Wenyu Han — accepted AI-conference papers

2023

Learning Simultaneous Navigation and Construction in Grid Worlds

Wenyu Han, Haoran Wu, Eisuke Hirota, Alexander Gao, Lerrel Pinto, Ludovic Righetti +1

ICLR 2023poster

We propose to study a new learning task, mobile construction, to enable an agent to build designed structures in 1/2/3D grid worlds while navigating in the same evolving environments. Unlike existing robot learning tasks such as visual navigation and object manipulation, this task is challenging bec…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2020

SPARE3D: A Dataset for SPAtial REasoning on Three-View Line Drawings

Wenyu Han, Siyuan Xiang, Chenhui Liu, Ruoyu Wang, Chen Feng

CVPR 2020poster

Spatial reasoning is an important component of human intelligence. We can imagine the shapes of 3D objects and reason about their spatial relations by merely looking at their three-view line drawings in 2D, with different levels of competence. Can deep networks be trained to perform spatial reasonin…

Cited by 20 PDF ↗code ↗Scholar ↗