Pith. sign in

REVIEW 1 cited by

Composing Pre-Trained Object-Centric Representations for Robotics From "What" and "Where" Foundation Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2404.13474 v1 pith:Z3WM4TXH submitted 2024-04-20 cs.RO cs.AIcs.CVcs.LG

Composing Pre-Trained Object-Centric Representations for Robotics From "What" and "Where" Foundation Models

classification cs.RO cs.AIcs.CVcs.LG
keywords pre-trainedrepresentationsroboticcontrolobject-centricmodelsbuildingcapturing
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

There have recently been large advances both in pre-training visual representations for robotic control and segmenting unknown category objects in general images. To leverage these for improved robot learning, we propose $\textbf{POCR}$, a new framework for building pre-trained object-centric representations for robotic control. Building on theories of "what-where" representations in psychology and computer vision, we use segmentations from a pre-trained model to stably locate across timesteps, various entities in the scene, capturing "where" information. To each such segmented entity, we apply other pre-trained models that build vector descriptions suitable for robotic control tasks, thus capturing "what" the entity is. Thus, our pre-trained object-centric representations for control are constructed by appropriately combining the outputs of off-the-shelf pre-trained models, with no new training. On various simulated and real robotic tasks, we show that imitation policies for robotic manipulators trained on POCR achieve better performance and systematic generalization than state of the art pre-trained representations for robotics, as well as prior object-centric representations that are typically trained from scratch.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Spotlighting Task-Relevant Features: Object-Centric Representations for Better Generalization in Robotic Manipulation

    cs.RO 2026-01 conditional novelty 6.0

    Slot-based object-centric visual representations, especially with robot-video pretraining, improve out-of-distribution generalization of robotic manipulation policies compared to global and dense pre-trained features.