Distinguish the Textures of Grasped Objects by Robotic Hand Using Artificial Neural-Network

Salman, Hassan D.; Hamzah, Mohsin N.; Bakhy, Sadeq H.

doi:10.30684/etj.v39i9.2072

	Distinguish the Textures of Grasped Objects by Robotic Hand Using Artificial Neural-Network
Engineering and Technology Journal
Article 11, Volume 39, Issue 9, September 2021, Pages 1420-1429 PDF (1.38 M)
Document Type: Research Paper
DOI: 10.30684/etj.v39i9.2072
Authors
Hassan D. Salman^* ; Mohsin N. Hamzah; Sadeq H. Bakhy
Mechanical Engineering Department, University of Technology, Baghdad, Iraq.
Abstract
The object identification properties with tactile sensing are valuable in interaction with the environment for both humans and robots, and it is the core of sensing used for exploration and determining properties of objects that are inaccessible from visual perception. Object identification often involves with rigid mechanical grippers, tactile information and intelligent algorithms. This paper proposes a methodology for feature extraction techniques and discriminates objects for different softness using adaptive robotic grippers, which are equipped with force and angle sensors in each four fingers of an underactuated robot hand. Arduino microcontroller and the Matlab program are integrated to acquire sensor data and to control the gripping action. The neural-network method used as an intelligent classifier to distinguish between different object softness by using feature vector acquired from the force sensor measurements and actuator positions in time series response during the grasping process using only a single closure grasping. The proposed method efficiency was validated using experimental paradigms that involving three sets of model objects and everyday life objects with various shapes, stiffness, and sizes.
Highlights
Feature vector was acquired from force and actuator sensors in time series response. Arduino microcontroller and the Matlab program are integrated to acquire sensor data. Neural-Network used as an intelligent classifier to distinguish the object softness.
Keywords
Tactile sensing Arduino; adaptive grasping Under-actuated robot hands Object feature extraction Neural-network

References
[1] E. Vander Poorten, E. Demeester, and P. Lammertse, “Haptic feedback for medical applications, a survey,” Proc. Actuator 2012, 2012. [2] B. Rasolzadeh, M. Björkman, K. Huebner, and D.Kragic,“An active vision system for detecting, fixating and manipulating objects in the real world,” Int. J. Rob. Res., vol. 29, no. 2–3, pp. 133–154, 2010. [3] M. Popović, G. Kootstra, D. Kragic and N. Krüger,“Grasping unknown objects using an early cognitive vision system for general scene understanding,” IEEE Int. Conf. Intell. Robot. Syst., pp. 987–994, 2011. [4] Y. Bekiroglu, D. Kragic, and V. Kyrki, “Learning grasp stability based on tactile data and HMMs,” Proc. - IEEE Int. Work. Robot Hum. Interact. Commun., pp. 132–137, 2010. [5] F. De Boissieu, C. Godin, C. Serviere, and D. Baudois, “Tactile texture recognition with a 3-axial force mems integrated artificial finger,” Robot. Sci. Syst., vol. 5, pp. 49–56, 2010. [6] T. Bhattacharjee, J. M. Rehg, and C. C. Kemp, “Inferring Object Properties with a Tactile-Sensing Array Given Varying Joint Stiffness and Velocity,” Int. J. Humanoid Robot., vol. 15, no. 1, pp. 1–12, 2018. [7] B. Frank and C. Stachniss, “Learning the Elasticity Parameters of Deformable Objects with a Manipulation Robot,” pp. 1877–1883, 2010. [8] J. Sinapov, S. Member, V. Sukhoy, R. Sahai, and A. Stoytchev, “Vibrotactile Recognition and Categorization of Surfaces by a Humanoid Robot,” vol. 27, no. 3, pp. 488–497, 2011. [9] A. Drimus, G. Kootstra, A. Bilberg, and D. Kragic, “Classification of rigid and deformable objects using a novel tactile sensor,” IEEE 15th Int. Conf. Adv. Robot. New Boundaries Robot., pp. 427–434, 2011. [10] H. Soh and Y. Demiris, “Incrementally learning objects by touch: Online discriminative and generative models for tactile-based recognition,” IEEE Trans. Haptics, vol. 7, no. 4, pp. 512–525, 2014. [11] R. S. Johansson and J. R. Flanagan, “Coding and use of tactile signals from the fingertips in object manipulation tasks,” Nat. Rev. Neurosci., vol. 10, no. 5, pp. 345–359, 2009. [12] K. Motoo, T. Fukuda, F. Arai, and T. Matsuno, “Piezoelectric vibration-type tactile sensor with wide measurement range using elasticity and viscosity change,” in 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2006, pp. 1946–1951. [13] J. Inouye, J. Kutch, and F. Valero,“A novel synthesis of computational approaches enables optimization of grasp quality of tendon-driven hands,” IEEE Trans. Robot., vol. 28, no. 4, pp. 958–966, 2012. [14] K. Weiß and H. Worn, “The working principle of resistive tactile sensor cells,” in IEEE International Conference Mechatronics and Automation, 2005, 2005, vol. 1, pp. 471–476. [15] F. Castelli, “An integrated tactile-thermal robot sensor with capacitive tactile array,” IEEE Trans. Ind. Appl., vol. 38, no. 1, pp. 85–90, 2002. [16] Y. Hasegawa et al., “Amicromachined active tactile sensor for hardness detection,” Sensors Actuators A Phys., vol. 114, no. 2–3, pp. 141–146, 2004. [17] J. Tegin and J. Wikander, “Tactile sensing in intelligent robotic manipulation–a review,” Ind. Robot An Int. J., 2005. [18] I. Bandyopadhyaya, D. Babu, and A. Kumar, “Tactile sensing based softness classification using machine learning,” in 2014 IEEE International Advance Computing Conference (IACC), 2014. [19] H. K. Lam et al., “A study of neural-network-based classifiers for material classification,” Neurocomputing, vol. 144, pp. 367–377, 2014. [20] J. A. Fishel and G. E. Loeb, “Bayesian exploration for intelligent identification of textures,” Front. Neurorobot., vol. 6, no. JUNE, pp. 1–20, 2012. [21] V. Chu et al., “Using robotic exploratory procedures to learn the meaning of haptic adjectives,” Proc. - IEEE Int. Conf. Robot. Autom., pp. 3048–3055, 2013.
Statistics Article View: 268 PDF Download: 268