Grasping an object is usually only an intermediate goal for a robotic manipulator. To finish the task, the robot needs to know where the object is in its hand and what action to execute. This paper presents a general statistical framework to address these problems. Given a novel object, the robot learns a statistical model of grasp state conditioned on sensor values. The robot also builds a statistical model of the requirements for a successful execution of the task in terms of uncertainty in the state of the grasp. Both of these models are constructed by offline experiments. The online process then grasps objects and chooses actions to maximize likelihood of success. This paper describes the framework in detail, and demonstrates its effectiveness experimentally in placing, dropping, and insertion tasks. To construct statistical models, the robot performed over 8,000 grasp trials, and over 1,000 trials each of placing, dropping, and insertion.
BalasubramanianRXuLBrookPSmithJMatsuokaY (2012) Physical human interactive guidance: Identifying grasping principles from human-planned grasps. IEEE Transactions on Robotics28(4): 899–910.
2.
BootsBSiddiqiSMGordonGJ (2011) Closing the learning-planning loop with predictive state representations. The International Journal of Robotics Research30(7): 954–966.
3.
BotevZIGrotowskiJFKroeseDP (2010) Kernel density estimation via diffusion. The Annals of Statistics38(5): 2916–2957.
4.
BrostRC (1988) Automatic grasp planning in the presence of uncertainty. The International Journal of Robotics Research7(1): 3–17.
5.
BrostRC (1991) Analysis and Planning of Planar Manipulation Tasks. Ph.D. thesis, Carnegie Mellon University School of Computer Science.
6.
BrostRCChristiansenAD (1996) Probabilistic analysis of manipulation tasks: a conceptual framework. The International Journal of Robotics Research15(1): 1–23.
7.
CarbonettoP (2007) A MATLAB interface for L-BFGS-B. Department of Computer Science, University of British Columbia.
8.
CassandraARKaelblingLPLittmanML (1994) Acting optimally in partially observable stochastic domains. In: Proceedings of the twelfth National conference on artificial intelligence (AAAI 1994). Menlo Park, CA: AAAI Press, pp. 1023–1028.
9.
ChristiansenAD (1990) Manipulation planning from empirical backprojections. In: International conference on robotics and automation, Sacramento, CA, pp. 762–768.
10.
ChristiansenAD (1992) Automatic acquisition of task theories for robotic manipulation. Technical Report CMU-CS-92-111, Carnegie Mellon University, Pittsburgh, PA, USA.
11.
ChristiansenADGoldbergKY (1995) Comparing two algorithms for automatic planning by robots in stochastic environments. Robotica13(06): 565–573.
12.
DogarMSrinivasaSS (2011) A framework for push-grasping in clutter. In: Robotics: Science and Systems (RSS).
13.
ErdmannM (1986) Using backprojections for fine motion planning with uncertainty. The International Journal of Robotics Research5(1): 19.
14.
ErdmannMAMasonMT (1988) An exploration of sensorless manipulation. IEEE Journal of Robotics and Automation4(4): 369–379.
15.
FariaDRMartinsRLoboJDiasJ (2012) Extracting data from human manipulation of objects towards improving autonomous robotic grasping. Robotics and Autonomous Systems60(3): 396–410.
16.
FuJSrinivasaSPollardNNabbeB (2007) Planar batting under shape, pose, and impact uncertainty. In: IEEE International conference on robotics and automation (ICRA).
17.
GadeyneKLefebvreTBruyninckxH (2005) Bayesian hybrid model-state estimation applied to simultaneous contact formation recognition and geometrical parameter estimation. The International Journal of Robotics Research24(8): 615–630.
18.
GoldbergKMasonMT (1990) Bayesian grasping. In: IEEE International conference on robotics and automation (ICRA), pp. 1264–1269.
19.
GoldbergKY (1990) Stochastic Plans for Robotic Manipulation. Ph.D. thesis (Technical Report CMU-CS-90-161), Carnegie Mellon University School of Computer Science.
HsiaoKKaelblingLLozano-PérezT (2011) Robust grasping under object pose uncertainty.
25.
InoueH (1974) Force Feedback in Precise Assembly Tasks. Technical Report MIT AIM-308, MIT.
26.
JiangYLimMZhengCSaxenaA (2012) Learning to place new objects in a scene. The International Journal of Robotics Research31(9): 1021–1043.
27.
KangDGoldbergK (1995) Sorting parts by random grasping. IEEE Transactions on Robotics and Automation11(1): 146–152.
28.
LaValleSMHutchinsonSA (1998). An objective-based framework for motion planning under sensing and control uncertainties. The International Journal of Robotics Research17(1): 19–42.
29.
Lozano-PerezTMasonMTTaylorRH (1984) Automatic synthesis of fine-motion strategies for robots. The International Journal of Robotics Research3(1): 3–24.
30.
MasonMT (1986) Mechanics and planning of manipulator pushing operations. The International Journal of Robotics Research5(3): 53–71.
31.
MasonMTRodriguezASrinivasaSSVazquezAS (2012) Autonomous manipulation with a general-purpose simple hand. The International Journal of Robotics Research31(5): 688–703.
32.
MoralesAChinellatoEFaggAHdel PobilAP (2004) Using experience for assessing grasp reliability. International Journal of Humanoid Robotics1(4): 671–691.
33.
PaoliniRRodriguezASrinivasaSSMasonMT (2012) A data-driven statistical framework for post-grasp manipulation. In: International Symposium on Experimental Robotics (ISER).
34.
PeshkinMASandersonAC (1988) The motion of a pushed, sliding workpiece. Journal of Robotics and Automation4(6): 569–598.
35.
PetrovskayaAKhatibOThrunSNgAY (2006) Bayesian estimation for autonomous object manipulation based on tactile sensors. In: IEEE International conference on robotics and automation, pp. 707–714.
36.
PlattR (2007) Learning grasp strategies composed of contact relative motions. In: 7th IEEE-RAS International conference on humanoid robots. IEEE, pp. 49–56.
37.
RasmussenCEHannesN (2010) Gaussian processes for machine learning (GPML) toolbox. The Journal of Machine Learning Research11: 3011–3015.
38.
RasmussenCEWilliamsCKI (2006) Gaussian Processes for Machine Learning. Cambridge, MA: MIT Press.
39.
RodriguezAMasonMTSrinivasaSS (2010) Manipulation capabilities with simple hands. In: International symposium on experimental robotics (ISER).
40.
RodriguezAMasonMTSrinivasaSSBernsteinMZirbelA (2011) Abort and retry in grasping. In: IEEE International conference on intelligent robots and systems (IROS).
41.
SimunovicSN (1979) An Information Approach to Parts Mating. Sc.D. Thesis, Massachusetts Institute of Technology.
42.
StulpFTheodorouEBuchliJSchaalS (2011) Learning to grasp under uncertainty. In: IEEE International conference on robotics and automation (ICRA).
43.
TrinkleJCAbelJMPaulRP (1988) An investigation of frictionless enveloping grasping in the plane. The International Journal of Robotics Research7(3): 33–51.
44.
WhitneyDEJunkelEF (1982) Applying stochastic control theory to robot sensing, teaching, and long term control. In: American control conference, pp. 1175–1183.
45.
WingateD (2008) Exponential Family Predictive Representations of State. Ph.D. thesis, University of Michigan.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
