Fig. 9. This sequence of images shows the process by which two robots flip a table.
To test robustness of the implementation, we performed
twelve repeated trials of the table assembly. Of those, nine
were completely successful. In three trials, a screw missed
the hole. Once, the screwing device failed due to software. In
all, we observed 48/48 successful pickups, 44/48 successful
placements, and 47/48 successful attach operations. Minor
human assistance permitted all trials to run to completion.
X. DISCUSSION AND FUTURE WORK
In this paper, we describe an implementation of a furniture
assembly system. Parts of the planning system are quite gen-
eral in capability, such as planning “from scratch” with only
the geometric form of the components as input—not even
their assembled shape. We introduce a new language that
is intuitive for humans and robots that efficiently expresses
symbolic planning problems. We describe a modular system
for powered tool use by the KUKA youBot. We discuss a
distributed task allocation system for a team of robots that is
capable of dynamically reassigning tasks as needed, subject
to the capabilities of each robot, demonstrated through the
assembly of an IKEA Lack table. Finally, we discuss an
approach to multi-robot coordination for co-manipulation,
illustrated through the flipping of the table.
Future work primarily revolves around making the system
more generic. We plan to generalize the implementation of
symbolic actions for manipulation to broaden the variety of
furniture kits the system can assemble. We also intend to
generalize the collaboration framework to achieve a variety
of co-manipulation tasks besides object-flipping. Finally,
failure detection and recovery will be added for robustness.
REFERENCES
[1] A. P. Ambler and R. J. Popplestone. Inferring the positions
of bodies from specified spatial relationships. Artificial Intel-
ligence, 6:157–174, 1975.
[2] J. Aycock. Compiling little languages in python. In Proceed-
ings of the 7th International Python Conference, 1998.
[3] R. Diankov. Automated Construction of Robotic Manipulation
Programs. PhD thesis, Carnegie Mellon University, Robotics
Institute, August 2010.
[4] F.W. Heger. Assembly Planning in Constrained Environments:
Building Structures with Multiple Mobile Robots. PhD thesis,
Carnegie Mellon University, Robotics Institute, August 2010.
[5] A. Hertle. Design and implementation of an object-
oriented planning language. Master’s thesis, Albert-Ludwigs-
Universit
¨
at Freiburg, 2011.
[6] J. Hoffmann and B. Nebel. The FF planning system: Fast
plan generation through heuristic search. Journal of Artificial
Intelligence Research, 14:253–302, month 2001.
[7] L.S. Homem de Mello and A.C. Sanderson. A correct and
complete algorithm for the generation of mechanical assembly
sequences. IEEE Transactions on Robotics and Automation,
7(2):228–240, April 1991.
[8] R.A. Knepper and D. Rus. Pedestrian-inspired sampling-based
multi-robot collision avoidance. In Proceedings of the IEEE
International Symposium on Robot and Human Interactive
Communication, Paris, France, September 2012.
[9] D. McDermott, M. Ghallab, A. Howe, C. Knoblock, A. Ram,
M. Veloso, D. Weld, and D. Wilkins. PDDL—the plan-
ning domain definition language. Technical Report CVC
TR98003/DCS TR1165, Yale Center for Computational Vi-
sion and Control, New Haven, USA, 1998.
[10] P.K. Nguyen, R. Ravindran, R. Carr, D.M. Gossain, and
K.H. Doetsch. Structural flexibility of the shuttle remote
manipulator system mechanical arm. Technical report, SPAR
Aerospace Ltd., 1982.
[11] J. Latombe R.H. Wilson. Geometric reasoning about mechan-
ical assembly. Artificial Intelligence, 71:371–396, 1994.
[12] J. Romanishin. Development of a robotic torque application
gripper for automated furniture assembly, 2012. Undergradu-
ate Thesis.
[13] D. Rus, B. Donald, and J. Jennings. Moving furniture with
teams of autonomous robots. In Proceedings of the IEEE
International Conference on Intelligent Robots and Systems,
August 1995.
[14] A. Spr
¨
owitz, P. Laprade, S. Bonardi, M. Mayer, R. Mckel,
P. Mudry, and A. Ijspeert. Roombots-towards decentralized
reconfiguration with self-reconfiguring modular robotic meta-
modules. In Proceedings of the IEEE International Confer-
ence on Intelligent Robots and Systems, IEEE International
Conference on Intelligent Robots and Systems, pages 1126–
1132, Taipei, Taiwan, 2010.
[15] D. Stein, T.R. Schoen, and D. Rus. Constraint-aware coor-
dinated construction of generic structures. In Proceedings of
the IEEE International Conference on Intelligent Robots and
Systems, 2011.
[16] A.W. Stroupe, T. Huntsberger, B. Kennedy, H. Aghazarian,
E.T. Baumgartner, A. Ganino, M. Garrett, A. Okon, M. Robin-
son, and J.A. Townsend. Heterogeneous robotic systems for
assembly and servicing. In Proceedings of the International
Symposium on Artifical Intelligence, Robotics and Automation
in Space, Munich, Germany, August 2005.
[17] F. Thomas and C. Torras. Inferring feasible assemblies
from spatial constraints. IEEE Transactions on Robotics and
Automation, 8(2):228–239, 1992.
[18] R.H. Wilson. Minimizing user queries in interactive assembly
planning. IEEE Transactions on Robotics and Automation, 11
(2), April 1995.
862