This work deals with neural network (NN)-based gait pattern adaptation algorithms for an active lowerlimb orthosis. Stable trajectories with different walking speeds are generated during an optimization process considering the zero-moment point (ZMP) criterion and the inverse dynamic of the orthosis-patient model. Additionally, a set of NNs is used to decrease the time-consuming analytical computation of the model and ZMP. The first NN approximates the inverse dynamics including the ZMP computation, while the second NN works in the optimization procedure, giving an adapted desired trajectory according to orthosis-patient interaction. This trajectory adaptation is added directly to the trajectory generator, also reproduced by a set of NNs. With this strategy, it is possible to adapt the trajectory during the walking cycle in an on-line procedure, instead of changing the trajectory parameter after each step. The dynamic model of the actual exoskeleton, with interaction forces included, is used to generate simulation results. Also, an experimental test is performed with an active ankle-foot orthosis, where the dynamic variables of this joint are replaced in the simulator by actual values provided by the device. It is shown that the final adapted trajectory follows the patient intention of increasing the walking speed, so changing the gait pattern.
This work deals with an optimization system developed to find optimal parameters for neural oscillators used to generate joint trajectories of an exoskeleton for lower limbs. The exoskeleton is considered as a biped robot that presents cyclical joint trajectories during the walking. Matsuoka neural oscillator, which consists of two mutual inhibitory neurons and is modeled by two differential equations for each one, is being used as trajectory generator for the robot joints. The neural oscillators are able to produce a cyclical output. However, the parameters of the differential equations are difficult to be set for a given desired output. Thus, we have implemented an optimization system to find the better values to the neural oscillator parameters given a predefined desired joint trajectory of an exoskeleton for lower limbs. This optimization system works to minimize the error between the trajectory generated by the oscillator and the desired trajectory, regarding the robot dynamics. The advantage of using oscillators is justified because the trajectories can be generated in real time, with a less time-consuming with relation to the analytical methods. A simulation of the exoskeleton considering the optimization system is presented. The results show the proposed optimization system and the trajectory generator using neural oscillators can be applied in an adaptive model that include interaction forces between the user and the robot, so changing the trajectory according to the user intention.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.