation tasks. However, the current operating speed of VLMs has limited the interaction frequency of users and the model to several seconds, which disables the real-time perception of environmental changes when executing tasks released by VLM. We propose Real-time Object Detection - VLM (ROD-VLM), a novel framework which combines classical Object Detection Algorithm YOLO-v5x with VLM to achieve the real-time robotic environmental perception, reasoning and manipulation. Specifically, we introduce the concept of key frame to VLM model, capturing the crucial information through object detection algorithm to assist VLM in perceiving varying environment. Our comprehensive real-world experiments show that ROD-VLM possess an excellent capability in real-time environmental understanding, decision-making and action executing.

In order to quickly and accurately detect the occurrence of accidental falls and save the lives of more elderly people living alone, this paper proposes a new convolutional network module Higher-order Coordinated Attention module (CAGn) based on the latest research, and uses it and the lightweight convolutional module (GSConv) to improve the YOLOv5s model to construct a new fall detection model YOLOv5s-CAGn-GSConv. In addition, a new fall detection dataset Fall-Dataset is produced, and a fall event triggering mechanism based on queue window is proposed to be applied to the fall detection system. Experimental results show that the CAGn module can capture cross-channel information and high-order spatial information at the same time, thereby effectively improving the accuracy of the detection model, and the introduction of GSConv module further improves the accuracy and greatly reduces the number of parameters of the detection model. The final YOLOv5s-CAGn-GSConv model only increases the number of parameters by 4.2% but improves the accuracy by 2.1% and the average accuracy by 0.9% ([email protected]) and 2.6% ([email protected]:0.95).

This article develops a new controller design approach to stabilize system states onto the equilibrium at an arbitrarily selected time instant irrespective of the initial system states and parameters. By the stabilization approach, the actual convergence time (not the bound of actual convergence time) is independent of the initial value of system states. This feature differentiates our proposed prescribed-instant stability from conventional fixed, predefined, and prescribed time stability. In this work, we propose the controller design method for the prescribed-instant stability of n -order integrator systems. The proposed control is bounded and can gradually go to zero at an arbitrarily selected time instant, at which the system states reach zero simultaneously. This special stability of the controlled system is analyzed by reduction to absurdity. In simulations, an example of comparison with frequently used prescribed-time control is presented to show the difference. Moreover, the proposed stabilization method is validated by a magnetic suspension system with matched disturbances.