It is crucial to optimize the control parameters of wearable robots for a possible reduction in the metabolic cost of the wearer. However, the limitation of the existing Human-in-the-Loop approaches is that the optimization can only be conducted inside the laboratory as it takes a long time to measure the human response (i.e., metabolic cost). Consequently, it demands high computational time and power, which restricts the application of wearable robots in daily life. Therefore, it is necessary to develop a mobile Human-in-the-Loop approach that can optimize the control parameters in real-time outside the laboratory. This paper presents the portable Human-in-the-Loop (HIL) optimization for autonomous exosuit with hip extension assistance. The optimization is conducted via the Bayesian optimization with maximizing the positive delivered mechanical power from the exosuit to the wearer, instead of the metabolic costs requiring time-consuming process. The preliminary result considering a single participant show an increase in mechanical power by as much as 210.9%, and a reduction in the metabolic cost by as much as 12.41% is achieved.

Funding Information
This work was supported by the R&D Program for Forest Science Technology (No. 2021364B10-2123-BD01) provided by the Korea Forest Service (Korea Forestry Promotion Institute), and the Industrial Strategic Technology Development Program (No. 20007058), funded by the Ministry of Trade, Industry, & Energy (MOTIE, Korea)