Neural fidelity warping for efficient robot morphology design

TL;DR

This paper introduces a multi-fidelity Bayesian Optimization approach with fidelity warping to efficiently optimize robot morphologies by leveraging low-fidelity evaluations, reducing computational costs.

Contribution

It proposes a novel fidelity warping mechanism to model non-stationarity in multi-fidelity Bayesian Optimization for robot design.

Findings

Outperforms existing methods in efficiency and accuracy

Effectively models non-stationary covariances across fidelities

Reduces computational resources needed for morphology optimization

Abstract

We consider the problem of optimizing a robot morphology to achieve the best performance for a target task, under computational resource limitations. The evaluation process for each morphological design involves learning a controller for the design, which can consume substantial time and computational resources. To address the challenge of expensive robot morphology evaluation, we present a continuous multi-fidelity Bayesian Optimization framework that efficiently utilizes computational resources via low-fidelity evaluations. We identify the problem of non-stationarity over fidelity space. Our proposed fidelity warping mechanism can learn representations of learning epochs and tasks to model non-stationary covariances between continuous fidelity evaluations which prove challenging for off-the-shelf stationary kernels. Various experiments demonstrate that our method can utilize the low-fidelity evaluations to efficiently search for the optimal robot morphology, outperforming state-of-the-art methods.