Skip to content
AI News HubLIVE
Original source2 min read

Joint Discovery of Object and Action Symbols through Effect Prediction for Robotic Manipulation Planning

Summary

The paper proposes a model that jointly discovers manipulation primitives and object categories via a binary bottleneck layer trained to predict multimodal outcomes from random interaction data, and uses discrete planning over predicted effect trajectories to outperform state-of-the-art and visual-based alternatives on tabletop repositioning and stacking tasks.

SourcearXiv RoboticsAuthor: Burcu Kilic, Berke Kartal, Fatih Dogangun, Erhan Oztop, Emre Ugur
Joint Discovery of Object and Action Symbols through Effect Prediction for Robotic Manipulation Planning
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 22 Jun 2026]

Title:Joint Discovery of Object and Action Symbols through Effect Prediction for Robotic Manipulation Planning

View a PDF of the paper titled Joint Discovery of Object and Action Symbols through Effect Prediction for Robotic Manipulation Planning, by Burcu Kilic and 4 other authors

View PDF HTML (experimental)

Abstract:To perform complex manipulation planning, autonomous robots are required to abstract continuous, high-dimensional sensorimotor interactions into discrete object and action representations. Earlier work either categorized objects based on visual appearances, which fails to distinguish objects that appear similar but behave differently, or based on effects under interaction, but was limited to predefined actions. To address these limitations, we propose a model that jointly discovers high-level manipulation primitives and object categories through a binary bottleneck layer, trained to predict multi-modal outcomes, including object motion, contact, and force feedback, from random interaction data. Building on these discovered binary representations, we leverage a discrete planning method that uses intermediate steps in the predicted effect trajectory to enable partial action executions for precise low-level control. Additionally, we evaluate our framework's generalization capabilities on novel objects by assigning object categories through comparing a small number of interaction effects with the predicted effects of learned object symbols, enabling few-shot generalization based on behavior rather than visual similarity. We conduct experiments on tabletop repositioning and stacking tasks, and confirm that our effect-driven planning approach outperforms both a state-of-the-art method and a visual-based alternative in planning precision across seen and novel objects.

Subjects:

Robotics (cs.RO)

Cite as: arXiv:2607.00031 [cs.RO]

(or arXiv:2607.00031v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2607.00031

arXiv-issued DOI via DataCite

Submission history

From: Burcu Kılıç [view email] [v1] Mon, 22 Jun 2026 11:58:11 UTC (4,969 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Joint Discovery of Object and Action Symbols through Effect Prediction for Robotic Manipulation Planning, by Burcu Kilic and 4 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.RO

new | recent | 2026-07

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • A binary bottleneck layer jointly discovers high-level manipulation primitives and object categories by predicting object motion, contact, and force feedback from random interaction data.
  • Discrete planning uses intermediate steps in predicted effect trajectories to enable partial action executions for precise low-level control.
  • Few-shot generalization to novel objects is achieved by comparing a small number of interaction effects with predicted effects of learned object symbols, based on behavior rather than visual similarity.
  • Experiments on tabletop repositioning and stacking confirm the effect-driven planner outperforms a state-of-the-art method and a visual-based alternative in planning precision for both seen and novel objects.

Highlights and analysis are generated automatically and may contain errors. Check the original source.