# Augmenting Physical Simulators with Stochastic Neural Networks: Case Study of Planar Pushing and Bouncing

arXiv: https://arxiv.org/abs/1808.03246 · HTML: https://mlsanity.com/paper/1808.03246/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Aug 2018.

## Built on by (most cited first, 30 of 36)

- [PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation](https://mlsanity.com/paper/2409.18964/) (2024)
- [ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills](https://mlsanity.com/paper/2502.01143/) (2025)
- [From Imitation to Refinement -- Residual RL for Precise Assembly](https://mlsanity.com/paper/2407.16677/) (2024)
- [Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modeling](https://mlsanity.com/paper/2102.13156/) (2021)
- [Learning rigid dynamics with face interaction graph networks](https://mlsanity.com/paper/2212.03574/) (2022)
- [From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligence](https://mlsanity.com/paper/2110.15245/) (2021)
- [Residual Reinforcement Learning from Demonstrations](https://mlsanity.com/paper/2106.08050/) (2021)
- [KNODE-MPC: A Knowledge-based Data-driven Predictive Control Framework for Aerial Robots](https://mlsanity.com/paper/2109.04821/) (2021)
- [The Reality Gap in Robotics: Challenges, Solutions, and Best Practices](https://mlsanity.com/paper/2510.20808/) (2025)
- [Learning 3D Particle-based Simulators from RGB-D Videos](https://mlsanity.com/paper/2312.05359/) (2023)
- [SAGCI-System: Towards Sample-Efficient, Generalizable, Compositional, and Incremental Robot Learning](https://mlsanity.com/paper/2111.14693/) (2021)
- [QuasiSim: Parameterized Quasi-Physical Simulators for Dexterous Manipulations Transfer](https://mlsanity.com/paper/2404.07988/) (2024)
- [Max-Min Off-Policy Actor-Critic Method Focusing on Worst-Case Robustness to Model Misspecification](https://mlsanity.com/paper/2211.03413/) (2022)
- [ArrayBot: Reinforcement Learning for Generalizable Distributed Manipulation through Touch](https://mlsanity.com/paper/2306.16857/) (2023)
- [Closing the Train-Test Gap in World Models for Gradient-Based Planning](https://mlsanity.com/paper/2512.09929/) (2025)
- [Machine-Learning Non-Conservative Dynamics for New-Physics Detection](https://mlsanity.com/paper/2106.00026/) (2021)
- [ElastoGen: 4D Generative Elastodynamics](https://mlsanity.com/paper/2405.15056/) (2024)
- [Residual Physics Learning and System Identification for Sim-to-real Transfer of Policies on Buoyancy Assisted Legged Robots](https://mlsanity.com/paper/2303.09597/) (2023)
- [Neural Robot Dynamics](https://mlsanity.com/paper/2508.15755/) (2025)
- [Generalizing Cooperative Eco-driving via Multi-residual Task Learning](https://mlsanity.com/paper/2403.04232/) (2024)
- [Precision-Focused Reinforcement Learning Model for Robotic Object Pushing](https://mlsanity.com/paper/2411.08622/) (2024)
- [PeRP: Personalized Residual Policies For Congestion Mitigation Through Co-operative Advisory Systems](https://mlsanity.com/paper/2308.00864/) (2023)
- [An Efficient Image-to-Image Translation HourGlass-based Architecture for Object Pushing Policy Learning](https://mlsanity.com/paper/2108.01034/) (2021)
- [Physics-Informed Model and Hybrid Planning for Efficient Dyna-Style Reinforcement Learning](https://mlsanity.com/paper/2407.02217/) (2024)
- [Learning Physics-Guided Residual Dynamics for Deformable Object Simulation](https://mlsanity.com/paper/2607.13451/) (2026)
- [Transfer Learning Approaches for Knowledge Discovery in Grid-based Geo-Spatiotemporal Data](https://mlsanity.com/paper/2110.00841/) (2021)
- [Zero-shot Sim2Real Adaptation Across Environments](https://mlsanity.com/paper/2302.04013/) (2023)
- [Neural Partial Differential Equations with Functional Convolution](https://mlsanity.com/paper/2303.07194/) (2023)
- [Physics-integrated generative modeling using attentive planar normalizing flow based variational autoencoder](https://mlsanity.com/paper/2404.12267/) (2024)
- [Cooperative Advisory Residual Policies for Congestion Mitigation](https://mlsanity.com/paper/2407.00553/) (2024)

## Abstract (arXiv)

An efficient, generalizable physical simulator with universal uncertainty estimates has wide applications in robot state estimation, planning, and control. In this paper, we build such a simulator for two scenarios, planar pushing and ball bouncing, by augmenting an analytical rigid-body simulator with a neural network that learns to model uncertainty as residuals. Combining symbolic, deterministic simulators with learnable, stochastic neural nets provides us with expressiveness, efficiency, and generalizability simultaneously. Our model outperforms both purely analytical and purely learned simulators consistently on real, standard benchmarks. Compared with methods that model uncertainty using Gaussian processes, our model runs much faster, generalizes better to new object shapes, and is able to characterize the complex distribution of object trajectories.