Abstract
Online navigation with known target and unknown obstacles is an interesting problem in mobile robotics. This article presents a technique based on utilization of neural networks and reinforcement learning to enable a mobile robot to learn constructed environments on its own. The robot learns to generate efficient navigation rules automatically without initial settings of rules by experts. This is regarded as the main contribution of this work compared to traditional fuzzy models based on notion of artificial potential fields. The ability for generalization of rules has also been examined. The initial results qualitatively confirmed the efficiency of the model. More experiments showed at least 32 % of improvement in path planning from the first till the third path planning trial in a sample environment. Analysis of the results, limitations, and recommendations is included for future work.
Similar content being viewed by others
References
Motlagh O, Tang SH, Ismail N (2009) Development of a new minimum avoidance system for a behavior-based mobile robot. Fuzzy Sets Syst 160(13):1929–1946
Motlagh O, Tang SH, Ismail N, Ramli AR (2012) An expert fuzzy cognitive map for reactive navigation of mobile robots. Fuzzy Sets Syst 201:105–121
Zhu A, Yang SX (2004) A fuzzy logic approach to reactive navigation of behavior-based mobile robots. In: Proceedings of the 2004 IEEE international conference on robotics and automation, 5:5045–5050
Hui NB, Mahendar V, Pratihar DK (2006) Time-optimal, collision-free navigation of a car-like mobile robot using neuro-fuzzy approaches. Fuzzy Sets Syst 157(16):2171–2204
Selekwa MF, Dunlap DD, Shi D, Collins EG Jr (2007) Robot navigation in very cluttered environments by preference-based fuzzy behaviors. Rob Auton Syst 56(3):231–246
Krishna KM, Kalra PK (2001) Perception and remembrance of the environment during real-time navigation of a mobile robot. Rob Auton Syst 37:25–51
Ordonez C, Collins EG Jr, Selekwa MF, Dunlap DD (2007) The virtual wall approach to limit cycle avoidance for unmanned ground vehicles. Rob Auton Syst 56(8):645–657
Xu WL, Tso SK (1999) Sensor-based fuzzy reactive navigation for a mobile robot through local target switching. IEEE Trans Syst Man Cybern C Appl Rev 29(3):451–459
Huq R, Mann GKI, Gosine RG (2008) Mobile robot navigation using motor schema and fuzzy context dependent behavior modulation. Appl Soft Comput 8(1):422–436
Tu K-Y, Baltes J (2006) Fuzzy potential energy for a map approach to robot navigation. Rob Auton Syst 54(7):574–589
Khatib O (1986) Real-time obstacle avoidance for manipulators and mobile robots. Int J Rob Res 5(1):90–98
Acar EU, Choset H (2002) Sensor-based coverage of unknown environments: incremental construction of morse decompositions. Int J Rob Res 21:345–366
Fekete SP, Schmidt C (2010) Polygon exploration with time-discrete vision. Comput Geom 43:148–168
MobotSim Version 1.0 (2001) Fully functional trial version of MobotSim. Retrieved from http://www.mobotsoft.com/?page_id=70
Stamova IM, Ilarionov R, Krustev K (2011) Asymptotic behavior of equilibriums of a class of impulsive bidirectional associative memory neural networks with time-varying delays. Neural Comput Appl 20(7):1111–1116
Leung ACS, Pui FS, Ho K (2011) The effect of weight fault on associative networks. Neural Comput Appl 20(1):113–121
Motlagh O, Tang SH, Ramli AR (2010) An FCM modeling for using a priori knowledge: application study in modeling quadruped walking. Neural Comput Appl 21(5):1007–1015
Motlagh O, Tang SH, Ismail N, Ramli AR, Samin R (2009) A new path estimation strategy for predicting blind persons’ motion in indoor environments. J Asian Arch Build Eng 8(2):371–377
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Motlagh, O., Nakhaeinia, D., Tang, S.H. et al. Automatic navigation of mobile robots in unknown environments. Neural Comput & Applic 24, 1569–1581 (2014). https://doi.org/10.1007/s00521-013-1393-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-013-1393-z