← Search

Chaewon Kim

3 accepted papers

2022

A Compact and Agile Angled-Spoke Wheel-Based Mobile Robot for Uneven and Granular Terrains

RA-L 2022

This study proposes an angled spoke-based wheel(ASW) design to enhance the driving speed of a mobile robot with angled spoke-based wheels called DODO on granular media, asphalt ground, and transitions between them. The design parameters were optimized using the Taguchi method and <inline-formula xml

Cited by 12SourceScholar
2021

Scaling Neural Tangent Kernels via Sketching and Random Features

NeurIPS 2021poster

The Neural Tangent Kernel (NTK) characterizes the behavior of infinitely-wide neural networks trained under least squares loss by gradient descent. Recent works also report that NTK regression can outperform finitely-wide neural networks trained on small-scale datasets. However, the computational co…