Collaborative and non-collaborative dynamic path prediction algorithm for mobile agents collision detection with dynamic obstacles in a two-dimensional space

In this research a new algorithm for dynamic collaborative path prediction for mobile agents is proposed. This algorithm is inspired by human behavior in group of dynamical obstacles. Mobile agent in collaborative manner uses coordinates of other mobile agents in the same environment to calculate and based on statistical methods predict future path of other objects. For this purpose spatial-temporal variables are decomposed in order to optimize the method and to make it more efficient. This algorithm can be used in mobile robotics, automobile industry and civil aeronautics. Moreover this method allows full decentralization of collision detection which allows many advantages from minimizing of network traffic to simplifying of inclusion of additional agents in relevant space. This algorithm in his implementation will be low resource consuming allowing mobile agents to free resources for additional tasks.

[1]  F. Kerestecioglu,et al.  On preserving connectivity of autonomous mobile robots , 2009, 2009 IEEE Control Applications, (CCA) & Intelligent Control, (ISIC).

[2]  Luis Payá,et al.  An educational tool for mobile robots remote interaction , 2010 .

[3]  Stephen Grossberg,et al.  SOVEREIGN: an Autonomous Neural System for Incrementally Learning to Navigate towards a Rewarded Goal , 2008 .

[4]  Metin Ozkan,et al.  A genetic algorithm for task completion time minimization for multi-robot sensor-based coverage , 2009, 2009 IEEE Control Applications, (CCA) & Intelligent Control, (ISIC).

[5]  J. Borenstein,et al.  Cross-coupling motion controller for mobile robots , 1993, IEEE Control Systems.

[6]  Gregory Dudek,et al.  Collaborative Robot Exploration and Rendezvous: Algorithms, Performance Bounds and Observations , 2001, Auton. Robots.

[7]  Nicholas Roy,et al.  Exponential Family PCA for Belief Compression in POMDPs , 2002, NIPS.

[8]  Dirk Aeyels,et al.  Multi-robot coverage to locate fixed and moving targets , 2009, 2009 IEEE Control Applications, (CCA) & Intelligent Control, (ISIC).

[9]  Andrea Garulli,et al.  A Matlab-based Remote Lab for Multi-Robot Experiments , 2010 .

[10]  Antonella Ferrara,et al.  A dynamic obstacle avoidance strategy for a mobile robot based on sliding mode control , 2009, 2009 IEEE Control Applications, (CCA) & Intelligent Control, (ISIC).

[11]  Léon J. M. Rothkrantz,et al.  Automated Static and Dynamic Obstacle Avoidance in Arbitrary 3D Polygonal Worlds , 2008 .

[12]  Sebastian Thrun,et al.  Probabilistic robotics , 2002, CACM.

[13]  Nicholas Roy,et al.  Efficient model learning for dialog management , 2007, 2007 2nd ACM/IEEE International Conference on Human-Robot Interaction (HRI).

[14]  Eiichi Yoshida,et al.  Cooperative sweeping by multiple mobile robots , 1996, Proceedings of IEEE International Conference on Robotics and Automation.

[15]  Akio Ishiguro,et al.  Fully decentralized control of a soft-bodied robot inspired by true slime mold , 2010, Biological Cybernetics.

[16]  E. Gat.  On Three-Layer Architectures , 1997 .

[17]  Yoon Keun Kwak,et al.  Driving Mode Decision in the Obstacle Negotiation of a Variable Single-Tracked Robot , 2008, Adv. Robotics.

[18]  Rolf Dieter Schraft,et al.  Mobile robot assistants , 2004, IEEE Robotics & Automation Magazine.

[19]  Y. Charlie Hu,et al.  Deployment of mobile robots with energy and timing constraints , 2006, IEEE Transactions on Robotics.

[20]  Johan Forsberg,et al.  Mobile robot navigation using the range-weighted Hough transform , 1995, IEEE Robotics Autom. Mag..

[21]  Nicholas Roy,et al.  CORL: A Continuous-state Offset-dynamics Reinforcement Learner , 2008, UAI.

[22]  Sebastian Thrun,et al.  Planning under Uncertainty for Reliable Health Care Robotics , 2003, FSR.