# ContactNets: Learning Discontinuous Contact Dynamics with Smooth, Implicit Representations

arXiv: https://arxiv.org/abs/2009.11193 · HTML: https://mlsanity.com/paper/2009.11193/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Sep 2020.

## Built on by (most cited first, 30 of 38)

- [Neural Fields in Visual Computing and Beyond](https://mlsanity.com/paper/2111.11426/) (2021)
- [Implicit Behavioral Cloning](https://mlsanity.com/paper/2109.00137/) (2021)
- [Learning Multi-Object Dynamics with Compositional Neural Radiance Fields](https://mlsanity.com/paper/2202.11855/) (2022)
- [Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environments](https://mlsanity.com/paper/2209.15090/) (2022)
- [Does equivariance matter at scale?](https://mlsanity.com/paper/2410.23179/) (2024)
- [Differentiable Physics Simulation of Dynamics-Augmented Neural Objects](https://mlsanity.com/paper/2210.09420/) (2022)
- [Learning rigid dynamics with face interaction graph networks](https://mlsanity.com/paper/2212.03574/) (2022)
- [Robust and Versatile Bipedal Jumping Control through Reinforcement Learning](https://mlsanity.com/paper/2302.09450/) (2023)
- [Learning Models as Functionals of Signed-Distance Fields for Manipulation Planning](https://mlsanity.com/paper/2110.00792/) (2021)
- [CCIL: Continuity-based Data Augmentation for Corrective Imitation Learning](https://mlsanity.com/paper/2310.12972/) (2023)
- [KNODE-MPC: A Knowledge-based Data-driven Predictive Control Framework for Aerial Robots](https://mlsanity.com/paper/2109.04821/) (2021)
- [A Survey of Optimization-based Task and Motion Planning: From Classical To Learning Approaches](https://mlsanity.com/paper/2404.02817/) (2024)
- [Chain-of-Thought Predictive Control](https://mlsanity.com/paper/2304.00776/) (2023)
- [ENFORCE: Nonlinear Constrained Learning with Adaptive-depth Neural Projection](https://mlsanity.com/paper/2502.06774/) (2025)
- [Learning to Walk from Three Minutes of Real-World Data with Semi-structured Dynamics Models](https://mlsanity.com/paper/2410.09163/) (2024)
- [Partition Speeds Up Learning Implicit Neural Representations Based on Exponential-Increase Hypothesis](https://mlsanity.com/paper/2310.14184/) (2023)
- [QuasiSim: Parameterized Quasi-Physical Simulators for Dexterous Manipulations Transfer](https://mlsanity.com/paper/2404.07988/) (2024)
- [Building Minimal and Reusable Causal State Abstractions for Reinforcement Learning](https://mlsanity.com/paper/2401.12497/) (2024)
- [From Screens to Scenes: A Survey of Embodied AI in Healthcare](https://mlsanity.com/paper/2501.07468/) (2025)
- [Explorable INR: An Implicit Neural Representation for Ensemble Simulation Enabling Efficient Spatial and Parameter Exploration](https://mlsanity.com/paper/2504.00904/) (2025)
- [Neural Robot Dynamics](https://mlsanity.com/paper/2508.15755/) (2025)
- [Manifold-Constrained Energy-Based Transition Models for Offline Reinforcement Learning](https://mlsanity.com/paper/2602.02900/) (2026)
- [OSCAR: Data-Driven Operational Space Control for Adaptive and Robust Robot Manipulation](https://mlsanity.com/paper/2110.00704/) (2021)
- [Differentiable Visual Computing for Inverse Problems and Machine Learning](https://mlsanity.com/paper/2312.04574/) (2023)
- [Verified Safe Reinforcement Learning for Neural Network Dynamic Models](https://mlsanity.com/paper/2405.15994/) (2024)
- [One-Shot Real-to-Sim via End-to-End Differentiable Simulation and Rendering](https://mlsanity.com/paper/2412.00259/) (2024)
- [Simulation Distillation: Pretraining World Models in Simulation for Rapid Real-World Adaptation](https://mlsanity.com/paper/2603.15759/) (2026)
- [LeTO: Learning Constrained Visuomotor Policy with Differentiable Trajectory Optimization](https://mlsanity.com/paper/2401.17500/) (2024)
- [TSINR: Capturing Temporal Continuity via Implicit Neural Representations for Time Series Anomaly Detection](https://mlsanity.com/paper/2411.11641/) (2024)
- [Differentiable Simulation of Hard Contacts with Soft Gradients for Learning and Control](https://mlsanity.com/paper/2506.14186/) (2025)

## Abstract (arXiv)

Common methods for learning robot dynamics assume motion is continuous, causing unrealistic model predictions for systems undergoing discontinuous impact and stiction behavior. In this work, we resolve this conflict with a smooth, implicit encoding of the structure inherent to contact-induced discontinuities. Our method, ContactNets, learns parameterizations of inter-body signed distance and contact-frame Jacobians, a representation that is compatible with many simulation, control, and planning environments for robotics. We furthermore circumvent the need to differentiate through stiff or non-smooth dynamics with a novel loss function inspired by the principles of complementarity and maximum dissipation. Our method can predict realistic impact, non-penetration, and stiction when trained on 60 seconds of real-world data.