AnyPlace: Learning Generalizable Object Placement for Robot Manipulation

Yuchi Zhao, Miroslav Bogdanovic, Chengyuan Luo, Steven Tohme, Kourosh Darvish, Alan Aspuru-Guzik, Florian Shkurti, Animesh Garg
Proceedings of The 9th Conference on Robot Learning, PMLR 305:4038-4057, 2025.

Abstract

Object placement in robotic tasks is inherently challenging due to the diversity of object geometries and placement configurations. We address this with AnyPlace, a two-stage method trained entirely on synthetic data, capable of predicting a wide range of feasible placement poses for real-world tasks. Our key insight is that by leveraging a Vision-Language Model (VLM) to identify approximate placement locations, we can focus only on the relevant regions for precise local placement, which enables us to train the low-level placement-pose-prediction model to capture multimodal placements efficiently. For training, we generate a fully synthetic dataset comprising 13 categories of randomly generated objects in 5370 different placement poses across three configurations (insertion, stacking, hanging) and train local placement-prediction models. We extensively evaluate our method in high-fidelity simulation and show that it consistently outperforms baseline approaches across all three tasks in terms of success rate, coverage of placement modes, and precision. In real-world experiments, our method achieves an average success and coverage rate of 76% across three tasks, where most baseline methods fail completely. We further validate the generalization of our approach on 16 real-world placement tasks, demonstrating that models trained purely on synthetic data can be directly transferred to the real world in a zero-shot setting. More at: https://anyplace-pnp.github.io.

Cite this Paper

BibTeX
@InProceedings{pmlr-v305-zhao25b, title = {AnyPlace: Learning Generalizable Object Placement for Robot Manipulation}, author = {Zhao, Yuchi and Bogdanovic, Miroslav and Luo, Chengyuan and Tohme, Steven and Darvish, Kourosh and Aspuru-Guzik, Alan and Shkurti, Florian and Garg, Animesh}, booktitle = {Proceedings of The 9th Conference on Robot Learning}, pages = {4038--4057}, year = {2025}, editor = {Lim, Joseph and Song, Shuran and Park, Hae-Won}, volume = {305}, series = {Proceedings of Machine Learning Research}, month = {27--30 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v305/main/assets/zhao25b/zhao25b.pdf}, url = {https://proceedings.mlr.press/v305/zhao25b.html}, abstract = {Object placement in robotic tasks is inherently challenging due to the diversity of object geometries and placement configurations. We address this with AnyPlace, a two-stage method trained entirely on synthetic data, capable of predicting a wide range of feasible placement poses for real-world tasks. Our key insight is that by leveraging a Vision-Language Model (VLM) to identify approximate placement locations, we can focus only on the relevant regions for precise local placement, which enables us to train the low-level placement-pose-prediction model to capture multimodal placements efficiently. For training, we generate a fully synthetic dataset comprising 13 categories of randomly generated objects in 5370 different placement poses across three configurations (insertion, stacking, hanging) and train local placement-prediction models. We extensively evaluate our method in high-fidelity simulation and show that it consistently outperforms baseline approaches across all three tasks in terms of success rate, coverage of placement modes, and precision. In real-world experiments, our method achieves an average success and coverage rate of 76% across three tasks, where most baseline methods fail completely. We further validate the generalization of our approach on 16 real-world placement tasks, demonstrating that models trained purely on synthetic data can be directly transferred to the real world in a zero-shot setting. More at: https://anyplace-pnp.github.io.} }
Endnote
%0 Conference Paper %T AnyPlace: Learning Generalizable Object Placement for Robot Manipulation %A Yuchi Zhao %A Miroslav Bogdanovic %A Chengyuan Luo %A Steven Tohme %A Kourosh Darvish %A Alan Aspuru-Guzik %A Florian Shkurti %A Animesh Garg %B Proceedings of The 9th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2025 %E Joseph Lim %E Shuran Song %E Hae-Won Park %F pmlr-v305-zhao25b %I PMLR %P 4038--4057 %U https://proceedings.mlr.press/v305/zhao25b.html %V 305 %X Object placement in robotic tasks is inherently challenging due to the diversity of object geometries and placement configurations. We address this with AnyPlace, a two-stage method trained entirely on synthetic data, capable of predicting a wide range of feasible placement poses for real-world tasks. Our key insight is that by leveraging a Vision-Language Model (VLM) to identify approximate placement locations, we can focus only on the relevant regions for precise local placement, which enables us to train the low-level placement-pose-prediction model to capture multimodal placements efficiently. For training, we generate a fully synthetic dataset comprising 13 categories of randomly generated objects in 5370 different placement poses across three configurations (insertion, stacking, hanging) and train local placement-prediction models. We extensively evaluate our method in high-fidelity simulation and show that it consistently outperforms baseline approaches across all three tasks in terms of success rate, coverage of placement modes, and precision. In real-world experiments, our method achieves an average success and coverage rate of 76% across three tasks, where most baseline methods fail completely. We further validate the generalization of our approach on 16 real-world placement tasks, demonstrating that models trained purely on synthetic data can be directly transferred to the real world in a zero-shot setting. More at: https://anyplace-pnp.github.io.
APA
Zhao, Y., Bogdanovic, M., Luo, C., Tohme, S., Darvish, K., Aspuru-Guzik, A., Shkurti, F. & Garg, A.. (2025). AnyPlace: Learning Generalizable Object Placement for Robot Manipulation. Proceedings of The 9th Conference on Robot Learning, in Proceedings of Machine Learning Research 305:4038-4057 Available from https://proceedings.mlr.press/v305/zhao25b.html.

Related Material