We are interested in incorporating the subject responses in human-in-the-loop optimization methods to directly target propulsion mechanics during training. Instrumental to this goal, we have established whether Gaussian process modeling can be used to describe data collected from our previous experiment. Using participants’ response of 16 pulse torque assistance profiles and optimal length scale hyperparameters for each input parameters, Gaussian process model of group-level hip extension and propulsive impulse data are fitted and shown in above figures. Red dashed line: model at the stride before intervention (stride −1); blue line: model at the stride of intervention (stride 0). Our analysis shows that the effect of pulses of torque on propulsion mechanics can be described using Gaussian process modeling, which opens the possibility for stochastic optimization methods such as Bayesian Optimization that we plan to test in coming experiments. (G. Kim and F. Sergi pre-print)

Active Pelvis Orthosis (APO) robot, light weight untethered exoskeleton robot which can provide hip joint torques to subject, is currently implemented with HIL using Bayesian optimization method. The goal of optimization is to target propulsion mechanics during training by controlling hip torque pulse profile applied to participant at every step. To increase computational capacity, optimization is conducted on a separate computer to derive control parameters for the APO robot.

Publications on this topic

 G. Kim, F. Sergi, “Modeling Neuromotor Adaptation to Pulsed Torque Assistance During Walking”, 2024, doi: 10.1101/2024.02.19.580556, pre-print.