Learning affordances in object-centric generative models
Given visual observations of a reaching task together with a stick-like tool, we propose a novel approach that learns to exploit task-relevant object affordances by combining generative modelling with a task-based performance predictor. The embedding learned by the generative model captures the fact...
主要な著者: | Wu, Y, Kasewa, S, Groth, O, Salter, S, Sun, L, Parker Jones, O, Posner, H |
---|---|
フォーマット: | Conference item |
言語: | English |
出版事項: |
International Conference on Machine Learning
2020
|
類似資料
-
Reconstruction bottlenecks in object-centric generative models
著者:: Engelcke, M, 等
出版事項: (2020) -
GENESIS: generative scene inference and sampling of object-centric latent representations
著者:: Engelcke, M, 等
出版事項: (2020) -
APEX: Unsupervised, object-centric scene segmentation and tracking for robot manipulation
著者:: Wu, Y, 等
出版事項: (2021) -
Object-centric generative models for robot perception and action
著者:: Wu, Y
出版事項: (2023) -
DreamUp3D: object-centric generative models for single-view 3D scene understanding and real-to-sim transfer
著者:: Wu, Y, 等
出版事項: (2024)