Embodied Representation Alignment with Mirror Neurons
This work addresses a fundamental gap in AI for embodied agents by integrating action understanding and execution, though it is incremental as it builds on existing representation learning methods.
The paper tackles the problem of modeling action understanding and embodied execution as separate tasks in machine learning by proposing a unified representation learning approach inspired by mirror neurons, which aligns observed and executed action representations using contrastive learning, resulting in improved representation quality and generalization.
Mirror neurons are a class of neurons that activate both when an individual observes an action and when they perform the same action. This mechanism reveals a fundamental interplay between action understanding and embodied execution, suggesting that these two abilities are inherently connected. Nonetheless, existing machine learning methods largely overlook this interplay, treating these abilities as separate tasks. In this study, we provide a unified perspective in modeling them through the lens of representation learning. We first observe that their intermediate representations spontaneously align. Inspired by mirror neurons, we further introduce an approach that explicitly aligns the representations of observed and executed actions. Specifically, we employ two linear layers to map the representations to a shared latent space, where contrastive learning enforces the alignment of corresponding representations, effectively maximizing their mutual information. Experiments demonstrate that this simple approach fosters mutual synergy between the two tasks, effectively improving representation quality and generalization.