Simulated Robot Research Articles

Variable admittance control for safe physical human–robot interaction considering intuitive human intention

The trajectory planning of the arm is greatly facilitated by the physical direct teaching technology. Variable admittance control is a promising technology when a robot is interacting with a variable environment, such as a human whose stiffness might change during the interaction. Nevertheless, a canonical admittance controller with imperfect parameters may lead to robot oscillation, which brings more challenges to a variable admittance controller. In this paper, we propose an energy-based variable admittance controller with intrinsic oscillation suppression property. During the physical human–robot interaction (pHRI), the human intention is predicted based on the robot’s state and interaction force. The admittance parameters are tuned automatically to conform the robot’s motion to human intention. When the oscillation is detected online by the proposed wavelet module, our variable admittance model reveals oscillation suppression ability because of dissipating the energy generated by high-frequency oscillation. We compared the proposed variable admittance controller with other admittance controller approaches in both simulation and actual robot experiments. The proposed method shows significant improvement in oscillation suppression and human energy conservation in the human–robot interaction application.

LunarSim: Lunar Rover Simulator Focused on High Visual Fidelity and ROS 2 Integration for Advanced Computer Vision Algorithm Development

Autonomous lunar exploration is a complex task that requires the development of sophisticated algorithms to control the movement of lunar rovers in a challenging environment, based on visual feedback. To train and evaluate these algorithms, it is crucial to have access to both a simulation framework and data that accurately represent the conditions on the lunar surface, with the main focus on providing the visual fidelity necessary for computer vision algorithm development. In this paper, we present a lunar-orientated robotic simulation environment, developed using the Unity game engine, built on top of robot operating system 2 (ROS 2), which enables researchers to generate quality synthetic vision data and test their algorithms for autonomous perception and navigation of lunar rovers in a controlled environment. To demonstrate the versatility of the simulator, we present several use cases in which it is deployed on various efficient hardware platforms, including FPGA and Edge AI devices, to evaluate the performance of different vision-based algorithms for lunar exploration. In general, the simulation environment provides a valuable tool for researchers developing lunar rover systems.

Exploring Micro Aerial Vehicle Mechanism and Controller Design Using Webots Simulation

Quadrotor Micro Aerial Vehicle (MAV) is one of the Unmanned Aerial Vehicle (UAV) which very versatile with their capabilities for specific purposes. Understanding and controlling MAV is important for various applications, from surveillance and delivery services to disaster response and entertainment. In engineering education, providing a hardware platform for understanding MAV mechanism and the controller design is very challenging in terms of cost and safety issue. This paper presents a study on drone mechanisms and controller design using Webots, a versatile robot simulation environment. The primary objectives of this research were to simulate and analyze the behavior of drones in a line following task, employing PID controller as the control strategies, and to evaluate the suitability of Webots as a simulation tool for drone-related teaching and learning as well as research. In the methodology section, the setup of the Webots-based drone simulation, including the selection of a suitable drone model, sensor configurations, and the implementation of control algorithms will be explained. Line following task will be focused to analyze the drone mechanism and the controller design. Data on the drone performance will be collected through the experiment and will be analyzed rigorously. The findings reveal the effectiveness of Webots as a platform for simulating drone behavior. The advantages of using simulation tools like Webots, including cost-effectiveness, safety, and the ability to test and refine control algorithms before deployment on physical drones was proved in this study. It is shown that Webots can be leveraged to teach and train individuals in drone technology without the need for physical hardware.

Cross-modal self-attention mechanism for controlling robot volleyball motion.

The emergence of cross-modal perception and deep learning technologies has had a profound impact on modern robotics. This study focuses on the application of these technologies in the field of robot control, specifically in the context of volleyball tasks. The primary objective is to achieve precise control of robots in volleyball tasks by effectively integrating information from different sensors using a cross-modal self-attention mechanism. Our approach involves the utilization of a cross-modal self-attention mechanism to integrate information from various sensors, providing robots with a more comprehensive scene perception in volleyball scenarios. To enhance the diversity and practicality of robot training, we employ Generative Adversarial Networks (GANs) to synthesize realistic volleyball scenarios. Furthermore, we leverage transfer learning to incorporate knowledge from other sports datasets, enriching the process of skill acquisition for robots. To validate the feasibility of our approach, we conducted experiments where we simulated robot volleyball scenarios using multiple volleyball-related datasets. We measured various quantitative metrics, including accuracy, recall, precision, and F1 score. The experimental results indicate a significant enhancement in the performance of our approach in robot volleyball tasks. The outcomes of this study offer valuable insights into the application of multi-modal perception and deep learning in the field of sports robotics. By effectively integrating information from different sensors and incorporating synthetic data through GANs and transfer learning, our approach demonstrates improved robot performance in volleyball tasks. These findings not only advance the field of robotics but also open up new possibilities for human-robot collaboration in sports and athletic performance improvement. This research paves the way for further exploration of advanced technologies in sports robotics, benefiting both the scientific community and athletes seeking performance enhancement through robotic assistance.

Integrating early assessment of robotic constructability into design optimization of a standalone classroom

Multi-objective optimization can enhance design quality through performance simulation. However, ease or efficiency of construction is also important, and optimization may lead to difficult-to-build designs. Early quantification of constructability would allow designers to balance performance and construction issues. While it is difficult to quantify all factors that influence constructability, robotic construction simulations offer rich datasets to compare potential outcomes. This paper integrates constructability knowledge into early-stage design and examines the impact on multi-objective optimization. It evaluates robotic material delivery systems in constructing a standalone classroom optimized for structural, daylighting, and energy goals. When considering robotic pick and place time, the optimized designs differ, offering the opportunity to change design directions based on construction knowledge. Broader implications also become observable, as incorporating robots with higher carrying capacities reduces the structural elements and embodied carbon of optimal designs. This paper thus demonstrates benefits of incorporating robotic constructability simulation into early design optimization.

End-to-end decentralized formation control using a graph neural network-based learning method.

Multi-robot cooperative control has been extensively studied using model-based distributed control methods. However, such control methods rely on sensing and perception modules in a sequential pipeline design, and the separation of perception and controls may cause processing latencies and compounding errors that affect control performance. End-to-end learning overcomes this limitation by implementing direct learning from onboard sensing data, with control commands output to the robots. Challenges exist in end-to-end learning for multi-robot cooperative control, and previous results are not scalable. We propose in this article a novel decentralized cooperative control method for multi-robot formations using deep neural networks, in which inter-robot communication is modeled by a graph neural network (GNN). Our method takes LiDAR sensor data as input, and the control policy is learned from demonstrations that are provided by an expert controller for decentralized formation control. Although it is trained with a fixed number of robots, the learned control policy is scalable. Evaluation in a robot simulator demonstrates the triangular formation behavior of multi-robot teams of different sizes under the learned control policy.

Design and simulation of a 3D-printed wall-climbing robot for high-risk construction tasks

This study aims to design and calculate a model for a wall-climbing robot to replace humans in performing dangerous tasks at great heights in construction sites. The research simultaneously addresses three main issues in the process of calculation, design, and simulation of the vertically climbing robot model. Firstly, the study conducts calculations and analyzes the dynamics of the model in various working states. Specifically, it calculates the suction force of the fan in non-contact conditions to ensure the suction capability of the model during practical operations. Secondly, the core content of this method involves utilizing the airflow generated by the engine through a specially designed suction mechanism to increase the airflow velocity significantly, thus creating a low-pressure area capable of adhering to the wall. This suction force calculation method and other forces acting on the robot model are based on numerical simulation software. The boundary conditions in the calculation process for the wall-climbing robot model are derived from the tasks that the robot performs during real operations, replacing humans. Thirdly, the study designs the wall-climbing robot using the non-contact suction force method through a 3D-printed fan model to enhance the model’s durability and optimize the airflow under various conditions. In summary, through this research, the paper aims to construct a robot model using non-contact suction and complete it entirely with 3D printing technology. This model will generate cost-effective and highly efficient robot vehicles that can be widely applied in modern industrial environments.

Simultaneous localization and mapping architecture for small bodies and space exploration

The development of autonomous robotic platforms for space applications such as satellites, robotic manipulators and rovers has driven the need for reliable control and navigation techniques. Simultaneous Localization and Mapping (SLAM) algorithms can be employed to determine the position and orientation of robotic platforms while generating a map of an unknown hostile environment. This article presents the successful integration of ORB-SLAM2, a localization algorithm, with Voxblox, an accurate three-dimensional mapping package. This integration aims to establish a pathway for occupancy maps to be generated from feature detection algorithms. Furthermore, virtual reality is presented as an innovative solution for testing the performance of this algorithm integration in a space environment. Providing a novel simulation environment with an opportunity to diversify applications. The effectiveness of this integration and SLAM accuracy was compared to a truth model extracted from the virtual reality environment. The accuracy is dependent on the number of observed and matched features in a given frame and are intrinsic characteristic of features in the environment. The robustness of the integration is also examined through the implementation of sensor inputs in the form of stereo and RGB-D cameras. The algorithms’ integration and embedding into virtual reality allows for further developments of SLAM algorithms, to improve accuracy and robustness for autonomous navigation in any virtual environment, and extend robotic simulations and visualizations.

Safe Machine-Learning-Supported Model Predictive Force and Motion Control in Robotics

Many robotic tasks, such as human-robot interactions or the handling of fragile objects, require tight control and limitation of appearing forces and moments alongside sensible motion control to achieve safe yet high-performance operation. We propose a learning-supported model predictive force and motion control scheme that provides stochastic safety guarantees while adapting to changing situations. Gaussian processes (GPs) are used to learn the uncertain relations that map the robot’s states to the forces and moments. The model predictive controller uses these Gaussian process models to achieve precise motion and force control under stochastic constraint satisfaction. As the uncertainty only occurs in the static model parts — the output equations — a computationally efficient stochastic MPC formulation is used. analysis of recursive feasibility of the optimal control problem and convergence of the closed loop system for the static uncertainty case are given. Chance constraint formulation and back-offs are constructed based on the variance of the Gaussian process to guarantee safe operation. The approach is illustrated on a lightweight robot in simulations and experiments.

Bridging Neuroscience and Robotics: Spiking Neural Networks in Action.

Robots are becoming increasingly sophisticated in the execution of complex tasks. However, an area that requires development is the ability to act in dynamically changing environments. To advance this, developments have turned towards understanding the human brain and applying this to improve robotics. The present study used electroencephalogram (EEG) data recorded from 54 human participants whilst they performed a two-choice task. A build-up of motor activity starting around 400 ms before response onset, also known as the lateralized readiness potential (LRP), was observed. This indicates that actions are not simply binary processes but rather, response-preparation is gradual and occurs in a temporal window that can interact with the environment. In parallel, a robot arm executing a pick-and-place task was developed. The understanding from the EEG data and the robot arm were integrated into the final system, which included cell assemblies (CAs)-a simulated spiking neural network-to inform the robot to place the object left or right. Results showed that the neural data from the robot simulation were largely consistent with the human data. This neurorobotics study provides an example of how to integrate human brain recordings with simulated neural networks in order to drive a robot.

Investigating frictional contact behavior for soft material robot simulations

The ability to interact safely with the environment is known as one of the major advantages of soft robots (SRs). Due to their low material stiffness, these continuously deformable robots offer inherent flexibility. These advantages make them suitable for application that involve human-robot collaboration in industrial settings as well as medical application such as minimally invasive surgery. To date only few research groups have analyzed the contact and frictional behavior of soft robots. In fact, the contact behavior is often oversimplified or neglected. Motivated by the idea to bridge this gap, this work presents measurements and the resulting coefficient of friction (COF) for silicone rubbers that are widely used in the field of SRs and different contact partners which depend on contact pressure and ambient temperature. From these measurements, a more representative contact model is established and used to more accurately simulate soft material robots’ frictional contact behavior. Moreover the influence of friction and therefore the need to implement frictional behavior is demonstrated for a typical application of a SR.

Playing the pipes: acoustic sensing and machine learning for performance feedback during endotracheal intubation simulation.

Objective: In emergency medicine, airway management is a core skill that includes endotracheal intubation (ETI), a common technique that can result in ineffective ventilation and laryngotracheal injury if executed incorrectly. We present a method for automatically generating performance feedback during ETI simulator training, potentially augmenting training outcomes on robotic simulators. Method: Electret microphones recorded ultrasonic echoes pulsed through the complex geometry of a simulated airway during ETI performed on a full-size patient simulator. As the endotracheal tube is inserted deeper and the cuff is inflated, the resulting changes in geometry are reflected in the recorded signal. We trained machine learning models to classify 240 intubations distributed equally between six conditions: three insertion depths and two cuff inflation states. The best performing models were cross validated in a leave-one-subject-out scheme. Results: Best performance was achieved by transfer learning with a convolutional neural network pre-trained for sound classification, reaching global accuracy above 98% on 1-second-long audio test samples. A support vector machine trained on different features achieved a median accuracy of 85% on the full label set and 97% on a reduced label set of tube depth only. Significance: This proof-of-concept study demonstrates a method of measuring qualitative performance criteria during simulated ETI in a relatively simple way that does not damage ecological validity of the simulated anatomy. As traditional sonar is hampered by geometrical complexity compounded by the introduced equipment in ETI, the accuracy of machine learning methods in this confined design space enables application in other invasive procedures. By enabling better interaction between the human user and the robotic simulator, this approach could improve training experiences and outcomes in medical simulation for ETI as well as many other invasive clinical procedures.

Robot Arm Reaching Based on Inner Rehearsal.

Robot arm motion control is a fundamental aspect of robot capabilities, with arm reaching ability serving as the foundation for complex arm manipulation tasks. However, traditional inverse kinematics-based methods for robot arm reaching struggle to cope with the increasing complexity and diversity of robot environments, as they heavily rely on the accuracy of physical models. In this paper, we introduce an innovative approach to robot arm motion control, inspired by the cognitive mechanism of inner rehearsal observed in humans. The core concept revolves around the robot's ability to predict or evaluate the outcomes of motion commands before execution. This approach enhances the learning efficiency of models and reduces the mechanical wear on robots caused by excessive physical executions. We conduct experiments using the Baxter robot in simulation and the humanoid robot PKU-HR6.0 II in a real environment to demonstrate the effectiveness and efficiency of our proposed approach for robot arm reaching across different platforms. The internal models converge quickly and the average error distance between the target and the end-effector on the two platforms is reduced by 80% and 38%, respectively.

Design of an optimized gait planning generator for a quadruped robot using the decision tree and random forest workspace model

AbstractReal-time gait trajectory planning is challenging for legged robots walking on unknown terrain. In this paper, to realize a more efficient and faster motion control of a quadrupedal robot, we propose an optimized gait planning generator (GPG) based on the decision tree (DT) and random forest (RF) model of the robot leg workspace. First, the framework of this embedded GPG and some of the modules associated with it are illustrated. Aiming at the leg workspace model described by DT and RF used in GPG, this paper introduces in detail how to collect the original data needed for training the model and puts forward an Interpolation Labeling with Dilation and Erosion (ILDE) data processing algorithm. After the DT and RF models are trained, we preliminarily evaluate their performance. We then present how these models can be used to predict the location relation between a spatial point and the leg workspace based on its distributional features. The DT model takes only 0.00011 s to process a sample, while the RF model can give the prediction probability. As a complement, the PID inverse kinematic model used in GPG is also mentioned. Finally, the optimized GPG is tested during a real-time single-leg trajectory planning experiment and an unknown terrain recognition simulation of a virtual quadrupedal robot. According to the test results, the GPG shows a remarkable rapidity for processing large-scale data in the gait trajectory planning tasks, and the results can prove it has an application value for quadruped robot control.

Sağlık Hizmetindeki Robotlar İçin Blokzincir Destekli Görev Yönetimi: Webots Simülasyonu

In recent years, the adoption of robotic systems has witnessed remarkable growth across diverse industries, revolutionizing various aspects of automation and human-robot interaction. Healthcare is one of the major professions where replacement of human labor with well-functioning service robots would be heavily desired. Mobile service robots in a multi robot system can work collaborately and cooperatively to assist medical personnel by performing work routines as simple or complex tasks. As these robots carry out complex tasks, there arises a crucial need for secure, efficient, and immutable storage mechanisms to manage the vast amount of task-related information generated during their operation. In this study, we propose a simulation where a system of multiple TIAGo++ robots can request and complete simple tasks while using Hyperledger Fabric (HLF) blockchain platform to address the requirements of storing and accessing task information. Communication with the blockchain network and controlling it in Webots environment for a single TIAGo++ robot are integrated into same Java application in this simulation. Experimental results show that HLF and Webots can successfully run concurrently for task allocation and to store data acquired from mobile robots in a multi robot simulation.

Cultural psychology of english translation through computer vision-based robotic interpretation

Computer Vision-based English translation approaches pledge robots to master complicated functions. Conversely, the debate remains unanswered as to how to extend persuasion skills to real-world relationships. The stable operation of robots in English translation is an upcoming development in the educational field. The development of science and technology in the form of robots helps in computer vision technology for object detection and learning. In education, the usage of advanced technology is still facing challenges in English translation based on the computer vision of robots. In the article, researchers investigate robotic simulation, movement identification, and target tracking in computer vision, learning from one illustration of the third person's perspective. Researchers consider using a previous information basis like a text repository to deduce the feature to be dealt with as part of a robot to promote its generalization through object detection and learning. A Robot translation based on computer vision of English translation (RT-CV) framework is proposed in the research. Robots' word recognition, facial expression, speech, and movement are captured and based on computer vision; the translation is permitted with the basic functions. RT-CV is implemented in real-world applications with manipulative functions with generalized outcomes. The results are obtained as emotional interaction with robots’ ratio is 87.6%, improving computer vision ratio is 88.7%, the Estimation of translating speed ratio is 84.5%, the efficiency of English translation ratio is 93.8%, and anxiety reduction through communication ratio is 82.2%.

Developing cognitive workload and performance evaluation models using functional brain network analysis

Cognition, defined as the ability to learn, remember, sustain attention, make decisions, and solve problems, is essential in daily activities and in learning new skills. The purpose of this study was to develop cognitive workload and performance evaluation models using features that were extracted from Electroencephalogram (EEG) data through functional brain network and spectral analyses. The EEG data were recorded from 124 brain areas of 26 healthy participants conducting two cognitive tasks on a robot simulator. The functional brain network and Power Spectral Density features were extracted from EEG data using coherence and spectral analyses, respectively. Participants reported their perceived cognitive workload using the SURG-TLX questionnaire after each exercise, and the simulator generated actual performance scores. The extracted features, actual performance scores, and subjectively assessed cognitive workload values were used to develop linear models for evaluating performance and cognitive workload. Furthermore, the Pearson correlation was used to find the correlation between participants’ age, performance, and cognitive workload. The findings demonstrated that combined EEG features retrieved from spectral analysis and functional brain networks can be used to evaluate cognitive workload and performance. The cognitive workload in conducting only Matchboard level 3, which is more challenging than Matchboard level 2, was correlated with age (0.54, p-value = 0.01). This finding may suggest playing more challenging computer games are more helpful in identifying changes in cognitive workload caused by aging. The findings could open the door for a new era of objective evaluation and monitoring of cognitive workload and performance.

CONSTRUCTION OF THE KINEMATIC MODEL OF ROBOTIC SYSTEMS IN THE MATLAB ENVIRONMENT

Robotics has become relatively accessible with low-cost projects, but there is still a need to create models that accurately represent the robot's physical behavior. Creating a virtual platform allows us to test behavioral algorithms using artificial intelligence. In addition, it will enable us to find potential problems in the physical design of the robot. The article describes the methodology of building a kinematic model and simulation of an autonomous robot. The development of a kinematic model and its implementation using several tools are presented. The environment used for the experiment is very close to natural conditions and reflects the kinematic characteristics of the robot. As a result, the simulation of the model following the mobile robot's kinematics is executed and tested in MATLAB. As a study, the m-file creation in MATLAB, its use with the Simulink package, and the solution of the forward and inverse problem of kinematics are shown. In addition to constructing the robot body using Simulink blocks, the structure of the kinematic scheme is simulated using the Denavit-Hartenberg (DH) parameters of the robot without blocks. "Simscape" and "Robotics System Toolbox" packages simulate forward and inverse kinematics using the Simulink package, and the robot's handle and body movement are observed. In the forward kinematics problem, the readings in the Scope compare the signals received from joint one and the end effector. For the inverse kinematic problem, the parameters of the manipulator along the XYZ axes are entered using the "Signal builder" block, and the circular movement of the arm is observed. In contrast, the handle of the manipulator remains fixed at a given point. Keywords: mobile robot, kinematic model, the forward and inverse problem of kinematics, Denavit-Hartenberg parameters, joint types

Can smoothed particle hydrodynamics simulate physically realistic movements of underwater vehicles?

ABSTRACT This work presents the first results using Smoothed Particle Hydrodynamics (SPH), a mesh-free technique, to simulate underwater vehicle motion with the goal of achieving sufficient physical realism and computation time performance capabilities. The objective is not to get very accurate values for the hydrodynamic parameters, but to show that SPH can simulate hydrodynamic parameters with the same order of magnitude as the reference, in order to allow a realistic control of robots in water. First, spherical objects are simulated to check buoyancy realism, speed limit existence, and hydrodynamic parameters in comparison with reference values. Then, horizontal and vertical movements of a capsule-shape object and a real torpedo-shape underwater robot are compared. The results show that buoyancy is respected, and that spherical objects reach a speed limit in accordance with the laws of physics. In addition, added-mass is simulated with 20 % variation on average with respect to the reference and varies homothetically with respect to the object's size. In contrast, drag forces cannot not be simulated with the same level of realism without reducing the particle size, which makes the simulation last longer. SPH for underwater robotics simulation appears to be promising, and ways of further improvements are being considered.

Automated method based on a neural network model for searching energy-efficient complex movement trajectories of industrial robot in a differentiated technological process

Purpose of the work: Researching possibility of creating a method for improving the energy efficiency of differentiated robotic technological process (RTP) in the food industry. The high rates of development of production processes robotization, including in the food industry, leading to increase the cost of electrical energy, determine the research tasks relevance in finding energy-efficient methods for controlling industrial robots.Methodology: The proposed approach is based on principles of object-oriented design and possibility of classifying robotic technological process: Applying specific model sets and methods to improve energy efficiency to individual classes. The existing possibility of energy consumption synthesizing models of robots inside differentiated robotic technological process, such as stacking loads, in reduced form, made it possible to use neural network methods to identify non-linear dependencies. At the same time, training sample for intelligent modules was formed on the basis of classical experiment planning algorithms. The synthesis of methods, models and procedures was implemented on the basis of high-level programming languages C++, MATLAB.Results: A mathematical model and automated algorithms for its synthesis are proposed, which make it possible to adjust robotic technological process simulation model taking into account its specifics and implement a method for finding the optimal parameters of its functioning. To confirm the effectiveness of proposed solution, the obtained neural network model and optimization method were tested on real robotic technological process, and the calculation of economic efficiency of proposed solution was also given.Conclusion/recommendations: The application of this approach will significantly reduce energy costs for robotic operations in the food industry.