# A probabilistic data-driven model for planar pushing

arXiv: https://arxiv.org/abs/1704.03033 · HTML: https://mlsanity.com/paper/1704.03033/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Apr 2017.

## Built on by (most cited first, 9 of 9)

- [Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills](https://mlsanity.com/paper/2104.07749/) (2021)
- [Does equivariance matter at scale?](https://mlsanity.com/paper/2410.23179/) (2024)
- [Learning rigid dynamics with face interaction graph networks](https://mlsanity.com/paper/2212.03574/) (2022)
- [Nonprehensile Planar Manipulation through Reinforcement Learning with Multimodal Categorical Exploration](https://mlsanity.com/paper/2308.02459/) (2023)
- [Learning Coordinated Bimanual Manipulation Policies using State Diffusion and Inverse Dynamics Models](https://mlsanity.com/paper/2503.23271/) (2025)
- [Learning Visuotactile Estimation and Control for Non-prehensile Manipulation under Occlusions](https://mlsanity.com/paper/2412.13157/) (2024)
- [Scaling Face Interaction Graph Networks to Real World Scenes](https://mlsanity.com/paper/2401.11985/) (2024)
- [Identifying Drivers of Predictive Aleatoric Uncertainty](https://mlsanity.com/paper/2312.07252/) (2023)
- [Non-Prehensile Aerial Manipulation using Model-Based Deep Reinforcement Learning](https://mlsanity.com/paper/2407.00889/) (2024)

## Abstract (arXiv)

This paper presents a data-driven approach to model planar pushing interaction to predict both the most likely outcome of a push and its expected variability. The learned models rely on a variation of Gaussian processes with input-dependent noise called Variational Heteroscedastic Gaussian processes (VHGP) that capture the mean and variance of a stochastic function. We show that we can learn accurate models that outperform analytical models after less than 100 samples and saturate in performance with less than 1000 samples. We validate the results against a collected dataset of repeated trajectories, and use the learned models to study questions such as the nature of the variability in pushing, and the validity of the quasi-static assumption.