標題: An Uphill Safety Controller With Deep Learning-Based Ramp Detection for Intelligent Wheelchairs
作者: Wu, Bing-Fei
Chen, Yung-Shin
Huang, Ching-Wei
Chang, Po-Ju
電控工程研究所
Institute of Electrical and Control Engineering
關鍵字: Command and control systems;learning;intelligent wheelchair;deep learning;adaptive network-based fuzzy inference system (ANFIS);Q-learning;ramp classification
公開日期: 1-一月-2018
摘要: In a society with aging population, the demand for electric wheelchairs is growing with the advancement of automation. However, many accidents have occurred due to the misjudgment of the slope angle and wheelchair speed while the wheelchair is traveling on ramps. This research employs the light electronic assistance pal compact motor package to reduce the weight and size of conventional electric wheelchairs. The modular design of proposed uphill controller and ramp detection functions allows users to easily select and incorporate only the functions they need. This paper proposes a ramp detection model implemented using the deep learning algorithm with CNN-4 structure to analyze depth image data. The model's recognition time of each video frame is 11 times faster than that of the AlexNet and GoogleNet. The uphill safety controller is designed as an adaptive network-based fuzzy inference system with Q-learning. The safe speed is automatically calculated according to the angle obtained from slope classification and revised in real-time during the slope driving to prevent the user from moving towards the dangerous ramp or rolling back due to inadequate speed. The accuracy of ramp detection is further increased by 5% to 97.1% due to assistance from the voting system processing and the gyroscope output data. The 5 degrees ramp experiment of our uphill controller with ramp classification takes 20 s to complete the slope driving which is 23% faster than the controller without ramp detection. The energy consumption is also one half less than the experiment without uphill detection.
URI: http://dx.doi.org/10.1109/ACCESS.2018.2839729
http://hdl.handle.net/11536/145156
ISSN: 2169-3536
DOI: 10.1109/ACCESS.2018.2839729
期刊: IEEE ACCESS
Volume: 6
起始頁: 28356
結束頁: 28371
顯示於類別:期刊論文