Sample-efficient Gear-ratio Optimization for Biomechanical Energy Harvester

TL;DR

This paper presents a data-driven, sample-efficient framework using multi-task Bayesian optimization to quickly find optimal gear ratios in a biomechanical energy harvester, adapting to various tasks and user conditions.

Contribution

The study introduces a novel multi-task Bayesian optimization framework that efficiently reuses data from similar tasks to optimize gear ratios in a CVT-equipped energy harvester.

Findings

Achieved 50% faster gear ratio optimization compared to random search.

Optimization process takes approximately 20 minutes per task.

Exploiting task similarities further accelerates the optimization.

Abstract

The biomechanical energy harvester is expected to harvest the electric energies from human motions. A tradeoff between harvesting energy and keeping the user's natural movements should be balanced via optimization techniques. In previous studies, the hardware itself has been specialized in advance for a single task like walking with constant speed on a flat. A key ingredient is Continuous Variable Transmission (CVT) to extend it applicable for multiple tasks. CVT could continuously adjust its gear ratio to balance the tradeoff for each task; however, such gear-ratio optimization problem remains open yet since its optimal solution may depend on the user, motion, and environment. Therefore, this paper focuses on a framework for data-driven optimization of a gear ratio in a CVT-equipped biomechanical energy harvester. Since the data collection requires a heavy burden on the user, we have to optimize the gear ratio for each task in the shortest possible time. To this end, our framework is designed sample-efficiently based on the fact that the user encounters multiple tasks, which are with similarities with each other. Specifically, our framework employs multi-task Bayesian optimization to reuse the optimization results of the similar tasks previously optimized by finding their similarities. Through experiments, we confirmed that, for each task, the proposed framework could achieve the optimal gear ratio of around 50~\% faster than one by random search, and that takes only around 20~minutes. Experimental results also suggested that the optimization can be accelerated by actively exploiting similarities with previously optimized tasks.