Cloud Robotics Research Articles

Predicting the internal model of a robotic system from its morphology

The estimation of the internal model of a robotic system results from the interaction of its morphology, sensors and actuators, with a particular environment. Model learning techniques, based on supervised machine learning, are widespread for determining the internal model. An important limitation of such approaches is that once a model has been learnt, it does not behave properly when the robot morphology is changed. From this it follows that there must exist a relationship between them. We propose a model for this correlation between the morphology and the internal model parameters, so that a new internal model can be predicted when the morphological parameters are modified. Different neural network architectures are proposed to address this high dimensional regression problem. A case study is analyzed in detail to illustrate and evaluate the performance of the approach, namely, a pan–tilt robot head executing saccadic movements. The best results are obtained for an architecture with parallel neural networks. Our results can be instrumental in state-of-the-art trends such as self-reconfigurable robots, reproducible research, cyber–physical robotic systems or cloud robotics, in which internal models would available as shared knowledge, so that robots with different morphologies can readily exhibit a particular behavior in a given environment.

A Comprehensive Survey of Recent Trends in Cloud Robotics Architectures and Applications

Cloud robotics has recently emerged as a collaborative technology between cloud computing and service robotics enabled through progress in wireless networking, large scale storage and communication technologies, and the ubiquitous presence of Internet resources over recent years. Cloud computing empowers robots by offering them faster and more powerful computational capabilities through massively parallel computation and higher data storage facilities. It also offers access to open-source, big datasets and software, cooperative learning capabilities through knowledge sharing, and human knowledge through crowdsourcing. The recent progress in cloud robotics has led to active research in this area spanning from the development of cloud robotics architectures to its varied applications in different domains. In this survey paper, we review the recent works in the area of cloud robotics technologies as well as its applications. We draw insights about the current trends in cloud robotics and discuss the challenges and limitations in the current literature, open research questions and future research directions.

Cloud robot: semantic map building for intelligent service task

When a robot provides intelligent services, it needs to obtain a semantic map of the complex environment. The robot’s vision is commonly used to obtain the semantic concepts and relations of objects and rooms in indoor environments, which are labeled semantic information on the map. In an actual indoor environment, because of the great variety of objects and complex arrangements, a key problem is building a semantic map successfully in which the scale of the semantic database is large and the query speed is highly efficient. However, this is often a difficult problem to solve. Combined with cloud technology, the semantic acquisition structure of an environment based on the cloud is constructed by designing a cloud semantic database; the cloud robot can not only obtain the geometric description of the environment but also obtain the semantic map that contains the objects’ relationships based on a rich semantic database of the complex environment. It solves the problems of low-reliability when adding semantic information, errors in updating the map and the lack of scalability in the process of constructing the semantic map. An SVM (Support Vector Machine) algorithm is used to classify the semantic subdatabase on the foundation of which the feature model database is formed by extracting key feature points based on network text classification. Combining the semantic subdatabase with the semantic classification list, the objects can be quickly identified. Based on the abundant cloud semantic database, the cloud semantic map for intelligent service tasks can be implemented. The classification efficiency of the simulated experiments in the semantic database is analyzed, and the validity of the method is verified.

Indian Scientist Research Productivity in Cloud Robotics: A Scientometric Analysis

This study analyses the Indian contributions of research papers related to Cloud Robotics was undertaken from Web of Science Databases has been used to retrieve the data for 15 years (1999-2013) by the searching the keyword “Cloud Robotics”. Most of the researchers preferred to publish their research results in 586 journal articles. The authorship trend shows that, out of total 629 research literatures published, 97% of them or published under the joint author of publications in Cloud Robotics research output. This study aims to examine the emergence of research areas, research groups and countries and the pattern of publication, authorship, institutions, growth rate of publication and journals coverage of the scientists in the field of Cloud Robotics.

Context-Aware Cloud Robotics for Material Handling in Cognitive Industrial Internet of Things

In the context of Industry 4.0, industrial robotics such as automated guided vehicles have drawn increased attention due to their automation capabilities and low cost. With the support of cognitive technologies for industrial Internet of Things (IoT), production processes can be significantly optimized and more intelligent manufacturing can be implemented for smart factories. In this paper, for advanced material handling, a cognitive industrial entity called context-aware cloud robotics (CACR) are introduced and analyzed. Compared with the one-time on-demand delivery, CACR is characterized by two features: 1) context-aware services and 2) effective load balancing. First, the system architecture, advantages, challenges, and applications for CACR are introduced. Then, fundamental functions for material handling are articulated, namely, decision-making mechanisms and cloud-enabled simultaneous localization and mapping. Finally, a CACR case study is performed to highlight its energy-efficient and cost-saving material handling capabilities. Simulations indicate the superiority of cognitive industrial IoT and show that using CACR for material handling can significantly improve energy efficiency and save cost.

Achieving Reproducibility and Closed-Loop Automation in Biological Experimentation with an IoT-Enabled Lab of the Future

A robotic cloud laboratory driven by a state-of-the-art unified laboratory operating system integrates automated hardware, humans, and sensors. This lab of the future system enables researchers to transparently and collaboratively create, optimize, and organize biological experiments to achieve more reproducible results, perform around-the-clock experimentation, and more efficiently navigate the vast parameter space of biology.

IOT and big data based cooperative logistical delivery scheduling method and cloud robot system

Many studies have been done for logistics delivery scheduling technologies, but the cooperating and relaying of resources in the process of logistics delivery remains elusive. We proposed IOT and big data based cooperative logistical delivery scheduling method and cloud robot system, After obtaining the big data of logistics delivery resources and requirements from logistics delivery companies through the IOT and/or Internet, establishing the map of logistics delivery routes based on the big data of logistics delivery resources, the logistics delivery route corresponding to the logistics delivery requirements is selected from the map of logistics delivery routes by using the shortest route algorithm of the graph theory, and then the logistics delivery resources corresponding to the logistics delivery route are scheduled to the corresponding logistics delivery requirements, which can greatly improve the cooperative scheduling of logistics delivery resources among different logistics delivery companies to enhance the level of logistics delivery resources utilization, reduce the logistics delivery costs, and improve customer experience.

The Exchange of Knowledge Using Cloud Robotics

To enable robots to perform human-level tasks flexibly in varying conditions, we need a mechanism that allows them to exchange knowledge between themselves for crowd-sourcing the knowledge gap problem. One approach to achieve this is to equip a cloud application with a range of encyclopedic knowledge (i.e. ontologies) and execution logs of different robots performing the same tasks in different environments. In this paper, we show how knowledge exchange between robots can be done using OPENEASE as the cloud application. We equipped OPENEASE with ontologies about the kitchen domain, execution logs of three robots operating in two different kitchens, and semantic descriptions of both environments. By addressing two different use cases, we show that two PR2 robots and one Fetch robot can successfully adapt each other's plan parameters and sub symbolic data to the experiments that they are conducting.

A BP Network Control Approach for QoS-Aware MAC in Cloud Robotics

The basic idea of Cloud Robotics is dynamically uploading the compute-intensive applications to the cloud, which greatly enhances the intelligence of robots for the high processing and parallel ability of cloud. However, for the nature of uncertainty of mobility, different kinds of applications on robot may have different Quality of service (QoS). The paper proposes a BP network for QoS-aware MAC(BPFD-MAC) in Cloud Robotics form a view control theory, which can support both absolute and relative QoS guarantees while the energy saving. The hard and soft QoS constraints are de-coupled by normalized into a two-level cascade feedback loop. The former is Active Time Loop (AT-Loop) to enforce the absolute QoS guarantee for real-time application and the later is Contention Window Loop (CW-Loop) to enforce the relative QoS guarantee for Best Effort traffics. Finally, the Back-propagating (BP) neuron network based PID is used for self-tuning parameters and controller design. The hardware experiments demonstrate the feasibility of BPFD-MAC. Comparing with FD-MAC, BPFD-MAC has new feature of absolute QoS support and further developed two advantages:In the condition of heavy loads, BPFD have about 18% great throughput and 14% great power efficient; and in light load, BPFD have lower total energy consumption.

A Study of Robotic Cooperation in Cloud Robotics: Architecture and Challenges

Networked robotics involves a collection of robots working together to perform complex tasks, such as search and rescue task in disaster management. Because such tasks are beyond the capacity of a single powerful robot, networked robotics has been widely researched. However, the modes of cooperation in traditional networked robotics have been restricted by the inherent physical constraint that all computations are performed in the robotic network, with knowledge sharing being limited to the collective storage in the network. Cloud robotics, which allows robots to benefit from the rich storage, computation, and communication resources of modern data centers, is widely accepted as a promising approach to efficient robot cooperation in applications, such as disaster management. In this paper, we study robotic cooperation in cloud robotics. We first give a conceptual view of the nature of this cooperation. We then propose three novel robotic cooperation frameworks for cloud robotics: robotic knowledge sharing cooperation, robotic physical-task cooperation, and robotic computation task cooperation. Finally, we identify several critical challenges, and illustrate the potential benefits of robotic cooperation in cloud robotics.

IAPcloud: A Cloud Control Platform for Heterogeneous Robots

The cloud robotic technology makes multiple robots share resources and collaborate with each other more flexibly. Although this concept has been widely accepted by academia since it was put forward, it still faces many challenges in engineering. The main problems are that the functions of industrial robotic systems become more and more complex, and the programming language and computing environment of multiple vendor robots are significantly different, accordingly the cooperative control of different devices and the online testing become extremely difficult. Therefore, this paper proposes a new control platform for cloud robots, called IAPcloud, which has significant advantages in solving the problem of collaborative control among heterogeneous robots and their auxiliary devices, declining the programming difficulties of cloud robotic control systems and shortening the development and deployment cycle of the application. Finally, we verify the scientific and effectiveness of the IAPcloud platform by three cases, including the image recognition and tracking, the human–machine gobang game, and the online dynamic reconfiguration of control algorithms.

A Reinforcement Learning-Based Resource Allocation Scheme for Cloud Robotics

In recent years, robotic systems combined with cloud computing capability have become an emerging topic of discussion in academic fields. The concept of cloud robotics allows the system to offload computing-intensive tasks from the robots to the cloud. An appropriate resource allocation scheme is necessary for the cloud computing service platform to efficiently allocate its computing resources, when the robots send requests asking for computing service. This paper proposes a resource allocation scheme based on reinforcement learning (RL), which can make the cloud to decide whether a request should be accepted and how many resources are supposed to be allocated. The scheme realizes an autonomous management of computing resources through online learning, reduces human participation in scheme planning, and improves the overall utility of the system in the long run. Numerical results demonstrate that the proposed RL-based computing resource allocation scheme has better performances than the greedy allocation scheme.

DroneTrack: Cloud-Based Real-Time Object Tracking Using Unmanned Aerial Vehicles Over the Internet

Low-cost drones represent an emerging technology that opens the horizon for new smart Internet-of-Things (IoT) applications. Recent research efforts in cloud robotics are pushing for the integration of low-cost robots and drones with the cloud and the IoT. However, the performance of real-time cloud robotics systems remains a fundamental challenge that demands further investigation. In this paper, we present DroneTrack, a real-time object tracking system using a drone that follows a moving object over the Internet. The DroneTrack leverages the use of Dronemap planner (DP), a cloud-based system, for the control, communication, and management of drones over the Internet. The main contributions of this paper consist in: (1) the development and deployment of the DroneTrack, a real-time object tracking application through the DP cloud platform and (2) a comprehensive experimental study of the real-time performance of the tracking application. We note that the tracking does not imply computer vision techniques but it is rather based on the exchange of GPS locations through the cloud. Three scenarios are used for conducting various experiments with real and simulated drones. The experimental study demonstrates the effectiveness of the DroneTrack system, and a tracking accuracy of 3.5 meters in average is achieved with slow-speed moving targets.

Robot Identification and Authentication in a Robot Cloud Service System

In recent years, information technology has become a focus of attention. All hardware, software, and communication technologies are growing rapidly. Nowadays, we can’t live without technology. We use technology anywhere and anytime, and enjoy the convenience of technology. In particular, all kinds of network services and applications. These communication technologies and services constitute the concept of cloud computing. Cloud computing involves virtualization of service resources on the network; the entire service resources include scheduling, management, maintenance, and so on, which are carried out by specialized personnel. The goal of cloud computing is enabling users to use virtual resource pools maximally and handle large-scale computing problems anytime and anywhere via the network. Robotics is one of the rapidly developing technologies. Although there are numerous research teams working on cloud robots, research on cloud robot systems is still in its infancy and many problems have not yet been considered, such as the issues of robot privatization and communication security. Therefore, we propose a robot cloud service system and focus on four crucial issues: cloud platform central control, robot intelligence technology, robot privatization, and communication security. Finally, we use BAN logic to prove that the proposed scheme achieves mutual authentication and user anonymity. The proposed scheme can also defend against several kinds of attacks, like eavesdropping attack, impersonation attack, parallel session attack, man-in-the-middle attack, and replay attack.

Implementation of Cloud Connected Smart Robot for Environmental and Industrial Platform

<p>Cloud robotics is an emerging field that is centred on the benefits of converged infrastructure and shared services of a cloud computing environment. In this paper, a system is designed with an autonomous Pick and Place robot to sense environmental data such as temperature and Motion, along with GPS coordinates and sends them on the cloud. The mobile robot is controlled using an LPC1764 microcontroller and communicates with the cloud via a CC3200 Launchpad. A private cloud is set up using Open Stack that provides Infrastructure as a Service. The collected data are stored in a cloud server which could be viewed through a mobile app and can be used to create awareness about the environmental changes of the location under study. A proof-of-concept prototype has been developed to illustrate the effectiveness of the proposed system.</p>

A Rapid Deployment Big Data Computing Platform for Cloud Robotics

The primary contribution of this research is the production of a general cloud robotics architecture that leverages established and evolving big data technologies. Prior research in this area has not released all details of their deployed architectures, which prevents experimental results from being replicated and verified. By providing a general purpose architecture, it is hoped this framework will allow future research to build upon and begin to create a standardised platform, where research can be easily repeated, validated and compared. The secondary contribution is the critical evaluation of the design of cloud robotic architectures. Whilst prior research has demonstrated that cloud based robotic processing is achievable via big data technologies, such research has not discussed the choice in design. With the ecosystem of big data technologies expanding in recent years, a review into the most relevant technologies for cloud robotics is appropriate to demonstrate and validate the proposed architecture design.

FastSLAM 2.0 tracking and mapping as a Cloud Robotics service

The Simultaneous Localization and Mapping (SLAM) by an autonomous robot is an intensive computational problem and is considered to be a time consuming process. A major limitation of the pose tracking is the real-time constraint. The pose estimation should be done at an acceptable latency to get accurate position information. In this paper, FastSLAM 2.0 approach is proposed, where the computational process is divided into two parallel tasks, the pose tracking and the map optimization. The presented work depends on a distributed architecture where the tracking and mapping tasks concurrently operate as a service in the Cloud. Therefore, the robot onboard system is freed from all the heavy computations. The experiments are performed on public dataset comparable to state-of-the-art techniques. The results show that the computational cost of the tracking process in the Cloud is reduced by 83.6% as compared to its execution on a single robot platform.

A novel green software evaluation model for cloud robotics

The energy consumption of cloud robotics is an important design factor to be considered early in system development. Software as the main enabler of cloud robots, its energy consumption will directly influence the energy consumption level of the entire system. In this paper, we propose a green software model for cloud robotics based on energy consumption time state transition matrix (ETSTM), which can effectively integrate the logic functions, energy consumption, and execution time of software into a single model. To improve the practicability of ETSTM, we provide a software energy consumption function based on software characteristic fitting by a backpropagation (BP) neural network, which can be used to predict software energy consumption. Furthermore, we provide two types of energy consumption analysis algorithms based on explicit execution path search and bounded model checking (BMC) for ETSTM. The experiment results show that the proposed method can achieve good performance.

Three dimensional memristor-based neuromorphic computing system and its application to cloud robotics

Neuromorphic computing based on three-dimensional inetgraed circuits (3D-NCs) offers a novel hardware implementation of neuromorphic computing, and provides high device density, massively parallel signal processing capability, low power consumption, and direct analog signal processing capability. In this paper, by replacing conventional CPUs based on Von Neumann architecture with 3D-NCs, a novel neuromorphic computing based cloud robotics (NC-robotics) system is proposed, which is constructed by 1) cloud server center using 3D-NCs as computing units, 2) neuromorphic robotics based on neural network control technology. Besides the benefits of normal Cloud Robotics platform, this NC- Robotics system has more advantages on massive parallel-computing, analog signals processing, and lower power consumption. In order to implement this NC––Robotics system, a novel 3D-NCs architecture combining vertical RRAM structure is investigated and its concise equivalent circuit model is created, evaluated, and analyzed through SPICE simulations.

Predictive current control of a switched reluctance machine in the direct-drive manipulator of cloud robotics

Cloud robotics has undergone rapid development. As an important candidate for direct-drive manipulator, switched reluctance machines (SRMs) face significant challenge in terms of control used in cloud robotics because of latency and package losses in network communication. In this paper, predictive current control of SRMs is extended to use in controller upon cloud in the face of latency and package losses. The starting point of predictive model is modified to eliminate errors caused by latency in sensor-controller communication, and the execution of control command sequence is dynamically regulated according to the arrival time of the following sequence to adapt for latency and package losses in controller-actuator communication. The proposed control method is evaluated in a 1.5 kW SRM test platform and comparison with a conventional control method is performed; the results show that the proposed control method has better tracking performance in face of time delay and package losses in transmission.