Robots Using ROS: RE2's Advanced Mobile Manipulators, DARPA ARM Robot

| No Comments | No TrackBacks

re2_automatic.drop.jpgRobotics Engineering Excellence (re2, Inc.) is a research and development company that focuses on advanced mobile manipulation, including self-contained manipulators and payloads for mobile robot platforms. As a spin-out of Carnegie Mellon, they've developed plug-n-play modular manipulation technologies, a JAUS SDK, and unmanned ground vehicles (UGV). They focus on the defense industry and their clients include DARPA, the US Armed Forces (Army, Navy, Air Force), Robotics Technology Consortium, and TSWG. RE2 has recently adopted ROS as a platform to architect and organize code.

RE2 has several projects using ROS, including interchangeable end-effectors and force/tactile feedback for manipulators. Their Small Robot Toolkit (SRT) is a plug-n-play robot arm with interchangeable end-effector tools, which can be used as a manipulator payload for mobile platforms. RE2 has also developed the capability to automatically change out end-effectors, which is being used with a modular recon manipulator for vehicle-borne IEDs. Bomb technicians can switch between various tools, like drills, saws, and scope cameras, to inspect vehicles remotely. RE2 is also working on a force and tactile sensing manipulator, which provides haptic feedback for an operator. This sort of feedback makes it easier to perform tasks like inserting a key into a lock, or controlling a drill.

RE2's manipulation technologies are also being used on mobile platforms. They are developing a Robotic Nursing Assistant (RNA) to help nurses with difficult tasks, such as helping a patient sit up, and transferring a patient to a gurney. The RNA uses a mobile hospital platform with dexterous manipulators to create a capable tool for nurses to use. RE2 is also working on an autonomous robotic door opening kit for unmanned ground vehicles.

RE2's expertise in manipulation made them a natural choice to be the systems integrator for the software track of the DARPA ARM program. The goal of this track is to autonomously grasp and manipulate known objects using a common hardware platform. Participants will have to complete various challenges with this platform, like writing with a pen, sorting objects on a table, opening a gym bag, inserting a key in a lock, throwing a ball, using duct tape, and opening a jar. There will also be an outreach track that will provide web-based access. This will enable a community of students, hobbyists, and corporate teams to test their own skills at these challenges.

RE2 had it own set of challenges: build a robust and capable hardware and software platform for these participants to use. The ARM robot is a two-arm manipulator with sensor head. The hardware, valued at around half a million dollars, includes:

  • Manipulation
    • Two Barrett WAM arms (7-DOF with force-torque sensors)
    • Two Barrett Hands (three-finger, tactile sensors on tips and palm)
  • Sensor head
    • Swiss Ranger 4000 (176x144 at 54fps)
    • Bumblebee 2 (648x488 at 48fps)
    • Color camera (5MP, 45 deg FOV)
    • Stereo microphones (44kHz, 16-bit)
    • Pan-tilt neck (4-DOF, dual pan-tilt)

A future version of the robot will incorporate a mobile base.

The software platform on the ARM robot is built on top of ROS. ROS was selected by RE2 for its modularity and tools. The modularity was important as the DARPA ARM project features an outreach program that will be providing a simulator. Users can switch between using the simulated and real robot with no changes to their code. The ARM platform also takes advantage of core ROS tools like rostest for testing and rosbag for data logging.

ROS has already proven itself on the similar CMU HERB robot, which has two Barrett arms and a mobile base. The various participants, including those in the outreach track, will be able to take advantage of the many ROS libraries for perception, grasping, and manipulation. This includes open-source frameworks like OpenRAVE, which was used on HERB for grasping and manipulation tasks.

No TrackBacks

TrackBack URL: https://www.ros.org/mt-tb.cgi/262

Leave a comment

Find this blog and more at planet.ros.org.


Monthly Archives

About this Entry

This page contains a single entry by kwc published on November 29, 2010 3:10 PM.

ISR-UC ROS repository major update was the previous entry in this blog.

Early Holiday Kinect Presents is the next entry in this blog.

Find recent content on the main index or look in the archives to find all content.