# Simultaneous Learning of Contact and Continuous Dynamics

arXiv: https://arxiv.org/abs/2310.12054 · HTML: https://mlsanity.com/paper/2310.12054/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Oct 2023.

## Built on by (most cited first, 8 of 8)

- [A Survey of Optimization-based Task and Motion Planning: From Classical To Learning Approaches](https://mlsanity.com/paper/2404.02817/) (2024)
- [Differentiable Simulation of Hard Contacts with Soft Gradients for Learning and Control](https://mlsanity.com/paper/2506.14186/) (2025)
- [CHyLL: Learning Continuous Neural Representations of Hybrid Systems](https://mlsanity.com/paper/2512.10117/) (2025)
- [From Variance to Veracity: Unbundling and Mitigating Gradient Variance in Differentiable Bundle Adjustment Layers](https://mlsanity.com/paper/2406.07785/) (2024)
- [DEFT: Differentiable Branched Discrete Elastic Rods for Modeling Furcated DLOs in Real-Time](https://mlsanity.com/paper/2502.15037/) (2025)
- [DLO-Splatting: Tracking Deformable Linear Objects Using 3D Gaussian Splatting](https://mlsanity.com/paper/2505.08644/) (2025)
- [Test-Time Spatial Reasoning for Robot Manipulation Using Generative Real-to-Sim](https://mlsanity.com/paper/2609.33982/) (2026)
- [ZeroBot: Learning from Scratch in Minutes with Generative Real2Sim](https://mlsanity.com/paper/2609.34010/) (2026)

## Abstract (arXiv)

Robotic manipulation can greatly benefit from the data efficiency, robustness, and predictability of model-based methods if robots can quickly generate models of novel objects they encounter. This is especially difficult when effects like complex joint friction lack clear first-principles models and are usually ignored by physics simulators. Further, numerically-stiff contact dynamics can make common model-building approaches struggle. We propose a method to simultaneously learn contact and continuous dynamics of a novel, possibly multi-link object by observing its motion through contact-rich trajectories. We formulate a system identification process with a loss that infers unmeasured contact forces, penalizing their violation of physical constraints and laws of motion given current model parameters. Our loss is unlike prediction-based losses used in differentiable simulation. Using a new dataset of real articulated object trajectories and an existing cube toss dataset, our method outperforms differentiable simulation and end-to-end alternatives with more data efficiency. See our project page for code, datasets, and media: https://sites.google.com/view/continuous-contact-nets/home