Skip to main content
Top

2018 | Book

Interactive Collaborative Robotics

Third International Conference, ICR 2018, Leipzig, Germany, September 18–22, 2018, Proceedings

insite
SEARCH

About this book

This book constitutes the proceedings of the Third International Conference on Interactive Collaborative Robotics, ICR 2018, held in Leipzig, Germany, in September 2018, as a satellite event of the 20th International Conference on Speech and Computer, SPECOM 2018.
The 30 papers presented in this volume were carefully reviewed and selected from 51 submissions. The papers presents challenges of human-robot interaction, robot control and behavior in social robotics and collaborative robotics, as well as applied robotic and cyberphysical systems.

Table of Contents

Frontmatter
Task and Spatial Planning by the Cognitive Agent with Human-Like Knowledge Representation
Abstract
The paper considers the task of simultaneous learning and planning actions for moving a cognitive agent in two-dimensional space. Planning is carried out by an agent who uses an anthropic way of knowledge representation that allows him to build transparent and understood planes, which is especially important in case of human-machine interaction. Learning actions to manipulate objects is carried out through reinforcement learning and demonstrates the possibilities of replenishing the agent’s procedural knowledge. The presented approach was demonstrated in an experiment in the Gazebo simulation environment.
Ermek Aitygulov, Gleb Kiselev, Aleksandr I. Panov
Path Finding for the Coalition of Co-operative Agents Acting in the Environment with Destructible Obstacles
Abstract
The problem of planning a set of paths for the coalition of robots (agents) with different capabilities is considered in the paper. Some agents can modify the environment by destructing the obstacles thus allowing the other ones to shorten their paths to the goal. As a result the mutual solution of lower cost, e.g. time to completion, may be acquired. We suggest an original procedure to identify the obstacles for further removal that can be embedded into almost any heuristic search planner (we use Theta*) and evaluate it empirically. Results of the evaluation show that time-to-complete the mission can be decreased up to 9–12 % by utilizing the proposed technique.
Anton Andreychuk, Konstantin Yakovlev
Sparse 3D Point-Cloud Map Upsampling and Noise Removal as a vSLAM Post-Processing Step: Experimental Evaluation
Abstract
The monocular vision-based simultaneous localization and mapping (vSLAM) is one of the most challenging problem in mobile robotics and computer vision. In this work we study the post-processing techniques applied to sparse 3D point-cloud maps, obtained by feature-based vSLAM algorithms. Map post-processing is split into 2 major steps: (1) noise and outlier removal and (2) upsampling. We evaluate different combinations of known algorithms for outlier removing and upsampling on datasets of real indoor and outdoor environments and identify the most promising combination. We further use it to convert a point-cloud map, obtained by the real UAV performing indoor flight to 3D voxel grid (octo-map) potentially suitable for path planning.
Andrey Bokovoy, Konstantin Yakovlev
Cloud Robotic Platform on Basis of Fog Computing Approach
Abstract
This article describes the possibility of using the ideas of FOG computing as an additional layer between robotic devices and the cloud infrastructure. FOG layer, represented as a P2P network in combination with the containerized cloud infrastructure inspired by microservice patterns, provides the ability to process data based on its time-sensitivity and to increase overall benefits despite the fact of exponential growth of data. We consider that the solution of assignment problem obtained in terms of the platform is one of the keys to achieve the goal of data analysis close to devices.
Aleksandr Chueshev, Olga Melekhova, Roman Meshcheryakov
Toward More Expressive Speech Communication in Human-Robot Interaction
Abstract
It is well known that speech communication is a very important segment of human-robot interaction. The paper presents our experience from the project “Design of Robots as Assistive Technology for the Treatment of Children with Developmental Disorders”, with focus on the development of more expressive dialogue systems based on automatic speech recognition (ASR) and text-to-speech synthesis (TTS) in South Slavic languages. The paper presents the most recent results of our research related to the development of expressive conversational human-robot interaction, specifically in the field of conversion of voice and style of synthesized speech based on a new generation of deep neural network (DNN) based speech synthesis algorithms, as well as the field of emotional speech recognition. The development of dialogue strategies is described in more details in the second part of the paper, as well as the experience in their clinical applications for treatment of children with cerebral palsy.
Vlado Delić, Branislav Borovac, Milan Gnjatović, Jovica Tasevski, Dragiša Mišković, Darko Pekar, Milan Sečujski
The Dynamic Model of Operator-Exoskeleton Interaction
Abstract
Improving efficiency and productivity is an important factor in the development of robotic devices that can solve many human problems. Complex and monotonous actions that require precision and accuracy when moving large objects or performing technological processes can be carried out by redistributing part of the load on the robotic system. An example of such a system is an exoskeleton device. Active exoskeletons are referred to robotic human-machine systems. The interaction of operator and exoskeleton determines the quality of the functioning of such systems.
Practical purpose of research and development of active exoskeleton device for the human limbs is the reallocation of labor-intensive, monotonous activities on mechatronic system of exoskeleton.
This paper discusses the dynamic model of interaction between exoskeleton system and operator.
Valery Gradetsky, Ivan Ermolov, Maxim Knyazkov, Eugeny Semenov, Artem Sukhanov
The Influence of Various Factors on the Control of the Exoskeleton
Abstract
The operator is an important component of the Operator-Exoskeleton system. He is a source of signals and he controls the result of the actuators motion. The main source that drives the links of the human skeleton is the force of muscle contraction. The amplitude and frequency of the control signal is formed by the central nervous system. The work of muscles due to physiological processes leads to movement of human limbs. Biomechanics deals with the problems and tasks of the human motor system, as well as the tasks of optimization of operator’s limbs movement, evaluation of the effectiveness of the application of forces for a better achievement of the goal. This paper discusses the influence of various factors on the control of the exoskeleton.
Valery Gradetsky, Ivan Ermolov, Maxim Knyazkov, Eugeny Semenov, Artem Sukhanov
Sign Language Numeral Gestures Recognition Using Convolutional Neural Network
Abstract
This paper presents usage of convolutional neural network for classification of sign language numeral gestures. For requirements of this research, we created a new dataset of these gestures. The dataset was recorded via Kinect v2 device and it consists of recordings of 18 different people. Only depth data-stream was used in our research. For a classification task, there was utilized classic VGG16 architecture and its results were compared with chosen baseline method and other tested architectures. Our experiment on classification showed the great potential of neural networks for this task. We reached recognition accuracy 86.45%, which is by more than 34% better result than chosen baseline method.
Ivan Gruber, Dmitry Ryumin, Marek Hrúz, Alexey Karpov
Consensus-Based Localization of Devices with Unknown Transmitting Power
Abstract
A novel localization scheme, based on RSSI is demonstrated in this manuscript. Previous methods require fingerprinting which is not suitable to locate sources in different environments or they need to know the transmitted power from the source as well as antenna and channel characteristics to apply the propagation loss formula. However, the proposed method of this paper only compares the received powers by antennas on a linear array and applying a control algorithm to ensure the formation, then find the location of the source device. The new control algorithm is driven by using the differences of received signal powers.
Nurbanu Güzey, Hacı Mehmet Güzey
Modelling Characteristics of Human-Robot Interaction in an Exoskeleton System with Elastic Elements
Abstract
In the paper, problem of modelling the human robot interactions in an exoskeleton system is investigated. In particular, a the case of a lower limb exoskeleton is considered. The interaction is supported by a special connector device featuring elastic elements and pressure sensors, allowing measuring the relative position of the human body and the mechanism links. An algorithm for calculating the position of the human body using the feedback from the pressure sensor is presented. Simulation results taking into account the noise and quantization of the sensor output showed validity of the proposed algorithm. Further simulations allowed to analyze the behavior of the control system in the case of harmonic inputs over a range of different frequencies.
Sergey Jatsun, Sergei Savin, Andrey Yatsun
Safety-Related Risks and Opportunities of Key Design-Aspects for Industrial Human-Robot Collaboration
Abstract
For several years, sensitive robots are used in industry and in some cases perform collaborative tasks directly with humans on shared workplaces. At first glance, this type of human-machine interaction is associated with high risks. However, additional devices, advanced functionalities and risk mitigation activities can ensure that such collaborative scenarios are safe for humans. The essential aspects are the collaborative operation methods, workspace layout, end effectors, human machine interfaces and ergonomics. In this work we shed light on these important aspects of human-robot collaboration and discuss its facets. By adequately reducing and communicate potential indiscernible risks a robot is made trustworthy for a human being.
Lukas Kaiser, Andreas Schlotzhauer, Mathias Brandstötter
Improvements in 3D Hand Pose Estimation Using Synthetic Data
Abstract
The neural networks currently outperform earlier approaches to the hand pose estimation. However, to achieve the superior results a large amount of the appropriate training data is desperately needed. But the acquisition of the real hand pose data is a time and resources consuming process. One of the possible solutions uses the synthetic training data. We introduce a method to generate synthetic depth images of the hand closely matching the real images. We extend the approach of the previous works to the modeling of the depth image data using the 3D scan of the subject’s hand and the hand pose prior given by the real data distribution. We found out that combining them with the real training data can result in a better performance.
Jakub Kanis, Dmitry Ryumin, Zdeněk Krňoul
Ontology-Based Human-Robot Interaction: An Approach and Case Study on Adaptive Remote Control Interface
Abstract
The paper presents an approach to human-robot interaction in socio-cyberphysical systems. The paper propose a socio-cyberphysical system ontology that is aimed at describing the knowledge of the system resources. Humans are interacted with robots using personal smartphones. Every robot and mobile application for smartphone are designed based on the ontology that allows to support their semantic interoperability in socio-cyberphysical system. A case study considered in the paper is aimed at controlling the robots by group of humans. Group of robot consists of several robot types. Every type of robot has competencies that are described in the robot competency profile. Human experts also have own competencies that are described in the human profile. To control a robot a human should be available and have an appropriate competency for such type of robot. The paper describes the developed prototype for Android-based smartphone. The prototype implements the proposed approach and based on the developed ontology and Smart-M3 information sharing platform.
Alexey Kashevnik, Darya Kalyazina, Vladimir Parfenov, Anton Shabaev, Olesya Baraniuc, Igor Lashkov, Maksim Khegai
A Decentralized Data Replication Approach for the Reconfigurable Robotic Information and Control Systems
Abstract
This paper continues our previous studies on the reconfigurable robotic information and control system dependability. We consider the approach to the configuration forming optimization problem solving. This approach presupposes the criteria number reducing by the additional software functions implementation. These functions include tasks context data replication to the computational units, where those tasks can be launched after the reconfiguration procedure. Within the current paper some generic approaches to the context data storage element interaction are presented. The first approach is centralized and based on the principles of Viewstamped replication protocol, the second one is fully decentralized. Both of the approaches are discussed and estimated in terms of the communication environment workload, the conclusion is made, as well as some outlines of the future work.
Eduard Menik, Anna Klimenko
The Model of Autonomous Unmanned Underwater Vehicles Interaction for Collaborative Missions
Abstract
Results of the work carried out by Saint-Petersburg State Marine Technical University in the framework of the project, connected with complex researches in maintenance of creation of a multi-agent sensory-communication network based on marine robotic platforms (MRP), are presented. In the context of the mentioned works, creation and testing of communication protocol for µAUVs with hydroacoustic modems is proposed. The article describes steps of protocol creation: from mission planning to modem control and modeling with digital imitation model testing (Solving the task of monitoring the seabed area). Within the framework of the concept of a “budget”, limited serial product, functional systems/modules of µAUV are worked out, taking into account the availability of equipment and components (concerning required technical characteristics and their cost). For the selected external appearance and design dimensions of the device, the simulation of hydrodynamic, signal power and energy characteristics were performed. Within the framework of the project, a software and hardware architecture of the information system of the vehicle was developed, as well as a model of interaction between the µAUV, the wave glider and control center. The work results in proposal and testing of µAUVs communication through the water. Simulation results of implementing mission by a group of developed µAUVs can be modeled by ground robots with some software limitations. Based on the results, ways for further work on the subjects are being determined.
Igor Kozhemyakin, Ivan Putintsev, Vladimir Ryzhov, Nikolay Semenov, Mikhail Chemodanov
Cognitive Components of Human Activity in the Process of Monitoring a Heterogeneous Group of Autonomous Mobile Robots on the Lunar Surface
Abstract
The article examines the peculiarities of cognitive activity of a Human Operator (HO) to remote monitoring a heterogeneous group of Autonomous (unmanned) Mobile Robots (AMR) in aspects of ensuring security of their collaborative operations. As an example of such a group, one of the possible solutions for the use of AMRs in lunar missions is considered: monitoring of a group of AMRs on the lunar surface by a cosmonaut, located over a long distance in a lunar base. In the “Human-Machine System” the cognitive approach to manage tasks is considered as a main principle of the distribution of functions. Current tasks assigned to the AMR are assumed by HO as separate cognitive units. In evaluating the current situation, this approach allows to use the following knowledge: (1) the available options for decision-making; (2) the conditions for the implementation of particular task in the required chain of tasks; (3) the parameters of activity of all members of the group, (4) the amount of data about the environment and the current situation. To build coordinated actions, that meet the requirements for collisions prevention, it is necessary to use a single semantic basis for designing Human-Robot Interaction (HRI) and special tools for information support of HO. This paper discusses a few of possible solutions.
Boris Kryuchkov, Vitaliy Usov, Denis Ivanko, Ildar Kagirov
About One Approach to Robot Control System Simulation
Abstract
Mobile robot onboard equipment functioning is considered. It is shown, that abstract analogue of one equipment unit operation is an ordinary semi-Markov process. This abstraction is insufficient for analytical modeling the mobile robot as a whole, so to simulate synchronized onboard equipment functioning, it is necessary to use more complicated abstraction based on integration of ordinary processes to so-called M-parallel semi-Markov process. For definition of such abstraction notification “functional states” as combinations of structural states is introduced. Method of definition of semi-Markov matrix parameters, such as time of residence in functional states and probabilities of switches from current functional states to neighboring functional states is proposed. Theoretical result is confirmed by modeling of homogeneous system, every unit of which may resident in “on” of “off” state.
Eugene Larkin, Alexey Bogomolov, Aleksandr Privalov, Maksim Antonov
Providing Availability of the Smart Space Services by Means of Incoming Data Control Methods
Abstract
This paper deals with estimating and providing availability of corporate smart space services on the example of the interactive corporate television service. For this purpose, the authors explore the known methods of traffic flow filtering, propose a technique to estimate the service availability, build the mass queuing model of the service and carry out the experiments with filtering methods. The experiments show that the effect values have peaks that depend on the conditions of operating and the filtering method parameters. So, the problem of determining the filtering method parameters can be represented as an optimization problem in a multidimensional space. The changing conditions of operating may be taken into account using adaptive approaches. Further research direction include: classifying and analyzing different ways (models, scenarios, modalities) of interaction between users and service, exploring the possibility of applying non-temporal parameters to analyze request flows, building the general threat taxonomy for the corporate smart space services including threats to confidentiality, integrity and availability, considering the possibility of implementing the complex service protection taking into account threat sources, threats, risk events and effects.
Dmitriy Levonevskiy, Irina Vatamaniuk, Anton Saveliev
Automatic Synthesis Gait Scenarios for Reconfigurable Modular Robots Walking Platform Configuration
Abstract
Reconfigurable mechatronic modular robots distinguished mainly by their ability to adapt their structure to specific tasks to be performed as well as to specific environments, are of great interest for a wide range of different applications. One of the key problems in motion control of this type of robots lies in the necessity to use original algorithms for each of the possible configurations whose variety is determined by the structure of mechatronic modules their number and the coupling option selected. Some standard configurations of mechatronic modular robots allow the possibility to develop motion control algorithms invariant to the number of modules in the kinematic structure. Yet, a promising approach to solving the problem is generally related to the development of self-learning means and methods to enable an automated synthesis of motion control algorithms for multi-unit mechatronic modular robots, taking into account the selected configuration. The present article discusses the results of exploratory research on using the apparatus of self-learning finite state machines for solving the problem of automated synthesis of gait scenarios in the walking plat-form configuration. The paper presents the results of model experiments confirming the workability and efficiency of the developed algorithms.
Sergey Manko, Evgeny Shestakov
Fast Frontier Detection Approach in Consecutive Grid Maps
Abstract
This paper deals with frontiers detection in occupancy grid maps. The proposed method is based on differences between consecutive maps. Using this approach, frontiers detection is accelerated by calculating the third map which contains only new data. Thus, only new frontiers are detected and added to the list of frontiers. The main contribution of this paper is the description of the proposed approach and its open sourced implementation in Python. Moreover, several results of experiments are discussed. The proposed approach is capable to run very fast even for large maps with many frontiers.
Petr Neduchal, Miroslav Flídr, Miloš Železný
Design and Operation Principles of the Magnetomechanical Connector of the Module of the Mobile Autonomous Reconfigurable System
Abstract
The object of this research is a multifunctional modular robot that can reconfigure the nodes and operatively change their position in the process of operation depending on the current task. The purpose of work is to study and develop homogeneous groups of robots capable of moving autonomously and forming various structures by connecting separate modules to each other. The novelty consists in the design of a module for mobile autonomous reconfigurable system (MARS), which differs from the analogues by the presence of a hybrid coupling mechanism embedded into the motor-wheel module. The developed magnetomechanical connector provides for positioning of the robotic modules relative to each other at the coupling stage and the connection of blocks of complex structures. Control of the polarity of the magnetic circuit, which is part of the connector, is carried out by the supply of short-term pulses that perform the coupling and decoupling of the units. In the course of experiments, we determined the parameters of the magnetic circuit and the principles of the functioning of the combined magnetic circuit ensuring the energy efficiency of the connector. The module moves along surfaces by means of motor wheels which comprise the coupling system of the modules. This approach allows one to save space in the robotics module and efficiently use its main part for the arrangement of power supplies and control devices. Two schemes for placing sets of magneto-mechanical connectors in the basic module were proposed.
Nikita Pavliuk, Konstantin Krestovnikov, Dmitry Pykhov, Victor Budkov
Trends in Development of UAV-UGV Cooperation Approaches in Precision Agriculture
Abstract
Multiple unmanned aerial vehicle (UAV) and unmanned ground vehicle (UGV) heterogeneous cooperation provides a new breakthrough for the effective applications. UGV is generally capable of operating outdoors and over a wide variety of terrain, functioning in place of humans. Multiple UAVs can be used to cover large areas searching for targets. However, sensors on UAVs are typically limited in operating airspeed and altitude, combined with attitude uncertainty, placing a lower limit on their ability to resolve and localize ground features. UGVs on the other hand can be deployed to accurately locate ground targets, but they have the disadvantage of not being able to move rapidly or see through such obstacles as buildings or fences. Analysis of the tasks of existing UAVs in the field of agriculture is presented and main tasks of UGV in context UAV-UGV cooperation are considered.
Quyen Vu, Mirko Raković, Vlado Delic, Andrey Ronzhin
Structural Analysis and Animated Simulation of Biotechnical Position-Velocity Control System of a Robot-Manipulator
Abstract
The comparative analysis of different types of structures of algorithms for a robot-manipulator control has been performed for the open-loop and closed-loop semi-automatic control by the gripper velocity and position vectors. Computer models have been developed for a position-velocity control system with reconfigurable structure of algorithms for a robot performing standard operations set by a human operator with a 3-degree-of-freedom handle. In the developed models an operator is represented by a vector dynamic element with dead time. Animated simulation of dynamic processes in systems with different structures of control algorithms has been performed and their precision characteristics have been evaluated. Some practical recommendations are given on the application of the achieved results for the development of training simulators for operators of robot control systems.
Ekaterina Rostova, Nikolay Rostov, Boris Sokolov
Proactive Localization System Concept for Users of Cyber-Physical Space
Abstract
We propose proactive localization system as a part of cyber-physical-social space. The proactive localization system allows to track every mobile entity of the system: man, autonomous mobile robot, etc. It’s possible to predict activity of the tracking object, using machine learning techniques. In this paper we compare different machine learning models for our system, and present the results of testing trained models.
Anton Saveliev, Dmitrii Malov, Alexander Edemskii, Nikita Pavliuk
Current Control in the Drives of Dexterous Robot Grippers
Abstract
At present, the actuality of improving approaches to the creation of dexterous gripper for robots with force controls and their control algorithms is growing due to the need to develop areas of robotics related to the manipulation of fragile objects, interaction with people, prosthetics and rehabilitation robotics. The force control in the dexterous grippers of robots using an electric drive is provided by current control. Therefore, the purpose of this article is to consider various current regulators in the context of their application in dexterous grippers and manipulators with the force control. PI, adaptive, relay and relay, with adjustment of the hysteresis loop, current regulators are compared in such characteristics as transient response, accuracy, robustness, switching losses and switching frequency stability. The article proposes a new method for synthesizing hysteresis regulators with the adjustment of the hysteresis loop, which assumes the use of standard frequency synthesis of control systems with feedback. The proposed method extends such quality parameters as stability stocks, transient time, cutoff frequency to the adjustment loop. The considered hysteresis controller with the adjustment loop, in contrast to the classical hysteresis regulator, ensures the stabilization of the switching frequency and the reduction of the current pulsations in the motor driver. The article also presents the results of the two-finger gripper force control with the use of various current regulators for the chosen law of forces distribution between the drives.
Vladimir Serebrennyj, Andrey Boshlyakov, Alexander Ogorodnik
Comparing Fiducial Markers Performance for a Task of a Humanoid Robot Self-calibration of Manipulators: A Pilot Experimental Study
Abstract
This paper presents our pilot study of experiments automation with a real robot in order to compare performance of different fiducial marker systems, which could be used in automated camera calibration process. We used Russian humanoid robot AR-601M and automated it’s manipulators for performing joint rotations. This paper is an extension of our previous work on ARTag, AprilTag and CALTag marker comparison in laboratory settings with large-sized markers that had showed significant superiority of CALTag system over the competitors. This time the markers were scaled down and placed on AR-601M humanoid’s palms. We automated experiments of marker rotations, analyzed the results and compared them with the previously obtained results of manual experiments with large-sized markers. The new automated pilot experiments, which were performed both in pure laboratory conditions and pseudo field environments, demonstrated significant differences with previously obtained manual experimental results: AprilTag marker system demonstrated the best performance with a success rate of 97,3% in the pseudo field environment, while ARTag was the most successful in the laboratory conditions.
Ksenia Shabalina, Artur Sagitov, Mikhail Svinin, Evgeni Magid
Robust Webcam-Based Hand Detection for Initialisation of Hand-Gesture Communication
Abstract
The recognition of hand gestures is still a challenging task in real-life scenarios, especially when the hardware is restricted to a cheap optical camera. The first step in such systems is to find at least one hand that can be tracked in order to identify postures or gestures. We propose a robust and real-time method that is able to reliably detect the hand in various environments to initialize hand-gesture communication. It is based on an innovative combination of different sources of information (colour, motion, trajectory) and a dynamic hand-wave gesture commencing hand tracking and hand gesture recognition.
Tilo Strutz, Alexander Leipnitz, Björn Senkel
Multi-agent Robotic Systems in Collaborative Robotics
Abstract
This paper describes the principles of control of multi-agent robotic systems. It is a new area of robotics oriented for introduction of robotic not only into industry but into life of human. The main principles of collaborative robotics are the safety of human and easiness of robot control. The problem is how to control not a single robot but a group of robots working together. It is most important for such tasks as rescue operations, environment monitoring etc. Some approaches to solve the task of human control of a group of robots are presented in the paper.
Sergey Vorotnikov, Konstantin Ermishin, Anaid Nazarova, Arkady Yuschenko
Hybrid Force/Position Control of a Collaborative Parallel Robot Using Adaptive Neural Network
Abstract
In this paper, a new stable adaptive neural network control scheme has been presented for hybrid position and force control of the Delta parallel robot. Force control is an important technique in programming and safety for collaborative robots. The hybrid control scheme is introduced to tackle the interaction problem between the robot and its environment such that the robot follows the position trajectory and desired force, which is applied in a certain position. The goal of the control is applying desired force trajectory in a certain position in which there is a constraint for movement. Fewer parameter settings, adaptive algorithm, and efficient control input signals are the advantages of the proposed controller.
Seyedhassan Zabihifar, Arkadi Yuschenko
Swarm Robotics: Remarks on Terminology and Classification
Abstract
Swarm robotics is a fast-growing field of research in recent years. As studies count increases, the terminology requires a revision in order to provide a proper level of unification and precision - even a unique “swarm robotics” term needs to be established. Since there are multiple types of collective robotics approaches and corresponding methodology, swarm robotics field terminology must be explicitly distinguished from others. In this paper, we attempt to compare and refine definitions that had been proposed in previous researches. We demonstrate relations between swarm robotics and concepts of adjacent fields including multi-agent systems, multi-robot systems and sensor networks.
Aufar Zakiev, Tatyana Tsoy, Evgeni Magid
Backmatter
Metadata
Title
Interactive Collaborative Robotics
Editors
Prof. Andrey Ronzhin
Prof. Gerhard Rigoll
Roman Meshcheryakov
Copyright Year
2018
Electronic ISBN
978-3-319-99582-3
Print ISBN
978-3-319-99581-6
DOI
https://doi.org/10.1007/978-3-319-99582-3

Premium Partner