On-line incremental learning for unknown conditions during assembly operations with industrial robots
- 285 Downloads
The assembly operation using industrial robots can be accomplished successfully in well-structured environments where the mating pair location is known in advance. However, in real-world scenarios there are uncertainties associated to sensing, control and modelling errors that make the assembly task very complex. In addition, there are also unmodeled uncertainties that have to be taken into account for an effective control algorithm to succeed. Among these uncertainties, it can be mentioned disturbances, backlash and aging of mechanisms. In this paper, a method to overcome the effect of those uncertainties based on the Fuzzy ARTMAP artificial neural network (ANN) to successfully accomplish the assembly task is proposed. Experimental work is reported using an industrial 6 DOF robot arm in conjunction with a vision system for part location and wrist force/torque sensing data for assembly. Force data is fed into an ANN evolving controller during a typical peg in hole (PIH) assembly operation. The controller uses an incremental learning mechanism that is solely guided by the sensed forces. In this article, two approaches are presented in order to compare the incremental learning capability of the manipulator. The first approach uses a primitive knowledge base (PKB) containing 16 primitive movements to learn online the first insertion. During assembly, the manipulator learns new patterns according to the learning criteria which turn the PKB into an enhanced knowledge base (EKB). During a second insertion the controller uses effectively the EKB and operation improves. The second approach employs minimum information (it contains only the assembly direction) and the process starts from scratch. After several operations, that knowledge base increases by including only the needed patterns to perform the insertion. Experimental results showed that the evolving controller is able to assemble the matting pairs enhancing its knowledge whenever it is needed depending on the part geometry and level of expertise. Our approach is demonstrated through several PIH operations with different tolerances and part geometry. As the robot’s expertise evolves, the PIH operation is carried out faster with shorter assembly trajectories.
KeywordsIncremental learning Unknown environments Fuzzy ARTMAP Learning criterion.
Authors want to acknowledge CONACyT for Mr. Navarro Gonzalez’s scholarship to pursue his doctoral studies.
- Angelov P, Filev D, Kasabov N (2010) Evolving intelligent systems: methodology and applications. IEEE Press Series on Computational Intelligence. WilleyGoogle Scholar
- Asada H (1990) Teaching and learning of compliance using neural nets. IEEE Int Conf Robot Autom. pp 1237–1244Google Scholar
- Baek J, Lee H, Lee B, Lee H, Kim E (2014) An efficient genetic selection of the presentation order in simplified fuzzy ARTMAP patterns. Appl Soft Comput. vol 22, pp 101–107Google Scholar
- Bruzzone LE, Molfino RM, Zoppi M (2002) Modelling and control of peg-in-hole assembly performed by a translational robot. In: Proceedings of the International Conference Modeling Identification and Control, Austria, pp 512–7Google Scholar
- Chen Y, Han X, Okada M, Chen Y, Naghdy F (2007) Intelligent robotic peg-in-hole insertion learning based on haptic virtual environment. In: Computer-Aided Design and Computer Graphics, 2007 10th IEEE International Conference on, pp 355–360Google Scholar
- Cervera E, del Pobil AP (1996) Learning and classification of contact states in robotic assembly tasks. In: Proceedings of the 9th International Conference on IEA/AIE, pp 725–730Google Scholar
- Cervera E, del Pobil AP (1997) Programming and learning in real-world manipulation tasks. In: IEEE/RSJ International Conference on Intelligent Robot and Systems, pp 471–476Google Scholar
- Duan F, Tan JTC, Zhang Y, Watanabe K, Pongthanya N, Sugi M, Arai T (2007) Analyze assembly skills using a motion simulator. In: Robotics and Biomimetics, 2007. ROBIO 2007. IEEE International Conference on, pp 1428–1433Google Scholar
- Gama J, Aguilar J (2007) Knowledge discovery from data streams. Intell Data Anal. vol 11, pp 1–2Google Scholar
- Gonçalves PJS, Lopes PJF, Torres PMB, Sequeira JMR (2013) Evolving fuzzy uncalibrated visual servoing for mobile robots. Comput Intell Decis Making. pp 57–68Google Scholar
- Gullapalli V, Franklin JA, Benbrahim H (1994) Acquiring robot skills via reinforcement learning. IEEE Control Systems. pp 13–24Google Scholar
- Howarth M (1998) An investigation of task level programming for robotic assembly, Ph.D. Thesis, The Nottingham Trent UniversityGoogle Scholar
- Huang L, Song Q, Kasabov N (2005) Evolving connectionist systems based role allocation of robots for soccer playing. Intelligent Control, 2005. In: Proceedings of the 2005 IEEE International Symposium on, Mediterrean Conference on Control and Automation, pp 36–40Google Scholar
- Kasabov N, Filev D (2006) Evolving intelligent systems: methods, learning, & applications. Evolving Fuzzy Systems. In: 2006 International Symposium on, pp 8–18Google Scholar
- Kasabov N (2007) Evolving connectionist systems: the knowledge engineering approach. Springer, BerlinGoogle Scholar
- Nedev DG, Haasdijk E et al (2014) Controlling maximum evaluation duration in on-line and on-board evolutionary robotics. Evolving Systems, pp 1–12Google Scholar
- Xu J, He H, Man H (2012) DCPE co-training for classification. Neurocomputing, vol 86, pp 75–85Google Scholar
- Yun SK (2008) Compliant manipulation for peg-in-hole: is passive compliance a key to learn contact motion? In: Robotics and Automation, 2008. ICRA 2008. IEEE International Conference on, pp 1647–1652Google Scholar