You are here: Foswiki>RoboticsWeb Web>HarrisUnderwaterGrasp (13 Jun 2013, lis12@RPI.EDU)EditAttach
Overview of Harris Underwater Grasping Project

Robotic grasping is a challenging problem. Performing the grasps underwater with a robotic arm attached to an Autonomous Underwater Vehicle is an even greater challenge. At each step uncertainty is introduced that must be overcome to achieve a successful grasp. Many of these challenges become even greater underwater.

The following questions are raised,
  • Perception - How well can we locate and identify objects vs. the background?
  • Collision Avoidance - How do we avoid all obstacles in the taskspace, even if we do not have a perfect model?
  • Grasp Planning - How do we pick the best approach direction?
  • Execution - How well can we execute the plan if our perception and control are not ideal?

  • The layout of our system is as follows(you may want to zoom in a little bit wink ),

    Diagram

    Our Solution Approach

    Perception data is taken in and matched against a database of known objects. Potential grasping positions a few inches away from the object (known as "pregrasps") are planned using RPI modified version of GraspIt!. The best reachable pregrasp is selected and execution can begin. To deal with perception and control uncertainties, the robot will monitor force and torque sensors at the wrist and between the fingers for unexpected readings indicating that there was unexpected contact. A negative space filtering technic is also used here, which takes in the perception data and ignore the grasps that try to grasp the part of the object that the perception system cannot "see". Then the robot controller will react to the contact to try to achieve the best possible grasp.

    Expriment Environment
    We set up our expriment environment at CSRL and test out our approaches before sending them to Harris. The environment sets are as follows,
  • 7DOF Barrett WAM
  • Schunk Parallel Jaw Gripper
  • Six-axis force torque sensor
  • Force sensors on the fingertips of the gripper
  • Nine camera OptiTrack System for object perception
  • Arm controller implemented in Matlab and xPC Target
  • Pregrasp planning performed in GraspIt!
  • Simulation performed in OpenRave
  • Results in Simulation and Actual Experiments
    Below is one of our experiments demonstrating the ability of our reactive grasping system. For more detail about our system, please check here. Also here are more videos about our progress on this project.
    dvc2d
  • The planned and filtered grasps simulated in Openrave. The user can choose which grasp he/she wants the system to execute.
  • actual_grasp
  • The grasp executed in the actual environment.
  • -- ShuaiLi - 2013-06-13
    Topic attachments
    I Attachment Action Size Date Who Comment
    GraspPlannerDiagram.pngpng GraspPlannerDiagram.png manage 351.2 K 13 Jun 2013 - 20:02 UnknownUser  
    IMAG0010.jpgjpg IMAG0010.jpg manage 1329.5 K 13 Jun 2013 - 20:22 UnknownUser  
    PREGRASP2.pngpng PREGRASP2.png manage 54.2 K 13 Jun 2013 - 20:22 UnknownUser  
    Topic revision: r1 - 13 Jun 2013, lis12@RPI.EDU
     

    This site is powered by FoswikiCopyright © by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
    Ideas, requests, problems regarding Foswiki? Send feedback