Assessment of rehabilitative exercises by humanoid robot

This article describes an approach in which the rehabilitative exercise prepared by health care professional (human) is encoded as formal knowledge and used by humanoid robot to assist patients in residential settings without involving other care actors. The authors are researching on the new cognitive capability enabling robots to judge about the correctness of the rehabilitative exercise performed by patients following the robot's indications. The proposed method uses the Dynamic Time Warping functionality comparing the correct sequence (encoded in the Knowledge Base) with the human actions being observed by the robot's eyes. The proposed approach is an enabler of better sustainable rehabilitative care services in remote residential settings because of lowering the need of human care.

[1]  Eamonn J. Keogh,et al.  Searching and Mining Trillions of Time Series Subsequences under Dynamic Time Warping , 2012, KDD.

[2]  Bernt Schiele,et al.  ADL recognition based on the combination of RFID and accelerometer sensing , 2008, 2008 Second International Conference on Pervasive Computing Technologies for Healthcare.

[3]  Nassir Navab,et al.  Human skeleton tracking from depth data using geodesic distances and optical flow , 2012, Image Vis. Comput..

[4]  G. Sen Gupta,et al.  Wireless Sensor Network for Selective Activity Monitoring In a Home for the Elderly , 2007, 2007 IEEE Instrumentation & Measurement Technology Conference IMTC 2007.

[5]  Dugki Min,et al.  Behavioral synchronization of human and humanoid robot , 2011, 2011 8th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI).

[6]  Wu Xiong,et al.  The design of lower limbs rehabilitative training device control system , 2010, 2010 International Conference on Computer Application and System Modeling (ICCASM 2010).

[7]  P. Caselli,et al.  Classification of Motor Activities through Derivative Dynamic Time Warping applied on Accelerometer Data , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[8]  R. Adams.  Proceedings , 1947 .

[9]  Diane J. Cook,et al.  Human Activity Recognition and Pattern Discovery , 2010, IEEE Pervasive Computing.

[10]  Ifeyinwa E. Achumba,et al.  On time series sensor data segmentation for fall and activity classification , 2012, 2012 IEEE 14th International Conference on e-Health Networking, Applications and Services (Healthcom).