Is an object-centric representation beneficial for robotic manipulation ?
Alexandre Chapin (imagine), Emmanuel Dellandrea (imagine), Liming Chen (imagine)

TL;DR
This paper investigates whether object-centric representations improve robotic manipulation by evaluating their generalization capabilities in complex, multi-object simulated environments, comparing them to holistic approaches.
Contribution
The study provides a systematic evaluation of object-centric representations in robotic manipulation tasks, highlighting their advantages over holistic methods in complex scenarios.
Findings
Object-centric methods outperform holistic approaches in complex scenes.
Existing object-centric models struggle with scene complexity and inter-object interactions.
Object-centric representations enhance generalization in multi-object robotic tasks.
Abstract
Object-centric representation (OCR) has recently become a subject of interest in the computer vision community for learning a structured representation of images and videos. It has been several times presented as a potential way to improve data-efficiency and generalization capabilities to learn an agent on downstream tasks. However, most existing work only evaluates such models on scene decomposition, without any notion of reasoning over the learned representation. Robotic manipulation tasks generally involve multi-object environments with potential inter-object interaction. We thus argue that they are a very interesting playground to really evaluate the potential of existing object-centric work. To do so, we create several robotic manipulation tasks in simulated environments involving multiple objects (several distractors, the robot, etc.) and a high-level of randomization (object…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsRobot Manipulation and Learning
