Citation
S. Srivastava, L. Riano, S. Russell, P. Abbeel. "Using Classical Planners for Tasks with Continuous Operators in Robotics". ICAPS Workshop on Planning and Robotics, 2013.

Abstract
The need for high-level task planning in robotics is well understood. However, interfacing discrete planning with continuous actions often requires extensive engineering of the solution. For instance, picking up an object may require removing many others that obstruct it. Identifying the exact obstructions requires geometric reasoning which is prohibitively expensive to precompute, with results that are difficult to represent efficiently at the level of a discrete planner. We propose a new approach that utilizes representation techniques from first-order logic and provides a method for synchronizing between continuous and discrete planning layers. We evaluate the approach and illustrate its robustness through a number of experiments using a state-of-the-art robotics simulator, accomplishing a variety of challenging tasks like picking objects from cluttered environments, where the planner needs to figure out which other objects need to be moved first to be able to reach the target object, and laying out a table for dinner, where the planner figures out effective tray-loading, navigation and unloading strategies.

Electronic downloads

• icaps13ws-planrob.pdf · application/pdf · 1193 kbytes

• HTML

  S. Srivastava, L. Riano, S. Russell, P. Abbeel. <a
  href="http://robotics.eecs.berkeley.edu/pubs/28.html"
  >Using Classical Planners for Tasks with Continuous
  Operators in Robotics</a>, ICAPS Workshop on Planning
  and Robotics, 2013.

• Plain text

  S. Srivastava, L. Riano, S. Russell, P. Abbeel. "Using
  Classical Planners for Tasks with Continuous Operators in
  Robotics". ICAPS Workshop on Planning and Robotics,
  2013.

• BibTeX

  @inproceedings{SrivastavaRianoRussellAbbeel13_UsingClassicalPlannersForTasksWithContinuousOperators,
      author = {S. Srivastava and L. Riano and S. Russell and P.
                Abbeel},
      title = {Using Classical Planners for Tasks with Continuous
                Operators in Robotics},
      booktitle = {ICAPS Workshop on Planning and Robotics},
      year = {2013},
      abstract = {The need for high-level task planning in robotics
                is well understood. However, interfacing discrete
                planning with continuous actions often requires
                extensive engineering of the solution. For
                instance, picking up an object may require
                removing many others that obstruct it. Identifying
                the exact obstructions requires geometric
                reasoning which is prohibitively expensive to
                precompute, with results that are difficult to
                represent efficiently at the level of a discrete
                planner. We propose a new approach that utilizes
                representation techniques from first-order logic
                and provides a method for synchronizing between
                continuous and discrete planning layers. We
                evaluate the approach and illustrate its
                robustness through a number of experiments using a
                state-of-the-art robotics simulator, accomplishing
                a variety of challenging tasks like picking
                objects from cluttered environments, where the
                planner needs to figure out which other objects
                need to be moved first to be able to reach the
                target object, and laying out a table for dinner,
                where the planner figures out effective
                tray-loading, navigation and unloading strategies.},
      URL = {http://robotics.eecs.berkeley.edu/pubs/28.html}
  }
  

Posted by Ehsan Elhamifar on 9 Jun 2014.
Groups: ehumans
For additional information, see the Publications FAQ or contact webmaster at robotics eecs berkeley edu.