Robot Arm Research Articles

Augmented Bodily Self in Performing a Button-Touching Task with Soft Supernumerary Robotic Arms

Extra or supernumerary robotic limbs are actively exploited in the field of body augmentation. The science of self-recognition of additional body parts is an interesting subject. Although the field is primarily led by psychological studies in virtual reality, which facilitate flexible experimental designs, we believe that assessments employing real robots are also essential. In this study, we investigated the sense of body ownership and agency of a dual-arm wearable robotic arm using an inexpensive and safe inflatable structure. We report the results of functional near-infrared spectroscopy (fNIRS) analysis of brain activity during the use of the robotic arm. The questionnaire results from the experiment, which involved a button-touching task, revealed that both the sense of ownership and sense of agency were significantly higher in the goal-oriented collaborative experience compared to the non-goal-oriented condition. This indicates that humans feel ownership of and agency toward an autonomous robot or a remote-controlled robotic arm operated by another person. The analysis of the fNIRS data included a two-factor analysis of variance for the learning and trial phases. While there was no main effect for the conditions within each phase, a significant interaction was observed between the two brain regions of the right angular gyrus and right postcentral gyrus.

Motion Planning for Dynamic Three-Dimensional Manipulation for Unknown Flexible Linear Object

Generally, deformable objects have large and nonlinear deformations. Because of these characteristics, recognition and estimation of their movement are difficult. Many studies have been conducted aimed at manipulating deformable objects at will. However, they have been focused on situations wherein a rope’s properties are already known from prior experiments. In our previous work, we proposed a motion planning algorithm to manipulate unknown ropes using a robot arm. Our approach considered three steps: motion generation, manipulation, and parameter estimation. By repeating these three steps, a parameterized flexible linear object model that can express the actual rope movements was estimated, and manipulation was realized. However, our previous work was limited to 2D space manipulation. In this paper, we extend our previously proposed method to address casting manipulation in a 3D space. Casting manipulation involves targeting the flexible linear object tips at the desired object. While our previous studies focused solely on two-dimensional manipulation, this work examines the applicability of the same approach in 3D space. Moreover, 3D manipulation using an unknown flexible linear object has never been reported for dynamic manipulation with flexible linear objects. In this work, we show that our proposed method can be used for 3D manipulation.

Sense of Embodiment Supports Motor Learning and Adaptation in Tele-robotics

In this paper, we transition from the theoretical and experimental groundwork of manipulating and measuring Sense of Embodiment (SoE) to addressing a fundamental question: What is the purpose of optimizing the SoE in a teleoperation system? This exploration centers on investigating the potential positive effects of SoE on motor adaptation, the acceleration of motor learning, and the potential enhancement of task performance. The paper delves into this investigation by focusing on two critical research questions: 1) what is the effect of SoE on task performance in a perceptual-motor task? 2) What is the effect of SoE on the asymptote of the learning curve in a perceptual-motor task? Drawing insights from the existing literature, the hypothesis emerges that enhancing SoE yields positive effects, not only on task performance (H1) but also on the overall embodiment experience (H2). An additional layer of exploration is introduced through an exploratory research question: Are these results consistent across diverse scenarios and tasks? The study design encompasses two distinct user studies, each set in different applications and featuring various avatars, yet all anchored in similar tasks, specifically a modified peg-in-hole task: 1) in the first experiment, participants operated a robotic arm with a human-like hand as end-effector, and they were required to perform a classic peg-in-hole task; 2) in user study 2, the task is transformed into a variation that we called “peg-on-button”, wherein participants use a robotic arm with a gripper as the end-effector to press a lit button. In both studies, a consistent pattern emerges: a setup that fosters embodiment has a positive impact on motor learning and adaptation, resulting in improved task performance. A supportive setup also reduces the perception of the surrogate as a mere mediator between the operator and the remote environment, especially when contrasted with a setup that suppresses embodiment. The positive effects on motor learning and task performance advocate for the incorporation of embodiment-supportive designs in teleoperational setups. However, the nuanced relationship between SoE and long-term task performance prompts a call for further exploration and consideration of various factors influencing teleoperation outcomes across diverse scenarios and tasks.

End-to-end stereo matching network with two-stage partition filtering for full-resolution depth estimation and precise localization of kiwifruit for robotic harvesting

Full-resolution depth estimation within operational space of robotic arms and accurate localization of kiwifruits is very important for automated harvesting. Depth estimation is expected to be accurate and full-resolution while current depth estimation methods are susceptible to depth missing due to occlusion and uneven illumination. And depth estimation mostly focuses on fruit localization, while obstacles such as branches and wires, which can affect harvesting strategy, have not been considered. This paper localized kiwifruits based on bounding boxes output by YOLOv8m and full-resolution depth from an end-to-end stereo matching network, i.e., LaC-Gwc Net, which was trained after generating a stereo matching dataset by proposing a two-stage partition filtering algorithm. Results showed that LaC-Gwc Net achieved an end-point error (EPE) of 3.8 pixels, which means that accurate depth estimation can also be achieved for thin obstacles such as the branches and the wires. Additionally, YOLOv8m obtained acceptable results in detecting kiwifruits and their calyxes, reaching mean average precision (mAP) of 93.1% and detection speed of 7.0 ms. The methodology obtained only kiwifruit localization error of 4.0 mm on the Z-axis, which meets requirements of robotic harvesting. Furthermore, this study considered the localization of obstacles in kiwifruit orchards, providing high-precision full-resolution depth estimation for agricultural harvesting robots.

Robotic Resection of Spinal and Paraspinal Tumors.

Robotic arm surgical systems provide minimally invasive access and are commonly used in multiple surgical fields, with limited application in neurosurgery. Our institutional experience has led us to explore the benefits of a neurosurgeon trained to perform robotic surgery as part of a multidisciplinary team. The objective of this study is to evaluate the feasibility, safety, and outcomes of robotic resection for spinal nerve sheath tumors (NST). Retrospective case series of robotic-assisted intracavitary approaches and resection of NSTs including thoracic, retroperitoneal, and transperitoneal. Surgical outcomes are compared to a historical cohort of open surgical resection of NSTs. Nineteen cases presented, of which 2 were combined posterior spinal followed by robotic tumor resection. One of 19 cases was converted to an open surgery. Gross total resection was achieved in all cases. There were 2 cases of postoperative Horner's syndrome, and 1 case with an intraoperative durotomy that was repaired primarily with no postoperative sequelae. Median estimated blood loss was 50 cc (range: 5-650) and median length of stay was 1 day (range: 0-6), with 9 (47.4%) patients discharged on postoperative day 1 and 3 (15.8%) patients discharged on an outpatient basis. Compared with our previously reported institutional outcomes for open resection of 25 tumors, there was a significant increase in rates of gross total resection (100 vs 60%, P = .002) and decrease in length of stay (median 1 vs 5 days, P < .0001). Robotic resection of complex paraspinal tumors appears safe and effective including for preservation of neurological function and may reduce surgical morbidity. Integration of robotic surgical platforms holds the potential to significantly affect neurological surgery.

Comparative Analysis of Structure and Motion of Vision Logistics Robotic Arms

This paper combines visual recognition and robotic arm, optimizes the design of robotic arm structure, and researches the logistics robotic arm with six degrees of freedom and visual perception ability to enrich the logistics robotic use scene. Firstly, the visual recognition system is installed on the existing six-degree-of-freedom robotic arm, and the coordinate system is established by the light bar recognition method combined with the D-H parameter method. Secondly, a kinematic simulation model was established by using MATLAB, and the state of the joints was analyzed by using forward and inverse kinematic simulation and fifth degree polynomial interpolation. Finally, the actual logistics fixed-point transportation task is designed for trajectory planning. The results show that the robotic arm is able to be able to perform different grasping tasks in non-structural environments, around the visual analysis of the robotic arm as well as the optimization of the motion track, to enhance the efficiency of the comprehensive use of visual and tactile information, to improve the adaptability of the robotic hand grasping, and to be able to meet the precise control of the pick-up process and the use of the realization of the payload grasping and dexterous movement. The research in this paper provides a certain reference value for the propulsion robot arm to perform intelligent grasping tasks.

Designing and Creating a Palletizing Robot Conbined with Image Processing

In this paper, we propose a solution of designing and building a three-order 4D magician robot arm to palletize goods. Inverse kinematic of system is calculated. Thence, we design a suitable robot arm which can utilizing camera to palletizing goods. PID controller is used to move operating point. Simulation and experimental results are shown to prove the well operation of this robot arm.

Soft Fibrous Syringe Architecture for Electricity-Free and Motorless Control of Flexible Robotic Systems.

Flexible robotic systems (FRSs) and wearable user interfaces (WUIs) have been widely used in medical fields, offering lower infection risk and shorter recovery, and supporting amiable human-machine interactions (HMIs). Recently, soft electric, thermal, magnetic, and fluidic actuators with enhanced safety and compliance have innovatively boosted the use of FRSs and WUIs across many sectors. Among them, soft hydraulic actuators offer great speed, low noise, and high force density. However, they currently require bulky electric motors/pumps, pistons, valves, rigid accessories, and complex controllers, which inherently result in high cost, low adaptation, and complex setups. This paper introduces a novel soft fibrous syringe architecture (SFSA) consisting of two or more hydraulically connected soft artificial muscles that enable electricity-free actuation, motorless control, and built-in sensing ability for use in FRSs and WUIs. Its capabilities are experimentally demonstrated with various robotic applications including teleoperated flexible catheters, cable-driven continuum robotic arms, and WUIs. In addition, its sensing abilities to detect passive and active touch, surface texture, and object stiffness are also proven. These excellent results demonstrate a high feasibility of using a current-free and motor-less control approach for the FRSs and WUIs, enabling new methods of sensing and actuation across the robotic field.

Brain-inspired biomimetic robot control: a review.

Complex robotic systems, such as humanoid robot hands, soft robots, and walking robots, pose a challenging control problem due to their high dimensionality and heavy non-linearities. Conventional model-based feedback controllers demonstrate robustness and stability but struggle to cope with the escalating system design and tuning complexity accompanying larger dimensions. In contrast, data-driven methods such as artificial neural networks excel at representing high-dimensional data but lack robustness, generalization, and real-time adaptiveness. In response to these challenges, researchers are directing their focus to biological paradigms, drawing inspiration from the remarkable control capabilities inherent in the human body. This has motivated the exploration of new control methods aimed at closely emulating the motor functions of the brain given the current insights in neuroscience. Recent investigation into these Brain-Inspired control techniques have yielded promising results, notably in tasks involving trajectory tracking and robot locomotion. This paper presents a comprehensive review of the foremost trends in biomimetic brain-inspired control methods to tackle the intricacies associated with controlling complex robotic systems.

U-TAG: Electromagnetic Wireless Sensing System for Robotic Hand Pre-Grasping.

In order to perform complex manipulation and grasp tasks, robotic hands require sensors that can handle increasingly demanding functionality and degrees of freedom. This research paper proposes a radiofrequency sensor that uses a wireless connection between a probe and a tag. A compact and low-profile antenna is mounted on the hand and functions as a probe to read a printed passive resonator on the plastic object being targeted, operating within a pre-touch sensing range. The grasping strategy consists of four stages that involve planar alignment in up-to-down and left-to-right directions between the probe and tag, the search for an appropriate distance from the object, and rotational (angular) alignment. The real and imaginary components of the probe-input impedance are analyzed for different orientation strategies and positioning between the resonator on the object and the probe. These data are used to deduce the orientation of the hand relative to the target object and to determine the optimal position for grasping.

Optimal Path Planning Algorithm with Built-In Velocity Profiling for Collaborative Robot.

This paper proposes a method for solving the path planning problem for a collaborative robot. The time-optimal, smooth, collision-free B-spline path is obtained by the application of a nature-inspired optimization algorithm. The proposed approach can be especially useful when moving items that are delicate or contain a liquid in an open container using a robotic arm. The goal of the optimization is to obtain the shortest execution time of the production cycle, taking into account the velocity, velocity and jerk limits, and the derivative continuity of the final trajectory. For this purpose, the velocity profiling algorithm for B-spline paths is proposed. The methodology has been applied to the production cycle optimization of the pick-and-place process using a collaborative robot. In comparison with point-to-point movement and the solution provided by the RRT* algorithm with the same velocity profiling to ensure the same motion limitations, the proposed path planning algorithm decreased the entire production cycle time by 11.28% and 57.5%, respectively. The obtained results have been examined in a simulation with the entire production cycle visualization. Moreover, the smoothness of the movement of the robotic arm has been validated experimentally using a robotic arm.

Microwall array tactile sensor fabricated by transferring CNT/PDMS composite material into high aspect metal mold

This paper proposes a slip sensor that assists an industrial robot to grasp an object with the minimum force required. The sensor developed in this study can detect whether an object is being pressed or sliding inside the robot hand. The developed sensor was fabricated using a custom-made metal mold, which is a block of 20 mm square and 3 mm thick with lines and spaces of 0.4 mm pitch and 2 mm depth, forming a vertical wall array (50 in total) with finely high aspect ratio of 10, i.e., the height of each wall is 2 mm and the thickness is 0.2 mm. The flexible sensor body is obtained by pouring a composite of polydimethylsiloxane (PDMS) and carbon nanotubes (CNTs) into this mold, heating it to solidify it, and then releasing it from the mold. This sensor is intended to attach to the grasping surface of a robot hand. This sensor is a resistive one, i.e., changes in the sensor's internal circuitry when the robot hand grasps an object are expressed as changes in the sensor resistance. The sensor can both estimate the pressing force and detect the object slippage, since the resistance rapidly changes when a slippage occurs. This sensor allows the robot to detect the contact state with a handling object.

P266. Level-specific pedicle screw accuracy using computer navigated robotic arm

P266. Level-specific pedicle screw accuracy using computer navigated robotic arm

Field test and evaluation of an innovative vision-guided robotic cotton harvester

Conventional cotton harvesters are efficient but heavy causing soil compaction. They normally perform one harvesting pass, but since cotton bolls mature over two months, the early opened bolls must wait for later ones to be harvested, exposing their fiber to weather and degrading fiber quality. A swarm of small, lightweight robotic cotton harvesters can address these issues. This study presents field tests and evaluations of an innovative robotic cotton harvester prototype. A stereovision camera in conjunction with the YOLOv4-tiny algorithm was used for cotton boll detection and localization. The picking system included a 3-DOF (degree of freedom) linear robotic arm, a three-finger end-effector, and an agile control algorithm. The performance rates of detection, localization, and picking systems were 78.1 %, 70.0 %, and 83.1 %, respectively, with an average cycle time of 8.8 s. Collecting cotton bolls orientation data proved that they tend to stay their faces upward causing difficulty in picking the rear part of the bolls in 40.5 % of cases. Controlling the illumination, developing more robust detection and localization systems, increasing the arm’s DOF, enhancing the end-effector’s operating speed, and its adaptability to different boll orientations can improve the robot’s performance in terms of the picking ratio of the seed cotton and speed. The dataset, including field images, annotations of cotton bolls, and the best training weights, is publicly available at: https://github.com/hussein-pasha/Robotic-Cotton-Harvester. A video demonstration of the harvester being tested in the field is available at: https://youtu.be/IztKk3E7zSc.

Trajectory Tracking of a Robot Arm Using Image Sequences

Trajectory Tracking of a Robot Arm Using Image Sequences

Design of a two‐degrees‐of‐freedom robotic arm for monitoring applications for teaching robotics and artificial intelligence technology

AbstractThis manuscript proposes a methodology for teaching undergraduate engineering students fundamental concepts of artificial intelligence and robotics applicable in Industry 4.0 using a project‐based learning strategy. A low‐cost prototype of a two‐degrees‐of‐freedom robotic arm was designed and implemented for monitoring applications, integrating the Internet of Things and artificial intelligence technology. Inverse and direct kinematics are applied in the robotic arm design, enabling the execution of desired trajectories by the robot's end effector. The robot, capable of following user‐programmed trajectories, uses two servo motors with a 180° mobility range, integrated into a 3D printed structure made from polylactic materials, whereas the programmable logic was accomplished using an ESP32 microcontroller. Furthermore, the robot is controlled through a MATLAB GUI (Graphical User Interface), designed to obtain detailed process information such as activity status, trajectory type, and quality. The results demonstrate the feasibility of integrating various cutting‐edge technologies to teach fundamental concepts of Industry 4.0. The proposed methodology could allow educators to design a robotics course where students are motivated by practical experience implementing impactful technologies beyond the academic realm.

History and trends of robot-assisted spine surgery

Spanning two decades since the 1st generation spinal robotics inception, the robot-assisted spine surgery (RSS) technology has evolved through generations, culminating in the 4th generation characterized by real-time visual navigation and wire-free screw placement. The fundamental principles of RSS technology include surgical planning, tracking, image registration, and robotic arm control technologies. Currently, RSS technology is maturely employed in thoracolumbar procedures and is progressively being applied in cervical surgeries, spinal tumor resections, and percutaneous operations, offering advantages in reducing tissue trauma and exposure to radiation, thereby improving patient outcomes. Emerging research also focuses on the cost-effectiveness of clinical applications and robot-specific complications. With the integration of artificial intelligence into surgical planning, RSS technology is poised to further incorporate emerging technologies and expand its application across a broader clinical spectrum.

Fruit flexible collecting trajectory planning based on manual skill imitation for grape harvesting robot

The flexible collection is vital for the intelligent grape-picking robot. In view of the reliable operation method obtained by long-term training of human prior skill, a fruit flexible collecting trajectory planning method based on manual skill imitation for grape harvesting robot is proposed. The method involves capturing manual teaching trajectory data using a motion capture system, preprocessing the data, extracting features from multiple teaching trajectories, and forming a probability distribution through Gaussian mixture model – Gaussian mixture regression (GMM-GMR). And combined with the key point of manual operation trajectory, the general trajectory generated by GMR is segmented and further imitated by kernelized movement primitives (KMP) to obtain the reference trajectory, respectively. An optimization method for hyperparameter adaptation KMP (O-KMP) was proposed to meet the trajectory fitting effect of multiple key points. Mean square error (MSE) was used to evaluate the deviation of the trajectory from the reference trajectory. The partial optimal trajectory is selected and integrated into a single trajectory. Two experiments were conducted to investigate imitation: For the same starting and ending points task, the MSE of the trajectory generated by O-KMP decreased by 15.274% compared to the original fixed hyperparameter KMP. For different placement tasks, the MSE of the trajectory generated by the O-KMP decreased by 7.296% compared to the original KMP. Finally, the robot arm of the actuator visually presents different task states for the compliant placement of fresh grapes.

Adversarial generative learning and timed path optimization for real-time visual image prediction to guide robot arm movements

Adversarial generative learning and timed path optimization for real-time visual image prediction to guide robot arm movements

Apple-Harvesting Robot Based on the YOLOv5-RACF Model.

To address the issue of automated apple harvesting in orchards, we propose a YOLOv5-RACF algorithm for identifying apples and calculating apple diameters. This algorithm employs the robot operating dystem (ROS) to control the robot's locomotion system, Lidar mapping, and navigation, as well as the robotic arm's posture and grasping operations, achieving automated apple harvesting and placement. The tests were conducted in an actual orchard environment. The algorithm model achieved an average apple detection accuracy (mAP@0.5) of 98.748% and a (mAP@0.5:0.95) of 90.02%. The time to calculate the diameter of one apple was 0.13 s, with a measurement accuracy within an error range of 1-3 mm. The robot takes an average of 9 s to pick an apple and return to the initial pose. These results demonstrate the system's efficiency and reliability in real agricultural environments.