5 accepted papers
Learning motion latents for robotic manipulation heavily relies on extracting motion patterns from visual sequences, yet effective action abstractions require understanding three-dimensional geometric transformations. Here, we introduce GeoMoLa (Geometry-Aware Motion Latents), which learns discrete …
Effective generalization in robotic manipulation requires representations that capture invariant patterns of interaction across environments and tasks. We present a self-supervised framework for learning hierarchical manipulation concepts that encode these invariant patterns through cross-modal sens…
Training embodied agents to perform complex robotic tasks presents significant challenges due to the entangled factors of task compositionality, environmental diversity, and dynamic changes. In this work, we introduce a novel imitation learning framework to train closed-loop concept-guided policies…
Effective policy learning for robotic manipulation requires scene representations that selectively capture task-relevant environmental features. Current approaches typically employ task-agnostic representation extraction, failing to emulate the dynamic perceptual adaptation observed in human cogniti…
We focus on the self-supervised discovery of manipulation concepts that can be adapted and reassembled to address various robotic tasks. We propose that the decision to conceptualize a physical procedure should not depend on how we name it (semantics) but rather on the significance of the informativ…