Types Of Robots Research Articles

A Data-Driven Approach for Online Path Correction of Industrial Robots Using Modified Flexible Dynamics Model and Disturbance State Observer

The typical industrial robots, though highly repeatable, have relatively low path accuracy. As the main source of the path deviations, joint flexibility-induced position errors between motor and link called joint position errors (JPEs) are difficult to compensate directly in the robot controller due to the lack of link-side encoders for most industrial robots. This limits the development of industrial robots to high-accuracy applications greatly. To solve this problem, this article presents a data-driven approach for online path correction of industrial robots. The proposed approach combines a novel link state estimator designed based on a modified flexible dynamics model called flexible-dynamics-based disturbance state observer with a locally weighted projection regression-based JPE prediction scheme to provide the accurate JPE estimation to the robot controller for direct compensation. Simulations and experiments, obtained on a six-axis industrial robot, demonstrate the feasibility and effectiveness of the proposed approach. Experimental results show significant improvement (>80%) in the path accuracy of a standard circular motion corrected using the proposed approach.

Robot Learning Incorporating Human Interventions in the Real World for Autonomous Surgical Endoscopic Camera Control

Recent studies in surgical robotics have focused on automating common surgical subtasks such as grasping and manipulation using deep reinforcement learning (DRL). In this work, we consider surgical endoscopic camera control for object tracking e.g. using the endoscopic camera manipulator (ECM) from the da Vinci Research Kit (dVRK) (Intuitive Inc., Sunnyvale, CA, USA) as a typical surgical robot learning task. A DRL policy for controlling the robot joint space movements is first trained in a simulation environment and then continues the learning in the real world. To speed up training and avoid significant failures (in this case, losing view of the object), human interventions are incorporated into the training process and regular DRL is combined with generative adversarial imitation learning (GAIL) to encourage imitating human behaviors. Experiments show that an average reward of 159.8 can be achieved within 1000 steps compared to only 121.8 without human interventions, and the view of the moving object is lost only twice during the training process out of 3 trials. These results show that human interventions can improve learning speed and significantly reduce failures during the training process.

Multimodal steerable earthworm-inspired soft robot based on vacuum and positive pressure powered pneumatic actuators

This article presents a multimodal steerable earthworm-inspired soft robot based on vacuum and positive pressure powered pneumatic actuators capable of crawling both inside pipelines and on planar surfaces. The optimized modular vacuum pressure-driven actuator can generate deformation and anchoring motion through a unified structure under low vacuum pressure, giving it significant speed advantages and multi-modal locomotion capabilities. Meanwhile, the positive pressure powered actuator (PPPA) enables the robot to achieve controlled multi-directional and multi-degrees-of-freedom steering, moreover, enhances the consistency of the driving mechanism. The incorporation of front-end pressure sensing enables the robot to autonomously detect and evaluate pressure, facilitating automatic obstacle avoidance through the activation of corresponding turning units of PPPA. In the process of optimizing motion parameters, the overall motion efficiency has been improved by 16.7% by improving the control law. Through adjustments and optimizations of the interval time (cycle time), the robot is able to achieve a speed of 7.16 mm s−1 during planar locomotion and 1.94 mm s−1 during in-pipe locomotion. Using the developed robot, we conducted a series of turning experiments, including surface obstacle avoidance and cross-plane crawling, which demonstrated its enhanced capability in cross-plane steering and locomotion. Its related speed indicators showcase superior overall performance compared to other developed robots of the same type.

A Novel Extensible Continuum Robot with Growing Motion Capability Inspired by Plant Growth for Path-Following in Transoral Laryngeal Surgery.

This article presents a novel extensible continuum robot (ECR) with growing motion capability for improved flexible access in transoral laryngeal procedures. The robot uses an extensible continuum joint with a staggered V-shaped notched structure as the backbone, driven by the pushing and pulling of superelastic Nitinol rods. The notched structure is optimized to achieve a wide range of extension/contraction and bending motion for the continuum joint. The successive and uniform deflection of the notches provides the continuum joint with excellent constant curvature bending characteristics. The bidirectional rod-driven approach expands the robot's extension capabilities with both pushing and pulling operations, and the superelasticity of the driving rods preserves the robot's bending performance. The ECR significantly increases motion dexterity and reachability through its variable length, which facilitates collision-free access to deep lesions by following the anatomy. To further exploit the advantages of the ECR in path-following for flexible access, a growing motion approach inspired by the plant growth process has been proposed to minimize the path deviation error. Characterization experiments are conducted to verify the performances of the proposed ECR. The extension ratio achieves up to 225.92%, and the average distal positioning error and hysteresis error values are 2.87% and 0.51% within the ±120° bending range. Compared with the typical continuum robot with a fixed length, the path-following deviation of this robot is reduced by more than 58.30%, effectively reducing the risk of collision during access. Phantom experiments validate the feasibility of the proposed concept in flexible access procedures.

Research and expectation on industrial welding robots

In the industrial producing field, the robots are gradually replacing the traditional manual works and their development is attracting more and more concern due to their great performance. The welding robot is a kind of typical industrial robot, which has been used in various fields to gradually replace the manual fields because of the advantages like high accuracy, persistent work, and fitness for complex environments. As China is transforming into the industrial powerful country, the demand for industrial welding robots is increasing. It is important to analyse the current development of welding robots. Through the analysis of the current situation of Chinas industrial welding robot industry, this article will introduce the concept of industrial welding robots, analyze the market shares of existing welding robots, summarize the key technologies and conclude the advantages and disadvantages of welding robots, to forecast the future market development of welding robots. This article may provide a reference for the development in future.

Remaining Useful Life Estimation for High Speed Industrial Robots Using an Unknown Input Observer for Feature Extraction

In industrial robots, a performance issue is backlash, which is the clearance between mating gears of its joints. Over time, backlash grows through wear and tear, causing inaccuracies in robot positioning. Current methods in backlash detection are performed in low-speed and laboratory settings, or require offline diagnostics. These methods are impractical in actual manufacturing environments, where industrial robots operate continuously at high speeds. Other methods require additional sensors unavailable in typical industrial robots. In this article, we present an online method to quantify backlash and predict the remaining useful life (RUL) in an industrial robot performing cyclic production tasks, using only standard available sensors. To achieve the robot's target position, the input torque oscillates; these oscillations grow as the backlash becomes more severe. We modeled the oscillations as an unknown input, and used an unknown input observer to estimate them and detect/quantify the backlash. Then, a health indicator (HI) is plotted over time and a failure threshold is set based on historical data. Finally, an exponential degradation model is used to predict the RUL of the robot joint. The UIO successfully detected and quantified the backlash through the HI. The degradation model gave a good estimate of the RUL with an accuracy of 20 days after 250 days of operation.

Sturdies Advanced in chatbots based on Deep learning

Chat robots have always been a hot research topic in the field of natural language processing and human-computer interaction, aiming to build models to understand human input and provide logical answers. Early chat robots were mostly based on matching or rules, but due to the lack of manual feature representation capabilities and the complexity of rules, they could not meet practical application requirements. Thanks to the rapid development of deep learning, chat robots based on convolutional neural networks have made breakthroughs in accuracy and speed in recent years. According to the different design ideas of chat robots, the existing work mainly includes two categories: retrieval type chat robots and generation type robots. Focusing on the two main frameworks mentioned above, this article introduces the latest research progress of chat robots in detail, including the basic steps, design ideas, advantages and disadvantages of representative algorithms. We also introduced common chat robot modeling data sets and evaluation indicators. Finally, we discussed the existing problems and future development directions in the field of chat robots.

RANCANG BANGUN MODUL UKUR TEKANAN PIJAK TELAPAK KAKI ROBOT HUMANOID

Maintaining balance for humanoid robots is one of the core problems to be solved. Krakatau FC as a humanoid type robot performs balancing based on error information obtained from the IMU sensor. Information from the IMU alone is considered inadequate because it ignores the contours of the robot's stepping area which greatly influences the actions that must be taken to maintain balance. The focus of this research is to create a foot pressure measurement module that is compatible with the Dynamixel communication protocol. The sensor used to measure pressure is a Force Sensitive Resistor (FSR) sensor. The test results show the module's ability to measure the pressure exerted by the robot's legs and communicate with the robot's main controller using the Dynamixel protocol. From the test, it is also known that the modules made can help the robot's mechanical calibration process based on the comparison of the pressure between the right and left soles of the feet.

The robot eyes don't have it. The presence of eyes on collaborative robots yields marginally higher user trust but lower performance

Eye gaze is a prominent feature of human social lives, but little is known on whether fitting eyes on machines makes humans trust them more. In this study we compared subjective and objective markers of human trust when collaborating with eyed and non-eyed robots of the same type. We used virtual reality scenes in which we manipulated distance and the presence of eyes on a robot's display during simple collaboration scenes. We found that while collaboration with eyed cobots resulted in slightly higher subjective trust ratings, the objective markers such as pupil size and task completion time indicated it was in fact less comfortable to collaborate with eyed robots. These findings are in line with recent suggestions that anthropomorphism may be actually a detrimental feature of collaborative robots. These findings also show the complex relationship between human objective and subjective markers of trust when collaborating with artificial agents.

Evaluation and Modification of Kinetic Gas Collision Theory as Applied to Encounter Rate Dynamics for Multi-Robot Groups and Robot Swarms

Abstract Robots encountering other robots in a group can be beneficial, e.g., to exchange information, or detrimental, e.g., obstructing one another from operating. Kinetic gas theory (KGT) provides a statistical mechanical analysis of the collision rate between molecules. KGT has been applied to model robot encounter rates but there has been some inconsistency in how it has been applied to robot groups. There is a nine order of magnitude difference in size between a typical robot and molecule, so it is not a surprise that some adjustments may need to be made when considering robots instead of molecules. This work develops a model in detail by applying KGT, articulates limitations of applying this theory to robots, highlights inconsistencies in how it has been previously applied to robots, and suggests modifications to the model. A simple numerical study is also shown to validate the model and highlight the effect of differences in the implementation. The most important gap that this research has identified is the need to collect data on the magnitude and direction distribution of robots' velocities. Robots move and behave differently than gas molecules, whose velocity magnitude follow a Boltzmann distribution. A second major result is the connection of the KGT-based model developed in this work and previous research on robot encounter rate which independently arrived at the same relationship between robot size, number of robots, and encounter rate.

Mechanical Designs for Field Undulatory Locomotion by a Wheeled Snake-Like Robot With Decoupled Neural Oscillators

In this article, we demonstrate the value of using decoupled neural oscillators in conjunction with appropriate mechanical designs for snake-like robots engaging in field locomotion. Even though our typical wheeled snake robot with decoupled neural oscillators incorporating angle joint feedback can generate consistent lateral undulation, it lacks robustness. A purely decoupled actuation strategy is not practical for field locomotion. However, the application of one-way wheels and elasticity between the modules improves robustness, allowing our robot to traverse outdoor open terrain. On the other hand, the physical form of the undulatory motion must be varied to pass through intricate narrow-field environments. The lack of neural constraints between the modules passively enables this variability and also facilitates each module independently gaining propulsion (i.e., by means of reflexive thrust via sensory feedback to the neural oscillator and one-way traction generated by one-way side rollers). The designed robot is able to engage in fast creeping motion through an environment containing randomly distributed logs. The results of the field experiments show that the specially designed mechanisms in conjunction with decoupled oscillators can enhance robustness, variability, and independent local propulsion.

Design And Development of Pneumatic Actuated Robotic Arm with Multipurpose Gripper

Grippers are attached at the end of an industrial arm robot for material handling purpose. Grippers plays a major role in all pick and place application industries. Those are connected as end effectors to realize and develop a task in an industrial work floor. Pneumatic gripper works with the principle of compressed air. The gripper is connected to a compressed air supply. When air pressure is applied on the piston, the gripper gets opened while the air gets exist from the piston it gets closed. It is possible to control the force acting on the gripper by controlling the air pressure with the help of the valve. The results from these experiments demonstrate that the master-slave attitude control can be realized by using an accelerometer and a simple analytical model of the robot arm. The trajectory control also was realized for a square trajectory by using an analytical model and a compact control system. C measured one is relatively large compared with typical robot arm. This is because by a friction that is existing in a rod-less type flexible pneumatic cylinder. The control performance can be improved by reducing the friction or by improving the control scheme. Pneumatic actuators have a number of advantages over electric motors, including strength-to-weight ratio, tunable compliance at the mechanism level, robustness, as well as price. The handling of materials and mechanisms to place of objects from lower plane to higher plane and are widely found in factories and industrial manufacturing. Pneumatic actuators have a number of advantages over electric motors, including strength-to-weight ratio, tunable compliance at the mechanism level, robustness, as well as price. The handling of materials and mechanisms to place of objects from lower plane to higher plane and are widely found in factories and industrial manufacturing.

Kinematic calibration for collaborative robots on a mobile platform using motion capture system

For modern robotic applications that go beyond the typical industrial environment, absolute accuracy is one of the key properties that make this possible. There are several approaches in the literature to improve robot accuracy for a typical industrial robot mounted on a fixed frame. In contrast, there is no method to improve robot accuracy when the robot is mounted on a mobile base, which is typical for collaborative robots. Therefore, in this work, we proposed and analyzed two approaches to improve the absolute accuracy of the robot mounted on a mobile platform using an optical measurement system. The first approach is based on geometric operations used to calculate the rotation axes of each joint. This approach identifies all rotational axes, which allows the calculation of the Denavit–Hartenberg (DH) parameters and thus the complete kinematic model, including the position and orientation errors of the robot end-effector and the robot base. The second approach to parameter estimation is based on optimization using a set of joint positions and end-effector poses to find the optimal DH parameters. Since the robot is mounted on a mobile base that is not fixed, an optical measurement system was used to dynamically and simultaneously measure the position of the robot base and the end-effector. The performance of the two proposed methods was analyzed and validated on a 7-DoF Franka Emika Panda robot mounted on a mobile platform PAL Tiago-base. The results show a significant improvement in absolute accuracy for both proposed approaches. By using the proposed approach with the optical measurement system, we can easily automate the estimation of robot kinematic parameters with the aim of improving absolute accuracy, especially in applications that require high positioning accuracy. • A geometric and numerical approach for the calibration of collaborative robots. • Sensitivity analysis for MoCap noise position measurement on DH parameter estimation. • A novel approach to map the optical base frame and robot base frame. • Statistical analysis of different methods for estimating DH parameters.

Robot Manipulation Skills Transfer for Sim-to-Real in Unstructured Environments

Robot force control that needs to be customized for the robot structure in unstructured environments with difficult-to-tune parameters guarantees robots’ compliance and safe human–robot interaction in an increasingly expanding work environment. Although reinforcement learning provides a new idea for the adaptive adjustment of these parameters, the policy often needs to be trained from scratch when used in new robotics, even in the same task. This paper proposes the episodic Natural Actor-Critic algorithm with action limits to improve robot admittance control and transfer motor skills between robots. The motion skills learned by simple simulated robots can be applied to complex real robots, reducing the difficulty of training and time consumption. The admittance control ensures the realizability and mobility of the robot’s compliance in all directions. At the same time, the reinforcement learning algorithm builds up the environment model and realizes the adaptive adjustment of the impedance parameters during the robot’s movement. In typical robot contact tasks, motor skills are trained in a robot with a simple structure in simulation and used for a robot with a complex structure in reality to perform the same task. The real robot’s performance in each task is similar to the simulated robot’s in the same environment, which verifies the method’s effectiveness.

Dynamic movement primitives based on positive and negative demonstrations

Dynamic motion primitive has been the most prevalent model-based imitation learning method in the last few decades. Gaussian mixed regression dynamic motion primitive, which draws upon the strengths of both the motion model and the probability model to cope with multiple demonstrations, is a very practical and conspicuous branch in the dynamic motion primitive family. As Gaussian mixed regression dynamic motion primitive only learns from expert demonstrations and requires full environmental information, it is incapable of handling tasks with unmodeled obstacles. Aiming at this problem, we proposed the positive and negative demonstrations-based dynamic motion primitive, for which the introduction of negative demonstrations can bring additional flexibility. Positive and negative demonstrations-based dynamic motion primitive extends Gaussian mixed regression dynamic motion primitive in three aspects. The first aspect is a new maximum log-likelihood function that balances the probabilities on positive and negative demonstrations. The second one is the positive and negative demonstrations-based expectation–maximum, which involves iteratively calculating the lower bound of a new Q-function. And the last is the application framework of data set aggregation for positive and negative demonstrations-based dynamic motion primitive to handle unmodeled obstacles. Experiments on several typical robot manipulating tasks, which include letter writing, obstacle avoidance, and grasping in a grid box, are conducted to validate the performance of positive and negative demonstrations-based dynamic motion primitive.

Two Design Proposals and Working Space Comparison for 3-CCC Type Robot with 6 Degrees of Freedom

Bu çalışmada 6 serbestlik derecesine sahip 3D3A sınıfı paralel robot yapılarından 3-CCC tipi asimetrik paralel mekanizmanın ters kinematik analizleri yapılmış ve iki adet tasarım önerisinde bulunulmuştur. Önerilen tasarımların çalışma uzayları hesaplanmıştır. Tasarımlarda D_4 tipi kısıt ile sağlanan CPAC (P: Aktif prizmatik eklem) bacak yapısı ve A_1 tipi kısıt ile sağlanan CPAC (A: Aktif dönel eklem) bacak yapısı kullanılmıştır. Ayrıca tek bir bacakta iki aktif eklem kullanılarak elde edilen CPAC (A: Aktif dönel eklem, P: Aktif prizmatik eklem) bacak yapısı da tasarımlarda kullanılmıştır. Bu robot tipi literatürde 3-CCC mekanizma olarak da geçmektedir. İlk tasarım önerisinde sabit ve hareketli platformlar kenarları silindirik eklem olan eşkenar üçgenler olacak şekilde belirlenmişlerdir. Platformlar birbirine 3 adet CCC bacak tipiyle bağlanmıştır. İkinci tasarım önerisinde XY, XZ ve YZ düzlemlerine yerleştirilmiş olan sabit silindirik eklemler ile nokta uç işlevcisine sahip olan hareketli platform, 3 adet CCC bacak tipiyle bağlanmıştır. Sabit ve haraketli platformda kullanılan silindirik eklem uzunlukları iki tasarımda da aynı tutulmuştur. Çalışma uzayları hesaplanırken uç işlevcinin ulaşabileceği sınır noktaları belirlenerek içeride kalan bölge üzerinde 5 mm aralıklarla tarama yapılmış ve ulaşılabilirliği kontrol edilmiştir. Hareketli platform önce sabit 0o tutularak sonra -30o +30o açıları arasında döndürülerek çalışma uzayları hesaplanmıştır. Elde edilen sonuçlarla, farklı tasarımlar yapılarak çalışma uzayının genişletilebildiği görülmüştür.

A Multimodal Fusion Model for Estimating Human Hand Force: Comparing surface electromyography and ultrasound signals

Biomimetic robots have received significant attention in recent years. Among them, the wearable exoskeleton, which imitates the functions of the musculoskeletal system to assist humans, is a typical biomimetic robot. Given that safe human–robot interaction plays a critical role in the successful application of wearable exoskeletons, this work studies the clinical readiness of a multimodal fusion model that estimates hand force based on the surface electromyography (sEMG) and A-mode ultrasound signals of the forearm muscles. The proposed multimodal fusion model affords the biomimetic hand exoskeleton assisting the elderly in completing daily tasks or quantitatively assessing the recovery level of poststroke patients. The suggested fusion model is called <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Optimization of Latent Representation for the Self-Attention Convolutional Neural Network</i> ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">OLR-SACNN</i> ), which utilizes a common component extraction module (CCEM) and a complementary component retention module (CCRM) to optimize latent representation of the multiple modalities. Then the optimized latent representations are fused with the self-attention mechanism. The experiments conducted on a self-collected multimodal data set verify performance of the proposed OLR-SACNN model. Specifically, compared to solely employing sEMG or A-mode ultrasound signals, the force estimation’s normalized mean-square error (NMSE) based on the multiple modalities decreases by 97.7 and 38.92%, respectively. Furthermore, the OLR-SACNN model has been used to estimate the hand force of some poststroke patients and attained the desired performance.

From Simulation to Reality: A Learning Framework for Fish-Like Robots to Perform Control Tasks

The fish-like robot is one of the typical underwater robots, which has the advantage of high maneuverability with low noise due to its bioinspired structure and biomimetic locomotion. However, it is challenging to efficiently design motion controllers for such robots to achieve satisfactory performance on specific control tasks in the real underwater environment, since the complex fluid-structure interaction exists during their swimming and exact dynamic models are absent. In this article, we propose a learning framework, incorporating a simulation system and a training methodology, to autonomously and fast train in simulation to create control policies that are capable of directly applying to a type of physical fish-like robots to perform motion control tasks. First, we construct a simulation system combining a data-driven environment and a computational fluid dynamics (CFD)-based environment, thus well balancing the simulation accuracy and the calculation speed. Second, we design a training methodology to train deep reinforcement learning (DRL)-based policies for the robot in our constructed simulation system to perform a specific control task. Then, we use two typical motion control tasks to verify our proposed framework. One is the path-following control task, which is a one-objective problem with dense rewards, while the other is the pose control task which is a two-objective problem with sparse rewards. For each task, the DRL-based control policy trained by our learning framework is directly deployed on the physical fish-like robot to perform the task in the real world. Experimental results show that the policies trained in simulation still work well in the real world, and perform even better in terms of control accuracy and stability compared with the traditional control methods, thus demonstrating the effectiveness of our learning framework.

Robot-aided Rehabilitation with SREx: A Smart Robotic Exoskeleton for Reducing Therapists' Physical Stress

<h3>Research Objectives</h3> Upper limb dysfunctions (ULD) are common following a neurological insult. Passive range of motion (PROM) exercise of the affected extremity is one of the critical components of current rehabilitation plans of care when treating these patients. Robot-aided rehabilitation is a promising technology for this and comes with the added advantage of reducing therapists' physical burden. This study describes the development of a robot-aided upper limb rehabilitation device, 7 degrees of freedom exoskeleton type robot named SREx. It also shows the preliminary testing results on healthy participants with emulated ULD patients. <h3>Design</h3> Experimental study. <h3>Setting</h3> In the BioRobotics Lab. <h3>Participants</h3> Five healthy male human subjects (age: 26-30 years) participated in this study. <h3>Interventions</h3> Healthy human subjects (n=5) wore the SREx on the lateral side of their right hands while being seated on chair. Isolated, composite joint PROM sessions containing slower, medium, and faster speed cycles. <h3>Main Outcome Measures</h3> Tests were carried out in three settings: (a) subject exerts no effort, (b) resistance to motion equivalent to patient with generalized spasticity resulting from ULD, and (c) sudden jerking/ perturbation during motion emulating real patients' muscle spasm. During all exercises human-robot interaction was measured with force-torque sensor. Collected ROM data was statistically analyzed. <h3>Results</h3> The robot was able to provide therapeutic PROM to all subjects' UL with a maximum ROM error of ∼3.6 degrees even under external perturbation of force at 6.8 lbs. The preliminary testing showed that the robot was able to provide PROM exercise without the need for physical intervention from anyone else, in an effective manner for emulated patient conditions. <h3>Conclusions</h3> The SREx can provide safe and measurable PROM exercises to healthy patients. The next step is to receive feedback from individuals suffering from ULD. <h3>Author(s) Disclosures</h3> The authors declare no conflict of interest.

GIS Partial Discharge Pattern Recognition Based on Multi-Feature Information Fusion of PRPD Image

Partial discharge (PD) pattern recognition is a critical indicator for evaluating the insulation state of gas-insulated switchgear (GIS). Aiming at the disadvantage of traditional PD pattern recognition methods, such as single feature extraction and low recognition accuracy, a pattern recognition method of PD based on multi-feature information fusion is proposed in this paper. Firstly, a recognition model based on quasi-Hausdorff distance is established according to the statistical characteristics of the phase-resolved partial discharge (PRPD) image, and then a modified convolutional neural network recognition model is established according to the image features of the PRPD image. Finally, Dempster–Shafer (D–S) evidence theory is used to fuse the two pattern recognition results and complement the advantages of the two approaches to improve the accuracy of partial discharge pattern recognition. The experimental results show that the total recognition accuracy rate of this method for four typical PD is more than 94.00%, and the recognition rate is significantly improved compared to support vector machine and normal convolution neural network. Maintaining stability in typical bipedal robots is challenging due to two main reasons.