Robot Manipulator Research Articles

Multi-receptor skin with highly sensitive tele-perception somatosensory.

The limitations and complexity of traditional noncontact sensors in terms of sensitivity and threshold settings pose great challenges to extend the traditional five human senses. Here, we propose tele-perception to enhance human perception and cognition beyond these conventional noncontact sensors. Our bionic multi-receptor skin employs structured doping of inorganic nanoparticles to enhance the local electric field, coupled with advanced deep learning algorithms, achieving a ΔV/Δd sensitivity of 14.2, surpassing benchmarks. This enables precise remote control of surveillance systems and robotic manipulators. Our long short-term memory-based adaptive pulse identification achieves 99.56% accuracy in material identification with accelerated processing speeds. In addition, we demonstrate the feasibility of using a two-dimensional (2D) sensor matrix to integrate real object scan data into a convolutional neural network to accurately discriminate the shape and material of 3D objects. This promises transformative advances in human-computer interaction and neuromorphic computing.

Adaptive fast terminal sliding mode control of robotic manipulators based on joint torque estimation and friction compensation

Adaptive fast terminal sliding mode control of robotic manipulators based on joint torque estimation and friction compensation

Perineal-First Approach in Robotic Abdominoperineal Resection.

Although abdominoperineal resection (APR) is required for rectal cancer invading the levator ani muscle, its curative outcomes remain poorer than those of other rectal surgeries.1-3 In particular, the anatomic complexity around the anterior wall of the rectum increases the technical difficulty during APR, resulting in a high frequency of margin involvement that causes local recurrence. In this video, we present the technical details of a robotic perineal-first APR approach. For a 46year-old man, locally advanced rectal cancer invading the levator ani muscles was diagnosed. Although total neoadjuvant therapy (8 cycles of induction FOLFOXIRI followed by chemoradiotherapy 50.4 Gy) decreased the tumor size, invasion was suspected still to remain. Therefore, robotic APR was performed. Written informed consent was obtained from the patient. For the perineal-first approach, we created a circular incision around the anus, then divided the fat tissues of the ischiorectal fossa until the levator ani muscle was exposed on both sides. Posterior and anterior dissections were performed along the coccyx and external anal sphincter, respectively. After placement of a lap protector to maintain air-tightness, the robotic approach was initiated. Posterior dissection was performed along the coccyx, then was connected to the already-dissected space created earlier by the perineal approach. Next, the levator ani muscle was divided from the dorsal to the lateral side. Finally, anterior dissection was performed along the prostate, followed by division of the rectourethral muscle, the smooth muscle fibers running vertically. The creation of the already-dissected space on the perineal side offers advantages of robotic manipulation from the abdominal side, especially anterior dissection. We performed robotic APR using the perineal-first approach for 17 consecutive patients (12 men and 5 women) between 2019 and 2023. All 17 patients achieved complete total mesorectal excision with negative margins. The mean time required for the perineal approach was about 25 min. In anterior dissection using the robotic approach, division of the smooth muscle fibers at the perineal body (i.e., rectourethral muscle in males4 or muscular intermingling in females5) was reproducibly performed in both males and females. Robotic APR with a perineal-first approach can be advantageous in ensuring surgical margin safety (especially for the anterior aspect of the rectum).

Design and development of a flexible-rigid Triglide sorting manipulator

Flexible manipulators have been widely applied in various tasks involving grasping and manipulation, and their unique characteristics in terms of lightweight design and adaptability make them particularly suitable for tackling complex spatial pick-and-place operations. In this work, a Triglide flexible manipulator is presented and developed, based on the parallel Biglide mechanism and dual leaf springs in parallelogram structure, which features adjustable stiffness by changing the transverse configuration of the leaf springs. To analyze the deflections of the leaf springs efficiently, a segmented approach is deployed, to calculate large deflection within the plane of the leaf-springs parallelogram structure. The adopted approach uses classical bending deformation formulas from mechanics of materials. Consequently, the static models of the manipulator are derived for analyzing bending deformation and workspace by means of numerical calculations. Finite element analysis is adopted to investigate the mechanical characteristics of the manipulator. A prototype of the variable stiffness manipulator is built, and an experimental setup is established for static testing. The obtained results align with the previously observed mechanical characteristics. The main advantages of the flexible robotic manipulator lie in its simple structure, small footprint, and simple kinematic model for control.

Triboelectric and iontronic dual-responsive bioinspired ionic skin for human–like dexterous robotic manipulation

Powerful tactile perception is keystone for robots to achieve human-like dexterous manipulation. However, endowing robots with tactile perception capabilities that approach or even surpass those of humans is a challenge. Organisms can perceive complex environments rapidly, and almost all perception is related to the directional transport of ions. Inspired by this mechanism, we design a flexible dual-responsive skin (FDRS) based on ions migration for proximity and tactile somatosensation, which is consisting of single-electrode triboelectric nanogenerator and iontronic sensor, achieving surpassing-skin capabilities. The single-electrode triboelectric nanogenerator can encode the proximity information of approaching targets into a series of voltage pulses with fast response time (100 μs). The iontronic tactile unit based on the hierarchical micro-hemispherical gel layer achieves high linearity (R2 = 0.998) over a broad range of 0–700 kPa. We demonstrate the applications of FDRS for three-dimensional object recognition and robotic control. These capabilities of the multilayer integrated FDRS provide new perspectives for the future development of human-like dexterous robotic manipulation.

Spring-reinforced pneumatic actuator and soft robotic applications

Abstract Compared to rigid-structure robots, soft robots possess higher degrees of freedom and stronger environmental adaptability, which has aroused increasing attention in the robotic field. Among them, soft pneumatic robots have excellent performances in various practical applications. However, the nonlinearity and instability of pressure response of soft actuators caused by lateral expansion come to a great challenge. To address this problem, we proposed to embed a spring constraint layer around each single air chamber. Following the design concept, we obtained single-cavity and multi-DoF pneumatic actuators and evaluated their elongation and bending characteristics. Experimental results demonstrated that our proposed actuators have more linear pressure response as well as higher consistency. Eventually, through robotic applications, including soft robotic hand and gripper our proposed actuators could facilitate flexible manipulation and elaborate performance.

Multifunctional Magnetic Muscles for Soft Robotics

Despite recent advancements, artificial muscles have not yet been able to strike the right balance between exceptional mechanical properties and dexterous actuation abilities that are found in biological systems. Here, we present an artificial magnetic muscle that exhibits multiple remarkable mechanical properties and demonstrates comprehensive actuating performance, surpassing those of biological muscles. This artificial muscle utilizes a composite configuration, integrating a phase-change polymer and ferromagnetic particles, enabling active control over mechanical properties and complex actuating motions through remote laser heating and magnetic field manipulation. Consequently, the magnetic composite muscle can dynamically adjust its stiffness as needed, achieving a switching ratio exceeding 2.7 × 10³. This remarkable adaptability facilitates substantial load-bearing capacity, with specific load capacities of up to 1000 and 3690 for tensile and compressive stresses, respectively. Moreover, it demonstrates reversible extension, contraction, bending, and twisting, with stretchability exceeding 800%. We leverage these distinctive attributes to showcase the versatility of this composite muscle as a soft continuum robotic manipulator. It adeptly executes various programmable responses and performs complex tasks while minimizing mechanical vibrations. Furthermore, we demonstrate that this composite muscle excels across multiple mechanical and actuation aspects compared to existing actuators.

A Multifunctional Tactile Sensory System for Robotic Intelligent Identification and Manipulation Perception.

Humans recognize and manipulate objects relying on the multidimensional force features captured by the tactile sense of skin during the manipulation. Since the current sensors integrated in robots cannot support the robots to sense the multiple interaction states between manipulator and objects, achieving human-like perception and analytical capabilities remains a major challenge for service robots. Prompted by the tactile perception involved in robots performing complex tasks, a multimodal tactile sensory system is presented to provide in situ simultaneous sensing for robots when approaching, touching, and manipulating objects. The system comprises a capacitive sensor owning the high sensitivity of 1.11E-2pFmm-1, a triboelectricity nanogenerator with the fast response speed of 30ms, and a pressure sensor array capable of 3D force detection. By Combining transfer learning models, which fuses multimodal tactile information to achieve high-precision (up to 95%) recognition of the multi-featured targets such as random hardness and texture information under random sampling conditions, including random grasp force and velocity. This sensory system is expected to enhance the intelligent recognition and behavior-planning capabilities of autonomous robots when performing complex tasks in undefined surrounding environments.

Calibration of rotary axis angular positioning deviations in a six-axis robotic manipulator by using the R-Test

Prediction accuracy of the kinematic model plays a pivotal role in offline numerical compensation for three-dimensional (3D) positioning error of a six-axis robotic manipulator. In addition to the Denavit-Hartenberg (D-H) error that was typically discussed in the analogous research, this paper proposes a novel scheme to identify the bidirectional angular positioning deviations of all the rotary axes without using the commercial laser tracker. This proposed scheme employs the R-Test, which is significantly more cost-efficient than a laser tracker employed in many past works. Compared to the conventional D-H model, significantly improved prediction performance of the proposed model was experimentally investigated on three rectangular paths covering the entire workspace. Experimental results indicate that the proposed scheme reduces the residual error from 505.2 to 215.2 mm, compared to 118.8 mm with a laser tracker, while maintaining a significantly lower cost that is 1/100 of a commercial laser tracker. Uncertainty analysis also clarify that when only the D-H error parameters are identified, as in many conventional works, the angular positioning deviations can be a major uncertainty contributor to the identification of the D-H errors. The proposed scheme does not require the R-Test locations to be calibrated, and its influence on the uncertainty in the identified errors is assessed.

Novel Design and Performance Analysis of 1R1T Remote Center-of-Motion Mechanisms With Partially Decoupled T- and R-Motions

Abstract Remote center-of-motion (RCM) mechanisms provide a way for surgical instruments to pass through a remote center (e.g., skin incision) under geometrical constraints, facilitating safer operations in minimally invasive surgery (MIS). One rotation and one translation (1R1T, pitch and insertion) are the basic requirements for RCM mechanisms. To make the structure simpler and control easier, a novel concept of 1R1T RCM mechanisms with partially decoupled motions, inspired by the double-parallelogram 1R RCM mechanisms, is proposed in this article, by investigating and proving its motion combination principle based on the screw theory. New evolution procedures based on the configuration evolution method have been derived to design 1R1T RCM mechanisms based on two approaches of inserting the T-motion in an original 1R RCM mechanism, resulting in two types of 1R1T RCM mechanisms with partially decoupled motions and base-locating actuators. The kinematic models of one typical proposed mechanism (including the forward and inverse kinematics) and its Jacobian matrix are derived. The performance analysis is presented, including RCM validation, velocity, singularity, and workspace analysis. Then, the dimensional optimization based on the discrete solution method is derived. Finally, a prototype of the proposed mechanism is presented with preliminary experiments performed to verify the feasibility of the synthesized RCM mechanisms. The results show that the RCM mechanism performs the 1R1T partially decoupled motion, and it can be used as the basic element of an active manipulator of an MIS robot.

Large area kidney imaging for pre-transplant evaluation using real-time robotic optical coherence tomography

Optical coherence tomography (OCT) can be used to image microstructures of human kidneys. However, current OCT probes exhibit inadequate field-of-view, leading to potentially biased kidney assessment. Here we present a robotic OCT system where the probe is integrated to a robot manipulator, enabling wider area (covers an area of 106.39 mm by 37.70 mm) spatially-resolved imaging. Our system comprehensively scans the kidney surface at the optimal altitude with preoperative path planning and OCT image-based feedback control scheme. It further parameterizes and visualizes microstructures of large area. We verified the system positioning accuracy on a phantom as 0.0762 ± 0.0727 mm and showed the clinical feasibility by scanning ex vivo kidneys. The parameterization reveals vasculatures beneath the kidney surface. Quantification on the proximal convoluted tubule of a human kidney yields clinical-relevant information. The system promises to assess kidney viability for transplantation after collecting a vast amount of whole-organ parameterization and patient outcomes data.

Trajectory tracking control based on deep reinforcement learning and ensemble random network distillation for robotic manipulator

Abstract In general, the trajectory tracking of robotic manipulator is exceptionally challenging due to the complex and strongly coupled mechanical architecture. In this paper, precise track control of the robotic manipulator is formulated as a dense reward problem for reinforcement learning(RL). A deep RL(DRL) approach combining the soft actor-critic (SAC) algorithm and ensemble random network distillation (ERND) is proposed to address the tracking control problem for robotic manipulator. Firstly, an ERND model is designed, consisting of a module list of multiple RND models. Each RND model obtains the error by learning the target features and the predicted features of the environment. The resulting error serves as internal rewards that drive the robotic agent to explore unknown and unpredictable environmental states. The ensemble model obtains the total internal reward by summing the internal rewards of each RND model, thereby obtaining more accurately reflecting the characteristics of the manipulator in tracking control tasks and improving control performance. Secondly, combining the SAC algorithm with ERND facilitates more robust exploration capabilities in environments with input saturation and joint angle constraints, thereby enabling faster learning of effective policies and enhancing the performance and efficiency of robotic manipulator tracking control tasks. Finally, the simulation results demonstrate that the robotic manipulator tracking control task is effectively completed in dense reward problems through the combination of the SAC algorithm and ERND.

A Policy Searched-Based Optimization Algorithm for Obstacle Avoidance in Robot Manipulators

A Policy Searched-Based Optimization Algorithm for Obstacle Avoidance in Robot Manipulators

Protein folding, protein dynamics and the topology of self-motions.

It has long been recognized that segments of the protein main chain are like robotic manipulators and inverse kinematics methods from robotics have been applied to model loops to bridge gaps in protein comparative modelling. The complex internal motion of a redundant manipulator with fixed ends is called a self-motion and its character is determined by the relative position of its ends. Self-motions that are topologically equivalent (homotopic) occupy the same continous region of the configuration space. Topologically inequivalent (non-homotopic) regions are separated by co-regular surfaces and crossing a co-regular surface can result in a sudden dramatic change in the character of the self-motion. It is shown, using a five-residue type I β-turn, that these concepts apply to protein segments and that as the ends of the five-residue segment come closer together, a co-regular surface is crossed, and the structure is locked in to becoming either a type I or type I' turn. It is also shown that the type II turn is topologically equivalent to the type I' turn, not the type I turn. These results have implications for both native-state protein dynamics and protein folding.

An FPGA-Implemented Antinoise Fuzzy Recurrent Neural Network for Motion Planning of Redundant Robot Manipulators.

When a robot completes end-effector tasks, internal error noises always exist. To resist internal error noises of robots, a novel fuzzy recurrent neural network (FRNN) is proposed, designed, and implemented on field-programmable gated array (FPGA). The implementation is pipeline-based, which guarantees the order of overall operations. The data processing is based on across-clock domain, which is beneficial for computing units' acceleration. Compared with traditional gradient-based neural networks (NNs) and zeroing neural networks (ZNNs), the proposed FRNN has faster convergence rate and higher correctness. Practical experiments on a 3 degree-of-freedom (DOs) planar robot manipulator show that the proposed fuzzy RNN coprocessor needs 496 lookup table random access memories (LUTRAMs), 205.5 block random access memories (BRAMs), 41384 lookup tables (LUTs), and 16743 flip-flops (FFs) of the Xilinx XCZU9EG chip.

The Distributed Adaptive Bipartite Consensus Tracking Control of Networked Euler–Lagrange Systems with an Application to Quadrotor Drone Groups

Actuator faults and external disturbances, which are inevitable due to material fatigue, operational wear and tear, and unforeseen environmental impacts, cause significant threats to the control reliability and performance of networked systems. Therefore, this paper primarily focuses on the distributed adaptive bipartite consensus tracking control problem of networked Euler–Lagrange systems (ELSs) subject to actuator faults and external disturbances. A robust distributed control scheme is developed by combining the adaptive distributed observer and neural-network-based tracking controller. On the one hand, a new positive definite diagonal matrix associated with an asymmetric Laplacian matrix is constructed in the distributed observer, which can be used to estimate the leader’s information. On the other hand, neural networks are adopted to approximate the lumped uncertainties composed of unknown matrices and external disturbances in the follower model. The adaptive update laws are designed for the unknown parameters in neural networks and the actuator fault factors to ensure the boundedness of estimation errors. Finally, the proposed control scheme’s effectiveness is validated through numerical simulations using two types of typical ELS models: two-link robot manipulators and quadrotor drones. The simulation results demonstrate the robustness and reliability of the proposed control approach in the presence of actuator faults and external disturbances.

Path signatures for diversity in probabilistic trajectory optimisation

Motion planning can be cast as a trajectory optimisation problem where a cost is minimised as a function of the trajectory being generated. In complex environments with several obstacles and complicated geometry, this optimisation problem is usually difficult to solve and prone to local minima. However, recent advancements in computing hardware allow for parallel trajectory optimisation where multiple solutions are obtained simultaneously, each initialised from a different starting point. Unfortunately, without a strategy preventing two solutions to collapse on each other, naive parallel optimisation can suffer from mode collapse diminishing the efficiency of the approach and the likelihood of finding a global solution. In this paper, we leverage on recent advances in the theory of rough paths to devise an algorithm for parallel trajectory optimisation that promotes diversity over the range of solutions, therefore avoiding mode collapses and achieving better global properties. Our approach builds on path signatures and Hilbert space representations of trajectories and connects parallel variational inference for trajectory estimation with diversity-promoting kernels. We empirically demonstrate that this strategy achieves lower average costs than competing alternatives on a range of problems, from 2D navigation to robotic manipulators operating in cluttered environments.

Multi-scale deep learning and clustering-based tabletop object instance segmentation for robot manipulation

3D object instance segmentation plays a vital role in various applications such as autonomous driving, robotics and virtual reality. However, tabletop scenes exhibit diverse object complexities and size variations. The challenge is to enhance the accuracy of segmenting these scenes for multiple object instances. This limitation directly impacts robots’ capabilities to effectively grasp and manipulate objects. In this paper, we propose a multi-scale deep learning and clustering-based approach for object instance segmentation in tabletop scenes. Our approach incorporates a multi-scale neighborhood feature sampling (MNFS) module specifically designed to extract local features, and a clustering algorithm to eliminate noise and preserve instance integrity. Furthermore, we combine the strength of both methods through ScoreNet and non-maximal suppression. We conducted extensive experiments on TO-Scene, the first large-scale dataset of 3D tabletop scenes, and observed an average mIoU improvement of approximately 4.07% compared to existing methods. This highlights the superior performance of our proposed method. In addition, we tested our algorithm on a real-scene robotics platform and showed that it has good performance and generalization capabilities to support future applications such as robot grasping.

Inverse kinematics of six degrees of freedom robot manipulator based on improved dung beetle optimizer algorithm

Inverse kinematics is a basic problem in robotics, which aims to solve the robot’s joint angles according to the end effector’s position and orientation. This paper proposed an improved spiral search multi-strategy dung beetle optimizer (DBO) algorithm for solving the inverse kinematics problem. The improved DBO algorithm considers not only the error between the target value and the current value but also the previous position of the robot to ensure minimum displacement during the movement. To solve the end position error and orientation error of the robot end effector more accurately, the quaternion is introduced as a penalty factor in the optimization objective function, which is of great significance for reducing the orientation error. Through the improved DBO algorithm, the position error is still accurate, and the orientation error is reduced from 9.5901 to 1.8718. Experimental results show that the proposed algorithm outperforms other swarm-intelligent algorithms in terms of accuracy and convergence speed. Overall, the proposed spiral search multi-strategy DBO algorithm provides an effective and efficient solution to the inverse kinematics problem in robotics.

A compliant and strong robotic manipulator that looks and works like an elephant trunk

A compliant and strong robotic manipulator that looks and works like an elephant trunk