Human-in-the-Loop Optimization of Knee Exoskeleton Assistance for Minimizing User's Metabolic and Muscular Effort

Abstract

Lower limb exoskeletons have the potential to mitigate work-related musculoskeletal disorders; however, they often lack user-oriented control strategies. Human-in-the-loop (HITL) controls adapt an exoskeleton's assistance in real time, to optimize the user-exoskeleton interaction. This study presents a HITL control for a knee exoskeleton using a CMA-ES algorithm to minimize the users' physical effort, a parameter innovatively evaluated using the interaction torque with the exoskeleton (a muscular effort indicator) and metabolic cost. This work innovates by estimating the user's metabolic cost within the HITL control through a machine-learning model. The regression model estimated the metabolic cost, in real time, with a root mean squared error of 0.66 W/kg and mean absolute percentage error of 26% (n = 5), making faster (10 s) and less noisy estimations than a respirometer (K5, Cosmed). The HITL reduced the user's metabolic cost by 7.3% and 5.9% compared to the zero-torque and no-device conditions, respectively, and reduced the interaction torque by 32.3% compared to a zero-torque control (n = 1). The developed HITL control surpassed a non-exoskeleton and zero-torque condition regarding the user's physical effort, even for a task such as slow walking. Furthermore, the user-specific control had a lower metabolic cost than the non-user-specific assistance. This proof-of-concept demonstrated the potential of HITL controls in assisted walking.

Keywords: exoskeletons; human-in-the-loop control; metabolic cost estimation; work-related musculoskeletal disorders.

Figure 1

HITL control proposed to minimize an exoskeleton user’s physical effort assessed in terms of metabolic cost and human–robot interaction torque.

Figure 2

Method for processing input data to estimate metabolic cost.

Figure 3

Knee torque profile optimized in real time by the CMA-ES.

Figure 4

Participant performing the standing, walking, and sitting activities.

Figure 5

Participant walking with the exoskeleton during HITL validation.

Figure 6

Experimental protocol performed to validate the HITL control.

Figure 7

Comparison of the metabolic cost estimated by indirect calorimetry and the regression model. Results from one representative participant.

Figure 8

Mean and variation of the RMSE (left view) and the MAPE (right view) between the metabolic cost estimated by indirect calorimetry and the regression model, for each activity.

Figure 9

Bland-Altman plots for each activity with data from the 5 participants. Indication of the bias between the ground-truth and the estimated metabolic cost. Each plot also depicts the upper and lower limits of agreement, with red and blue lines, respectively.

Figure 10

Evolution of the torque flexion and extension peaks of torque (top view) and the cost function value (bottom view) during the 120 iterations (20 min) of the CMA-ES optimizer.

Figure 11

Boxplots displaying the metabolic cost variation during the tested conditions. The median value during the tested conditions is marked in blue.

Figure 12

Boxplots displaying the interaction torque variation and median value during the tested conditions.