Learning from Demonstration with State Based Obstacle Avoidance for Mobile Service Robots

Abstract:

Learning from Demonstration (LfD) is a technique for teaching a system through demonstration. In areas like service robotics the robot should be user friendly in terms of coding, so LfD techniques will be of greater advantage in this domain. In this paper two novel approaches, counter based technique and encoder based technique is proposed for teaching a mobile service robot to navigate from one point to another with a novel state based obstacle avoidance technique. The main aim of the work is to develop an LfD Algorithm which is less complex in terms of hardware and software. Both the proposed methods along with obstacle avoidance have been implemented and tested using Player/Stage robotics simulator.

• Periodical: Applied Mechanics and Materials (Volume 394)
• Pages: 448-455
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.394.448
• Online since: September 2013
• Authors: A.A. Nippun Kumaar, T.S.B. Sudarshan
• Keywords: Counter Method, Encoder Method, Learning from Demonstration, Mobile Robot, Navigation, Service Robots

References

[1] Brenna D. Argall a, Sonia Chernovab, Manuela Veloso b, Brett Browninga, A survey of robot learning from demonstration, Robotics and Autonomous Systems 57 (2009) pg 469 – 483.

DOI: 10.1016/j.robot.2008.10.024

[2] Siciliano, Bruno; Khatib, Oussama A Handbook for Robotics, Springer publication, ISBN 978-3-540-30301-5, (2008).

[3] Kerr, U. Nehmzow, S.A. Billings, Towards Automated Code Generation for Autonomous Mobile Robots in, Advances in Intelligent Systems Research AGI-10, Atlantis Press. March (2010).

DOI: 10.2991/agi.2010.37

[4] Roberto Iglesias, Ulrich Nehmzow, Theocharis Kyriacou and Steve Billings, Modelling and characterisation of a mobile robot's operation Current Topics in Artificial Intelligence 11th Conference of the Spanish Association for Artificial Intelligence, CAEPIA 2005 Santiago de Compostela, Spain, Springer Verlag (2006).

DOI: 10.1007/11881216_49

[5] R. Iglesias, T. Kyriacou, U. Nehmzow, S.A. Billings, Task Identification and characterisation in mobile robotics through non-linear modeling, in Robotics and Autonomous Systems 55 (2007) pg267–275.

DOI: 10.1016/j.robot.2006.11.007

[6] Halit Bener Suay, Russell Toris, Sonia Chernova, Special Issue on Robot Learning from Demonstration, In International Journal of Social Robotics, August 2012, pg 319-330.

DOI: 10.1007/s12369-012-0158-7

[7] Baris Akgun, Maya Cakmak, Karl Jiang, Andrea L. Thomaz, Keyframe-based Learning from Demonstration Method and Evaluation, In International Journal of Social Robotics, August 2012, pg 343-335.

DOI: 10.1007/s12369-012-0160-0

[8] Daniel H. Grollman, Aude G. Billard, Robot Learning from Failed Demonstrations, In International Journal of Social Robotics, August 2012, pg 331-342.

DOI: 10.1007/s12369-012-0161-z

[9] Shuonan Dong, BrianWilliams, Learning and Recognition of Hybrid Manipulation Motions In Variable Environments Using Probabilistic Flow Tubes, In International Journal of Social Robotics, August 2012, pg 357-368.

DOI: 10.1007/s12369-012-0155-x

[10] Yasser Mohammad, Toyoaki Nishida, Fluid Imitation Discovering What to Imitate?, In International Journal of Social Robotics, August 2012, pg 369-382.

DOI: 10.1007/s12369-012-0153-z

[11] Brenna D. Argall, Brett Browning, Manuela M. Veloso, Policy Feedback for the Refinement of Learned Motion Control on a Mobile Robot, In International Journal of Social Robotics, August 2012, pg 383-395.

DOI: 10.1007/s12369-012-0156-9

[12] W. Bradley Knox, Brian D. Glass, Bradley C. Love, W. Todd Maddox, Peter Stone How Humans Teach Agents A New Experimental Perspective, In International Journal of Social Robotics, August 2012, pg 409-421.

DOI: 10.1007/s12369-012-0163-x

[13] Çetin Meriçli, Manuela Veloso, H. Levent Akın Multi-resolution Corrective Demonstration for Efficient Task Execution and Refinement, In International Journal of Social Robotics, August 2012, pg 423-435.

DOI: 10.1007/s12369-012-0159-6

[14] Rainer Jäkel, Sven R. Schmidt-Rohr, SteffenW. Rühl, Alexander Kasper, Zhixing Xue, Rüdiger Dillmann, Learning of Planning Models for Dexterous Manipulation Based on Human Demonstrations, In International Journal of Social Robotics, August 2012, pg 437-448.

DOI: 10.1007/s12369-012-0162-y

[15] Brian P. Gerkey, Richard T. Vaughan, and Andrew Howard, The Player/Stage Project: Tools for Multi-Robot and Distributed Sensor Systems, In Proc. of the Intl. Conf. on Advanced Robotics (ICAR), pages 317-323, Coimbra, Portugal, July (2003).

[16] A.A. Nippun Kumaar, Sudarshan TSB, Mobile Robot Programming By Demonstration, 2011 Fourth International Conference on Emerging Trends in Engineering & Technology, (ICETET-11), IEEE Computer Society, November 18-20, 2011, Mauritius. pg 206 – 209.

DOI: 10.1109/icetet.2011.30