Teach-and-Replay of Mobile Robot with Particle Filter on Episode

A novel method for replaying behavior of a mobile robot from its memory of past experiences is presented in this paper. The method is a version of a particle filter on episode (PFoE), which applies a particle filter on the memory so as to efficiently find some similar situations with the current one. Though the original PFoE was proposed as a reinforcement learning method, we once removed the reward system from the original one so as to apply it to task teaching. In the experiment, we gave several kinds of motion to a micromouse type robot with the proposed method through a gamepad. The robot replayed the behaviors robustly with sensor feedback after several number of repetitive teaching.

[1]  Wolfram Burgard,et al.  Lidar-based teach-and-repeat of mobile robot trajectories , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[2]  Morgan Quigley,et al.  ROS: an open-source Robot Operating System , 2009, ICRA 2009.

[3]  Gordon Wyeth,et al.  Mapping a Suburb With a Single Camera Using a Biologically Inspired SLAM System , 2008, IEEE Transactions on Robotics.

[4]  G. Buzsáki,et al.  Memory, navigation and theta rhythm in the hippocampal-entorhinal system , 2013, Nature Neuroscience.

[5]  Manuela M. Veloso,et al.  Sensor resetting localization for poorly modelled mobile robots , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).

[6]  Chu Kiong Loo,et al.  Humanoid behaviour learning through visuomotor association by self-imitation , 2014, 2014 Joint 7th International Conference on Soft Computing and Intelligent Systems (SCIS) and 15th International Symposium on Advanced Intelligent Systems (ISIS).

[7]  David M. Lane,et al.  Probabilistic Behaviour Signatures: Feature-based behaviour recognition in data-scarce domains , 2010, 2010 13th International Conference on Information Fusion.

[8]  Chin-Hui Lee,et al.  An integrated approach to feature compensation combining particle filters and hidden Markov models for robust speech recognition , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[9]  Hiroyuki Okada,et al.  Particle Filter on Episode for Learning Decision Making Rule , 2016, IAS.

[10]  Peng Zhang,et al.  Behavior prediction using an improved Hidden Markov Model to support people with disabilities in smart homes , 2016, 2016 IEEE 20th International Conference on Computer Supported Cooperative Work in Design (CSCWD).

[11]  Masahiro Kato,et al.  Particle Filter on Episode , 2019, ArXiv.

[12]  Satoshi Nakamura,et al.  Learning, Generation and Recognition of Motions by Reference-Point-Dependent Probabilistic Models , 2011, Adv. Robotics.

[13]  Ryuichi Ueda,et al.  Raspberry Pi Mouse : A Micromouse with Full Linux Environment , 2015 .

[14]  Tamio Arai,et al.  Expansion resetting for recovery from fatal error in Monte Carlo localization - comparison with sensor resetting methods , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).

[15]  Miroslav Kulich,et al.  Monte Carlo Localization for Teach-and-Repeat Feature-Based Navigation , 2014, TAROS.