Regular condition measurements of bridge structures are essential to bridge safety. Nevertheless, sensor placement for inspection on certain high-elevation bridges is difficult. To enhance inspection efficiency, a bilateral teleoperation system using an aerial manipulator (AM) is developed to support sensor placement tasks. A fully actuated hexacopter with fixed-tilt rotors is used as the flying platform of the AM, enabling stable aerial physical interaction for sensor placement without the need for a multi-degree-of-freedom (DoF) robotic manipulator. A rope-driven gripper serves as the end-effector and is rigidly connected to the platform. Operators use a haptic device to teleoperate the AM via position–velocity mapping. Unlike traditional bilateral teleoperation methods that primarily reflect contact forces, the proposed system incorporates measurement-driven haptic feedback in both free-flight and contact phases, where distance sensing and contact-force sensing are rendered as haptic cues to assist the operator throughout the deployment procedure. In free flight, a 2D LiDAR measures the distance between the AM and the target/obstacles, and this distance is mapped to a nonlinear spring-like feedback force to regulate the approach motion and facilitate smooth contact at an appropriate velocity, thereby improving the consistency of the approach in visually challenging environments. During contact, the interaction force measured by an onboard force sensor is processed and rendered to the leader side, enabling stable contact maintenance to satisfy the sustained-contact requirement for successful deployment. A leader controller is designed, and the input-to-state (ISS) stability of the closed-loop teleoperation system is analyzed. The effectiveness of the approach was validated through real-world bridge experiments, including a task-level human-subject evaluation that reports success rate and completion time under three feedback conditions.

For autonomous navigation in indoor environments, aerial robots mostly take cameras, LiDAR, ultrasonic ranging sensors, and other devices for collision avoidance, rarely using tactile sensors. However, cameras are susceptible to lighting conditions, LiDAR requires high computational resources, and ultrasonic sensors have blind zones when measuring at short distances. In contrast, insects and rodents can perceive their surroundings via tactile sensing even in complete darkness. Inspired by the escape strategy of mosquitoes that navigate along boundaries using tactile sensing in confined spaces, this paper proposes an indoor navigation and escape method based on active tactile perception for a blimp robot. The robot comprises a rigid multi-rotor structure and a soft balloon body, with bio-inspired whisker sensors mounted on the soft body surface to enable safe contact with walls. First, we studied mosquito escape behavior experimentally. Then, we designed the robot's mechanical structure and tactile perception system. Subsequently, an interaction model between the robot and the wall was established, and a flight controller was developed. We classified the typical indoor wall scenarios and proposed a 'Sense-Plan-Act' framework for wall-following navigation and escape. Next, the designed controller and strategy were validated through simulations. Finally, we conducted experiments using a robot prototype to verify the proposed method. Results showed that the robot successfully achieved indoor wall-following navigation during flight and ultimately escaped. The proposed active tactile perception method is straightforward and practical for the indoor navigation and escape tasks of blimp robots.

Purpose This paper aims to present an aerial manipulator that can measure the crack depth of concrete structures. Currently, the detection of crack depth in concrete structures depends mainly on manual operations with nondestructive testing (NDT) instruments. There still lacks automatic equipment to release the workers at height from the highly dangerous and time-consuming NDT detection tasks. Design/methodology/approach The proposed aerial manipulator consists of a hexacopter, a two degrees of freedom (DOF) manipulator and a custom-designed ultrasonic crack detector based on the ultrasonic flat-measured principles. A four-phase control strategy is proposed for the aerial manipulator to complete the concrete crack depth measuring task. Findings The experimental results show that the proposed control strategy is effective and the prototype of the aerial manipulator succeeds in contact detection of the cracks in the concrete specimens. The field test results further verify that the proposed aerial manipulator is capable of contact inspection of bridge piers and other similar concrete structures. Originality/value The proposed aerial manipulator provides an unmanned aerial vehicle (UAV) based solution for NDT detection of concrete crack depth. It serves as a novel tool for the inspection personnel working at height to get the interior damage conditions of concrete structures safely and quickly.

Hydraulic structure inspection and maintenance are essential for structural health and operational safety. To address the limitations of underwater intervention, this article introduces an integrated underwater manipulator system that supports both teleoperation and automatic operation modes. The automatic mode incorporates visual position estimation for locating structures, robust motion capability for accurate trajectory tracking, and compliance and force tracking for safe interaction. An uncertainty-based underwater disparity estimation network (UWNet) is developed to enhance position estimation accuracy. This network combines global and local features effectively and integrates uncertainty estimation and pseudolabel generation to adapt the pretrained UWNet, improving underwater disparity predictions. In addition, a robust controller is designed, comprising an inner-loop position controller based on modified unknown system dynamics estimator and supertwisting sliding mode control to mitigate hydrodynamic disturbances and model uncertainties. An outer-loop variable admittance controller with adaptive feedback compensation ensures compliant interaction and force tracking. Experimental results show that, with reliable disparity estimation from the adapted UWNet, the system achieves a trajectory tracking RMSE of 1.44 mm at 1.0 m/s flow and a mean force error of 0.63 N during thickness measurement, while enabling stable surface cleaning under varying flow conditions, thereby facilitating hydraulic structure inspection and maintenance.

Postural synergies provide a compact representation for controlling high degrees of freedom robotic hands, but conventional synergy-based approaches struggle to accurately represent and reconstruct complete, time-varying reach-to-grasp trajectories across diverse grasp types. This paper proposes a novel method based on HMM-driven segmentation and connection of local trajectory nonlinear synergy representations to improve reach-to-grasp trajectory modeling and reconstruction. A left-right Hidden Markov Model (HMM) is first trained on joint-angle demonstrations to decompose reach-to-grasp motions into locally coherent segments. For each local sub-dataset, a back-constrained Gaussian Process Latent Variable Model (GP-LVM) learns a nonlinear trajectory representation in a low-dimensional synergy subspace. During reconstruction, local GP-LVMs decode full trajectories, which are probabilistically blended using smoothed HMM state posteriors to obtain continuous reach-to-grasp motions. The proposed framework is evaluated on two datasets: a simulated 15-DoF University of Bologna (UB) Hand IV robot hand performing 31 grasps, and a real AR10 robot hand executing 10 grasps for a kitchen-related coffee-preparation task. Experimental results demonstrate significant reductions in reconstruction error for both final grasp poses and complete trajectories. These results indicate that the proposed method provides an accurate and compact representation of reach-to-grasp motions and offers a useful basis for future motion planning and adaptation in dexterous robotic manipulation.

Purpose Robotic manipulators improve the safety and feasibility of underwater maintenance. Accurate position and contour data are crucial for enhancing automation and efficiency. Although learning-based stereo matching methods show promise, current algorithms face challenges in underwater environments, such as domain shifts and limited ground truth data. The purpose of this paper is to design a stereo vision system to guide robotic manipulators in underwater structure maintenance, thereby enabling automated operations and improving efficiency. Design/methodology/approach An Uncertainty-Based Pyramid Disparity Distribution Smoothing Network (UPDSNet) is proposed, leveraging pyramid information and cross-domain features to enhance generalizability in underwater environments. A novel loss function is designed, integrating uncertainty estimation with Kullback-Leibler divergence to promote unimodal disparity distributions and improve underwater precision. Additionally, an uncertainty-based filtering approach is introduced that generates sparse yet highly accurate pseudo-labels, effectively addressing the scarcity of underwater ground truth data. Findings Experimental results demonstrate that UPDSNet achieves strong cross-domain generalization, effectively adapting from land to underwater environments and achieving centimeter-level reconstruction accuracy. Furthermore, the stereo vision system built on UPDSNet is integrated with an underwater manipulator, demonstrating the effectiveness of the entire system in autonomous underwater maintenance tasks. Originality/value An efficient stereo vision system is proposed, enabling an underwater manipulator to autonomously perform underwater maintenance tasks and thereby significantly improving operational efficiency.

Inspection of hydraulic structures is crucial for ensuring the reliability and safety of infrastructures. Although underwater manipulators are essential tools, existing systems often lack sufficient compliance and safe interaction capabilities. This study develops a novel underwater manipulator system with a robust admittance control framework designed specifically for safe contact inspection tasks. The manipulator integrates a 6-axis force/torque sensor for contact force measurement and an ultrasonic detector for structural inspection. An underwater force estimation algorithm is implemented to ensure accurate force measurement under varying flow conditions. The proposed robust admittance control strategy comprises an inner-loop position controller, enhanced by an unknown system dynamics estimator and super-twisting sliding mode control, to counteract hydrodynamic disturbances and improve trajectory tracking accuracy. An outer-loop variable admittance controller, incorporating variable damping mechanism and adaptive feedback compensation, ensures compliant interactions and precise force control with minimal overshoot. Extensive experiments, including force measurement, motion and contact force control, and underwater thickness measurement, demonstrate the system's excellent performance, validating its effectiveness for hydraulic structure inspection tasks.

PurposeThis study aims to address the challenges of the automated inspection of concrete bridge piers, as existing climbing robots often encounter constraints related to their adhesion methods. Furthermore, achieving consistent omnidirectional movement on these large vertical structures is a complex control task that evaluates traditional estimation and control techniques.Design/methodology/approachThis study addresses these limitations by presenting an innovative climbing robot featuring a distinctive force-controlled gripping mechanism for robust, adaptable adhesion and Mecanum wheels for full omnidirectional movement. To achieve accurate control in complex scenarios, this paper presents two methodologies: a Long Short-Term Memory Random Forest (LSTM-RF) model that integrates data from multiple Inertial Measurement Units (IMU) for reliable attitude estimation, and a Deep Q-Network Tube Model Predictive Control (DQN-Tube MPC) framework for motion control.FindingsThe controller's remarkable tracking accuracy, with a Root Mean Square Error (RMSE) of 1.17 cm for the Zr-axis position, 1.17 degrees for Roll, 0.78 degrees for Pitch and 1.725 degrees for Yaw angle.Originality/valueThe proposed robotic system offers an effective and dependable solution for the automated inspection of bridge piers.

The cooperation of a pair of robot manipulators is required to manipulate a target object without any fixtures. The conventional control methods coordinate the end-effector pose of each manipulator with that of the other using their kinematics and joint coordinate measurements. Yet, the manipulators' inaccurate kinematics and joint coordinate measurements can cause significant pose synchronization errors in practice. This paper thus proposes an image-based visual servoing approach for enhancing the cooperation of a dual-arm manipulation system. On top of the classical control, the visual servoing controller lets each manipulator use its carried camera to measure the image features of the other's marker and adapt its end-effector pose with the counterpart on the move. Because visual measurements are robust to kinematic errors, the proposed control can reduce the end-effector pose synchronization errors and the fluctuations of the interaction forces of the pair of manipulators on the move. Theoretical analyses have rigorously proven the stability of the closed-loop system. Comparative experiments on real robots have substantiated the effectiveness of the proposed control.

To address the issue that current transformable spoke-wheeled leg-wheel robots cannot simultaneously achieve simple structure, stable locomotion and open step climbing ability, a novel robot design method is proposed. The robot called BiTSpoke is driven by two transformable spoke wheels, with a passive wheel mounted at the tail end serving as support and reducing friction. Each transformable spoke wheel is driven by a single motor and primarily consists of two parts: a two-way hub and a one-way hub. The forward rotation of the drive motor controls the robot to move forward, while the reverse rotation of the drive motor causes relative rotation between the two-way hub and one-way hub, thereby switching between wheeled mode and legged mode. The dynamic model and maximum step climbing height of the robot were analyzed. The physical experiment results show that the wheeled motion speed can reach 50.14mm/s in the forward direction and 43.21mm/s in the backward direction, the legged motion speed can reach 47.43mm/s in the forward direction and 42.55mm/s in the backward direction on a painted desktop, mode transformation can be achieved on different terrains in 2.73s, maximum closed step climbing height is 52mm, which is 1.44 times the radius of the wheel, maximum open step climbing height is 61mm, which is 1.69 times the radius of the wheel, and BiTSpoke can adapt to different terrain features. This robot is expected to be used in search and rescue (SAR) missions, leveraging its advantages of low cost and strong terrain adaptability.

This article proposes a distributed passivity-based bilateral teleoperation control for optimizing the velocity/force manipulability of the coordinated remote redundant manipulators during the task execution. Following the leader-follower paradigm, the control connects a local haptic device with a leader remote manipulator and coordinates all the leader and follower remote manipulators. The approach is novel in reconciling the potential conflicts between the pose synchronization task and the manipulability optimization task for the remote manipulators by two-layer auxiliary systems. The first layer decouples the pose synchronization constraints into separable position and orientation constraints, and the second layer optimizes the manipulability under the position and orientation constraints. The approach is robust by designing smooth controls for the manipulators without knowing their dynamic parameters. Finally, the control renders the bilateral teleoperator output strictly passive for stable physical interactions with the human user and the environment. Comparative experiments verify the effectiveness of the proposed control in the presence of time-varying communication delays.

During the inspection and maintenance of the underwater part of hydraulic structures, it is often necessary to clean the surface of a certain area for subsequent operations. At present, there are still few robots capable of underwater fine cleaning. Therefore, this letter introduces the design of a novel tracked robot system that can be used for underwater fine surface cleaning operations. The robot uses a crawling track chassis and is equipped with a self-designed high-precision operating robotic arm, force-controlled grippers, and underwater brushing tools. Considering the complexity of the underwater environment, an underwater force-position hybrid control algorithm suitable for the robot is proposed, taking into account the water flow resistance. Its effectiveness has been verified in the experimental pool and the proposed robot system has been applied in the actual engineering site. The robot achieves a brushing efficiency of approximately 72 m(2) per hour, with a force control accuracy of +/- 0.5 N, and the cleaning effect shows a significant improvement when compared to the condition before cleaning.

This article presents a passivity-based shared control for a multirobot teleoperation system to perform extravehicular assembly tasks. At the remote site, an eye-in-hand camera is integrated with three manipulators that cooperatively drive a customized tool. A haptic device at the local site allows a human operator to intervene when necessary via bilateral teleoperation. To enable intuitive user control, a homography-based method seamlessly integrates visual servoing and operator input to guide the remote camera. To accommodate different peg geometries and enable adaptive tool actuation, a partial pose synchronization method decouples roll from the other pose dimensions. It allows each manipulator to independently actuate a gripper by rotating its end-effector frame around the roll axis, without interfering with cooperative motion in position, pitch, and yaw. In addition, to minimize undesired internal forces, we formulate and solve a passivity-constrained interaction wrench optimization problem that enhances stability. The proposed control ensures smooth transitions between autonomous and teleoperated modes, supporting flexible human intervention. Theoretical analysis and experimental validation confirm the system’s stability and effectiveness in achieving precise, robust, and responsive multirobot teleoperation for complex space assembly tasks.

An aerial manipulator (AM) system for thickness measurement of metal facilities is introduced in this article, which includes a fully actuated flying platform and an end effector. The AM utilizes the fully actuated advantage of the flying platform to apply controlled contact forces to the environment without the need for complex robotic manipulators. An end effector is designed, which includes an ultrasonic thickness (UT) probe mounted on a spring-damping buffer, and a coupling agent injection device allows the coupling to be applied during the inspection process. We divide the aerial inspection process into two phases: the approach phase and the contact phase. In the approach phase, we design a yaw control assistance method to ensure that the AM can contact the target surface with the desired yaw, even outside the operator's line of sight. In the contact phase, a parallel force/velocity controller tailored to the motion characteristic of the AM is proposed to achieve precise contact force control. A switching function is designed to ensure stable transitions between the motion control and force control. The control effectiveness and the ability to measure the thickness of the metal facility of the AM system are demonstrated by practical experiments.

The condition of bridge piers is crucial for ensuring vehicle safety. Automated tools have been increasingly utilized for bridge pier repair in recent years. These pieces of equipment have resulted in improving worker safety, reducing maintenance costs, and enhancing overhaul efficiency. Nevertheless, there is no viable alternative to manual techniques in an underwater setting. This research proposes the use of an octagon-rack-type climbing robot (OCRobot) for the maintenance of concrete bridge piers. The robot is designed to operate both above water and underwater, with a running speed of 0.01 m/s and a maximum carrying capacity of 10 kg. The carbon fiber octagonal frame of the robot provides both strength and lightweight construction, allowing for efficient water flow distribution. The servo driving module enables the robot to operate underwater up to 100 m deep, and the electric linear actuator module allows the robot to adapt to circular piers with diameters ranging from 800 to 1300 mm. In addition, a proportional-integral (PI) parameter adaptive controller, utilizing reinforcement learning (RL), is proposed to effectively manage the robot's tension force as it hovers on the piers in order to tackle many kinds of the nonlinear interference. The capacity of OCRobot to adapt its orientation during climbing is eventually assessed in an experimental pool using a circular cross-section concrete pier simulator. The robot efficiently conducts a comprehensive assessment of the entire pier using four sets of underwater cameras that cover its entire circumference. OCRobot's remarkable durability and efficiency make it a highly promising instrument for the maintenance of underwater bridge structures, particularly in the examination of piers.

The safety and stability of bridge piers, which are a crucial element of bridge structures, are of utmost significance due to the rapid advancement in bridge construction. Nevertheless, the intricate and imperceptible nature of the underwater environment makes inspecting the underwater section of bridge piers a challenging task. This study presents the development of a C2f-HG attention-depthwise separable convolution network (CADNet) for accurate identification and evaluation of defects in the underwater structure of bridge piers. The primary components of CADNet's infrastructure are the CADblocks and an SPPF module, which possess the capability of conducting multilevel and deep feature learning. The CADNet is employed in the advanced crawling robot for bridge pier inspection to enable the automated analysis and processing of high-definition underwater images. The advanced bridge pier inspection crawling robot uses the CADNet to automate the analysis and processing of high-definition underwater photos of bridge piers. The system can precisely detect cracks and spalling, effectively separating them from the complicated background. This provides inspectors with clear and easily understandable detection data. In the segmentation and detection tasks, CADNet achieved precision of 79.8% and 77.2% and recall of 78.7% and 76.6%, respectively. The use of the suggested underwater defect instance segmentation technique in the developed bridge pier inspection crawling robot holds significant practical importance and promising application potential.

Robotic manipulators are nowadays widely used in various underwater scenarios, but their motion control remains a challenging task due to hydrodynamic effects. This article proposes a novel adaptive fuzzy sliding mode control (AFSMC) strategy for precise and robust control of underwater manipulators. To simulate the movement of the robotic manipulators in the underwater environment, the Unified Robot Description Format (URDF) file of a custom-designed electric underwater manipulator is imported into the Simscape Multibody and the hydrodynamic disturbance is modeled according to Morison's equation. Furthermore, the proposed control strategy takes advantage of the universal approximation capability of fuzzy systems to avoid chattering and observe disturbances by adjusting the control gains of classical sliding mode control (CSMC). And adaptive laws are designed to update the parameters of the fuzzy systems. The strong friction caused by the seal is also compensated by actual test data. In the simulation experiments, a special environment of water flow and variable loads is considered. The results demonstrate that the AFSMC strategy can achieve high precision and strong robustness against disturbances for trajectory tracking. More importantly, the chattering caused by CSMC can be eliminated and the hydrodynamic disturbance can be estimated with high precision through the proposed control strategy.

Underwater manipulators are essential for the inspection and maintenance of underwater structures, requiring both compliance and safe intervention. Thus, we have developed a novel lightweight underwater manipulator based on ROS2 to safely interact with underwater environments. Firstly, the new underwater manipulator is designed with 6-DoF, equipped with a 6-axis F/ T sensor, binocular camera, and various end-effectors. Then, a ROS2-based control system is implemented for robot admittance control, underwater image acquisition, and teleoperation. Underwater experiments on automated contact and teleoperated contact with the environment were conducted in a laboratory pool. The novel underwater manipulator, employing admittance control and teleoperation methods, demonstrates its effectiveness and facilitates reliable intervention during underwater structure inspection and maintenance.