Special Issue — Tactile Sensing for Manipulation; Guest Editors: Q. Li, L. Natale, R. Haschke, A. Cherubini, A.-V. Ho and H. RitterNo Access

GPAtlasRRT: A Local Tactile Exploration Planner for Recovering the Shape of Novel Objects

Carlos Rosales

Centro di Ricerca E. Piaggio, Università di Pisa, Pisa, Italy

E-mail Address: [email protected]

Search for more papers by this author

Federico Spinelli

Centro di Ricerca E. Piaggio, Università di Pisa, Pisa, Italy

E-mail Address: [email protected]

Search for more papers by this author

Marco Gabiccini

Dipartimento di Ingegneria Civile e Industriale, Largo Lucio Lazzarino 1, Universita di Pisa, 56122 Pisa Pl, Italy

E-mail Address: [email protected]

Search for more papers by this author

Claudio Zito

IRLab, CN–CR, School of Computer Science, University of Birmingham, Birmingham B15 2TT, UK

E-mail Address: [email protected]

Search for more papers by this author

, and

Jeremy L. Wyatt

http://orcid.org/0000-0001-6991-356X

IRLab, CN–CR, School of Computer Science, University of Birmingham, Birmingham B15 2TT, UK

E-mail Address: [email protected]

Corresponding author.

Search for more papers by this author

https://doi.org/10.1142/S0219843618500147Cited by:16 (Source: Crossref)

Abstract

Touch is an important modality to recover object shape. We present a method for a robot to complete a partial shape model by local tactile exploration. In local tactile exploration, the finger is constrained to follow the local surface. This is useful for recovering information about a contiguous portion of the object and is frequently employed by humans. There are three contributions. First, we show how to segment an initial point cloud of a grasped, unknown object into hand and object. Second, we present a local tactile exploration planner. This combines a Gaussian Process (GP) model of the object surface with an AtlasRRT planner. The GP predicts the unexplored surface and the uncertainty of that prediction. The AtlasRRT creates a tactile exploration path across this predicted surface, driving it towards the region of greatest uncertainty. Finally, we experimentally compare the planner with alternatives in simulation, and demonstrate the complete approach on a real robot. We show that our planner successfully traverses the object, and that the full object shape can be recovered with a good degree of accuracy.

Keywords:

References

1. D. Kragic and H. I. Christensen, Survey on Visual Servoing for Manipulation, Technical Report, ISRN KTH/NA/P-02/01-SE (Royal Institute of Technology, Stockholm, Sweden, 2002). Google Scholar
2. J. Nunez-Varela and J. L. Wyatt, Models of gaze control for manipulation tasks, ACM Trans. Appl. Percept. 10 (4) (2013) 20. Crossref, Web of Science, Google Scholar
3. E. Arruda, J. L. Wyatt and M. Kopicki, Active vision for dexterous grasping of novel objects, in IEEE/RSJ Int. Conf. Intelligent Robots and Systems (IROS) (IEEE, Daejeon, 2016), pp. 2881–2888. Google Scholar
4. M. Kopicki, R. Detry, M. Adjigble, A. Leonardis and J. L. Wyatt, One-shot learning and generation of dexterous grasps for novel objects, Int. J. Robot. Res. 35 (8) (2015) 959–976. Crossref, Web of Science, Google Scholar
5. G. Kootstra, M. Popovi, J. Jørgensen, K. Kuklinski, K. Miatliuk, D. Kragic and N. Kruger, Enabling grasping of unknown objects through a synergistic use of edge and surface information, Int. J. Robot. Res. 34 (2012) 26–42. Google Scholar
6. R. J. Johansson and K. J. Cole, Sensory-motor coordination during grasping and manipulative actions, Curr. Opin. Neurobiol. 2 (1992) 815–823. Crossref, Web of Science, Google Scholar
7. C. Zito, M. Kopicki, C. Borst, F. Schmidt, M. Roa and J. L. Wyatt, Sequential trajectory re-planning with tactile information gain for dexterous grasping under object-pose uncertainty, in 2013 IEEE/RSJ Int. Conf. Intelligent Robots and Systems (IROS) (IEEE, Tokyo, 2013), pp. 4013–4020. Google Scholar
8. L. P. Jentoft, Q. Wan and R. D. Howe, Limits to compliance and the role of tactile sensing in grasping, in IEEE Int. Conf. Robotics and Automation (IEEE, Hong Kong, 2014), pp. 6394–6399. Google Scholar
9. M. Bjorkman, Y. Bekiroglu, V. Hogman and D. Kragic, Enhancing visual perception of shape through tactile glances, in IEEE/RSJ Int. Conf. Intelligent Robots and Systems (IEEE, Tokyo, 2013), pp. 3180–3186. Google Scholar
10. P. Hebert, T. Howard, N. Hudson, J. Ma, J. Burdickand and W. Joel, The next best touch for model-based localization, in IEEE Int. Conf. Robotics and Automation (IEEE, Karlsruhe, 2013), pp. 99–106. Google Scholar
11. A. Petrovskaya and O. Khatib, Global localization of objects via touch, IEEE Trans. Robot. 27 (3) (2011) 569–585. Crossref, Web of Science, Google Scholar
12. H. Gu, S. Fan, H. Zong, M. Jin and H. Liu, Haptic perception of unknown object by robot hand: Exploration strategy and recognition approach, Int. J. Hum. Robot. 13 (3) (2016) 1650008. Link, Web of Science, Google Scholar
13. H. Gu, Y. Zhang, S. Fan, M. Jin and H. Liu, Grasp configurations optimization of dexterous robotic hand based on haptic exploration information, Int. J. Hum. Robot. 14 (4) (2017) 1750013. Link, Web of Science, Google Scholar
14. R. Bajcsy, Active perception, Proc. IEEE 76 (8) (1988) 966–1005. Crossref, Web of Science, Google Scholar
15. W. E. L. Grimson and T. Lozano-Perez, Model-based recognition and localization from sparse range or tactile data, J. Robot. Res. 3 (3) (1984) 3–35. Crossref, Web of Science, Google Scholar
16. O. Faugeras and M. Hebert, A 3D recognition and positioning algorithm using geometrical matching between primitive surfaces, in Proc. 8th Int. Joint Conf. Artificial Intelligence (William Kaufmann, Karlsruhe, 1983), pp. 996–1002. Google Scholar
17. S. Shekhar, O. Khatib and M. Shimojo, Sensor fusion and object localization, in IEEE Int. Conf. Robotics and Automation (IEEE, San Francisco, 1986), pp. 1623–1628. Google Scholar
18. R. Bajcsy, S. Lederman and R. L. Klatzky, Machine Systems for Exploration and Manipulation: A Conceptual Framework and Method of Evaluation, Technical Report, MS-CIS-89-03 (Moore School of Electrical Engineering, Philadelphia Department of Computer and Information Sciences, 1989). Google Scholar
19. S. Dragiev, M. Toussaint and M. Gienger, Gaussian process implicit surfaces for shape estimation and grasping, in Proc. IEEE Int. Conf. Robotics and Automation (IEEE, Shanghai, 2011), pp. 2845–2850. Google Scholar
20. N. Sommer, M. Li and A. Billard, Bimanual compliant tactile exploration for grasping unknown objects, in IEEE Int. Conf. Robotics and Automation (IEEE, Hong Kong, 2014), pp. 6400–6407. Google Scholar
21. C. Rasmussen and C. Williams, Gaussian Processes for Machine Learning (MIT Press, Boston, 2006). Google Scholar
22. L. Jaillet and J. M. Porta, Path planning under kinematic constraints by rapidly exploring manifolds, IEEE Trans. Robot. 29 (1) (2013) 105–117. Crossref, Web of Science, Google Scholar
23. P. K. Allen and R. Bajcsy, Robotic object recognition using vision and touch, in Proc. 9th Int. Joint Conf. Artificial Intelligence (Morgan Kaufmann, Milan, 1987), pp. 1131–1137. Google Scholar
24. P. K. Allen and P. Michelman, Acquisition and interpretation of 3D sensor data from touch, IEEE Trans. Robot. Autom. 6 (4) (1990) 397–404. Crossref, Google Scholar
25. K. Roberts, Robot active touch exploration: Constraints and strategies, in IEEE Int. Conf. Robotics and Automation (IEEE, Cincinnati, 1990), pp. 980–985. Google Scholar
26. S. Caselli, C. Magnanini, F. Zanichelli and E. Caraffi, Efficient exploration and recognition of convex objects based on haptic perception, in IEEE Int. Conf. Robotics and Automation (IEEE, Minneapolis, 1996), pp. 3508–3513. Google Scholar
27. M. Moll and M. A. Erdmann, Reconstructing the shape and motion of unknown objects with active tactile sensors, in Springer Tracts in Advanced Robotics, Chap. 17 (Springer-Verlag, Berlin, 2003), pp. 293–310. Google Scholar
28. M. Meier, M. Schopfer, R. Haschke and H. Ritter, A probabilistic approach to tactile shape reconstruction, IEEE Trans. Robot. 27 (3) (2011) 630–635. Crossref, Web of Science, Google Scholar
29. S. Dragiev, M. Toussaint and M. Gienger, Uncertainty aware grasping and tactile exploration, in IEEE Int. Conf. Robotics and Automation (IEEE, Karlsruhe, 2013), pp. 113–119. Google Scholar
30. S. Ottenhaus, M. Miller, D. Schiebener, N. Vahrenkamp and T. Asfour, Local implicit surface estimation for haptic exploration, in IEEE Humanoids (IEEE, Cancun, 2016), pp. 850–856. Google Scholar
31. A. Bierbaum, M. Rambow, T. Asfour and R. Dillmann, A potential field approach to dexterous tactile exploration of unknown objects, in 8th IEEE–RAS Int. Conf. Humanoid Robots (IEEE, Daejeon, 2008), pp. 360–366. Google Scholar
32. O. Williams and A. Fitzgibbon, Gaussian process implicit surfaces, in PASCAL — Pattern Analysis, Statistical Modelling and Computational Learning — Gaussian Processes in Practice Workshop (2007). Google Scholar
33. T. Matsubara, K. Shibata and K. Sugimoto, Active touch point selection with travel cost in tactile exploration for fast shape estimation of unknown objects, in IEEE Int. Conf. Advanced Intelligent Mechatronics (AIM) (IEEE, Banff, 2016), pp. 1115–1120. Google Scholar
34. U. Martinez-Hernandez, T. J. Dodd, M. H. Evans, T. J. Prescott and N. F. Lepora, Active sensorimotor control for tactile exploration, Robot. Auton. Syst. 87 (2017) 15–27. Crossref, Web of Science, Google Scholar
35. N. Jamali, C. Ciliberto, L. Rosasco and L. Natale, Active perception: Building objects’ models using tactile exploration, in IEEE–RAS 16th Int. Conf. Humanoid Robots (Humanoids) (IEEE, Cancun, 2016), pp. 179–185. Google Scholar
36. N. Tosi, O. David and H. Bruyninckx, Action selection for touch-based localisation trading off information gain and execution time, in IEEE Int. Conf. Robotics and Automation (ICRA 2014) (IEEE, Hong Kong, 2014), pp. 2270–2275. Google Scholar
37. N. F. Lepora, K. Aquilina and L. Cramphorn, Exploratory tactile servoing with active touch, IEEE Robot. Autom. Lett. 2 (2017) 1156–1163. Crossref, Web of Science, Google Scholar
38. M. E. Henderson, Computing Implicitly-Defined Surfaces: Two-Parameter Continuation, Technical Report 18777 (T. J. Watson Research Center, IBM Research Division, 1993). Google Scholar
39. S. M. LaValle, Motion planning, IEEE Robot. Autom. Magn. 18(1) (2011) 79–89. Google Scholar
40. M. Li, K. Hang, D. Kragic and A. Billard, Dexterous grasping under shape uncertainty, Robot. Auton. Syst. 75 (2016) 352–364. Crossref, Web of Science, Google Scholar
41. J. Porta, L. Ros, O. Bohigas, M. Manubens, C. Rosales and L. Jaillet, The CUIK suite: Analyzing the motion closed-chain multibody systems, IEEE Robot. Autom. Magn. 21(3) (2014) 105–114. Google Scholar
42. A. Bicchi, J. K. Salisbury and D. L. Brock, Contact sensing from force measurements, Int. J. Robot. Res. 12 (3) (1993) 249–262. Crossref, Web of Science, Google Scholar
43. M. G. Catalano, G. Grioli, E. Farnioli, A. Serio, C. Piazza and A. Bicchi, Adaptive synergies for the design and control of the Pisa/IIT soft hand, Int. J. Robot. Res. 33 (5) (2014) 768–782. Crossref, Web of Science, Google Scholar
44. G. Santaera, E. Luberto, A. Serio, M. Gabiccini and A. Bicchi, Low-cost, fast and accurate reconstruction of robotic and human postures via IMU measurements, in IEEE Int. Conf. Robotics and Automation (IEEE, Stockholm, 2015), pp. 2728–2735. Google Scholar
45. M. Quigley, K. Conley, B. P. Gerkey, J. Faust, T. Foote, J. Leibs, R. Wheeler and A. Y. Ng, ROS: An open-source robot operating system, in ICRA Workshop on Open Source Software (Willow Garage, Kobe, 2009). Google Scholar
46. C. Rosales, A. Ajoudani, M. Gabiccini and A. Bicchi, Active gathering of frictional properties from objects, in 2014 IEEE/RSJ Int. Conf. Intelligent Robots and Systems (IEEE, Chicago, 2014), pp. 3982–3987. Google Scholar
47. E. Solak, R. Murray-Smith, W. E. Leithead, D. J. Leith and C. E. Rasmussen, Derivative observations in Gaussian process models of dynamic systems, in Advances in Neural Information Processing Systems, eds. S. Becker, S. Thrun and K. Obermayer (Curran Associates, Vancouver, 2003), pp. 1057–1064. Google Scholar