Robot Prototype Research Articles

Behavioral Cloning Strategies in Steering Angle Prediction: Applications in Mobile Robotics and Autonomous Driving

Artificial neural networks (ANNs) are artificial intelligence techniques that have made autonomous driving more efficient and accurate; however, autonomous driving faces ongoing challenges in the accuracy of decision making based on the analysis of the vehicle environment. A critical task of ANNs is steering angle prediction, which is essential for safe and effective navigation of mobile robots and autonomous vehicles. In this study, to optimize steering angle prediction, NVIDIA’s architecture was adapted and modified along with the implementation of the Swish activation function to train convolutional neural networks (CNNs) by behavioral cloning. The CNN used human driving data obtained from the UDACITY beta simulator and tests in real scenarios, achieving a significant improvement in the loss function during training, indicating a higher efficiency in replicating human driving behavior. The proposed neural network was validated through implementation on a differential drive mobile robot prototype, by means of a comparative analysis of trajectories in autonomous and manual driving modes. This work not only advances the accuracy of steering angle predictions but also provides valuable information for future research and applications in mobile robotics and autonomous driving. The performance results of the model trained with the proposed CNN show improved accuracy in various operational contexts.

A repeated jumping solution based on the bistable film structure for film-structured miniature soft robots

Abstract Miniature film-structured robots achieved remarkable locomotion performance and various applications. The integration of a jumping function could empower existing film-structured terrestrial robots to conquer complex terrains. However, current repeated jumping mechanisms for miniature soft robots are often constrained to specific materials and mechanical configurations, rendering them incompatible with film-structured robots. A solution that effectively addresses these limitations remains absent in the field. This work introduces an electrically actuated solution for repeated jumping in miniature soft robots, utilizing a bistable film structure coupled with a numerical two-rod model. The bistable film structure integrates a flexible film, polydimethylsiloxane (PDMS) linear spring, and a shape memory alloy spring to achieve repeated jumping motion through snap-through buckling. The numerical model is employed to optimize the spring parameters, tailoring the structure to the specific properties of the target robot. To demonstrate the practicality of this solution, the bistable film structure is seamlessly integrated into an existing fast-steering insect robot, which previously lacks jumping capabilities. By customizing PDMS spring design based on the robot body’s dimensions and stiffness, the prototype robot, measuring 23 × 16 × 8 mm3 in size and 120 mg in weight, demonstrates repeated jumping ability with a maximum horizontal jumping distance of 11.8 cm (5.1 body lengths), a jumping height of 3.8 cm (4.7 body heights) and a jumping frequency of 0.1 Hz. The robot traverses a 43 cm-long road with half walls and trench obstacles in 41 s. This work presents the bistable film structure’s potential as a repeated jumping solution for film-structured robots, enhancing their obstacle-crossing abilities and expanding their applicability in complex environments.

Investigation of the Possibility of High-Speed Motion of a Non-Pulley Musculoskeletal Robot

Robots with parallel-link structures are generally considered useful for achieving high-speed motion; however, they are typically large in size. Robot size can be reduced by using a serial-link structure. However, their moving parts, typically having a large mass or moment of inertia, are considered unsuitable for high-speed motion. High-speed motion performance can be improved by avoiding mounting actuators on the moving parts using some method to transmit the drive force or motion. In this letter, we propose a model in which a non-pulley musculoskeletal robot, previously studied by us, is modified to avoid mounting actuators on the movable parts. We demonstrate that the robot can be controlled to achieve the target posture using this modified model. We also discuss the feasibility of high-speed motion of a prototype robot using muscular forces computed for several motion patterns based on the minimum muscle-tension change model.

Development of a Robotic Device That Performs Head Bunting to Relieve User Tension

Inspired by an animal behavior called bunting, in which the animal rubs its head against other objects, including humans, we developed robotic prototypes capable of performing such bunting behaviors. Since physical contact plays an important role in therapeutic interactions between pets and their owners, we hypothesize that robot bunting can have a similar effect on its user. This paper reports on the development of such a robot with a flexible neck that can change its stiffness while the robot is rubbing its head against the user. An exploratory study was also conducted with 22 human participants, on whom the developed robot performed head bunting with three different (low/high/variable) stiffness conditions. The results show that the participants’ psychological tension, as measured by the Temporary Mood Scale (TMS), was significantly reduced ( \(p\lt 0.001\) ) after interacting with the robot. The difference between the three stiffness conditions was not significant in this study. Due to the lack of a control condition, we cannot confirm a clear effect of the stiffness change; however, some participants commented that the stiffness change made the robot's behavior lifelike and relaxing.

RANCANG BANGUN PROTOTYPE SMART GREENHOUSE MENGGUNAKAN THINGSPEAK

The design of this smart greenhouse prototype is one of the implementations of artificial intelligence controlled by the Arduino uno microcontroller, which has actuators in the form of lights and pumps and is equipped with DHT22 sensors, Soil Moisture and Temperature Sensors. The method used in making this smart greenhouse prototype is the Prototype method. There are seven stages in the prototype method that guide the process of making robots, namely gathering requirements, building prototypes/prototypes, evaluating prototypes, programming systems, testing systems, evaluating systems, and using the system. The most important stage in making this smart greenhouse prototype is the stage where at this stage testing is carried out on the results of the design and programming of the robot that has been made to prove the robot prototype is in accordance with what is desired or not. The testing process is carried out in tandem with the assembly process and programming process. In the process of assembling and programming the robot prototype, it is done with system errors. Testing with system errors is carried out to get a robot prototype that works optimally.

Soft modular pipe robot inspired by earthworm for adaptive pipeline internal structure

Abstract The inspection, maintenance, and repair of complex pipelines have motivated the development of soft robots with highly flexible and good adaptability. In this study, inspired by the unique locomotion of earthworms, we developed a type of smart material–driven soft modular pipe robot capable of stable manipulation and performing in unstructured pipe environments, which easily assembles into more complex configurations with multiple modules for practical use. Our prototype robot consists of three soft telescopic modules connected in series with flexible bellows and a tail friction mechanism, where the modules adopt a high-energy density shape memory alloy spring as an actuator. Based on analyzing the peristaltic process of the module inside the pipe, it is ensured that the geometric constraint performance of the braided mesh pipe is reasonably matched with the thermomechanical performance of the SMA spring to realize the alternating conversion of anchoring and releasing. By optimizing the overall robotic structure, it is demonstrated that our robot achieves robust crawling in horizontal, vertical, variable-diameter, and curved pipes, wet pipes with the partial presence of water, and pipes with complex cavities through simple open-loop on/off control.

Development of a Small-Sized Urban Cable Conduit Inspection Robot

Cable conduits are crucial for urban power transmission and distribution systems. However, current conduit robots are often large and susceptible to tilting issues, which hampers the effective and intelligent inspection of these conduits. Therefore, there is an urgent need to develop a smaller-sized conduit inspection robot to address these challenges. Based on an in-depth analysis of the characteristics of the cable conduit working environment and the associated functional requirements, this study successfully developed a small-scale urban cable conduit inspection robot prototype. This development was grounded in relevant design theories, simulation analyses, and experimental tests. The test results demonstrate that the robot’s bracing module effectively prevents tilting within the conduit. Additionally, the detection module enables comprehensive 360-degree conduit inspections, and the vacuuming module meets the negative pressure requirements for efficient absorption of dust and foreign matter. The robot has met the expected design goals, effectively enhanced the automation of the cable conduit construction process, and improved the quality control of cable laying.

Learning complex nonlinear dynamics of a 3D translational parallel manipulator using neural network

This study investigates modeling the dynamics of a 3D translational parallel manipulator with closed chains using feedforward neural networks (FFNNs). The dataset exceeds 50,000 samples, incorporating experimental data collected from a robot prototype using MATLAB® real-time workshop and the National InstrumentsTM DAQ toolbox, as well as CAD simulation data from MSC ADAMS software. While achieving satisfactory mean squared error (MSE), some predictions did not fully capture the manipulator's dynamics, with small overfitting observed. A Deep Neural Network (DNN) was tested but faced overfitting and high computational costs, despite being trained on a subset of the dataset. This highlighted the limitations of DNNs for modeling such complicated parallel robots with closed chains and parallelograms. FFNNs were preferred for their simplicity and lower overfitting risk. L2 regularization and k-fold validation were applied to improve performance. Transfer learning (TL) was also employed, fine-tuning a new network with weights from pre-trained FFNNs using a smaller, unseen dataset. This approach significantly reduced MSE and completely eliminated overfitting, demonstrating the effectiveness of TL in refining model performance for forward and inverse dynamics. These findings suggest that FFNNs, combined with TL, L2 regularization, and k-fold validation, offer a robust method for accurately modeling complex robotic dynamics, enhancing control and optimization strategies for complicated robotic systems. Training for all networks was conducted within the MATLAB® environment.

Scientific habilty by using DNA and robotic activities in the science class

Educational robotics as an area of pedagogy is a discipline whose objective is the development of robotic prototypes that support the learning of natural sciences, demonstrating its potential as a didactic proposal that integrates technology into transdisciplinary thinking favoring digital thinking in the 21st century, in which we can mention scientific ability and the development of solutions to problems that favor scientific thinking. This educational research aims to connect the fields of chemistry and biology with the growing technology of educational robotics. A descriptive interpretive methodology was applied to a group of 80 high school students; They conducted experimental activities such as extracting DNA from tomatoes and observing the stages of mitosis in onion apical meristems. After observing the chromosomes in a microscope, the students use an augmented reality application, contrasting the information and creating a robotic model with recyclable material, programmed using the open-source ap-plication Arduino. No significant differences were found during the development of the activities between public and private schools, showing that 90% of the students obtained the DNA and 67% managed to develop robotic programming activities.

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.

Deep learning guided variable rate robotic sprayer prototype

This paper presents the development of a robotic sprayer that combines artificial intelligence with robotics for optimal spray application on citrus nursery plants grown in an indoor environment. The robotic platform is integrated with an embedded firmware of MobileNetV2 model to identify and classify the plant samples with a classification accuracy of 100 % which is used to dispense variable rate spraying of pesticide based on the health status of the plant foliage. The disease detection model was developed through the edge impulse platform and deployed on Raspberry Pi 4. The robot navigates through an array of plants, stops beside each plant, and captures an image of the citrus plants. It feeds the image into the deployed embedded model to generate a disease inference that informs the variable rate application of spray during real-time actuation. To test the spraying performance of the prototype within the growing environment, water sensitive cards were placed in each plant's canopy. After spraying, the samples of water sensitive cards were collected and quantified using a smart spray app to determine the classification accuracy as well as the extent of spray coverage on the citrus samples. The robot spray coverage results show an average spray coverage of 87 % on lemon foliage when compared with 67 % for navel orange, during the spray performance test of the robot.

Design and workspace analysis of a cable-driven space capture robot for noncooperative targets

Capturing noncooperative targets in space has garnered continuous research interest in aerospace applications. This study addresses the demands of large-scale, multifaceted activities and varied working conditions for space capture missions by designing a space capture robot composed of multiple cable-driven manipulators operating in parallel. First, single- and multi-segment cable-driven robot models were designed, and a geometric model was subsequently built. The optimal number of segments was determined by analysing the condition number of a Jacobian matrix using the Monte Carlo method. Subsequently, based on the constant-curvature assumption, a kinematic model of the cable-driven space capture robot was formulated, and capture methods for different capture targets were designed using the Monte Carlo method. Finally, an eight-segment cable-driven robot prototype was developed, and compliance and driving experiments were conducted. This robot exhibits promising application potential for space noncooperative target capture and can be feasibly manufactured using on-orbit 3D machining technology.

Design Ideation for Autonomous Reproductive Worm Robot: Inheritance from Biological Worm C.elegans

The vast domain of Bio-inspired Robotics has been nourished with several key-themes of design over the years and those are, no doubt conceptually brilliant. The size effect of such bio-robotic gadgets was also tackled through modern-age manufacturing as well as assembly technologies and we have got experimental gadgets like worm robots as outcome. However, in all such prototypes of miniature bio-robots and/or worm robots, the essence of biological science has been missing to date. The concept of bio-inspired team robots having near-identical features, symbolizing biological off-springs was not explored hitherto. We are attempting to provide a novel autonomous assistive robotic system having ‘Mother’ and ‘Daughter(s)’ for use in agricultural fields. Our design has been nucleated from a famous biological worm, namely, Caenorhabditis elegans (C.elegans) which has a fully-developed reproductive system, notwithstanding its length (~ 1 mm.) or even the diameter (~ 50 microns). In this paper, we will report the technological ideation design of a representative ‘Mother-Daughter’ Worm Robotic system by naturally inheriting the reproductive mechanism of the biological C.elegans worm (barring the size effect).

Design of a bipedal robot for water running based on a six-linkage mechanism inspired by basilisk lizards

Legged robots have received widespread attention in academia and engineering owing to their excellent terrain adaptability. However, most legged robots can only adapt to high-hardness environments instead of flexible environments. Expanding the motion range of legged robots to water is a promising but challenging work. Inspired by basilisk lizards which can run on water surfaces by feet, this paper proposes a bipedal robot for water running by hydrodynamics instead of buoyancy. According to the motion parameters of the basilisk lizard during water running, a single-degree of freedom bipedal mechanism is proposed to reproduce the motion trajectory of the feet of the basilisk lizard. Scale optimization is conducted by a particle swarm optimization algorithm to determine the geometrical parameters of the mechanism. The effects of motion frequency and foot area on mechanism performance are studied and the optimal solutions are determined by the maximum single-cycle lift impulse through numerical calculations. A bipedal water running robot prototype was fabricated, and the experimental results show that the prototype can generate enough support for the robot running on the water by providing a maximum lift of 2.4 times its weight (160 g) and reaching a horizontal forward speed range of 0.3-0.8 m s-1, compared with the basilisk lizard weighs 2-200 g, generates a lift impulse that is 111%-225% of its body weight, and moves at a speed of 1.3 ± 0.1 m s-1.

Microcontroller-based Forklift Path Following Robot Prototype

The development of science in the field of robotics has made many heavy jobs that cannot be done by humans replaced by robots, especially in the factory industry. In modern factories, most of them have a warehouse or similar facility that contains heavy equipment for use in a factory, for example, forklift heavy equipment. Based on an interview with one of the forklift operators, the problem of using forklifts is usually when there are items that must be moved that cannot be lifted by humans which must be done immediately according to the route where the item is stored. To answer the existing problems, a robot prototype was made which is useful to help facilitate the work of factory workers. This robot prototype was built using the User Centered Design (UCD) method. This robot prototype uses the main components of Arduino UNO, L293D Motor Driver, and PWM Servo Motor Driver. Based on the overall testing that has been done, it can be said that the robot prototype can follow the route according to the program and can lift and remove objects in front of it with a score of 80%. So that workers can be helped to facilitate their work.

A Parallel Robot With Remote Centre-of-Motion for Eye Surgery: Design, Kinematics, Prototype, and Experiments.

Millions of patients suffering from eye disease cannot receive proper treatment due to the lack of qualified surgeons. Medical robots have the potential to solve this problem and have attracted significant attention in the research community. This paper proposes a novel parallel robot with a remote centre of motion for minimally invasive eye surgery. Kinematics models, singularity and workspace analyses, and dimension optimisation are conducted. A prototype was developed, and experiments were conducted to test its mobility, accuracy, precision and stiffness. The prototype robot can successfully perform the required motions, and has a precision ranging from 7±2μm to 30±8μm, accuracy from 21±10μm to 568±374μm, and stiffness ranging from 1.22±0.39N/mm to 10.53±5.18N/mm. The prototype robot has a great potential for performing the minimally invasive surgery. Its stiffness meets the design requirement, but its accuracy and precision need to be further improved.

Terrestrial locomotion stability of undulating fin amphibious robots: Separated elastic fin rays and asynchronous control

To address the problem of poor postural stability in an undulating fin robot during terrestrial locomotion, this study proposes a novel design featuring separate elastic fin rays with an asynchronous control scheme for bilateral fin surfaces. In this scheme, the robotic fin ray structure and surface driving mode are innovatively designed to mitigate the pitch-angle instability caused by adverse factors, such as integral rigid fin rays and synchronized fin surfaces. Expanding on the ground dynamics model of the robot, this study examined the variation in the pitch angle of the robot body. In this study, an innovative design with separated elastic fin rays was proposed and their feasibility was validated through finite element simulations. In addition, a virtual simulation prototype of the robot was developed to verify the robot body stability under asynchronous fin surface control. The simulation results show that separate elastic fin rays and asynchronous control can effectively improve the postural stability of robots in terrestrial locomotion. In this study, a robot prototype was tested experimentally in various terrestrial environments. The experimental results indicate that equipping the robot with separated elastic fin rays and employing asynchronous motion control significantly enhances the motion postural stability across typical terrain conditions. The maximum pitch angle range can be reduced by 42.7–52.4%, providing new insights for the design of amphibious robots with undulating fins.

Art, AI and Robotics: A New Pathway for Youth to Voice and Identity

To address the critical lack of representation in computer science and STEAM (science, technology, engineering, art, and mathematics), we designed learning experiences for high school youth using culturally situated art and design principles structured to increase authentic engagement, particularly for underrepresented and underestimated youth. Referencing sociocultural practices from hip-hop, we invited students to engage with us in an iterative process of storytelling, creation, and fabrication. Through design cyphers, we centered student knowledge to define the why behind making robotic prototypes and address the benefits and dangers of artificial intelligence such as bias and stereotypes. By integrating cyphers into the design thinking process, we created spaces for students to communicate, collaborate, and create innovative solutions to prototype, iterate, remix, and advance to their final project. In collaborative peer reviews and gallery walks, the groups received constructive critiques at each step of the design process, from prototype to final project.

Jellyfish-Inspired Soft Robot Driven by Pneumatic Bistable Actuators.

Soft actuators offer numerous potential applications; however, challenges persist in achieving a high driving force and fast response speed. In this work, we present the design, fabrication, and analysis of a soft pneumatic bistable actuator (PBA) mimicking jellyfish subumbrellar muscle motion for waterjet propulsion. Drawing inspiration from the jellyfish jet propulsion and the characteristics of bistable structure, we develop an elastic band stretch prebending PBA with a simple structure, low inflation cost, exceptional driving performance, and stable driving force output. Through a bionic analysis of jellyfish body structure and motion, we integrate the PBA into a jellyfish-like prototype, enabling it to achieve jet propulsion. To enhance the swimming performance, we introduce a skin-like structure for connecting the soft actuator to the jellyfish-like soft robot prototype. This skin-like structure optimizes the fluid dynamics during jet propulsion, resulting in improved efficiency and maneuverability. Our study further analyzes the swimming performance of the jellyfish-like prototype, demonstrating a swimming speed of 3.8 cm/s (0.32 body length/s, BL/s) for the tethered prototype and 4.7 cm/s (0.38 BL/s) for the untethered prototype. Moreover, we showcase the jellyfish-like prototype's notable load-bearing capacity and fast-forward swimming performance compared to other driving methods for underwater biomimetic robots. This work provides valuable insights for the development of highly agile and fast responsive soft robots that imitate the subumbrellar muscle of jellyfish for efficient water-jet propulsion, utilizing skin-like structures to enhance swimming performance.

Developing a tablet-based brain-computer interface and robotic prototype for upper limb rehabilitation.

The current study explores the integration of a motor imagery (MI)-based BCI system with robotic rehabilitation designed for upper limb function recovery in stroke patients. We developed a tablet deployable BCI control of the virtual iTbot for ease of use. Twelve right-handed healthy adults participated in this study, which involved a novel BCI training approach incorporating tactile vibration stimulation during MI tasks. The experiment utilized EEG signals captured via a gel-free cap, processed through various stages including signal verification, training, and testing. The training involved MI tasks with concurrent vibrotactile stimulation, utilizing common spatial pattern (CSP) training and linear discriminant analysis (LDA) for signal classification. The testing stage introduced a real-time feedback system and a virtual game environment where participants controlled a virtual iTbot robot. Results showed varying accuracies in motor intention detection across participants, with an average true positive rate of 63.33% in classifying MI signals. The study highlights the potential of MI-based BCI in robotic rehabilitation, particularly in terms of engagement and personalization. The findings underscore the feasibility of BCI technology in rehabilitation and its potential use for stroke survivors with upper limb dysfunctions.