Interactive Collaborative Robotics

In this paper a lower limb exoskeleton with a toe joint is studied. A mathematical model of the exoskeleton is presented, and the equations of motion are given. The exoskeleton is controlled with a feedback controller. The control system attempts to move the center of mass of the exoskeleton along the desired trajectory. To find the joint space trajectory that allows to perform the desired motion a numerical optimization-based iterative algorithm for solving inverse kinematics is given. The algorithm allows to engage and disengage the toe joint, based on how close the mechanism is to a singular position. That gives us an automatic human-like toe joint engagement, that can be controlled though certain parameters, which is discussed in the paper. The results of the numerical simulation of the exoskeleton motion are presented.

The fault of the robotic control system is critical and leads to the general system failure, while autonomous robots have to gain their aims without any maintenance. Contemporary academic studies propose decentralized control systems as prospective from the robustness point of view. On the other hand, a performance redundancy allows to optimize resource utilization and improve the fault-tolerance potential of the control system. This paper is devoted to the recovery method of the robotic decentralized control system with performance redundancy. A reconfiguration problem has been formalized, decentralized method of the solution obtaining is represented. Also some simulation results are given and discussed.

This paper presents an analysis of datasets of images of human faces with annotated facial keypoints, which are important in human-machine interaction, and their comparison. Datasets are divided according to external conditions of the subject into two groups: datasets in laboratory conditions and in the wild data. Moreover, a quick review of the state-of-the-art methods for keypoints detection is provided. Existing methods are categorized into the following three groups according to the approach to the solution of the problem: top-down, bottom-up and their combination.

This paper describes design, creation and preliminary testing of hardware and software for BCI (Brain-Computer interface)-based humanoid robot control. The system, the concept of which is presented in the article, is assumed to use for training ADHD patient’s attention.

In this paper, we propose a conceptual model of a cyberphysical environment based on a new approach to distribution of sensor, network, computing, information-control and service tasks between mobile robots, embedded devices, mobile client devices, stationary service equipment, and cloud computing and information resources. The task of structural-parametric synthesis of the corresponding cyberphysical system is formalized. Methods of integer-valued programming are used for the task solution.

The article considers the problem of distributed control for a group of heterogeneous vehicles. A survey of tasks and group control methods is given. A problem is posed to synthesize a local control algorithm ensuring motion if a heterogeneous group in a 2D environment with nonstationary obstacles. The algorithm is used to calculate the required speed and robot’s heading. A principle is used that allows us to treat all the neighboring objects as repellers. Unlike the known methods, in the proposed approach the repelling forces are formed at the outputs of dynamic units allowing us to perform synthesis in the state space instead of a geometric space. Motion steady state modes analysis of the planned paths is performed and their stability is considered. The presented results allows to improve the operation of the robot safety among human environment.

The current paper covers the solution of the problem of decentralized control of a network-centric group of heterogeneous robots (robots of various types), that have various functional capabilities, during collective execution of complicated tasks received from consumers in a priori unknown moments of time. Here, the complicated task is the task which requires performance of a certain set of various interconnected operations for its execution. In the paper we describe methods of multi-agent adaptive distribution of operation of complicated tasks between the robots of the network-centric group according to their current condition and functional specialization. The methods are based on interaction of program agents which represent interests of the individual robots of the group during distribution of operations of the incoming tasks.

The aim of this paper is to develop a robotic system which can navigate in an indoor environment and charge several electrical devices. Several algorithms such as Travel Salesman Problem, Probabilistic Roadmap and Fuzzy C-means Clustering are used for development of such a system. The testbed is constructed by Arduino Uno, Arduino WIFI Shield, Go-between Shield by Mayhew Lab and Polulu Zumo robot for Arduino Ver.1.2. All the algorithms are coded by MathWorks MATLAB and Simulink. The core of the wireless charging robot is to optimize the best performance for single robot to charge multiple devices. Owing to the computation restriction of the mobile robot, the calculation will be done on remote server and communicate with the robot through Wi-Fi connection. By this, the computation load on mobile robot can be reduced as well as improving the efficiency. A real-time feedback system is also built to promote accuracy in actual environment. After the development of improved stability and flexibility, the robot can be brought to real life as an interactive and collaborative robotic system.

In this paper we describe our experiments with a group of collaborative robots, IoT devices connected to robots based on WebSockets RFC 6455 Protocol using Google protocol buffers for message handling, distributed information system for it and a human interaction problem with these systems.

In the paper, we consider a method of developing a simulation model of a humanoid robot preserving its size and mass-inertial characteristics. We describe a developed model of the servomotor and a method of tuning its PID controller as well as a method of robot interaction with the surface based on the PD controller. With the help of a special method of tuning the PID controller in Simulink program, controls coefficients for the servomotor models were selected. The experimental results have shown that the servomotors can reach a predetermined angle of rotation and maintain this position with sufficient accuracy. We have conducted a simulation of the interaction of the humanoid robot with the floor surface. With Simulink software blocks, we have made a switch that activates support reaction force at the transition of the robot foot coordinates along a vertical axis to a negative value, which provides an adequate interaction of the model of the robot with the floor model.

The concept, general provisions and some results of the research & education initiative of Saint-Petersburg State Marine Technical University (SMTU) «Marine Robotics: Education through Research» (MRER) are considered in the paper. The directions of research conducted at SMTU in the field of marine robotics, as well as up-to-date technologies of training of future engineers specializing in a certain area are represented. Some work results of a student team, developing a small unmanned remotely operated vehicle (ROV) are presented to exemplify the «through project study» approach. One of the innovative solutions validated on this ROV is implementation of hydroacoustic modem based on polyphase filters and employed for positioning and communication with other AUV.

In this paper, an overview of human-machine interactive communication for controlling lifting devices is presented, covering also the integration with vision and sensorial systems. Following a general concept, and motivation towards intelligent human-machine communication through artificial neural networks, selected methods are proposed, which provide further directions both of recent as well as of future research on human-machine interaction. The aim of the experimental research is to design a prototype of an innovative interaction system, equipped with a speech interface in a natural language, augmented reality and interactive manipulators with force feedback.

This study describes a new approach to a problem of the human-robot interaction for remote control of robot behavior. Finding a solution to this problem is important for providing control of robots and unmanned vehicles. At the interaction a human operator can form commands for robot control. It is proposed to use a noninvasive brain-computer interface based on the decoding of signals of brain activity during motor imagery to generate the supervisor commands for robot control. The principles of the interaction of human as an operator and robot as an executor are considered. Using the brain-computer interface the operator can change robot behavior without any special movements and modules embedded into robot’s program. The study aimed to development of the human-robot interaction system for non-direct control of the robot behavior based on the brain-computer interface for classification of EEG patterns of imaginary movements of one hand fingers in real-time. Example of such human-robot interaction realization for Nao robot with neurofeedback is considered.

The article represents a review of the world current state in robotics, its fields of implementation and application. It provides a description of a complex collaborative robotic system for monitoring and reconnaissance of leaks and spills of flammable, explosive and toxic substances, for elimination and prevention of accidents aftermaths. The work describes the robotic system software and functional modules. It introduces methods and algorithms of natural language interaction on the basis of multi-agent recursive cognitive architecture.

An overview of the existing anthropomorphic robots and an analysis of servomechanisms and bearing parts involved in the assembly of robot legs are presented. We propose an option for constructing the legs of the robot Antares under development. A two-motor layout, used in the knee, ensures higher joint power along with independent interaction with the neighboring upper and lower leg joints when bending. To reduce the electrical load on the main battery of the robot, the upper legs are provided with a mounting pad for additional batteries powering servos. Direct control of the servos is also carried out through the sub-controllers, responsible for all 6 engines installed in the articular joints of the robot legs.

Formation task in a group of unmanned aerial vehicles (UAVs) is a very important problem in a multi-robotics. The paper contains a brief analysis of existing methods for formation task in groups of robots. A new method for solving formation task in a group of quadrotors is proposed. The method make it possible to ensure accurate compliance with distances between quadrotors in the formation, as well as featuring low computational complexity.

This paper describes the principles of mimic recognition and reproduction for robots with ability to simulate facial emotional states of a human face. A new method of describing and managing the emotional state from basic emotional states is proposed. The method introduces a more natural way to control facial states and can be combined with a proposed natural speech interface model. The research results were tested in real conditions on several events using robots with silicone human-like faces.

In this work we consider an environment exploration and mapping task for a group of heterogeneous mobile robots. We propose a range of methods tied together in a hierarchical two-level control system. The distinguished features of the proposed system are the use of subdefinite models for robot localization as well as an original mechanism for local interaction. We present both theoretical and experimental results. On the experimental side of the study we conduct both simulation experiments as well as a real robotic swarm system investigation.

This paper proposes an automatic laparoscopic camera tracking for conducting optimal visualization of the required area such as operated field in the minimally invasive surgery. A robotic surgery system was designed and developed to perform the camera handling and tracking task during laparoscopic surgery. The method of positioning and automatic tracking for the surgical instruments during the laparoscopic operations was developed. The significant difference of the method is the usage of the markers and reference points that are placed at the visible area (outside the abdomen). This technique allows us to define the coordinates of the laparoscope and the surgical instruments in the operated field by the usage of the methods of vector algebra and geometric transformations without application of the image recognition. The algorithm of the laparoscope control and automatic tracking for the surgical instruments was offered. Also the conditions for the optimal visualization of the operated field were determined. The field of the required laparoscope position according to the surgical instruments was defined. The experimental research of the offered method was done and its justifiability was confirmed. The offered method of positioning and tracking is universal for the different types of the robotic holders with different number of DOFs.

The recognition of facial gestures using biopotentials muscle signals has been proposed for human machine interface. Real-time myoelectric control requires a high level of accuracy and computational load, so a compromise between these two main factors should be considered. The most informative electromyogram features, required number of channels and the most suitable architecture of the neural network were identified in this study. In this paper, a results of preprocessing data were proposed to use in facial gestures classifier. The effectiveness of different sets input data combinations was also explored to introduce the most discriminating.

This paper considers the task of implementing proactive control of robotic systems (RS) to rescue the sufferers. The use of a wide range of sensory elements in the RS allows you to expand the list of monitored parameters and to generate the control action with the use of predictive and proactive capabilities based on the methods and technology of integrated modeling. Consider a set of models allows to estimate the effectiveness of the existing RS rescue of sufferers or form of requirements to performance characteristics of the created RS to provide the necessary indicators of the effectiveness of rescue operations.

This paper describes the RoboCup Humanoid KidSize team Photon. We used Robotis DARwIn-OP robot platform and develop own software to create robot soccer team. We discuss about our software implementation of computer vision, communications, movements and main control modules.

The process of control of mobile robots (MR) with typical structure, which includes sensors, onboard computer, servomechanisms being organized in multi-loop control systems, and a communicator, is investigated. It is shown, that distinctive feature of the process of MR control is rigid demands both to time of sensors/servomechanisms interrogation, and to delay between receiving information from sensors and delivering adequate command to servomechanism. Approach to modeling of the process of interpretation of external commands by onboard digital control system, based on representation of cyclogram of equipment functioning as 2-parallel semi-Markov process, is proposed. Method of transformation of 2-parallel process into ordinary semi-Markov process is worked out. Dependencies for definition of elements of semi-Markov matrix of pooled semi-Markov process are obtained. Also are obtained dependencies for calculation of time and stochastic parameters of wandering through pooled semi-Markov process and distribution of probabilities of residence of process in its states in steady state regime of functioning. Perspectives of development of direction of mobile robot control are determines.

The paper propose an interaction scenario for collaborative work of mobile robots for coalition creation and joint task solving. Scenario is considered as cyber-physical-social system that includes acting resources (mobile robots) that implements actions in physical space; information resources (robot control blocks, user mobile devices, computation services, etc.) that operate in information space; and social resources (users) that form tasks in social space. The following main operations have been identified for robot interaction scenario: mobile robot set forming that are ready to participate in scenario, coalition creation, scenario operation. Scenario has been implemented based on Smart-M3 information sharing platform that provides possibilities for different resources to share information and knowledge in cyber space with each other based on RDF ontologies.

One of the most significant features in applied linguistics and recognition technologies used in methods of spoken language recognition is speech signal which includes some primary tasks: preprocessing, processing and recognition regarding next main important features of acoustic analysis of spoken language: \(F_{0i}, I_{{i}}, t_{{i}}, F_{{ni}}\). This paper presents one of the human machine methods with regard to continuous speech detection on the basis of formant Fni analysis. There are many ways to perform acoustic analysis, but the acoustic-phonetic recognition functions at the phoneme and prosody level seem to be one of the classical speech recognition methods.

The prototype software for humanoid robot assistant for a preschool children was developed. Aldebaran NAO robot was used for this development. This paper describes the idea, main concepts and applications for robot.

The paper describes the control system of an autonomous mobile service robot using a human-machine dialogue to control the robot in a way natural for human with the help of syntactic structures that define the sequence of certain actions. The interaction with the robot by means of natural language in the formation of target designations is provided by the multimodal representation of the working area in the form of a hybrid map of the surrounding space with highlited work areas and locations of key objects complemented by a set of semantic relations that characterize features of the robot operation and impact of the environmental changes on its operation. The article discusses the control system of the mobile service robo, performing transport and logistics operations in a public place in direct contact with lots of people around. The proposed approach to the dialog control of the robot based on the multimodal representation of the robot operation area not only simplifies the process of determining the sequence of operations, but also enhances the level of safety for other people, objects and the robot itself in the process of fulfilling its service tasks.

We present software and hardware solutions for volumetric display testing unit with projector array. We designed workstation based on sixteen single-board computers Raspberry Pi 2 Model B, which connect our testing unit to the user computer. Also there is provided the interface to load and control three-dimensional models in .3ds format through user computer. Our experimental system provides sixteen images with 800\(\,\times \,\)600 resolution for forming volume in \(160^\circ \) visibility in horizontal direction. Our developing project will be useful for application in simulators and for solving CAD tasks in mechatronic systems. Further, it is planned to create a volumetric display with all-round visibility of dynamic full-color images with real-time visualization for dispatching applications.

Human-robot collaboration is a novel hot topic in robotics research opening a broad range of new opportunities. However, the number of sensible and efficient use cases having been presented and analysed in literature is still very limited. In this technical article, we present and evaluate a collaborative use case for a gaming application in which a two-arm robot has to piece a Tangram puzzle together with a human partner. Algorithms and methods employed for this purpose are presented, performance rates are given for different setups, and remaining problems and future developments are outlined.