We propose an algorithm used to obtain the information on stride length, height difference, and direction based on user's intent during walking. For exoskeleton robots used to assist paraplegic patients' walking, this information is used to generate gait patterns by themselves in on-line. To obtain this information, we attach an inertial measurement unit(IMU) on crutches and apply an extended kalman filter-based error correction method to reduce the phenomena of drift due to bias of the IMU. The proposed method is verifed in real walking scenarios including walking, climbing up-stairs, and changing direction of walking with normal.

This paper proposes a gait phase classifier using a Recurrent Neural Network (RNN). Walking is a type of dynamic system, and as such it seems that the classifier made by using a general feed forward neural network structure is not appropriate. It is known that an RNN is suitable to model a dynamic system. Because the proposed RNN is simple, we use a back propagation algorithm to train the weights of the network. The input data of the RNN is the lower body's joint angles and angular velocities which are acquired by using the lower limb exoskeleton robot, ROBIN-H1. The classifier categorizes a gait cycle as two phases, swing and stance. In the experiment for performance verification, we compared the proposed method and general feed forward neural network based method and showed that the proposed method is superior.

No abstract

No abstract