5 papers
Retriever: Composing Closed-Loop Asynchronous Robot Programs
Linfeng Zhao, Haojie Huang, Jiayuan Mao +3
Building long-horizon robot agents requires composing closed-loop pipelines -- perception, belief update, planning, and control -- whose components run at different clocks and with…
Pix2Act: Image-Space Manipulation Policies with Equivariant Augmentation
Haojie Huang, Linfeng Zhao, Haotian Liu +9
Representing manipulation actions as 2D trajectories in the camera plane provides a compact and interpretable basis for learning complex 3D manipulation policies. However, it also…
Action Map Policy: Learning 3D Closed-loop Manipulation via Pixel Classification
Haojie Huang, Zhang Ye, Linfeng Zhao +7
The action space poses a major challenge in robot learning, since it is often high-dimensional, can span long time horizons, and frequently admits multi-modal optimal solutions. A…
Clebsch-Gordan Transformer: Fast and Global Equivariant Attention
Owen Lewis Howell, Linfeng Zhao, Xupeng Zhu +6
The global attention mechanism is one of the keys to the success of transformer architecture, but it incurs quadratic computational costs in relation to the number of tokens. On th…
Hierarchical Equivariant Policy via Frame Transfer
Haibo Zhao, Dian Wang, Yizhe Zhu +6
Recent advances in hierarchical policy learning highlight the advantages of decomposing systems into high-level and low-level agents, enabling efficient long-horizon reasoning and…