Skip to main content
. 2021 Jul 19;8:702845. doi: 10.3389/frobt.2021.702845

FIGURE 13.

FIGURE 13

Performance of learned controller under human-exoskeleton interactions in 200 simulated environments with different dynamics. The dynamic model of the exoskeleton is randomly initialized. (A) Rewards statistics (curve: mean; shade: STD) with respect to time for 200 simulated environments. (B) Average reward of a complete squatting cycle for each simulated environment.