Skip to main content
SpringerLink
Log in

Implementation of a Gaussian process-based machine learning grasp predictor

  • Published:
Autonomous Robots Aims and scope Submit manuscript

Abstract

With the goal of advancing the state of automatic robotic grasping, we present a novel approach that combines machine learning techniques and physical validation on a robotic platform to develop a comprehensive grasp predictor. After collecting a large grasp sample set (522 grasps), we first conduct a statistical analysis of the predictive ability of grasp quality metrics that are commonly used in the robotics literature. We then apply principal component analysis and Gaussian process (GP) algorithms on the grasp metrics that are discriminative to build a classifier, validate its performance, and compare the results to existing grasp planners. The key findings are as follows: (i) several of the existing grasp metrics are weak predictors of grasp quality when implemented on a robotic platform; (ii) the GP-based classifier significantly improves grasp prediction by combining multiple grasp metrics to increase true positive classification at low false positive rates; (iii) The GP classifier can be used generate new grasps to improve bad grasp samples by performing a local search to find neighboring grasps which have improved contact points and higher success rate.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

Notes

  1. http://www.mathworks.com/.

  2. http://www.gaussianprocess.org/gpml/code/matlab/doc/.

  3. www.thearmrobot.com.

References

  • Balasubramanian, R., Xu, L., Brook, P. D., Smith, J. R., & Matsuoka, Y. (2012). Physical human interactive guidance: Identifying grasping principles from human-planned grasps. IEEE Transactions on Robotics, 28(4), 899–910.

    Article  Google Scholar 

  • Bodenhagen, L., Detry, R., Piater, J., & Kruger, N. (2011). What a successful grasp tells about the success chances of grasps in its vicinity. In IEEE International Conference on Development and Learning, ICDL 2011. IEEE Computational Intelligence Society; Frankfurt Institute for Advanced Studies (FIAS); Bielefeld Univ., Cognitive Interact.; Technol. Cent. Excellence (CITEC); italk

  • Bohg, J., Morales, A., Asfour, T., & Kragic, D. (2013). Data-driven grasp synthesis—A survey. IEEE Transactions on Robotics, PP(99), 1–21.

    Google Scholar 

  • Bounab, B., Sidobre, D., & Zaatri, A. (2008). Central axis approach for computing n-finger force-closure grasps. In Proceedings of IEEE International Conference on Robotics and Automation, pp. 1169–1174.

  • Chinellato, E., Fisher, R. B., Morales, A., & Del Pobil, A. P. (2003). Ranking planar grasp configurations for a three-finger hand. Proceedings of IEEE International Conference on Robotics and Automation, 1, 1133–1138.

    Google Scholar 

  • Chinellato, E., Morales, A., Fisher, R. B., & del Pobil, A. P. (2005). Visual quality measures for characterizing planar robot grasps. IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews, 35(1), 30–41.

    Article  Google Scholar 

  • Ciocarlie, M., Goldfeder, C., & Allen, P. (2007). Dimensionality reduction for hand-independent dexterous robotic grasping. In IEEE International Conference on Intelligent Robots and Systems, pp. 3270–3275.

  • Diankov, R. (2010). Automated construction of robotic manipulation programs. PhD thesis, Carnegie Mellon University, Robotics Institute.

  • Ekvall, S., & Kragic, D. (2007). Learning and evaluation of the approach vector for automatic grasp generation and planning. In Proceedings of IEEE International Conference on Robotics and Automation, pp. 4715–4720.

  • El-Khoury, S., & Sahbani, A. (2009). On computing robust n-finger force-closure grasps of 3d objects. In Proceedings of IEEE International Conference on Robotics and Automation, pp. 2480–2486.

  • El-Khoury, S., Sahbani, A., & Bidaud, P. (2011). 3d objects grasps synthesis: A survey. In 13th World Congress in Mechanism and Machine Science, pp. 573–583.

  • Faria, D. R., Martins, R., Lobo, J., & Dias, J. (2012). Extracting data from human manipulation of objects towards improving autonomous robotic grasping. Robotics and Autonomous Systems, 60(3), 396–410.

    Article  Google Scholar 

  • Ferrari, C., & Canny, J. (1992). Planning optimal grasps. Proceedings of IEEE International Conference on Robotics and Automation, 3, 2290–2295.

    Google Scholar 

  • Fischinger, D., Vincze, M., & Jiang, Y. (2013). Learning grasps for unknown objects in cluttered scenes. In Proceedings of IEEE International Conference on Robotics and Automation, pp. 609–616.

  • Goins, A. K., Carpenter, R., Wong, W. K., & Balasubramanian, R. (2014). Evaluating the efficacy of grasp metrics for utilization in a Gaussian process-based grasp predictor. In IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS.

  • Gossow, D., Leeper, A., Hershberger, D., & Ciocarlie, M. (2011). ROS topics: Interactive markers: 3-d user interfaces for ROS applications. IEEE Robotics and Automation Magazine, 18(4), 14–15.

    Article  Google Scholar 

  • Hanley, J. A., & McNeil, B. J. (1982). The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology, 143(1), 29–36.

    Article  Google Scholar 

  • Hastie, T., Tibshirani, R., & Friedman, J. (2009). The elements of statistical learning: Data mining, inference, and prediction. New York: Springer.

    Book  Google Scholar 

  • Hunter, J. D. (2007). Matplotlib: A 2d graphics environment. Computing In Science & Engineering, 9(3), 90–95.

    Article  Google Scholar 

  • Kehoe, B., Berenson, D., & Goldberg, K. (2012). Toward cloud-based grasping with uncertainty in shape: Estimating lower bounds on achieving force closure with zero-slip push grasps. In Proceedings of IEEE International Conference on Robotics and Automation, pp. 576–583.

  • Kim, J., Iwamoto, K., Kuffner, J., Ota, Y., & Pollard, N. (2012). Physically-based grasp quality evaluation under uncertainty. In IEEE International Conference on Robotics and Automation (ICRA), pp. 3258–3263.

  • Kirkpatrick, D., Mishra, B., & Yap, C. K. (1992). Quantitative steinitz’s theorems with applications to multifingered grasping. Discrete & Computational Geometry, 7(1), 295–318.

    Article  MathSciNet  MATH  Google Scholar 

  • Leon, B., Sancho-Bru, J. L., Jarque-Bou, N. J., Morales, A., & Roa, M. A. (2012). Evaluation of human prehension using grasp quality measures. International Journal of Advanced Robotic Systems 9.

  • Li, Z., & Sastry, S. (1988). Task-oriented optimal grasping by multifingered robot hands. IEEE Journal of Robotics and Automation, 6(2), 32–44.

    Article  Google Scholar 

  • Lin, Q., Burdick, J. W., & Rimon, E. (2000). Stiffness-based quality measure for compliant grasps and fixtures. IEEE Transactions on Robotics and Automation, 16(6), 675–688.

    Article  Google Scholar 

  • Lopez-Damian, E., Sidobre, D., & Alami, R. (2005). A grasp planner based on inertial properties. In Proceedings of IEEE International Conference on Robotics and Automation, pp. 754–759.

  • Miller, A. T., & Allen, P. K. (1999). Examples of 3d grasp quality computations. Proceedings of IEEE International Conference on Robotics and Automation, 2, 1240–1246.

    Article  Google Scholar 

  • Miller, A. T., & Allen, P. K. (2004). Graspit: A versatile simulator for robotic grasping. IEEE Robotics and Automation Magazine, 11(4), 110–122.

    Article  Google Scholar 

  • Molina-Vilaplana, J., Feliu-Batlle, J., & Lopez-Coronado, J. (2007). A modular neural network architecture for step-wise learning of grasping tasks. Neural Networks, 20(5), 631–645.

    Article  Google Scholar 

  • Morales, A., Chinellato, E., Fagg, A. H., & Del Pobil, A. P. (2003). Experimental prediction of the performance of grasp tasks from visual features. IEEE International Conference on Intelligent Robots and Systems, 4, 3423–3428.

    Google Scholar 

  • Morales, A., Chinelalto, E., Sanz, P., Del Pobil, A., & Fagg, A. H. (2004). Learning to predict grasp reliability for a multifinger robot hand by using visual features. In Proceedings of the Eighth IASTED International Conference on Artificial Intelligence and Soft Computing, pp. 249 – 254.

  • Pelossof, R., Miller, A., Allen, P., & Jebara, T. (2004). An svm learning approach to robotic grasping. Proceedings of IEEE International Conference on Robotics and Automation, 4, 3512–3518.

    Google Scholar 

  • Platt, R., Grupen, R., & Fagg, A. (2006). Learning grasp context distinctions that generalize. In International Conference on Humanoid Robots, 2006 6th IEEE-RAS, pp. 504–511.

  • Rasmussen, C. E. (2006). Gaussian processes for machine learning. Cambridge, MA: MIT Press.

    MATH  Google Scholar 

  • Saxena, A., Driemeyer, J., & Ng, A. Y. (2008a). Robotic grasping of novel objects using vision. International Journal of Robotics Research, 27(2), 157–173.

    Article  Google Scholar 

  • Saxena, A., Wong, L. L., & Andrew, Y. (2008b). Learning grasp strategies with partial shape information. Proceedings of the National Conference on Artificial Intelligence, 3, 1491–1494.

    Google Scholar 

  • Shimoga, K. B. (1996). Robot grasp synthesis algorithms: A survey. The International Journal of Robotics Research, 15(3), 230–266.

    Article  Google Scholar 

  • Song, D., Ek, C., Huebner, K., & Kragic, D. (2011). Multivariate discretization for bayesian network structure learning in robot grasping. In IEEE International Conference on Robotics and Automation (ICRA), pp. 1944–1950.

  • Srinivasa, S. S., Ferguson, D., Helfrich, C. J., Berenson, D., Collet, A., Diankov, R., et al. (2010). HERB: A home exploring robotic butler. Autonomous Robots, 28(1), 5–20.

    Article  Google Scholar 

  • Suárez, R., Cornellà, J., & Garzón, M. R. (2006). Grasp quality measures. Institut dÓrganització i Control de Sistemes Industrials.

  • Townsend, W. (2000). The BarrettHand grasper-programmably flexible part handling and assembly. Industrial Robot: An International Journal, 27(3), 181–188.

    Article  MathSciNet  Google Scholar 

  • Weisz, J., & Allen, P. K. (2012). Pose error robust grasping from contact wrench space metrics. In Proceedings of IEEE International Conference on Robotics and Automation, pp. 557–562.

Download references

Author information

Authors and Affiliations

  1. School of Mechanical, Industrial, and Manufacturing Engineering, Oregon State University, Corvallis, OR, 97331, USA

    Alex K. Goins, Ryan Carpenter & Ravi Balasubramanian

  2. School of Electrical Engineering and Computer Science, Oregon State University, Corvallis, OR, 97331, USA

    Weng-Keen Wong

Authors
  1. Alex K. Goins
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ryan Carpenter
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Weng-Keen Wong
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ravi Balasubramanian
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Alex K. Goins.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Goins, A.K., Carpenter, R., Wong, WK. et al. Implementation of a Gaussian process-based machine learning grasp predictor. Auton Robot 40, 687–699 (2016). https://doi.org/10.1007/s10514-015-9488-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10514-015-9488-2

Keywords

Search

Navigation