Neural fidelity warping for efficient robot morphology design
This work provides a more efficient method for robot designers to optimize robot morphology, which is a problem for robotics and control engineers.
This paper addresses the challenge of optimizing robot morphology under computational constraints by proposing a continuous multi-fidelity Bayesian Optimization framework. It introduces a fidelity warping mechanism to model non-stationary covariances between continuous fidelity evaluations, which allows for efficient utilization of low-fidelity evaluations to search for optimal robot morphology, outperforming state-of-the-art methods.
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.