This paper presents a cooperative control framework for dual-arm robots that integrates vision-language models (VLMs) with online reinforcement learning (RL) to enhance autonomy and adaptability in complex manipulation tasks. The proposed framework adopts a hierarchical architecture: at the top level, the VLM interprets natural language instructions and visual image to generate task plans; at the middle level, an online RL module refines manipulation policies and ensures adaptive decision-making under environmental uncertainty; and at the bottom level, compliant control based on trajectory planning and impedance regulation enables safe and robust execution. In the feedback, YOLOv5 is used to detect the object, GraspNet is used to obtain the optimal grasp pose, and CLIP (Contrastive Language-Image Pre-Training) is used to judge whether task is completed. Simulations and real-world experiments validate the effectiveness of the proposed method. The dual-arm robot successfully performed various cooperative tasks such as grasping, bottle-cap unscrewing, water pouring, and box carrying, achieving an increase in the task success rate from 43% to 100% with online adaptive learning and training. These results demonstrate that the proposed framework effectively bridges high-level reasoning with low-level control, providing a scalable solution for future applications in service robotics, industrial automation, and human-robot collaboration.

Most existing robotic fruit harvesting systems rely on mechanically complex end-effectors that lack delicate tactile dexterity and fail to replicate the sophisticated sensory-motor coordination of human pickers. To enable safe, reliable, and efficient automated harvesting of delicate fruits, this paper presents a novel bio-inspired humanoid TacTip gripper for precision strawberry harvesting. Inspired by human thumbfinger opposition, we design an asymmetric TacTip gripper that integrates a Thumb tactile sensor with a built-in fingernail for stem cutting and a supporting Pillow tactile sensor. We further develop a hybrid SSIM-CNN perception framework that fuses real-time structural similarity index measure (SSIM) from both fingertips with convolutional neural network (CNN) features, enabling precise closed-loop grasp-state detection and gentle force adjustment. In addition, a segmented dynamic system (DS) motion planner decomposes the harvesting task into approach, cut, and place phases, generating reactive, smooth, and biologically plausible trajectories. Experimental results on both laboratory setups and live potted strawberry plants demonstrate reliable full-cycle harvesting with high success rates and minimal fruit damage. The proposed system provides a practical and effective solution for automated delicate fruit harvesting.

How to guarantee the effective planning trajectory of autonomous driving for mobile vehicles is the main challenge. This study provides a multi-constraint trajectory planning technique to construct safe, smooth, and dynamically viable trajectories in complicated situations. Firstly, a two-stage sampling path generation algorithm is proposed to obtain a cluster of candidate paths, considering road geometry, vehicle kinematics, and static obstacle avoidance constraints. Secondly, a cost function is designed to select the optimal path based on smoothness, consistency with the reference path, and distance to obstacles. Finally, a speed planning model is developed using convex optimization to allocate speed profiles for each path point with dynamic constraints, including time efficiency, boundary conditions, and dynamic obstacle avoidance. Experimental results on mobile vehicles demonstrate the effectiveness and stability of the proposed trajectory planning algorithm in real-world environments and its ability to handle various typical driving scenarios. The success rate of trajectory planning in the experiments was 94%, with an average planning time of 37.3ms.

It is challenging to employ a quadruped robot for real-time mapping and positioning in a large range of scenes. The significant vibration and instability of the quadruped robot during mobility, as well as the quantity of computation required to convey a wide variety of complex landscapes, result in unsatisfactory drawing construction accuracy and inefficient real-time performance. Therefore, we propose an accurate robust spinning LiDAR SLAM (ARS-SLAM) algorithm for a quadruped robot under the large-scale scene. The tightly coupled iterative Kalman filter in FAST-LIO2 is introduced into the front end of the cartographer framework to improve the accuracy and robustness of robot pose estimation. To reduce the computational complexity of the original cartographer framework, a pose threshold optimization algorithm was introduced to effectively remove redundant information from loop detection and improve computational efficiency and real-time performance. We tested the system's performance against the most advanced point-cloud-based methods, LIO-SAM and FAST-LIO2, on a large dataset of large science parks and underground parking lots, and the results show that the proposed system achieves the same or better accuracy and real-time performance.

LiDAR-based segmentation tasks pose substantial challenges in complex urban environments, particularly in high-density traffic scenarios, where existing methods often struggle to accurately detect and analyze the true motion states of individual vehicles. Accordingly, this paper presents a task-specific multi-head attention network for semantic segmentation in urban scene. This network integrates the global context modeling capability of Transformers with the local feature extraction strengths of Convolutional Neural Networks (CNNs), effectively capturing multi-scale contextual information through a hierarchical feature fusion module. Additionally, a lightweight fully-MLP (Multilayer Perceptron) decoder is proposed, which progressively recovers high-resolution representations through cascaded upsampling and skip connections, enabling efficient yet precise semantic segmentation. To further enhance model performance and address the issue of information loss caused by point cloud sparsity and discretization in the Range View, this paper introduces a supervised post-processing method named Ms-clouds. Ms-clouds employs an equidistant partitioning strategy to extract denser and more consistent feature representations in long-range regions, while simultaneously utilizing the network for smoothing and label inference in void areas, thereby improving overall prediction accuracy and strengthening the model's robustness. Extensive experiments on the public SemanticKITTI and nuScenes datasets validate the effectiveness of the proposed RangeBlock module. Our method achieves 74.5% mIoU on SemanticKITTI and 83.9% mIoU on nuScenes, outperforming state-of-the-art methods and demonstrating substantial performance gains.

Limited by the working principles, LiDAR-SLAM systems suffer from the degeneration phenomenon in environments such as long corridors and tunnels, due to the lack of sufficient geometric features for frame-to-frame matching. The accuracy and sensitivity of existing degeneracy detection methods need to be further improved. In this paper, we propose a novel method for degeneracy detection using local geometric models based on point-to-distribution matching. To obtain an accurate description of local geometric models, an adaptive adjustment of voxel segmentation according to the point cloud distribution and density is designed. The codes of the proposed method is open-source and available at https://github.com/jisehua/Degenerate-Detection.git. Experiments with public datasets and self-build robots were conducted to evaluate the methods. The results exhibit that our proposed method achieves higher accuracy than the other existing approaches. Applying our proposed method is beneficial for improving the robustness of the LiDAR-SLAM systems.

With the rapid development of Autonomous Rail Rapid Transit technology, lithium-ion battery as its main power source, the research of its charging technology has become particularly important. At present, the charging scheme of lithium-ion battery mainly includes two ways: single high-power charging and multiple low-power charging modules in parallel. However, the single high-power charging scheme has the problems of high cost and low efficiency, and the traditional parallel charging method lacks effective module management strategy, resulting in unbalanced load between modules during charging, affecting charging efficiency a nd safety. A iming at the shortcomings of current research, this paper proposes a parallel charging scheme of multiple DC-DC modules based on cooperative control. By designing a closed-loop control system of current inner loop and voltage outer loop, the precise control and cooperative work of parallel modules are realized. The experimental results show that the scheme not only improves the charging efficiency, but also ensures the stability and safety of the charging process, which provides an effective and reliable solution for the lithium-ion battery charging of the intelligent rail train.

With rubber wheels instead of steel wheels and no need to be guided by steel rails, Autonomous rail Rapid Transit(ART), is gradually coming into people's lives. However, ART still occupies existing lanes and the relatively small station spacing of ART means that ART needs to be started and stopped frequently, all of which can lead to fluctuations in DC bus voltage during ART operation, making it difficult for loads (such as motors, air conditioners, and sensors) to operate properly. Therefore, this paper proposes the use of predictive set-point modulation to suppress DC bus voltage fluctuations. The predictive set-point modulation method is able to predict the direction of DC bus voltage changes prospectively, and then adjust the voltage preset value to balance the fluctuation of the output voltage, optimizing the closed-loop system's transient dynamic performance. Moreover, since lithium ion battery has high power and high energy consumption, using only one DC-DC circuit can reduce system reliability and cost. Therefore, we propose to use parallel DC-DC modules to balance the excessive power of the battery and verify the feasibility of the proposed method through simulation experiments. The experiments show that the proposed method can effectively suppress the DC bus voltage fluctuation and improve the system reliability.

The State-of-Charge (SOC) estimation for super-capacitors has been thoroughly examined in the literature, while the majority of the research to far is concentrating on the SOC estimation of single supercapacitor units. Nevertheless, the system dynamics of the battery may shift to a different system when utilizing the recently suggested reconfigurable circuit, suggesting that the straightforward use of current SOC estimate techniques is not possible. In order to assess the battery's state of charge (SOC), we use a switching systems technique in this paper. We establish the supercapacitor's RC model with a reconfigurable circuit and carefully investigate the continuity of the state and observability of the switched system. Afterwards, we propose a switching observer and compare the performance of various observers, analyzing its convergence qualities. We compare the proposed observer with other observers through a hardware platform, and the experimental results prove the superiority of the proposed observer in SOC estimation.

This article investigates the real-time semantic segmentation in robot engineering applications based on the Broad Learning System (BLS), and a novel Multi-level Enhancement Layers Network (MELNet) based on BLS framework is proposed for real-time vision tasks in a complex street scene on the unmanned mobile robot. This network mainly solves two problems: (1) mitigating the contradiction between accuracy and speed while maintaining low model complexity, and (2) accurately describing objects based on their shape despite their different sizes. Firstly, the BLS architecture is expanded to the deep network with trainable parameters. This trainable network could adjust its weights in a complex environment, and mitigate the adverse impact of the environment on the complex tasks. Secondly, enhancement layers with the extended enhancement layers could extract both detailed information and semantic information. Moreover, an Upsampling Atrous Spatial Pyramid Pooling (UPASPP) is designed to fuse detail and semantic information to describe object features properly. Finally, in the case of the MNIST dataset and Cityscapes dataset, we get high accuracy with 8.01M parameters and quicker inference speed on a single GTX 1070 Ti card. At the same time, the unmanned mobile robot (BIT-NAZA) is employed to evaluate semantic performance in real-world situations. This reveals that MELNet could be run adequately on the embedded device and effectively operate in the real-robot system.

Accurate path tracking and stability are the main challenges of lateral motion control in mobile robots, especially under the situation with complex road conditions. The interaction force between robots and the external environment may cause interference, which should be considered to guarantee its path tracking performance in dynamic and uncertain environments. In this article, a flexible lateral control scheme is considered for the developed wheel-legged robot, which consists of a cubature Kalman algorithm to evaluate the centroid slip angle and the yaw rate. Furthermore, a fuzzy compensation and preview angle-enhanced sliding model controller to improve the tracking accuracy and robustness. Finally, some simulations and experimental demonstrations using the four-wheel-legged robot (BIT-NAZA) are carried out to illustrate the effectiveness and robustness, and the proposed method has achieved satisfactory results in high-precision trajectory tracking and stability control of the mobile robot.

In this paper, an Internet of Things-based human-robot collaborative control scheme is developed in Robot-assisted Minimally Invasive Surgery scenario. A hierarchical operational space formulation is designed to exploit the redundancies of the 7-DoFs redundant manipulator to handle multiple operational tasks based on their priority levels, such as guaranteeing a remote center of motion constraint and avoiding collision with a swivel motion without influencing the undergoing surgical operation. Furthermore, the concept of the Internet of Robotic Things is exploited to facilitate the best action of the robot in human-robot interaction. Instead of utilizing compliant swivel motion, HTC VIVE PRO controllers, used as the Internet of Things technology, is adopted to detect the collision. A virtual force is applied to the robot elbow, enabling a smooth swivel motion for human-robot interaction. The effectiveness of the proposed strategy is validated using experiments performed on a patient phantom in a lab setup environment, with a KUKA LWR4+ slave robot and a SIGMA 7 master manipulator. By comparison with previous works, the results show improved performances in terms of the accuracy of the RCM constraint and surgical tip.

In this paper, an improved motion planning scheme is proposed for surgical robot control with multiple active constraints, including joint constraints, joint velocity constraints and remote center of motion constraints. It introduces an improved recurrent neural network (RNN) to optimize the online motion planning respect to multiple constraints. The demonstrated surgical operation trajectory is derived using teaching by demonstration. An improved motion planning scheme using the novel recurrent neural network is then designed to achieve the accurate task tracking under the multiple constraints. The general quadratic performance index is adopted to represent the constraints. Finally, the effectiveness of the proposed algorithm is demonstrated using KUKA LWR4+ robot in a lab setup environment.