Short abstract: How can we move beyond hand-crafted assumptions in building intelligent systems? Rigid priors hold back embodied AI: forcing perception to handle only predefined transformations, treating locomotion and navigation as isolated silos, and reducing perception to a single, context-free snapshot. I’ll present recent work on data-driven, context-adaptive approaches that move beyond these constraints, pointing toward agents that see robustly, act cohesively, and reason flexibly.

Long abstract:

A central challenge for embodied AI is moving beyond rigid priors – fixed assumptions that oversimplify perception, action, or representation. In perception, such priors appear as hand-crafted equivariant architectures or augmentation-heavy training, limiting generalization. In action, locomotion and navigation are often studied in isolation, assuming complex behavior can be modularized into separate skills. In representation learning, an image is typically treated as an objective measurement to be compressed into a single, context-free feature vector, overlooking that perception is subjective, context-dependent, and shaped by top-down as well as bottom-up processes.

I will present recent work that replaces these constraints with data-driven, context-adaptive methods. For perception, a test-time canonicalization framework leverages foundation models to achieve robustness across viewpoint, lighting, and temporal variation without retraining. For action, a trail-hiking framework unifies long-horizon navigation with fine-grained locomotion, driving cohesive skill development in humanoids. For representation, a contextualized feature learning approach supports open ad-hoc categorization, dynamically discovering novel concepts from sparse exemplars and unlabeled data. Furthermore, context itself can emerge naturally from data through internal visual consistency rather than external labels. These directions advance embodied AI toward more robust, cohesive, and flexible agents.

—

To request the Zoom link send an email to jteeters@berkeley.edu.  Also indicate if you would like to be added to the Redwood Seminar mailing list.