USA-Net: Unified Semantic and Affordance Representations for Robot Memory
Ben Bolte,Austin Wang,Jimmy Yang,Mustafa Mukadam,Mrinal Kalakrishnan,Chris Paxton,Ben Bolte,Austin Wang,Jimmy Yang,Mustafa Mukadam,Mrinal Kalakrishnan,Chris Paxton
In order for robots to follow open-ended instructions like “go open the brown cabinet over the sink,” they require an understanding of both the scene geometry and the semantics of their environment. Robotic systems often handle these through separate pipelines, sometimes using very different representation spaces, which can be suboptimal when the two objectives conflict. In this work, we present U...
