Neural Network Based Reactive Navigation for Mobile Robot in Dynamic Environment

Abstract:

When mobile robots are used among people, the best accepted motion related behavior is a human-like motion of the robot. Such behavior is difficult to obtain with commonly used finite state machine based planners, but can easily be evoked when human controls the robot. The paper presents the way of transforming such knowledge from human controller to reactive planner in the robot navigation module. Reactive planner is based on machine learning, neural networks in particular. The planner consists of two separate neural networks, one serving as predictor of dynamic obstacles behavior, second one serving as the reactive planner itself, producing desirable actions of the robot both in terms of velocity and direction. Planner was verified on real robot producing human-like behavior when used in real environment.

• Periodical: Solid State Phenomena (Volume 198)
• Pages: 108-113
• DOI: https://doi.org/10.4028/www.scientific.net/SSP.198.108
• Online since: March 2013
• Authors: Jiri Krejsa, Stanislav Vĕchet, Tomas Ripel
• Keywords: Artificial Neural Network (ANN), Mobile Robot, Reactive Navigation

References

[1] K. Fujimura, H. Samet, A hierarchical strategy for path planning among moving obstacles, IEEE Trans. Robot. Automat., vol. 5, pp.61-69, (1989).

DOI: 10.1109/70.88018

[2] P. Fiorini, Z. Shiller, Motion planning in dynamic environments using velocity obstacles, International Journal of Robotic Research, vol. 17, no. 7., pp.760-772, (1998).

DOI: 10.1177/027836499801700706

[3] X. Xu, X. N. Wang, H.G. He, A self learning reactive navigation method for mobile robots, in Proceedings of the Second International Conference on Machine Learning and Cybernetics, Xian, pp.2384-2388, (2003).

DOI: 10.1109/icmlc.2003.1259909

[4] S. Věchet, V. Ondroušek, Motion planning of autonomous mobile robot in highly populated dynamic environment, in Mechatronics, recent technological and scientific advances, Springer, pp.453-462, (2011).

DOI: 10.1007/978-3-642-23244-2_55

[5] S. Věchet, The rule based path planner for autonomous mobile robot, 17th International Conference on Soft Computing MENDEL 2011, Brno, pp.546-551, (2011).

[6] J. Krejsa, S. Věchet, Mobile Robot Motion Planner via Neural Network, in Proceedings of Engineering Mechanics 2011, Svratka, pp.327-330, (2011).

[7] D. Janglová, Neural Networks in Mobile Robot Motion, International Journal of Advanced Robotic Systems, vol. 1 (1), pp.15-22, (2004).

[8] M.Y. Sirotenko, Applications of Convolutional Neural Networks in Mobile Robots Motion Trajectory Planning. Mobile Robots and Mechatronic Systems: Proceedings of Scientific Conference and Workshop, Moscow, pp.174-181, (2006).

[9] S.X. Yang, M.H. Meng, Real-time collision-free motion planning of a mobile robot using a Neural Dynamics-based approach, IEEE Transaction of neural networks, vol. 14 (6), pp.1541-1552, (2003).

DOI: 10.1109/tnn.2003.820618

[10] J. Krejsa, S. Věchet, Infrared beacons based localization of mobile robot, ELECTRONICS AND ELECTRICAL ENGINEERING, 1(117), pp.17-22, (2012).

DOI: 10.5755/j01.eee.117.1.1046

[11] M.T. Hagan, M. Menhaj, Training feedforward networks with the Marquardt algorithm, IEEE Transactions on Neural Networks, vol. 5, no. 6, pp.989-993, (1994).

DOI: 10.1109/72.329697