Browsing by Author "Sriti, Mohamed-Foued"
Now showing 1 - 8 of 8
Results Per Page
Sort Options
- Dronemap Planner: A Service-Oriented Cloud-Based Management System for the Internet-of-DronesPublication . Koubaa, Anis; Qureshi, Basit; Sriti, Mohamed-Foued; Allouch, Azza; Javed, Yasir; Alajlan, Maram; Cheikhrouhou, Omar; Khalgui, Mohamed; Tovar, EduardoLow-cost Unmanned Aerial Vehicles (UAVs), also known as drones, are increasingly gaining interest for enabling novel commercial and civil Internet-of-Things (IoT) applications. However, there are still open challenges that restrain their real-world deployment. First, drones typically have limited wireless communication ranges with the ground stations preventing their control over large distances. Second, these low-cost aerial platforms have limited computation and energy resources preventing them from running heavy applications onboard. In this paper, we address this gap and we present Dronemap Planner (DP), a service-oriented cloud-based drone management system that controls, monitors and communicates with drones over the Internet. DP allows seamless communication with the drones over the Internet, which enables their control anywhere and anytime without restriction on distance. In addition, DP provides access to cloud computing resources for drones to offload heavy computations. It virtualizes the access to drones through Web services (SOAP and REST), schedules their missions, and promotes collaboration between drones. DP supports two communication protocols: (i.) the MAVLink protocol, which is a lightweight message marshaling protocol supported by commodities Ardupilot-based drones. (ii.) the ROSLink protocol, which is a communication protocol that we developed to integrate Robot Operating System (ROS)-enabled robots into the IoT. We present several applications and proof-of-concepts that were developed using DP. We demonstrate the effectiveness of DP through a performance evaluation study using a real drone for a real-time tracking application.
- Move and Improve: a Market-Based Mechanism for the Multiple Depot Multiple Travelling Salesmen ProblemPublication . Koubâa, Anis; Cheikhrouhou, Omar; Bennaceur, Hachemi; Sriti, Mohamed-Foued; Javed, Yasir; Ammar, AdelConsider the problem of having a team of cooperative and autonomous robots to repeatedly visit a set of target locations and return back to their initial locations. This problem is known as multi-robot patrolling and can be cast to the multiple depot multiple traveling salesman problem (MD-MTSP), which applies to several mobile robots applications. As an NP-Hard problem, centralized approaches using meta-heuristic search are typically used to solve it, but such approaches are computation-intensive and cannot effectively deal with the dynamic nature of the system. This paper provides a distributed solution based on a market-based approach, called Move-and-Improve. It involves the cooperation of the robots to incrementally allocate targets and remove possible overlap. The concept is simple: in each step, a robot moves and attempts to improve its solution while communicating with its neighbors. Our approach consists of four main phases: (1) initial target allocation, (2) tour construction, (3) negotiation of conflicting targets, (4) solution improvement. To validate the efficiency of the Move-and-Improve distributed algorithm, we first conducted extensive simulations using Webots and evaluated its performance in terms of total traveled distance, maximum tour length, and ratio of overlapped targets, under different settings. We also demonstrated through MATLAB simulations the benefits of using our decentralized approach as compared to a centralized Genetic Algorithm approach to solve the MD-MTSP problem. Finally, we implemented Move-and-Improve using ROS and deployed it on real robots.
- Move and Improve: a Market-Based Mechanism for the Multiple Depot Multiple Travelling Salesmen ProblemPublication . Koubâa, Anis; Cheikhrouhou, Omar; Bennaceur, Hachemi; Sriti, Mohamed-Foued; Javed, Yasir; Ammar, AdelConsider the problem of having a team of cooperative and autonomous robots to repeatedly visit a set of target locations and return back to their initial locations. This problem is known as multi-robot patrolling and can be cast to the multiple depot multiple traveling salesman problem (MD-MTSP), which applies to several mobile robots applications. As an NP-Hard problem, centralized approaches using meta-heuristic search are typically used to solve it, but such approaches are computation-intensive and cannot effectively deal with the dynamic nature of the system. This paper provides a distributed solution based on a market-based approach, called Move-and-Improve. It involves the cooperation of the robots to incrementally allocate targets and remove possible overlap. The concept is simple: in each step, a robot moves and attempts to improve its solution while communicating with its neighbors. Our approach consists of four main phases: (1) initial target allocation, (2) tour construction, (3) negotiation of conflicting targets, (4) solution improvement. To validate the efficiency of the Move-and-Improve distributed algorithm, we first conducted extensive simulations using Webots and evaluated its performance in terms of total traveled distance, maximum tour length, and ratio of overlapped targets, under different settings. We also demonstrated through MATLAB simulations the benefits of using our decentralized approach as compared to a centralized Genetic Algorithm approach to solve the MD-MTSP problem. Finally, we implemented Move-and-Improve using ROS and deployed it on real robots.
- MyBot: Cloud-Based Service Robot using Service-Oriented ArchitecturePublication . Koubâa, Anis; Sriti, Mohamed-Foued; Javed, Yasir; Alajlan, Maram; Qureshi, Basit; Ellouze, Fatma; Mahmoud, AbdelrahmanThis paper presents a viable solution for the development of service robots by leveraging cloud and Web services technologies, modular software architecture design, and Robot Operating System (ROS). The contributions of this paper are two- folded (1) Design of ROS Web services to provide new abstract interfaces to service robots that makes easier the interaction with and the development of service robots applications, and (2) Integration of the service robot to the cloud using the ROSLink protocol. We demonstrate through real-world implementation on the MyBot robot the effectiveness of these software abstraction layers in developing applications for service robots through the Internet and the cloud, and in accessing them through Internet. We believe that this work represents an important step towards a more popular use of service robots.
- Performance of a Low Cost Hadoop Cluster for Image Analysis in Cloud Robotics EnvironmentPublication . Qureshi, Basit; Javed, Yasir; Koubâa, Anis; Sriti, Mohamed-Foued; Alajlan, MaramWith the emergence of cloud robotics, the cloud computing paradigm becomes increasingly attractive to robotics, where the cloud acts as the remote brain of low-cost robots, such as commodity drones. The idea is to offload heavy computations, like image processing, from the robot to the cloud; process it in short time (near real-time) and send back commands to the robot. This paper investigates the performance of a back-end cloud computing framework in deploying robotics-like applications (i.e. image analysis and processing) using low-cost Hadoop clusters. The design of a low-cost mini-data center built with readily available commodity 32-bit ARM boards, i.e. Raspberry Pi 2 Model B, is presented. Furthermore, the performance of RPi-based clusters is extensively tested with different types of data including text, text/image and image, and a comparative analysis against Hadoop cluster running on virtual machines is presented. The Hadoop Image Processing Interface (HIPI) Library was used and also configured to optimally utilize the Pi Cluster resources for improved performance. Results show that the RPi Hadoop cluster lags in performance when compared to Hadoop cluster running on virtual machines, the low cost and small form factor makes it ideal for remote Image analysis in surveillance / disaster recovery scenarios where UAVs can transmit image streams to the Cluster for remote processing.
- Robot Path Planning and CooperationPublication . Koubaa, Anis; Bennaceur, Hachemi; Chaari, Imen; Trigui, Sahar; Ammar, Adel; Sriti, Mohamed-Foued; Alajlan, Maram; Cheikhrouhou, Omar; Javed, YasirThis book presents extensive research on two main problems in robotics: the path planning problem and the multi-robot task allocation problem. It is the first book to provide a comprehensive solution for using these techniques in large-scale environments containing randomly scattered obstacles. The research conducted resulted in tangible results both in theory and in practice. For path planning, new algorithms for large-scale problems are devised and implemented and integrated into the Robot Operating System (ROS). The book also discusses the parallelism advantage of cloud computing techniques to solve the path planning problem, and, for multi-robot task allocation, it addresses the task assignment problem and the multiple traveling salesman problem for mobile robots applications. In addition, four new algorithms have been devised to investigate the cooperation issues with extensive simulations and comparative performance evaluation. The algorithms are implemented and simulated in MATLAB and Webots.
- A Service-Oriented Cloud-Based Management System for the Internet-of-DronesPublication . Koubâa, Anis; Qureshi, Basit; Sriti, Mohamed-Foued; Javed, Yasir; Tovar, EduardoDeploying drones over the Cloud is an emerging research area motivated by the emergence of Cloud Robotics and the Internet-of-Drones (IoD) paradigms. This paper contributes to IoD and to the deployment of drones over the cloud. It presents, Dronemap Planner, an innovative service-oriented cloud based drone management system that provides access to drones through web services (SOAP and REST), schedule missions and promotes collaboration between drones. A modular cloud proxy server was developed; it acts as a moderator between drones and users. Communication between drones, users and the Dronemap Planner cloud is provided through the MAVLink protocol, which is supported by commodity drones. To demonstrate the effectiveness of Dronemap Planner, we implemented and validated it using simulated and real MAVLink-enabled drones, and deployed it on a public cloud server. Experimental results show that Dronemap Planner is efficient in virtualizing the access to drones over the Internet, and provides developers with appropriate APIs to easily program drones’ applications.
- Turtlebot at Office: A Service-Oriented Software Architecture for Personal Assistant Robots using ROSPublication . Koubâa, Anis; Sriti, Mohamed-Foued; Javed, Yasir; Alajlan, Maram; Qureshi, Basit; Ellouze, Fatma; Mahmoud, AbdelrahmanThis paper presents the design of an assistive mobile robot to support people in their everyday activities in office and home environments. The contribution of this paper consists in the design of a modular component-based software architecture that provides different abstraction layers on top of Robot Operating System (ROS) to make easier the design and development of service robots with ROS. The first abstraction layer is the COROS framework composed of complementary software subsystems providing different interfaces between ROS and the client applications. The second abstraction layer is the integration of Web services into ROS to allow client applications to seamlessly and transparently interact with the robot while hiding all implementation details. The proposed software architecture was validated through a experimental prototype of Turtlebot deployed in University campus. Furthermore, we outline the challenges incurred during experimentation and focus on lessons learned throughout the implementation and deployment.