Michael Taylor — accepted AI-conference papers

2024

Neural Isometries: Taming Transformations for Equivariant ML

Thomas Mitchel, Michael Taylor, Vincent Sitzmann

NeurIPS 2024poster

Real-world geometry and 3D vision tasks are replete with challenging symmetries that defy tractable analytical expression. In this paper, we introduce Neural Isometries, an autoencoder framework which learns to map the observation space to a general-purpose latent space wherein encodings are related…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2021

Learning Bipedal Robot Locomotion from Human Movement

Michael Taylor, Sergey Bashkirov, Javier Fernandez Rico, Ike Toriyama, Naoyuki Miyada, Hideki Yanagisawa +1

ICRA 2021poster

Teaching an anthropomorphic robot from human example offers the opportunity to impart humanlike qualities on its movement. In this work we present a reinforcement learning based method for teaching a real world bipedal robot to perform movements directly from human motion capture data. Our method se…

Cited by 23 Source ↗Scholar ↗