Robot Arm Research Articles

Gaze tracking embedded collaborative robots for automated metrology and reverse engineering

Conventional geometric metrology, or three-dimensional (3D) scanning, and reverse engineering heavily rely on the experience of the operators. With an increasing need for automation, robot arms have been adopted for this task. However, due to the large variety of parts and designs, automated path planning could provide a scanning solution that may overlook the critical area, which could potentially deteriorate the scan results. This article explores the integration of collaborative robotics (cobots) with eye-tracking technology to improve the autonomous 3D scanning process. The primary objective of this study is to enhance the accuracy and efficiency of cobots in 3D scanning, particularly in the capture of functionally critical areas, and to provide a detailed description of regions with complex geometric features. The study develops a framework where the scanning path of the robot-driven scanner is partially guided by eye tracking data, that is, calibrated gaze tracking, to improve the automated 3D scanning process. This framework provides an innovative integration of human gaze movement with automatic robot path planning, providing a new way of human-autonomy teaming. Case studies are presented to present and validate the proposed framework to automatically improve the 3D point cloud collection process, specifically in areas that usually require human manual intervention to capture details.

ROBOTIC ARM DESIGNED FOR ACTIVITIES IN HAZARDOUS ENVIRONMENTS

The purpose of the project that is presented in this document is to present the idea of a robotic arm that is capable of operating in environments that present imminent damage to living organisms. Mainly , this robotic arm is designed to be easily built, maintained, operated and the possibility to be replaced partially or totally at a reasonable cost and be a reliable tool.

A robotic fish processing line enhanced by machine learning

This paper presents the design of a comprehensive automatic fish processing line utilizing machine learning algorithms. The processing line encompasses several essential steps, including fish identification by type, fish sorting by size, fish orientation based on shape, and fish cutting at the optimal chopping points. The primary objective of this design is not just automation but also maximizing economic benefits by preserving the maximum amount of fish meat during the cutting process, achieved through the application of machine learning algorithms. To accomplish these goals, we employ a combination of transfer learning and convolutional neural networks to establish criteria for actions across all stages of automatic fish processing. At the heart of the processing station is a conveyor belt equipped with numerous sensors and lenses. Positioned along this conveyor belt are two robotic arms, responsible for precise positioning and cutting operations, all guided by the machine learning algorithms. To provide a visual representation of these design concepts, we have created a 3D SolidWorks model.

Integrating machine vision in the development of automatic mounting system for massive electroplating components

Abstract The traditional industrial electroplating parts manufacturing process typically relies on manual labour to suspend them in the electroplating tank, requiring a significant amount of manual work. However, due to a shortage of manpower and frequent staff turnover, this has posed challenges to production efficiency. Therefore, this research proposes an automated mounting system by integrating machine vision technology and the development of robotic arms to replace the conventional manual suspension method. The automated mounting system initially separates individual ring-shaped electroplating components using a disk vibratory feeder. Subsequently, it utilizes a unidirectional reciprocating mechanism and infrared detection to position these electroplating components onto a backlit panel. Then, the IDS uEye XS2 autofocus camera captures images, and in conjunction with machine vision technology, rapidly determines the position, characteristics, and orientation of these ring components. Finally, through TCP communication protocol, commands for gripping points are transmitted to the robotic arm, which uses electromagnetic valves on the arm to pick up the components and suspend them onto the hanger using an optimized path. The final test results demonstrate that the automated installation system can complete 14 installation operations per minute, effectively reducing the time and cost associated with manual labour, significantly enhancing the production output of the assembly line. Therefore, this study combines machine vision technology to propose a solution for the automated installation system of large-scale electroplating components.

A shared robot control system combining augmented reality and motor imagery brain–computer interfaces with eye tracking

Objective: Brain-computer interface (BCI) control systems monitor neural activity to detect the user's intentions, enabling device control through mental imagery. Despite their potential, decoding neural activity in real-world conditions poses significant challenges, making BCIs currently impractical compared to traditional interaction methods. This study introduces a novel motor imagery (MI) BCI control strategy for operating a physically assistive robotic arm, addressing the difficulties of MI decoding from electroencephalogram (EEG) signals, which are inherently non-stationary and vary across individuals.
Approach: A proof-of-concept BCI control system was developed using commercially available hardware, integrating MI with eye tracking in an augmented reality (AR) user interface to facilitate a shared control approach. This system proposes actions based on the user's gaze, enabling selection through imagined movements. A user study was conducted to evaluate the system's usability, focusing on its effectiveness and efficiency.
Main results:Participants performed tasks that simulated everyday activities with the robotic arm, demonstrating the shared control system's feasibility and practicality in real-world scenarios. Despite low online decoding performance (mean accuracy: 0.52 9, F1: 0.29, Cohen's Kappa: 0.12), participants achieved a mean success rate of 0.83 in the final phase of the user study when given 15 minutes to complete the evaluation tasks. The success rate dropped below 0.5 when a 5-minute cutoff time was selected.
Significance: These results indicate that integrating AR and eye tracking can significantly enhance the usability of BCI systems, despite the complexities of MI-EEG decoding. While efficiency is still low, the effectiveness of our approach was verified. This suggests that BCI systems have the potential to become a viable interaction modality for everyday applications
in the future.

Effect of training method and dairy cow personality traits on adaptation to an automated milking system

Training dairy cows on the automated milking system (AMS) can improve their performance, however, the ideal training method and how their individual personality relates to training is unknown. The objectives of this study were to determine: 1) the effect of AMS training method on adaptation of primiparous cows to an AMS, 2) whether the personality of a cow affects their adaptation to the AMS, and 3) whether certain personality types adapt better based on the type of training they receive. Forty-eight primiparous Holstein dairy cows, who had not previously been milked by an AMS, were enrolled in the study at ∼85 DIM and were assessed for personality traits using a combined arena test comprised of 3 parts: a novel arena test, a novel object test, and a novel human test. Cows were allocated into 1 of 4 AMS training treatments (n = 12): control (CON; no training), environment exposure only (ENV), environment and AMS concentrate provision (PEL), and environment and mechanics exposure (MEC). Cows in the ENV, PEL, and MEC treatments were subjected to training 4 × /d for 4 d, and then cows from all 4 treatments were milked on the AMS in the evening of the 4th training d. Milking activity and production were recorded for the first 14 d on the AMS. PEL cows had fewer visits to the AMS, fewer milkings, and fewer voluntary milkings compared with CON cows across the 14 d. Cows on all experimental treatments had more fetching events than CON cows, while MEC and ENV treatment cows had a higher milk yield compared with those on the CON treatment. Principal component analysis of the behaviors recorded during the personality assessment revealed 2 factors interpreted as personality traits, "explore-active" and "bold." Across all cows, more "explore-active" cows had greater milk yield. Only the performance of ENV cows was associated with personality; ENV cows who scored low for "explore-active" differed from CON cows, through increased visits and voluntary milkings. Overall, the results demonstrate that providing concentrate on its own during AMS training may not be motivating enough to improve adaptation and performance. However, exposing cows to the mechanics (e.g., the robotic arm and sounds of the AMS) before first milking may improve milk yield. Finally, cow personality may influence the performance of cows trained using less complicated training methods, such as only exposing them to the environment of the AMS.

A flexible proximity-pressure–temperature tri-mode robotic sensor with stimulus discriminability, high sensitivity and wide perception range

Along with the explosive utilization of intelligent and bionic robotics, the rise of somatosensory system with excellent flexibility and multiple biological sensing characteristic emerges as a substantial crux of this domain. Herein, we propose a flexible high-performance multi-mode sensor for real-time proximity–pressure–temperature perception based on a monolithic sensing unit with fingerprint-like hierarchical architecture. The monolithic sensing unit, primarily constituted by a double-permeable ionic liquids/Multi-walled nanotubes conductive network, demonstrates dual-functionality in detecting pressure and temperature. Making use of the further synergy of rational topographical architecture engineering and feasible decoupling algorithm construction, extraordinary progress in sensing performances for both pressure and temperature are attained with negligible mutual interferences. Additionally, the sensor is capable of switching to touchless mode to detect objects at distance up to 200 mm, validating its remarkable proximity sensing ability. The multifunctional nature of sensor is further substantiated through its integration with a robotic hand, highlighting its practical applicability in advanced robotic systems.

Bio-inspired e-skin with integrated antifouling and comfortable wearing for self-powered motion monitoring and ultra-long-range human-machine interaction

Electronic skin (e-skin) inspired by the sensory function of the skin demonstrates broad application prospects in health, medicine, and human–machine interaction. Herein, we developed a self-powered all-fiber bio-inspired e-skin (AFBI E-skin) that integrated functions of antifouling, antibacterial properties, biocompatibility and breathability. AFBI E-skin was composed of three layers of electrospun nanofibrous films. The superhydrophobic outer layer Poly(vinylidene fluoride)-silica nanofibrous films (PVDF-SiO2 NFs) possessed antifouling properties against common liquids in daily life and resisted bacterial adhesion. The polyaniline nanofibrous films (PANI NFs) were used as the electrode layer, and it had strong “static” antibacterial capability. Meanwhile, the inner layer Polylactic acid nanofibrous films (PLA NFs) served as a biocompatible substrate. Based on the triboelectric nanogenerator principle, AFBI E-skin not only enabled self-powered sensing but also utilized the generated electrical stimulation for “dynamic” antibacterial. The “dynamic-static” synergistic antibacterial strategy greatly enhanced the antibacterial effect. AFBI E-skin could be used for self-powered motion monitoring to obtain a stable signal output even when water was splashed on its surface. Finally, based on AFBI E-skin, we constructed an ultra-long-range human-machine interaction control system, enabling synchronized hand gestures between human hand and robotic hand in any internet-covered area worldwide theoretically. AFBI E-skin exhibited vast application potential in fields like smart wearable electronics and intelligent robotics.

Consumer Attention to a Coffee Brewing Robot: An Eye‐Tracking Study

ABSTRACTDuring the COVID‐19, robots were increasingly utilized in the food service industry. This study compared perceptions of robot and human baristas by tracking participants' eye‐gaze behavior. Seventy participants viewed videos and images of both baristas, and their eye movements were tracked. Metrics such as entry time, dwell time, total fixation, hit ratio, revisits, revisitors, average fixation, first fixation, and fixation count in defined areas of interest (AOIs) were measured. Participants focused mostly on robot's body during coffee preparation and human barista's face. Attention stayed on the coffee with human baristas, while robot stimuli drew focus to the robot's hand and kettle. Participants fixated more on the robot itself, potentially due to its novelty in coffee preparation. This study can provide directions for the development of robots, including their appearance, so that they could be accepted familiarly by consumers and introduced seamlessly in the food industries.

Pain neuroscience education and therapeutic exercise for the treatment of sequelae in breast cancer survivors living with chronic pain: A pilot study

BackgroundBreast cancer represents the most common type of malignant neoplasm worldwide. Advances in diagnosis and treatment have increased the life expectancy of patients. However, the sequelae associated with the treatment of the disease such as chronic pain, kinesiophobia and loss of physical function in breast cancer survivors (BCS) are a long-term health problem. Therapeutic strategies are required for the treatment of chronic sequelae in this population. ObjectivesTo evaluate the effectiveness of a pain neuroscience education (PNE) and therapeutic exercise (TE) for the treatment of chronic sequelae in BCS. MethodsQuasi-experimental repeated measures study. The intervention lasted 9 weeks, with 3 educational and 24 exercise sessions. Pain frequency and intensity (VAS scale), neuropathic pain (DN4), kinesiophobia level (TSK-11V), central sensitization (CSI-Sp), functionality of the affected arm (ULFI-Sp) and active joint range (ROM) with goniometry were measured at baseline, 3rd, 6th and 9th week. Statistical analysis included Friedman's test and ANOVA according to normality criteria. ResultsA total sample of 26 BCS participate in the study. Significant statistical changes were found from the 3rd week of treatment in the frequency and intensity of pain, kinesiophobia and neuropathic pain (p < 0.05). All variables had significant changes at the 9th week (p = 0.001). ConclusionThe results of the present investigation suggest that the combination of PNE and TE are effective in treating sequelae at short term in BCS with chronic pain.

Robots in the kitchen: The automation of food preparation in restaurants and the compounding effects of perceived love and disgust on consumer evaluations

Restaurants are swiftly embracing automation to prepare food, experimenting with innovations from robotic arms for frying foods to pizza-making robots. While these advances promise to enhance efficiency and productivity, their impact on consumer psychology remains largely unexplored. We present four experiments that demonstrate how food service automation leads to negative downstream effects (i.e., diminished taste perceptions, decreased willingness to pay, less favorable attitudes towards food items) across multiple food categories. This stems in part from two distinct contagion effects, whereby automation appears to undermine the food’s ability to contain symbolic love (positive contagion from human contact) while simultaneously increasing feelings of disgust (negative contagion from machine contact). Moreover, we highlight how communicating the consumer-oriented benefits of automation can suppress the disgust associated with automation and subsequently mitigate the deleterious effects on consumer evaluations. Our findings suggest that service retailers should consider the psychological impact on consumers when shifting away from human involvement in a category as intimate and consequential as the production of our food.

Chinese Bayberry Detection in an Orchard Environment Based on an Improved YOLOv7-Tiny Model

The precise detection of Chinese bayberry locations using object detection technology is a crucial step to achieve unmanned harvesting of these berries. Because of the small size and easy occlusion of bayberry fruit, the existing detection algorithms have low recognition accuracy for such objects. In order to realize the fast and accurate recognition of bayberry in fruit trees, and then guide the robotic arm to carry out accurate fruit harvesting, this paper proposes a detection algorithm based on an improved YOLOv7-tiny model. The model introduces partial convolution (PConv), a SimAM attention mechanism and SIoU into YOLOv7-tiny, which enables the model to improve the feature extraction capability of the target without adding extra parameters. Experimental results on a self-built Chinese bayberry dataset demonstrate that the improved algorithm achieved a recall rate of 97.6% and a model size of only 9.0 MB. Meanwhile, the precision of the improved model is 88.1%, which is 26%, 2.7%, 4.7%, 6.5%, and 4.7% higher than that of Faster R-CNN, YOLOv3-tiny, YOLOv5-m, YOLOv6-n, and YOLOv7-tiny, respectively. In addition, the proposed model was tested under natural conditions with the five models mentioned above, and the results showed that the proposed model can more effectively reduce the rates of misdetections and omissions in bayberry recognition. Finally, the improved algorithm was deployed on a mobile harvesting robot for field harvesting experiments, and the practicability of the algorithm was further verified.

Pre-clinical training, technical adjustment and human case experience of transoral robotic surgery using Versius System

ObjectiveThis study describes the training experience with the Versius Robotic System (CMR Surgical) for Transoral Robotic Surgery (TORS), the setup of the robot and its applicability in a human case. MethodsA model mannequin with anatomical characteristics simulating the TORS working space was used for training purposes. Optimal docking, positioning of robotic arms and placement of instruments were defined using the mannequin. A human patient was selected based on the inclusion criteria, and a standardized protocol for robotic techniques was developed. The surgical procedure was conducted in accordance with ethical guidelines. ResultsThe synthetic polymer mannequin mimicking human tissues and anatomy was used to define the robot set up for TORS. The patient was indicated for bilateral tonsillectomy due to recurrent episodes of tonsillitis. Bipolar Maryland and monopolar scissors were used. The procedure was uneventful. The patient remained hospitalized for 1 day and returned to work activities within 6-days, with no complications. ConclusionThe specialized mannequin proved to be effective in the simulation, training proposal and set up standardization. Furthermore, the Versius robot was found to be safe and achieved excellent results during surgery. Despite being very promising, the Versius system is still in its developmental phase and requires larger-scale samples for a more comprehensive evaluation. Level of evidence4.

Collision Localization for a Robotic Arm Based on Fiber-Optic Sensing and Machine Learning

Collision Localization for a Robotic Arm Based on Fiber-Optic Sensing and Machine Learning

Reliability Centered Modeling of an Automated Waste Sorting Robotic Arm System

In contemporary society, proper waste management is a critical issue that needs to be addressed. Waste management encompasses the collection, transportation, segregation and disposal of waste material to minimize health risks and environment impact. Manual segregation, along with other methods of waste segregation, is often inefficient and time consuming. To address this challenge, numerous industries have embraced automation in waste sorting to expedite the process through advanced technological interventions. Therefore, the optimal functioning of the components of these automated systems is crucial for rapid and accurate segregation of waste. This work is oriented toward the study of a system which is used to segregation of waste and known as waste sorting robotic arm system (WSRAS). Author used Markov decision process, along with mathematical modeling, to evaluate the different performance measure of WSRAS. Sensitivity analysis have also been done to understand the contribution of different components failure in overall performance of WSRAS.

Open Wide for This Robot Arm

Open Wide for This Robot Arm

Maximizing Date Palm Yield: Automatic Extension Sprinklers for Enhanced Aerial Pollination

Abstract Date palms require pollen transfer from male to female palms in order to yield a fruitful harvest. The traditional method of accomplishing this artificial cross-pollination involved climbing each palm tree and physically putting male flower spikelets on female inflorescences. This process required a great deal of labor and was time-consuming. Due to developments in farming practices during the modern age, farmers have experimented with mechanical pollination systems. Recently, to pollinate date palms very quickly, safely, affordably, and with a minimum of risk of injury, agricultural drones have been used. In this research, experiments on drone dispersal pollination are conducted on three Omani date palm cultivars—Al Naghal, Al Khanezi, and Al Kasab. The applicability of this method is evaluated by comparing its fruit yield properties to those of the conventional method, which is commonly employed, and the less popular machine/hand pollination methods. The main limitations of drone dispersal pollination are, its inability to disperse exact amount of pollen to the target location of female inflorescences, especially in shorter palms; wastage of pollens and environmental pollution. The study recommends the use of a novel design of extendable pollen sprinkler for target-specific pollination in order to increase pollination efficiency and decrease DPP waste. The designed system comprises of a robotic arm extension with a remotely controlled sprayer mounted on a computer vision android device; that can shoot themselves out to the female flowers and disperse the required amount of pollens in the specific location. This unique spraying mechanism can overcome the drawbacks of aerial pollination and increase its effectiveness.

Real-Time Home Automation System Using BCI Technology.

A Brain-Computer Interface (BCI) processes and converts brain signals to provide commands to output devices to carry out certain tasks. The main purpose of BCIs is to replace or restore the missing or damaged functions of disabled people, including in neuromuscular disorders like Amyotrophic Lateral Sclerosis (ALS), cerebral palsy, stroke, or spinal cord injury. Hence, a BCI does not use neuromuscular output pathways; it bypasses traditional neuromuscular pathways by directly interpreting brain signals to command devices. Scientists have used several techniques like electroencephalography (EEG) and intracortical and electrocorticographic (ECoG) techniques to collect brain signals that are used to control robotic arms, prosthetics, wheelchairs, and several other devices. A non-invasive method of EEG is used for collecting and monitoring the signals of the brain. Implementing EEG-based BCI technology in home automation systems may facilitate a wide range of tasks for people with disabilities. It is important to assist and empower individuals with paralysis to engage with existing home automation systems and gadgets in this particular situation. This paper proposes a home security system to control a door and a light using an EEG-based BCI. The system prototype consists of the EMOTIV Insight™ headset, Raspberry Pi 4, a servo motor to open/close the door, and an LED. The system can be very helpful for disabled people, including arm amputees who cannot close or open doors or use a remote control to turn on or turn off lights. The system includes an application made in Flutter to receive notifications on a smartphone related to the status of the door and the LEDs. The disabled person can control the door as well as the LED using his/her brain signals detected by the EMOTIV Insight™ headset.

An experimental study of ultrasonic-knife cutting for a woven carbon fiber preform by an industrial robot

This study investigates the effect of the cutting process parameters on the cutting forces and the quality parameters of a woven carbon fiber preform during robotic ultrasonic-knife cutting. An ultrasonic cutting device, with a power of 1200 W, a frequency of 24 kHz, and an amplitude of 60 µm, mounted on the end effector of a six-axis degree of freedom industrial robot to make linear cuts. A three-level factorial experimental design was used to examine the effect of the feed rate (1 m/min to 5 m/min) and the knife’s attack angle (45° to 75°) on the cutting forces, the dimensional accuracy of the machined preform coupons, and the damage on the machined preform edges. The cutting force analysis results show that the increasing feed rate resulted in increasing feed force and thrust force. However, the increase of the attack angle increases the feed force but decreases the thrust force. The average width and damage of the ultrasonic knife cut preform coupons are highly related to the process conditions. The combination of the low feed rate, 1 m/min, and the low attack angle, 45°, resulted in dimensional errors ranging from 253 μm to 365 μm oversized from the programmed 15.0 mm width with no damage. When the feed became 3 m/min and 5 m/min at the attack angle of 75°, the preform coupons’ dimensional accuracy and damage formation worsened. In these conditions, the ultrasonic knife attached to the industrial robot arm could not cut the preform plate effectively, so the tows on the preform were unevenly cut or dislodged.

“Together with who?” Recognizing partners during Collaborative Avatar Manipulation

The development of novel computer interfaces has led to the possibility of integrating inputs from multiple individuals into a single avatar, fostering collaboration by combining skills and sharing the cognitive load. However, the collaboration dynamic and its effectiveness may vary depending on the individuals involved. Particularly in scenarios where two individuals remotely control a robotic avatar without the possibility of direct communication, understanding each other’s characteristics can result in enhanced performance. To achieve this, it is essential to ascertain if individuals can discern their partner’s characteristics within merged embodiment. This paper investigates the accuracy with which participants can distinguish between two different collaborating partners (one attempting to lead and one attempting to follow) when sharing control of a robot arm during a block pick-and-place task. The results suggested that participants who changed their role according to the different roles of the two partners achieved the highest discrimination rates. Furthermore, participants changed their movements through the trials, adapting their actions to their preferred approach. This research provides insights into the factors determining individuals’ ability to understand partner characteristics during control of collaborative avatar.