# Neural Robot Dynamics

arXiv: https://arxiv.org/abs/2508.15755 · HTML: https://mlsanity.com/paper/2508.15755/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 50 references that are in the map.
- First posted on arXiv 21 Aug 2025.

## Builds on (most cited first, 30 of 38)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [Learning to Simulate Complex Physics with Graph Networks](https://mlsanity.com/paper/2002.09405/) (2020)
- [Learning Mesh-Based Simulation with Graph Networks](https://mlsanity.com/paper/2010.03409/) (2020)
- [When to Trust Your Model: Model-Based Policy Optimization](https://mlsanity.com/paper/1906.08253/) (2019)
- [Learning Dexterous In-Hand Manipulation](https://mlsanity.com/paper/1808.00177/) (2018)
- [Scientific Machine Learning through Physics-Informed Neural Networks: Where we are and What's next](https://mlsanity.com/paper/2201.05624/) (2022)
- [Learning Quadrupedal Locomotion over Challenging Terrain](https://mlsanity.com/paper/2010.11251/) (2020)
- [RMA: Rapid Motor Adaptation for Legged Robots](https://mlsanity.com/paper/2107.04034/) (2021)
- [Evaluating Real-World Robot Manipulation Policies in Simulation](https://mlsanity.com/paper/2405.05941/) (2024)
- [Temporal Difference Learning for Model Predictive Control](https://mlsanity.com/paper/2203.04955/) (2022)
- [ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills](https://mlsanity.com/paper/2302.04659/) (2023)
- [Graph networks as learnable physics engines for inference and control](https://mlsanity.com/paper/1806.01242/) (2018)
- [PAC-NeRF: Physics Augmented Continuum Neural Radiance Fields for Geometry-Agnostic System Identification](https://mlsanity.com/paper/2303.05512/) (2023)
- [DeXtreme: Transfer of Agile In-hand Manipulation from Simulation to Reality](https://mlsanity.com/paper/2210.13702/) (2022)
- [TossingBot: Learning to Throw Arbitrary Objects with Residual Physics](https://mlsanity.com/paper/1903.11239/) (2019)
- [Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning](https://mlsanity.com/paper/2304.13653/) (2023)
- [Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapes](https://mlsanity.com/paper/2211.11744/) (2022)
- [NeuralSim: Augmenting Differentiable Simulators with Neural Networks](https://mlsanity.com/paper/2011.04217/) (2020)
- [An End-to-End Differentiable Framework for Contact-Aware Robot Design](https://mlsanity.com/paper/2107.07501/) (2021)
- [Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics](https://mlsanity.com/paper/2501.10100/) (2025)
- [Learning rigid dynamics with face interaction graph networks](https://mlsanity.com/paper/2212.03574/) (2022)
- [ContactNets: Learning Discontinuous Contact Dynamics with Smooth, Implicit Representations](https://mlsanity.com/paper/2009.11193/) (2020)
- [Augmenting Physical Simulators with Stochastic Neural Networks: Case Study of Planar Pushing and Bouncing](https://mlsanity.com/paper/1808.03246/) (2018)
- [Neural Cloth Simulation](https://mlsanity.com/paper/2212.11220/) (2022)
- [AutoMate: Specialist and Generalist Assembly Policies over Diverse Geometries](https://mlsanity.com/paper/2407.08028/) (2024)
- [OCRTOC: A Cloud-Based Competition and Benchmark for Robotic Grasping and Manipulation](https://mlsanity.com/paper/2104.11446/) (2021)

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

- [Simulation Distillation: Pretraining World Models in Simulation for Rapid Real-World Adaptation](https://mlsanity.com/paper/2603.15759/) (2026)
- [FreeForm: Reduced-Order Deformable Simulation from Particle-Based Skinning Eigenmodes](https://mlsanity.com/paper/2605.29318/) (2026)
- [NeuralActuator: Neural Actuation Modeling for Robot Dynamics and External Force Perception](https://mlsanity.com/paper/2607.11734/) (2026)
- [Can AI Follow In Einstein's Footsteps?](https://mlsanity.com/paper/2607.27794/) (2026)
- [Learning the Right Abstraction: Neural Reduced Dynamics for Complex Robot Control](https://mlsanity.com/paper/2608.19375/) (2026)
- [Pretraining in Actor-Critic Reinforcement Learning for Locomotion](https://mlsanity.com/paper/2510.12363/) (2025)
- [Domain Adaptation with Adaptive Imagination for Visual Reinforcement Learning under Limited Target Data](https://mlsanity.com/paper/2606.30192/) (2026)
- [Amortized Low-Rank Adaptation for Model-Based Reinforcement Learning](https://mlsanity.com/paper/2609.12278/) (2026)

## Abstract (arXiv)

Accurate and efficient simulation of modern robots remains challenging due to their high degrees of freedom and intricate mechanisms. Neural simulators have emerged as a promising alternative to traditional analytical simulators, capable of efficiently predicting complex dynamics and adapting to real-world data; however, existing neural simulators typically require application-specific training and fail to generalize to novel tasks and/or environments, primarily due to inadequate representations of the global state. In this work, we address the problem of learning generalizable neural simulators for robots that are structured as articulated rigid bodies. We propose NeRD (Neural Robot Dynamics), learned robot-specific dynamics models for predicting future states for articulated rigid bodies under contact constraints. NeRD uniquely replaces the low-level dynamics and contact solvers in an analytical simulator and employs a robot-centric and spatially-invariant simulation state representation. We integrate the learned NeRD models as an interchangeable backend solver within a state-of-the-art robotics simulator. We conduct extensive experiments to show that the NeRD simulators are stable and accurate over a thousand simulation steps; generalize across tasks and environment configurations; enable policy learning exclusively in a neural engine; and, unlike most classical simulators, can be fine-tuned from real-world data to bridge the gap between simulation and reality.