This article introduces a dome-type soft tactile sensor that can autonomously adjust its stiffness to evaluate surface contact characteristics, including the elastic modulus, contact force, and the presence of abnormal hardness within soft materials, using a strain gauge as a single sensing element. The strain sensor element is placed at the tip of the dome to measure the deformations during contact that reflect the properties of the contacted object. Using machine learning techniques, the sensor system can accurately predict these characteristics in various materials with an error rate of less than approximately 8%. A hybrid approach that combines experimental and simulation data enables the sensor to be trained effectively, generating sufficient data for accurate predictions without extensive experiments. The high accuracy results of the machine learning models demonstrate that the sensor system can precisely calculate the elastic modulus and depth of the defect. The adaptability and precision of the proposed sensor make it ideal for applications in medical diagnostics and other fields requiring careful interaction with soft materials. Furthermore, its innovative approach can be referenced for exploiting the properties of soft materials to achieve task-specific morphology without redesigning soft sensors or soft robots.

Due to the complexity of urban and rural drainage systems, although many types of robots have been designed for this purpose, the mainstream pipeline inspection robots are currently dominated by four-wheeled designs. In this study, the shortcomings of four-wheeled pipeline robots were analyzed, including poor passability, difficulties in spatial positioning and orientation, and the limited effectiveness of conventional two-degree-of-freedom observation systems. Based on these issues, the spatial pose mathematical model of the four-wheeled robot inside the pipeline was investigated, along with the spatial geometric constraints and speed characteristics during cornering. This study was intended to reveal the spatial geometric parameter limitations and the kinematic characteristics of the four-wheeled pipeline robot under these constraints, providing corresponding recommendations. To address the issue of the outdated two-degree-of-freedom vision component, a three-degree-of-freedom visual component was designed, and forward kinematics analysis was conducted using Standard-Denavit-Hartenberg parametric modeling, revealing its motion speed and characteristics. Based on this visual component, a new concept of in-pipeline robot vision was proposed, providing new references for the design of four-wheeled pipeline robots.

This paper presents the design and experimental validation of a robust flight control strategy for quadrotor unmanned aerial vehicles (UAVs) based on the Interconnection and Damping Assignment Passivity-Based Control (IDA-PBC) methodology. The proposed approach is specifically tailored to the Parrot Bebop 2, a commercial UAV. The IDA-PBC control law is derived using the Hamiltonian model of the UAV dynamics obtained from experimental data to represent the dynamics of all six degrees of freedom, including translational and rotational motions. The control strategy was validated through numerical simulations and experimental tests conducted in an indoor flight setup using MATLAB, Robot Operating System, and an OptiTrack motion capture system. Numerical and experimental results demonstrate that the controller effectively tracks desired flight trajectories, ensuring stable and robust performance.

This paper presents a general approach to synthesizing closed-loop robots for machining and manufacturing of complex quadric surfaces, such as toruses, helicoids, and helical tubes. The proposed approach begins by employing finite screw theory to describe the motion sets generated by prismatic, rotational, and helical joints. Subsequently, generatrices and generating lines are put forward and combined for type synthesis of serial kinematic limbs capable of generating single-DoF translations along spatial curves and two-DoF translations on complex quadric surfaces. Following this manner, the two-DoF translational motion patterns on these complex quadric surfaces are algebraically defined and expressed as finite screw sets. Type synthesis of close-loop robots having the newly defined motion patterns can thus be carried out based upon analytical computations of finite screws. As application of the presented approach, closed-loop robots for machining toruses are synthesized, resulting in four-DoF and five-DoF standard and derived limbs together with their corresponding assembly conditions. Additionally, brief descriptions of robots for machining helicoids and helical tubes are provided, along with a comprehensive list of all the feasible limbs for these kinds of robots. The robots synthesized in this paper have promised applications in machining and manufacturing of spatial curves and surfaces, enabling precise control of machining trajectories ensured by mechanism structures and achieving high precision with low cost.

Unmanned surface vehicles (USVs) frequently encounter inadequate energy levels while navigating to their destinations, which complicates their successful berthing in intricate harbor environments. A bacterial foraging optimization algorithm (BFO) is proposed that takes energy consumption into account and incorporates multiple constraints (MC-BFO). The energy consumption model is redefined for wind environments, enhancing the sensitivity of USVs to wind conditions. Additionally, a reward function is integrated into the algorithm, and the fitness function is reconstructed to improve the goal orientation of the USV. This approach enables the USV to maintain a reasonable path length while pursuing low energy consumption, resulting in more practical navigation. Constraining the USV’s sailing posture for smoother paths and restricting the USV’s heading and speed near the berthage facilitate safe berthing. Finally, three distinct experimental environments are established to compare the paths generated by MC-BFO, BFO, and genetic algorithm under both downwind and upwind conditions, ensuring consistency in relevant parameters. Data on sailing posture, energy consumption, and path length are collected, generalized, and analyzed. The results indicate that MC-BFO effectively reduces energy consumption while maintaining an acceptable path length, resulting in smoother and more coherent paths compared to traditional segmented planning. In conclusion, this method significantly enhances the quality of the berthing path.

Efficient local trajectory optimization of the coordinated manipulator is a bottleneck task in the narrow feeding scenario. To optimize the trajectory locally and generate collision-free trajectories with local support performance, the analytical reinforcement method is proposed. Firstly, multiple coordinated machines operating in the narrow space are transformed into decentralized dynamic constraints for the target manipulator. Combined with the circle envelope method in the dynamic constraint, the collision-free gradient optimization function determines the support region of the local optimal trajectory. Based on the forward kinematics and inverse kinematics method, the collision-prone pose of the target manipulator outside the support region is analytically optimized. And chi-square distribution further ensures the smooth interpolation of the variable-period trajectory outside the fixed-period support region. For the emergency collision avoidance of the coordinated manipulator in the flexible stamping line, the analytical reinforcement method is successfully verified by generating the collision-free and smooth trajectory. It provides an optimization direction for rapidly improving the work efficiency of multi-machine coordination in the narrow feeding scenario.

Wheel-leg composite robots exhibit robust mobility and exceptional obstacle-crossing capabilities in complex environments. This paper proposes a novel transformable wheel-leg composite structure and presents the design of a wheel-leg composite obstacle-crossing robot, fundamentally configured as a two-wheeled quadruped. The research encompasses a comprehensive analysis of the robot’s overall mechanical structure, a detailed kinematic investigation of its body and obstacle-crossing gait planning, virtual prototype dynamics simulation, and field experimentation. Utilizing advanced modeling software, a 3D model of the robot was established. The kinematic characteristics of the robot in both wheeled and legged modes were thoroughly examined. Specifically, for the legged mode, the Denavit-Hartenberg coordinate system was established, and a detailed kinematic model was analyzed. The obstacle-crossing gait was planned based on the robot’s leg action mechanism. Furthermore, the Lagrangian method was employed to develop a mathematical model for the dynamics of the robot in both wheel-foot modes, allowing for a comprehensive force analysis. To validate the feasibility and rationality of the robot’s obstacle-crossing capabilities under various conditions, extensive simulations and prototype tests were conducted across diverse terrains. The results provide valuable insights and practical guidance for the structural design of wheel-leg composite obstacle-crossing robots, contributing to advancements in this promising field.

Detecting cracks in underwater dams is crucial for ensuring the quality and safety of the dam. However, underwater dam cracks are easily obscured by aquatic plants. Traditional single-view visual inspection methods cannot effectively extract the feature information of the occluded cracks, while multi-view crack images can extract the occluded target features through feature fusion. At the same time, underwater turbulence leads to nonuniform diffusion of suspended sediments, resulting in nonuniform flooding of image feature noise from multiple viewpoints affecting the fusion effect. To address these issues, this paper proposes a multi-view fusion network (MVFD-Net) for crack detection in occluded underwater dams. First, we propose a feature reconstruction interaction encoder (FRI-Encoder), which interacts the multi-scale local features extracted by the convolutional neural network with the global features extracted by the transformer encoder and performs the feature reconstruction at the end of the encoder to enhance the feature extraction capability and at the same time in order to suppress the interference of the nonuniform scattering noise. Subsequently, a multi-scale gated adaptive fusion module is introduced between the encoder and the decoder for feature gated fusion, which further complements and recovers the noise flooding detail information. Additionally, this paper designs a multi-view feature fusion module to fuse multi-view image features to restore the occluded crack features and achieve the detection of occluded cracks. Through extensive experimental evaluations, the MVFD-Net algorithm achieves excellent performance when compared with current mainstream algorithms.

Multi-loop coupling mechanisms (MCMs) are extensively utilized in the aerospace and aviation industries. This paper analyzes the mobility, singularity, and optimal actuation selection of a 3RR-3RRR MCM on the basis of geometric algebra (GA), where R denotes revolute joint. First, the principle of the shortest path is employed to identify the basic limbs and ascertain the type of coupling limbs. The analytical expression for the twist space and mobility characteristics of the mechanism is obtained by calculating the intersection of the limb’s twist space. The blade of limb constraint is subsequently employed to construct the singular polynomials of the mechanism. The singular configurations of the 3RR-3RRR MCM are analyzed in accordance with the properties of the outer product, resulting in the identification of two distinct types of boundary singularities. Next, the local transmission index is employed to evaluate the motion/force transmission performance of the two actuation schemes and finalize the selection of the superior actuation scheme for the mechanism. Finally, a prototype is developed to evaluate the energy loss resulting from the two actuation schemes, which verifies the correctness of the actuation selection scheme.

With the rapid advancements in robotics and autonomous driving, SLAM (simultaneous localization and mapping) has become a crucial technology for real-time localization and map creation, seeing widespread application across various domains. However, SLAM’s performance in dynamic environments is often compromised due to the presence of moving objects, which can introduce errors and inconsistencies in localization and mapping. To overcome these challenges, this paper presents a visual SLAM system that employs dynamic feature point rejection. The system leverages a lightweight YOLOv7 model for detecting dynamic objects and performing semantic segmentation. Additionally, it incorporates optical flow tracking and multiview geometry techniques to identify and eliminate dynamic feature points. This approach effectively mitigates the impact of dynamic objects on the SLAM process, while maintaining the integrity of static feature points, ultimately enhancing the system’s robustness and accuracy in dynamic environments. Finally, we evaluate our method on the TUM RGB-D dataset and in real-world scenarios. The experimental results demonstrate that our approach significantly reduces both the root mean square error (RMSE) and standard deviation (Std) compared to the ORB-SLAM2 algorithm.

Stroke is a prevalent neurological event that often induces significant motor impairments in the upper extremities, such as hemiplegia, which impacts bimanual coordination and fine motor skills. Robotic-assisted therapy has gained prominence as a contemporary rehabilitation modality, providing augmented motor repetitions and proprioceptive feedback, thereby potentiating neuroplasticity and functional recovery. This pilot study aimed to examine the therapeutic efficacy of a robotic intervention for wrist rehabilitation in two post-stroke adults aged 50–70 years. The intervention protocol, implemented biweekly over four weeks, encompassed 45-minute sessions consisting of passive muscle elongation (5 min) and robotic-facilitated exercises targeting pronation-supination (10 min), flexion-extension (10 min), and radial-ulnar deviation (10 min). Outcome measures included pre- and post-intervention assessments utilizing the motor activity log, Fugl-Meyer Scale, and robotic metrics for muscular strength. Results indicated enhancements in joint range of motion, motor precision, and neuromuscular control, with patient “B” demonstrating superior improvements, particularly in complex motor patterns. In contrast, patient “A” exhibited attenuated progress, attributable to pronounced baseline deficits and fatigue. Specific gains were observed in flexion-extension for patient “A” and pronation-supination for patient “B,” with minimal advancements in radial-ulnar deviation across both subjects. These findings provide preliminary evidence supporting the efficacy of robotic-assisted therapy in motor rehabilitation post-stroke with the novel proposed wrist rehabilitation device.

Most research on UAV swarm architectures remains confined to simulation-based studies, with limited real-world implementation and validation. In order to mitigate this issue, this research presents an improved task allocation and formation control system within ARCog-NET (Aerial Robot Cognitive Architecture), aimed at deploying autonomous UAV swarms as a unified and scalable solution. The proposed architecture integrates perception, planning, decision-making, and adaptive learning, enabling UAV swarms to dynamically adjust path planning, task allocation, and formation control in response to evolving mission demands. Inspired by artificial intelligence and cognitive science, ARCog-NET employs an Edge-Fog-Cloud (EFC) computing model, where edge UAVs handle real-time data acquisition and local processing, fog nodes coordinate intermediate control, and cloud servers manage complex computations, storage, and human supervision. This hierarchical structure balances real-time autonomy at the UAV level with high-level optimization and decision-making, creating a collective intelligence system that automatically fine-tunes decision parameters based on configurable triggers. To validate ARCog-NET, a realistic simulation framework was developed using SITL (Software-In-The-Loop) with actual flight controller firmware and ROS-based middleware, enabling high-fidelity emulation. This framework bridges the gap between virtual simulations and real-world deployments, allowing evaluation of performance in environmental monitoring, search and rescue, and emergency communication network deployment. Results demonstrate superior energy efficiency, adaptability, and operational effectiveness compared to conventional robotic swarm methodologies. By dynamically optimizing data processing based on task urgency, resource availability, and network conditions, ARCog-NET bridges the gap between theoretical swarm intelligence models and real-world UAV applications, paving the way for future large-scale deployments.

This paper introduces the Arachne System, a scalable, cost-effective mobile microrobot swarm platform designed for educational and research applications. It details the design, functionalities, and potential of the Arachne Bots, emphasizing their accessibility to users with minimal robotics expertise. By providing a comprehensive overview of the system’s hardware, sensory capabilities, and control algorithms, the paper demonstrates the platform’s capacity to democratize and reduce entry barriers in mobile robotic swarms research, fostering innovation and educational opportunities in the field. Extensive experimental validation of the system showcases its broad range of capabilities and effectiveness in real-world implementation.

In response to the prevailing trend of an aging society and the increasing requirements of rehabilitation, this paper presents an approach involving brain-machine interaction (BMI) for a single-degree-of-freedom (1-DOF) sit-to-stand transfer robot. Based on a 1-DOF rehabilitation robot, three experiment paradigms involving motor imagery (MI), action observation of motor imagery (AO-MI) and motor execution are designed using both electroencephalography (EEG) and electromyography (EMG). To enhance motion intention recognition accuracy, a Gumbel-ResNet-KANs decoding model is established. The Gumbel-ResNet-KANs model integrates the Gumbel-Softmax method with the ResNet-KANs network module and demonstrates strong decoding capability, as demonstrated by comparative tests in this paper. To validate the effect of robotic assistance, EEG and EMG coherence are analyzed to assess the impact of robotic assistance on rehabilitation from a neuromuscular perspective in both assisted and unassisted conditions. We assessed the effect of robotics on rehabilitation from an emotional perspective by analyzing the difference between the differential entropy of the right and left brain. The proposed study also reveals that the movement-related cortical potentials in AO-MI are beneficial for promoting the performance of BMI in sit-to-stand training, which provides a possible approach for the development of new types of robots for lower limb rehabilitation.

Capturing the non-cooperative tumbling target by the free-floating space robot stands as a crucial task within on-orbit servicing. However, the strong dynamic coupling of the base-spacecraft and the manipulator seriously disturbs the base-spacecraft, which reduces the power generation efficiency of solar panels and the communication quality with the earth station. In this paper, the trajectory planning method of the free-floating space robot for non-cooperative tumbling target capture based on deep reinforcement learning is proposed, which can reduce the disturbance of the base-spacecraft during target capture. First, the generalized Jacobian matrix of the space robot is derived, from which the dynamics model is obtained. The kinematics model of the space non-cooperative tumbling target is established. And the contact collision dynamics between the space robot and the tumbling target are analysed. Second, the twin delayed deep deterministic policy gradient algorithm is introduced to plan the trajectory for capturing the non-cooperative tumbling target, where apart from the motion parameters of the manipulator and the generalized manipulability of the space robot, the pose disturbance of the base-spacecraft is initially added to the reward function. Finally, the simulation for target capture is carried out. The results show that compared with the existing method, the proposed method converges faster with a larger reward, and the pose disturbance of the base-spacecraft is reduced. Moreover, the method performs well for capturing the non-cooperative tumbling target with different initial rotational angular velocities.

In recent years, the removal of orbital debris has become an increasingly urgent task due to advancements in human space exploration. Capturing space debris through caging manipulation offers notable advantages in terms of robustness and controllability. This paper proposes a configuration-based caging manipulation design method for a cable-driven flexible arm. First, the cable-driven flexible arm with multi self-lockable links is introduced. To quantify the caging configurations formed by different self-lockable link selections, a novel planar caging quality metric is then presented for arbitrary planar objects. Using this metric, a caging design method is developed for the flexible arm to conduct caging manipulations. Finally, the caging manipulation strategies are discussed with lock selection maps for different objects, and a robust caging strategy considering uncertainty is further explored. Simulation and experimental results validate the effectiveness of the proposed caging design method and demonstrate better performance compared to conventional caging methods.

Indoor positioning systems (IPS) are essential for mobile robot navigation in environments where global positioning systems (GPS) are unavailable, such as hospitals, warehouses, and intelligent infrastructure. While current surveys may limit themselves to specific technologies or fail to provide practical application-specific details, this review summarizes IPS developments directed specifically towards mobile robotics. It examines and compares a breadth of approaches that vary across non-radio frequency, radio frequency, and hybrid sensor fusion systems, through the lens of performance metrics that include accuracy, delay, scalability, and cost. Distinctively, this work explores emerging innovations, including synthetic aperture radar (SAR), federated learning, and privacy-aware AI, which are reshaping the IPS landscape. The motivation stems from the’ increasing complexity and dynamic nature of indoor environments, where high-precision, real-time localization is essential for safety and efficiency. This literature review provides a new conceptual, cross-border pathway for research and implementation of IPS in mobile robotics, addressing both technical and application-related challenges in sectors related to healthcare, industry, and smart cities. The findings from the literature review allow early career researchers, industry knowledge workers, and stakeholders to provide secure societal, human, and economic integration of IPS with AI and IoT in safe expansions and scale-ups.

Interfacial interactions, including adhesion and friction, directly affect the ability of the robot system to interact with the external environment, such as the realization of operation and motion functions. Bionics provides guidance for the active control of interface forces. Creatures such as geckos, tree frogs, octopuses, and beetles have developed delicate topological structures and smart control strategies during long-term evolution, facilitating their ability to adhere to, manipulate, capture, and traverse various surfaces across diverse environments. Inspired by the advantages of high strength, adaptability, controllability, durability, and no residue, biomimetic controllable adhesion structures, materials, and systems have been developed, showing a wide range of potential applications in reversible attachment, flexible locomotion, and dexterous grasping. In this paper, the mechanisms and theoretical models of various biological reversible adhesion systems in nature are summarized. Then the design criteria, optimization method, and preparation technology of the artificial adhesion structures based on van der Waals interaction, capillary force, negative pressure, and mechanical interlocking mechanisms are reviewed. In particular, the adhesion/load ratio and the switch ratio of adhesive materials and structures are highlighted to evaluate the adhesion ability and controllability of various designs. The applications of biomimetic controllable adhesion structures and systems in robotics manipulation and locomotion are presented. Finally, the conclusion and possible future direction are discussed.