Abstract
This paper presents a novel strategy to learn a positional controller for the body of a flexible surgical manipulator used for minimally invasive surgery. The manipulator is developed within the STIFF-FLOP European project and is targeted for a laparoscopic use in remote areas of the abdominal region that are not easily accessible by means of currently available rigid tools. While the surgeon controls the end-effector during the task, the flexible body of the manipulator needs to be displaced to enter inside constrained spaces by efficiently exploiting its flexibility, without touching vital organs and structures. The proposed algorithm exploits the instruments of machine learning within the programming by demonstrations paradigm to produce a statistical model of the natural movements of the surgeon during the task. The gathered information is then reused to determine a controller in the null space of the robot that does not interfere with the surgeon task and displaces the robot body within the available space in a fully automated manner.
Similar content being viewed by others
References
Bruno, D., Calinon, S., & Caldwell, D. G. (2014). Null space redundancy learning for a flexible surgical robot. In IEEE international conference on robotics and automation (ICRA) (pp. 2443–2448). Hong Kong.
Calinon, S., Bruno, D., & Caldwell, D. G. (2014a). A task-parameterized probabilistic model with minimal intervention control. In IEEE international conference on robotics and automation (ICRA) (pp. 3339–3344). Hong Kong.
Calinon, S., Bruno, D., Malekzadeh, M. S., Nanayakkara, T., & Caldwell, D. G. (2014b). Human-robot skills transfer interfaces for a flexible surgical robot. Computer Methods and Programs in Biomedicine, 116(2), 81–96. Special issue on new methods of human-robot interaction in medical practice.
Calinon, S., D’halluin, F., Sauser, E. L., Caldwell, D. G., & Billard, A. G. (2010). Learning and reproduction of gestures by imitation: An approach based on hidden Markov model and Gaussian mixture regression. IEEE Robotics and Automation Magazine, 17(2), 44–54.
Cianchetti, M., Ranzani, T., Gerboni, G., De Falco, I., Laschi, C., & Menciassi, A. (2013). Stiff-flop surgical manipulator: mechanical design and experimental characterization of the single module. In IEEE/RSJ international conference on intelligent robots and systems (IROS) (pp. 3567–3581).
Flash, T., & Hogan, N. (1985). The coordination of the arm movements: An experimentally confirmed mathematical model. Neurology, 5(7), 1688–1703.
Gauvain, J.-L., & Lee, C.-H. (1994). Maximum a posteriori estimation for multivariate gaussian mixture observations of markov chians. IEE Transactions on Speech and Audio Processing, 2(2), 291–298.
Gielniak, M. J., Liu, C. K., & Thomaz, A. L. (2011). Task-aware variations in robot motion. In IEEE international conference on robotics and automation (ICRA) (pp. 3921–3927).
Jiang, A., Ataollahi, A., Althoefer, K., Dasgupta, P., & Nanayakkara, T. (2012a). A variable stiffness joint by granular jamming. In ASME international design engineering technical conference and computers and information in engineering conference (IDETC/CIE) (pp. 267–275).
Jiang, A., Xynogalas, G., Dasgupta, P., Althoefer, K., & Nanayakkara, T. (2012b). Design of a variable stiffness flexible manipulator with composite granular jamming and membrane coupling. In IEEE/RSJ international conference on intelligent robots and systems (IROS) (pp. 2922–2927).
Kulis, B., & Jordan, M. I. (2012). Revisiting k-means: New algorithms via bayesian nonparametrics. In Proceedings of the international conference on machine learning (ICML), Edimburgh.
Lee, D., & Ott, C. (2011). Incremental kinesthetic teaching of motion primitives using the motion refinement tube. Autonomous Robots, 31(2), 115–131.
Lobaton, E., Fu, J., Torres, L., & Alterovitz, R. (2013). Continuous shape estimation of continuum robots using x-ray images. In IEEE international conference on robotics and automation (ICRA) (pp. 725–732).
Lyons, L., Webster, R., & Alterovitz, R. (2010). Planning active cannula configurations through tubular anatomy. In IEEE international conference on robotics and automation (ICRA) (pp. 2082–2087). Anchorage, AK.
MacQueen, J. B. (1967). Some methods for classification and analysis of multivariate observations. In Proceedings of the symposium on mathematical statistics and probability (pp. 281–297), Berkeley: University of California Press.
Malekzadeh, M. S., Calinon, S., Bruno, D., & Caldwell, D. G. (2014). Learning by imitation with the STIFF-FLOP surgical robot: A biomimetic approach inspired by octopus movements. Robotics and Biomimetics Special Issue on Medical Robotics, 1(13), 1–15.
Nordmann, A., Emmerich, C., Ruether, S., Lemme, A., Wrede, S., & Steil, J. (2012). Teaching nullspace constraints in physical human-robot interaction using reservoir computing. In IEEE international conference on robotics and automation (ICRA) (pp. 1868–1875).
Quinlan, S., & Khatib, O. (1993). Elastic bands: Connecting path planning and control. In Proceedings of the international conference on robotics and automation (ICRA) (pp. 802–807).
Rajiv Ranganatan, A. A., & Mussa-Ivaldi, F. A. (2013). Learning to be lazy, exploiting redundancy in a novel task to minimize movement-related effort. Journal of Neuroscience, 33(7), 2754–2760.
Reiter, A., Goldman, R. E., Bajo, A., Iliopoulos, K., Simaan, N., & Allen, P. K. (2011). A learning algorithm for visual pose estimation of continuum robots. In IEEE international conference on robotics and automation (ICRA) (pp. 2390–2396), San Francisco, CA.
Song, M., & Wang, H. (2005). Highly efficient incremental estimation of Gaussian mixture models for online data stream clustering. In Proceedings of SPIE: Intelligent computing—theory and applications III (Vol. 5803, pp. 174–183).
Sternad, D., Abe, M. O., Hu, X., & Mueller, H. (2011). Neuromotor noise, error tolerance and velocity-dependent costs in skilled performance. PLoS Computational Biology, 7(9), e1002159.
Todorov, E., & Jordan, M. I. (2002). A minimal intervention principle for coordinated movement. In Advances in neural information processing systems (NIPS) (pp. 27–34).
Towell, C., Howard, M., & Vijayakumar, S. (2010). Learning nullspace policies. In Proceedings of IEEE/RSJ international conference on intelligent robots and systems (IROS) (pp. 241–248).
Van Den Berg, J., Miller, S., Duckworth, D., Hu, H., Wan, A., Fu, X., et al. (2010). Superhuman performance of surgical tasks by robots using iterative learning from human-guided demonstrations. In IEEE international conference on robotics and automation (ICRA) (pp. 2074–2081). Anchorage, AK.
Yang, X., Zhu, C., Yang, M., Hu, H., Xia, L., & Pan, K. (2012). Laparoscopic radical resection for rectal cancer. Translational Gastrointestinal Cancer, 1(3), 255–271.
Zelman, I., Titon, M., Yekutieli, Y., Hanassy, S., Hochner, B., & Flash, T. (2013). Kinematic decomposition and classification of octopus arm movements. Frontiers in Computational Neuroscience, 7, 60.
Zhang, Z., Chen, C., Sun, J., & Chan, K. L. (2003). EM algorithms for Gaussian mixtures with split-and-merge operation. Pattern Recognition, 36(9), 1973–1983.
Acknowledgments
This work was partially supported by the STIFF-FLOP European project under contract FP7-ICT-287728.
Author information
Authors and Affiliations
Corresponding author
Appendix 1: Gaussian mixture models
Appendix 1: Gaussian mixture models
The observations \(\{{\varvec{\xi }}_n\}_{n=1}^N\) representing the points of the demonstrations are assumed to be independent realizations of a random vector, that is assumed to be distributed as a linear combination of Normal distributions as
with
The parameters of a Gaussian mixture model (GMM) with K components are thus defined by \(\{\pi _k,{\varvec{\mu }}_k,{\varvec{\varSigma }}_k\}_{k=1}^K\), where \(\pi _k\) is the prior (mixing coefficient), \({\varvec{\mu }}_k\) is the center, and \({\varvec{\varSigma }}_k\) is the covariance matrix of the k-th mixture component.
The estimation of mixture parameters can be performed by maximizing the log-likelihood of the above distribution of the given dataset. For the set of observations \(\{{\varvec{\xi }}_n\}_{n=1}^N\), the log-likelihood of the GMM is
The maximization of the likelihood leads to an expectation-maximization (EM) process iteratively refining the model parameters to converge to a local optimum of the likelihood. These two steps are iteratively applied until a stopping criterion is satisfied. The two steps are described below.
E-step:
M-step:
The reproduction of an average movement or skill behavior can be formalized as a statistical regression problem. We demonstrated in previous work that Gaussian mixture regression (GMR) offers a simple and elegant solution to handle encoding, recognition, prediction and reproduction in robot learning (Calinon et al. 2010). It provides a probabilistic representation of the movement, where the model can retrieve actions in real-time, within a computation time that is independent of the number of datapoints in the training set.
By defining which variables span for input and output parts (noted respectively by \({\mathcal {I}}\) and \({\mathcal {O}}\) superscripts), a block decomposition of the datapoint \({\varvec{\xi }}_n\), vectors \({\varvec{\mu }}_i\) and matrices \({\varvec{\varSigma }}_i\) can be written as
The GMM thus encodes the joint distribution \({\mathcal {P}}({\varvec{\xi }}^{\scriptscriptstyle I},{\varvec{\xi }}^{\scriptscriptstyle O})\sim \sum _{i=1}^K\pi _i{\mathcal {N}}({\varvec{\mu }}_i,{\varvec{\varSigma }}_i)\) of the data \({\varvec{\xi }}\). At each reproduction step n, \({\mathcal {P}}({\varvec{\xi }}^{\scriptscriptstyle O}_n|{\varvec{\xi }}^{\scriptscriptstyle I}_n)\) is computed as the conditional distribution
In the general case, Eq. (13) represents a multimodal distribution. In problems where a single output is expected (single peaked distribution), Eq. (13) can be approximated by a single normal distribution \({\mathcal {N}}(\hat{{\varvec{\mu }}}^{\scriptscriptstyle O}_n, \hat{{\varvec{\varSigma }}}^{\scriptscriptstyle O}_n)\) with parameters
Equation (16) is computed in real-time from the model parameters. The retrieved signal encapsulates variation and correlation information in the form of a probabilistic flow tube, see e.g., Lee and Ott (2011).
Rights and permissions
About this article
Cite this article
Bruno, D., Calinon, S. & Caldwell, D.G. Learning autonomous behaviours for the body of a flexible surgical robot. Auton Robot 41, 333–347 (2017). https://doi.org/10.1007/s10514-016-9544-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10514-016-9544-6