Search results

The patient-side manipulator (PSM) achieves high torque capability by combining harmonic servo system with high reduction ratio and low torque motor. However, high reduction ratio can increase inertia and decrease compliance of the manipulator. To enhance the backdrivability of the minimally invasive surgical robot, this paper aims to propose a resistance torque compensation algorithm.

A resistance torque compensation algorithm based on dynamics and Luenberger observer is proposed. The dynamics are established, considering joint flexibility and an improved Stribeck friction model. The dynamic parameters are experimentally identified by using the least squares method. With the advantages of clear structure, simple implementation and fast solution speed, the Luenberger observer is selected to estimate the unmeasured dynamic information of PSM and realize the resistance torque compensation.

For low-speed surgical robots, the centrifugal force term in the dynamic model can be simplified to reduce computational complexity. Joint flexibility and an improved Stribeck friction model can be considered to improve the accuracy of the dynamic model. Experiment results show that parameter identification and estimated results of the Luenberger observer are accurate. The backdrivability of the PSM is enhanced in ease and smoothness.

This algorithm provides potential application prospects for surgical robots to maintain high torque while remaining compliant. Meanwhile, the enhanced backdrivability of the manipulator helps to improve the safety of the preoperative manual adjustment.

The purpose of this paper is to introduce a variable distance pneumatic gripper with embedded flexible sensors, which can effectively grasp fragile and flexible objects.

Based on the motion principle of the three-jaw chuck and the pneumatic “fast pneumatic network” (FPN), a variable distance pneumatic holder embedded with a flexible sensor is designed. A structural design plan and preparation process of a soft driver is proposed, using carbon nanotubes as filler in a polyurethane (PU) sponge. A flexible bending sensor based on carbon nanotube materials was produced. A static model of the soft driver cavity was established, and a bending simulation was performed. Based on the designed variable distance soft pneumatic gripper, a real-time monitoring and control system was developed. Combined with the developed pneumatic control system, gripping experiments on objects of different shapes and easily deformable and fragile objects were conducted.

In this paper, a variable-distance pneumatic gripper embedded with a flexible sensor was designed, and a control system for real-time monitoring and multi-terminal input was developed. Combined with the developed pneumatic control system, a measure was carried out to measure the relationship between the bending angle, output force and air pressure of the soft driver. Flexible bending sensor performance test. The gripper diameter and gripping weight were tested, and the maximum gripping diameter was determined to be 182 mm, the maximum gripping weight was approximately 900 g and the average measurement error of the bending sensor was 5.91%. Objects of different shapes and easily deformable and fragile objects were tested.

Based on the motion principle of the three-jaw chuck and the pneumatic FPN, a variable distance pneumatic gripper with embedded flexible sensors is proposed by using the method of layered and step-by-step preparation. The authors studied the gripper structure design, simulation analysis, prototype preparation, control system construction and experimental testing. The results show that the designed flexible pneumatic gripper with variable distance can grasp common objects.

This research paper aims to optimize the calibration process for an ABB IRB 120 robot, specifically for robotic orbital milling applications, by introducing and validating the use of the observability index and telescopic ballbar for accuracy enhancement.

The study uses the telescopic ballbar and an observability index for the calibration of an ABB IRB 120 robot, focusing on robotic orbital milling. Comparative simulation analysis selects the O₃ index. Experimental tests, both static and dynamic, evaluate the proposed calibration approach within the robot’s workspace.

The proposed calibration approach significantly reduces circularity errors, particularly in robotic orbital milling, showcasing effectiveness in both static and dynamic modes at various tool center point speeds.

The study focuses on a specific robot model and application (robotic orbital milling), limiting generalizability. Further research could explore diverse robot models and applications.

The findings offer practical benefits by enhancing the accuracy of robotic systems, particularly in precision tasks like orbital milling, providing a valuable calibration method.

While primarily technological, improved robotic precision can have social implications, potentially influencing fields where robotic applications are crucial, such as manufacturing and automation.

This study’s distinctiveness lies in advancing the accuracy and precision of industrial robots during circular motions, specifically tailored for orbital milling applications. The innovative approach synergistically uses the observability index and telescopic ballbar to achieve these objectives.

The purpose of this paper aims to investigate the adaptive impedance control and its optimized PSO algorithm for force tracking of a dual-arm cooperative robot. Because the dual-arm robot is directly in contact with external environment, controlling the mutual force between robot and external environment is of great importance. Besides, a high compliance of the robot should be guaranteed.

An impedance control based on Particle Swarm Optimization (PSO) algorithm is designed to track the mutual force and achieve compliance control of the robot end.

The experimental results show that the impedance control coefficients can be automatically tuned converged by PSO algorithm.

The system can reach a steady state within 0.03 s with overshoot convergence, and the force fluctuation range at the steady state decreases to about ±0.08 N even under the force mutation condition.

Proper platform pose is important for the mobile manipulator to accomplish dexterous manipulation tasks efficiently and safely, and the evaluation criterion to qualify manipulation performance is critical to support the pose decision process. This paper aims to present a comprehensive index to evaluate the manipulator’s operation performance from various aspects.

In this research, a criterion called hybrid manipulability (HM) is proposed to assess the performance of the manipulator’s operation, considering crucial factors such as joint limits, obstacle avoidance and stability. The determination of the optimal platform pose is achieved by selecting the pose that maximizes the HM within the feasible inverse reachability map associated with the target object.

A self-built mobile manipulator is adopted as the experimental platform, and the feasibility of the proposed method is experimentally verified in the context of object-grasping tasks both in simulation and practice.

The proposed HM extends upon the conventional notion of manipulability by incorporating additional factors, including the manipulator’s joint limits, the obstacle avoidance situation during the operation and the manipulation stability when grasping the target object. The manipulator can achieve enhanced stability during grasping when positioned in the pose determined by the HM.

This paper aims to present a novel lightweight distribution grid operating robot system with focus on lightweight and multi-functionality, aiming for autonomous and live-line maintenance operations.

A ground-up redesign of the dual-arm robotic system with 12-DoF is applied for substantial weight reduction; a dual-mode operating control framework is proposed, with vision-guided autonomous operation embedded with real-time manual teleoperation controlling both manipulators simultaneously; a quick-swap tooling system is developed to conduct multi-functional operation tasks. A prototype robotic system is constructed and validated in a series of operational experiments in an emulated environment both indoors and outdoors.

The overall weight of the system is successfully brought down to under 150 kg, making it suitable for the majority of vehicle-mounted aerial work platforms, and it can be flexibly and quickly deployed in population dense areas with narrow streets. The system equips with two dexterous robotic manipulators and up to six interchangeable tools, and a vision system for AI-based autonomous operations. A quick-change tooling system ensures the robot to change tools on-the-go without human intervention.

The resulting dual-arm robotic live-line operation system robotic system could be compact and lightweight enough to be deployed on a wide range of available aerial working platforms with high mobility and efficiency. The robot could both conduct routine operation tasks fully autonomously without human direct operation and be manually operated when required. The quick-swap tooling system enables lightweight and durable interchangeability of multiple end-effector tools, enabling future expansion of operating capabilities across different tasks and operating scenarios.

The purpose of this paper is to present a wall-climbing robot platform for heavy-load with negative pressure adsorption, which could be equipped with a six-degree of freedom (DOF) collaborative robot (Cobot) and detection device for inspecting the overwater part of concrete bridge towers/piers for large bridges.

By analyzing the shortcomings of existing wall-climbing robots in detecting concrete structures, a wall-climbing mobile manipulator (WCMM), which could be compatible with various detection devices, is proposed for detecting the concrete towers/piers of the Hong Kong-Zhuhai-Macao Bridge. The factors affecting the load capacity are obtained by analyzing the antislip and antioverturning conditions of the wall-climbing robot platform on the wall surface. Design strategies for each part of the structure of the wall-climbing robot are provided based on the influencing factors. By deriving the equivalent adsorption force equation, analyzed the influencing factors of equivalent adsorption force and provided schemes that could enhance the load capacity of the wall-climbing robot.

The adsorption test verifies the maximum negative pressure that the fan module could provide to the adsorption chamber. The load capacity test verifies it is feasible to achieve the expected bearing requirements of the wall-climbing robot. The motion tests prove that the developed climbing robot vehicle could move freely on the surface of the concrete structure after being equipped with a six-DOF Cobot.

The development of the heavy-load wall-climbing robot enables the Cobot to be installed and equipped on the wall-climbing robot, forming the WCMM, making them compatible with carrying various devices and expanding the application of the wall-climbing robot.

A heavy-load wall-climbing robot using negative pressure adsorption has been developed. The wall-climbing robot platform could carry a six-DOF Cobot, making it compatible with various detection devices for the inspection of concrete structures of large bridges. The WCMM could be expanded to detect the concretes with similar structures. The research and development process of the heavy-load wall-climbing robot could inspire the design of other negative-pressure wall-climbing robots.

The current difficulties of distribution network working robots are mainly in the performance and operation mode. On the one hand, high-altitude power operation tasks require high load-carrying capacity and dexterity of the robot; on the other hand, the fully autonomous mode is uncontrollable and the teleoperation mode has a high failure rate. Therefore, this study aims to design a distribution network operation robot named Sky-Worker to solve the above two problems.

The heterogeneous arms of Sky-Worker are driven by hydraulics and electric motors to solve the contradiction between high load-carrying capacity and high flexibility. A human–robot collaborative shared control architecture is built to realize real-time human intervention during autonomous operation, and control weights are dynamically assigned based on energy optimization.

Simulations and tests show that Sky-Worker has good dexterity while having a high load capacity. Based on Sky-Worker, multiuser tests and practical application experiments show that the designed shared-control mode effectively improves the success rate and efficiency of operations compared with other current operation modes.

The designed heterogeneous dual-arm distribution robot aims to better serve distribution line operation tasks.

For the first time, the integration of hydraulic and motor drives into a distribution network operation robot has achieved better overall performance. A human–robot cooperative shared control framework is proposed for remote live-line working robots, which provides better operation results than other current operation modes.

This paper aim to solve the problem of low assembly success rate for 3c assembly lines designed based on classical control algorithms due to inevitable random disturbances and other factors,by incorporating intelligent algorithms into the assembly line, the assembly process can be extended to uncertain assembly scenarios.

This work proposes a reinforcement learning framework based on digital twins. First, the authors used Unity3D to build a simulation environment that matches the real scene and achieved data synchronization between the real environment and the simulation environment through the robot operating system. Then, the authors trained the reinforcement learning model in the simulation environment. Finally, by creating a digital twin environment, the authors transferred the skill learned from the simulation to the real environment and achieved stable algorithm deployment in real-world scenarios.

In this work, the authors have completed the transfer of skill-learning algorithms from virtual to real environments by establishing a digital twin environment. On the one hand, the experiment proves the progressiveness of the algorithm and the feasibility of the application of digital twins in reinforcement learning transfer. On the other hand, the experimental results also provide reference for the application of digital twins in 3C assembly scenarios.

In this work, the authors designed a new encoder structure in the simulation environment to encode image information, which improved the model’s perception of the environment. At the same time, the authors used the fixed strategy combined with the reinforcement learning strategy to learn skills, which improved the rate of convergence and stability of skills learning. Finally, the authors transferred the learned skills to the physical platform through digital twin technology and realized the safe operation of the flexible printed circuit assembly task.

Limited by the types of sensors, the state information available for musculoskeletal robots with highly redundant, nonlinear muscles is often incomplete, which makes the control face a bottleneck problem. The aim of this paper is to design a method to improve the motion performance of musculoskeletal robots in partially observable scenarios, and to leverage the ontology knowledge to enhance the algorithm’s adaptability to musculoskeletal robots that have undergone changes.

A memory and attention-based reinforcement learning method is proposed for musculoskeletal robots with prior knowledge of muscle synergies. First, to deal with partially observed states available to musculoskeletal robots, a memory and attention-based network architecture is proposed for inferring more sufficient and intrinsic states. Second, inspired by muscle synergy hypothesis in neuroscience, prior knowledge of a musculoskeletal robot’s muscle synergies is embedded in network structure and reward shaping.

Based on systematic validation, it is found that the proposed method demonstrates superiority over the traditional twin delayed deep deterministic policy gradients (TD3) algorithm. A musculoskeletal robot with highly redundant, nonlinear muscles is adopted to implement goal-directed tasks. In the case of 21-dimensional states, the learning efficiency and accuracy are significantly improved compared with the traditional TD3 algorithm; in the case of 13-dimensional states without velocities and information from the end effector, the traditional TD3 is unable to complete the reaching tasks, while the proposed method breaks through this bottleneck problem.

In this paper, a novel memory and attention-based reinforcement learning method with prior knowledge of muscle synergies is proposed for musculoskeletal robots to deal with partially observable scenarios. Compared with the existing methods, the proposed method effectively improves the performance. Furthermore, this paper promotes the fusion of neuroscience and robotics.