Enabling Heterogeneous Robot and Control System Communication through Network Integration

Location

Atrium

Session Format

Poster Presentation

Research Area Topic:

Engineering and Material Sciences - Mechanical

Co-Presenters and Faculty Mentors or Advisors

Biswanath Samanta, Faculty Advisor

Christopher Kadlec, Faculty Advisor

Abstract

The use of robots in complex tasks such as search and rescue operations is becoming more and more common. These robots often work independently with no cooperation with other robots or control software, and are very limited in their ability to perform dynamic tasks and interact with both humans and other robots. To this end, a system must be developed to facilitate the cooperation of heterogeneous robots to complete complex tasks for research purposes. To model and study human-robot and robot-robot interactions in a multi-system environment, a robust network infrastructure must be implemented to support the broad nature of these studies. The work presented here details the creation of a cloud-based infrastructure designed to support the introduction and implementation of multiple heterogeneous robots, hardware, and control systems to the environment utilizing the Robot Operating System (ROS).

To support such a variety of hardware and software, the network implements services such as Domain Name Service (DNS) and Dynamic IP Addressing. Wireless access was built into the network to allow mobile robots to connect to the network and access the cloud resources. The server resources are virtualized, bringing the benefits of virtualization to the robotics field. Fault tolerance and high availability ensure that robots operated by remote software through the cloud are robust and will rarely have downtime. The ability to quickly build and provide virtual machines to clients enables researchers to quickly implement additional control software without having to search for and add new hardware resources to the machines. Furthermore, virtualization allows for provisioning and reallocation of hardware resources to virtual machines quickly, with little downtime and with no need to physically rearrange hardware resources.

Implemented robots in the network include both ground-based (e.g. Kobuki Turtlebot) and air-based (e.g Parrot ARDrone2.0) systems. Additional hardware is also implemented, such as embedded vision systems, an overhead camera network for motion sensing, pattern recognition, and positional feedback, and client machines with graphics processing units (GPUs) for additional computational resources that were added to the cloud. Control software for the robots is implemented in the system with complexities ranging from simple teleoperation to skeletal tracking and spiking neural network simulators utilizing GPUs.

A robust integration of multiple heterogeneous components, including both hardware and software, is achieved. Robots were able to quickly communicate through the network to send and receive commands and data, and communications between heterogeneous robots was established and used to implement pose-mimicking, where a ground based robot would mimic an air-based robot’s orientation and velocity.

Keywords

Robotics, Virtualization, Network, Heterogeneous, Cloud, Multi-robot

Presentation Type and Release Option

Presentation (Open Access)

Start Date

4-24-2015 10:45 AM

End Date

4-24-2015 12:00 PM

This document is currently not available here.

Share

COinS
 
Apr 24th, 10:45 AM Apr 24th, 12:00 PM

Enabling Heterogeneous Robot and Control System Communication through Network Integration

Atrium

The use of robots in complex tasks such as search and rescue operations is becoming more and more common. These robots often work independently with no cooperation with other robots or control software, and are very limited in their ability to perform dynamic tasks and interact with both humans and other robots. To this end, a system must be developed to facilitate the cooperation of heterogeneous robots to complete complex tasks for research purposes. To model and study human-robot and robot-robot interactions in a multi-system environment, a robust network infrastructure must be implemented to support the broad nature of these studies. The work presented here details the creation of a cloud-based infrastructure designed to support the introduction and implementation of multiple heterogeneous robots, hardware, and control systems to the environment utilizing the Robot Operating System (ROS).

To support such a variety of hardware and software, the network implements services such as Domain Name Service (DNS) and Dynamic IP Addressing. Wireless access was built into the network to allow mobile robots to connect to the network and access the cloud resources. The server resources are virtualized, bringing the benefits of virtualization to the robotics field. Fault tolerance and high availability ensure that robots operated by remote software through the cloud are robust and will rarely have downtime. The ability to quickly build and provide virtual machines to clients enables researchers to quickly implement additional control software without having to search for and add new hardware resources to the machines. Furthermore, virtualization allows for provisioning and reallocation of hardware resources to virtual machines quickly, with little downtime and with no need to physically rearrange hardware resources.

Implemented robots in the network include both ground-based (e.g. Kobuki Turtlebot) and air-based (e.g Parrot ARDrone2.0) systems. Additional hardware is also implemented, such as embedded vision systems, an overhead camera network for motion sensing, pattern recognition, and positional feedback, and client machines with graphics processing units (GPUs) for additional computational resources that were added to the cloud. Control software for the robots is implemented in the system with complexities ranging from simple teleoperation to skeletal tracking and spiking neural network simulators utilizing GPUs.

A robust integration of multiple heterogeneous components, including both hardware and software, is achieved. Robots were able to quickly communicate through the network to send and receive commands and data, and communications between heterogeneous robots was established and used to implement pose-mimicking, where a ground based robot would mimic an air-based robot’s orientation and velocity.