Identification of abnormal movement state and avoidance strategy for mobile robots

Abstract

Abnormal movement states for a mobile robot were identified by four multi-layer perceptron. In the presence of abnormality, avoidance strategies were designed to guarantee the safety of the robot. Firstly, the kinematics of the normal and abnormal movement states were exploited, 8 kinds of features were extracted. Secondly, 4 multi-layer perceptrons were employed to classify the features for four 4-driving wheels into 4 kinds of states, i.e. normal, blocked, deadly blocked, and slipping. Finally, avoidance strategies were designed based on this. Experiment results show that the methods can identify most abnormal movement states and avoid the abnormality correctly and timely.

Keywords

mobile robot / abnormal movement state / avoidance strategy

References

[1] RoumeliotisS. I., SukhatmeG. S., BekeyG. A.. Sensor fault detection and identification in a mobile robot[C]. IEEE/RSJ International Conference on Intelligent Robots and Systems, 1998, Victoria, IEEE Press: 1383-1388

[2] GoelP., DedeogluG., RoumeliotisS. I., et al.. Fault detection and identification in a mobile robot using multiple model estimation and neural network[C]. IEEE International Conference on Robotics & Aufomation, 2000, San Francisco, IEEE Press: 2302-2309

[3] WashingtonR.. On-board real-time state and fault identification for rovers[C]. IEEE Int’l Conference on Robotics & Automation, 2000, San Francisco, IEEE Press: 1175-1181

[4] VermaV., GordonG., SimmonsR.. Efficient monitoring for planetary rovers[C]. International Symposium on Artificial Intelligence and Robotics in Space, 2003, Nara, IEEE Press

[5] KawabataKuniaki, OkinaShinnosuke, FujiiTeruo, AsamaHajime. A system for self-diagnosis of an autonomous mobile robot using an internal state sensory system: fault detection and coping with the internal condition. Advanced Robotics, 2003, 17(9): 925-950

[6] DixonW. E., WalkerI. D., DawsonD. M.. Fault detection for wheeled mobile robots with parametric uncertainty[C]. IEEE/ASME Intl’ Conference on Advanced Intelligent Mechatronics, 2001, Como, IEEE Press: 1245-1250

[7] DuanZ.-h., CaiZ.-x., YuJ.-xia.. Fault diagnosis and fault tolerant control for wheeled mobile robots under unknown environments: A survey[J]. Robot, 2005, 27(4): 373-379

[8] TingH. N., YunusJ.. Speaker-independent Malay vowel recognition of children using multi-layer perceptron[C]. 2004 IEEE Region 10 Conference Proceedings: Analog and Digital Techniques in Electrical Engineering, 2004, Chiangmai, IEEE Press: A68-A71

[9] PurushothamaG. K., NarendranathA. U., ThukaramD., et al.. ANN applications in fault locators[J]. International Journal of Electrical Power and Energy System, 2001, 23(6): 491-506

[10] YuD.-j., ZhaoH.-t., YangJ.-yu.. Face recognition: An approach based on feature fusion and neural network[J]. Journal of System Simulation, 2005, 17(5): 1179-1181

[11] CAI Zi-xing, ZOU Xiao-bing, WANG Lu, et al. A research on mobile robot navigation control in unknown environment: objectives, design and experiences[C]// Proceedings of Korea-Sino Symposium on Intelligent Systems. Busan: 2004: 57–63.

[12] AlexanderJ. C., MaddocksJ. H.. On the kinematics of wheeled mobile robots[J]. International Journal of Robotics Research, 1989, 8(5): 15-27