SOURCE-LINKED INTELLIGENCE

Rethinking Visual Embodiment Dependence in Visuomotor Policies

arXiv · AI, language, vision and robotics · article · Sep 15, 2026 · UTC

Visuomotor policies observe both the task scene and the acting embodiment, allowing embodiment-specific visual cues to influence action prediction. We study this phenomenon as visual embodiment dependence (VED) and show, through cue-conflict interventions across representative policies, that visible robot configuration can become a shortcut to task progress. Rather than eliminating VED, we argue that it should be structured around embodiment information that supports control and generalization. We realize this through embodiment canonicalization in 3D point clouds, replacing the original embod

Read original source ↗ Open in workspace

recordType

paper

region

Global