A system for robotic heart surgery that learns to tie knots using recurrent neural networks

Advanced Robotics

Volumn 22, Issue 13-14, 2008, Pages 1521-1537

  Mayer, Hermann ^a   Gomez, Faustino ^b   Wierstra, Daan ^b   Nagy, Istvan ^a   Knoll, Alois ^a   Schmidhuber, Jürgen ^a,b  

^a TECHNICAL UNIVERSITY OF MUNICH   (Germany)

^b DALLE MOLLE INSTITUTE FOR ARTIFICIAL INTELLIGENCE IDSIA   (Switzerland)

Author keywords

Artificial evolution; Automated knot tying; Minimally invasive surgery; Recurrent neural networks; Supervised learning

Indexed keywords

ARTIFICIAL EVOLUTION; AUTOMATED KNOT TYING; FEED-FORWARD; INTERNAL MEMORY; INTERNAL STATE; MINIMALLY INVASIVE SURGERY; NEURAL NET; PRE-PROGRAMMED CONTROL; ROBOTIC HEART SURGERY; SHORT TERM MEMORY; SUPERVISED MACHINE LEARNING; TIME-CONSUMING TASKS;

SUPERVISED LEARNING; SURGERY; SWITCHING CIRCUITS;

RECURRENT NEURAL NETWORKS;

EID: 69549086702     PISSN: 01691864     EISSN: 15685535     Source Type: Journal    
DOI: 10.1163/156855308X360604     Document Type: Article

References (24)

1. G. Guthart and J. K. Salisbury Jr, The Intuitive™ telesurgery system: overview and application, in: Proc. Int. Conf. on Robotics and Automation, San Francisco, CA, pp. 618-621 (2000).
2. A. Garcia-Ruiz, N. G. Smedira, F. D. Loop, J. F. Hahn, C. P. Steiner, J. H. Miller and M. Gagner, Robotic surgical instruments for dexterity enhancement in thorascopic coronary artery bypass graft, J. Laparoendoscop. Adv. Surg. Tech. 7, 277-283 (1997).
3. A. Garcia-Ruiz, Manual vs robotically assisted laparoscopic surgery in the performance of basic manipulation and suturing tasks, Arch. Surg. 133, 957-961 (1998).
4. H. Kang, Robotic assisted suturing in minimally invasive surgery, PhD Thesis, Rensselaer Polytechnic Institute, Troy, NY (2002).
5. H. Mayer, I. Nagy, A. Knoll, E. U. Schirmbeck and R. Bauernschmitt, The EndoPAR system for minimally invasive surgery, in: Proc. Int. Conf. on Intelligent Robots and Systems, Sendai, pp. 3637-3642 (2004).
6. P. Werbos, Backpropagation through time: what does it do and how to do it, Proc. IEEE 78, 1550-1560 (1990).
7. A. J. Robinson and F. Fallside, The utility driven dynamic error propagation network, Technical Report CUED/F-INFENG/TR.1, Engineering Department, Cambridge University (1987).
8. R. J. Williams and D. Zipser, A learning algorithm for continually running fully recurrent networks, Neural Comput. 1, 270-280 (1989).
9. S. Hochreiter and J. Schmidhuber, Long short-term memory, Neural Comput. 9, 1735-1780 (1997).
10. J. Schmidhuber, D. Wierstra and F. Gomez, Evolino: hybrid neuroevolution/optimal linear search for sequence learning, in: Proc. 19th Int. Joint Conf. on Artificial Intelligence, Edinburgh, pp. 853-858 (2005).
11. D. Wierstra, F. Gomez and J. Schmidhuber, Modeling systems with internal state using Evolino, in: Proc. Genetic Evolutionary Computation Conf, New York, NY, pp. 1795-1802 (2005).
12. H. Mayer, F. Gomez, D. Wierstra, I. Nagy, A. Knoll and J. Schmidhuber, A system for robotic heart surgery that learns to tie knots using recurrent neural networks, in: Proc. Int. Conf. on Intelligent Robotics and Systems, Beijing, pp. 543-548 (2006).
13. J. Schmidhuber, D. Wierstra, M. Gagliolo and F. Gomez, Training recurrent neural networks by Evolino, Neural Comput. 19, 757-779 (2007).
14. I. Nagy, H. Mayer, A. Knoll, E. U. Schirmbeck and R. Bauernschmitt, EndoPAR: an open evaluation system for minimally invasive robotic surgery, in: Proc. IEEE Conf. on Mechatronics and Robotics, Aachen, pp. 1464-1467 (2004).
15. H. Mayer, I. Nagy, A. Knoll, E. U. Braun, R. Lange and R. Bauernschmitt, Adaptive control for human-robot skilltransfer: trajectory planning based on fluid dynamics, in: Proc. IEEE Int. Conf. on Robotics and Automation, Rome, pp. 1800-1807 (2007).
16. V. Vapnik, The Nature of Statistical Learning Theory. Springer, New York, NY (1995).
17. F. J. Gomez, Robust nonlinear control through neuroevolution, PhD Thesis (Technical Report AI-TR-03-303), Department of Computer Sciences, University of Texas at Austin, Austin, TX (2003).
18. D. E. Moriarty and R. Miikkulainen, Efficient reinforcement learning through symbiotic evolution, Mack Learn. 11, 11-32 (1996).
19. H. T. Siegelmann and E. D. Sontag, Turing computability with neural nets, Appl. Math. Lett. 4, 77-80 (1991).
20. S. Hochreiter, Y. Bengio, P. Frasconi and J. Schmidhuber, Gradient flow in recurrent nets: the difficulty of learning long-term dependencies, in: A Field Guide to Dynamical Recurrent Neural Networks, S. C. Kremer and J. F. Kolen (Eds), pp. 237-244. IEEE Press, New York, NY (2001).
21. F. A. Gers, J. Schmidhuber and F. Cummins, Learning to forget: continual prediction with LSTM, Neural Comput. 12, 2451-2471 (2000).
22. F. A. Gers and J. Schmidhuber, LSTM recurrent networks learn simple context free and context sensitive languages, IEEE Trans. Neural Netw. 12, 1333-1340 (2001).
23. R. Penrose, A generalized inverse for matrices, in: Proc. Cambridge Philos. Soc. 51, 406-413 (1955).
24. E. P. Maillard and D. Gueriot, RBF neural network, basis functions and genetic algorithms, in: Proc. IEEE Int. Conf. on Neural Networks, Piscataway, NJ, pp. 2187-2190 (1997).