E(2)-Equivariant Graph Planning for Navigation

We study E(2) Euclidean equivariance in navigation on geometric graphs and develop message passing network to solve it.

Can Euclidean Symmetry Help in Reinforcement Learning and Planning?

We study whether Euclidean symmetry can help in reinforcement learning and planning, which models the geometric transformations between reference frames of robots.

Equivariant Single View Pose Prediction Via Induced and Restriction Representations

We train an equivariant network for pose prediction from single 2D image by using induced and restricted representations.

Learning to Navigate in Mazes with Novel Layouts Using Abstract Top-down Maps

This work learns to navigate end-to-end with map input, aiming to generalize to novel map layouts in zero-shot.

Model-based Navigation in Environments with Novel Layouts Using Abstract 2-D Maps

This work aims to improve the zero-shot generalization performance in map-based navigation on novel layouts.

InterFact: Towards Interactive Factorization of Actionable Entities

This work proposes a reinforcement learning framework for compositional object-oriented environments.