# NeuralActuator: Neural Actuation Modeling for Robot Dynamics and External Force Perception

arXiv: https://arxiv.org/abs/2607.11734 · HTML: https://mlsanity.com/paper/2607.11734/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 53 references that are in the map.
- First posted on arXiv 13 Jul 2026.

## Builds on (most cited first, 19 of 19)

- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [Learning agile and dynamic motor skills for legged robots](https://mlsanity.com/paper/1901.08652/) (2019)
- [Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation](https://mlsanity.com/paper/2106.13281/) (2021)
- [DiffTaichi: Differentiable Programming for Physical Simulation](https://mlsanity.com/paper/1910.00935/) (2019)
- [TossingBot: Learning to Throw Arbitrary Objects with Residual Physics](https://mlsanity.com/paper/1903.11239/) (2019)
- [NeuralSim: Augmenting Differentiable Simulators with Neural Networks](https://mlsanity.com/paper/2011.04217/) (2020)
- [Augmenting Physical Simulators with Stochastic Neural Networks: Case Study of Planar Pushing and Bouncing](https://mlsanity.com/paper/1808.03246/) (2018)
- [Dojo: A Differentiable Physics Engine for Robotics](https://mlsanity.com/paper/2203.00806/) (2022)
- [EasyHeC: Accurate and Automatic Hand-eye Calibration via Differentiable Rendering and Space Exploration](https://mlsanity.com/paper/2305.01191/) (2023)
- [Bridging the Sim-to-Real Gap for Athletic Loco-Manipulation](https://mlsanity.com/paper/2502.10894/) (2025)
- [ILBiT: Imitation Learning for Robot Using Position and Torque Information based on Bilateral Control with Transformer](https://mlsanity.com/paper/2401.16653/) (2024)
- [Neural Robot Dynamics](https://mlsanity.com/paper/2508.15755/) (2025)
- [Data-Augmented Contact Model for Rigid Body Simulation](https://mlsanity.com/paper/1803.04019/) (2018)
- [Visual Haptic Reasoning: Estimating Contact Forces by Observing Deformable Object Interactions](https://mlsanity.com/paper/2208.05632/) (2022)
- [Visual Contact Pressure Estimation for Grippers in the Wild](https://mlsanity.com/paper/2303.07344/) (2023)
- [Learning Object Properties Using Robot Proprioception via Differentiable Robot-Object Interaction](https://mlsanity.com/paper/2410.03920/) (2024)
- [Learning a Unified Policy for Position and Force Control in Legged Loco-Manipulation](https://mlsanity.com/paper/2505.20829/) (2025)
- [Force Map: Learning to Predict Contact Force Distribution from Vision](https://mlsanity.com/paper/2304.05803/) (2023)

## Built on by (most cited first, 1 of 1)

- [Learning Physical Interaction: A Survey of Tactile- and Force-aware Robot Learning](https://mlsanity.com/paper/2608.07558/) (2026)

## Abstract (arXiv)

Differentiable simulators have advanced policy learning and model-based control across robotic tasks. Yet actuator dynamics remain underexplored and can be a major source of sim-to-real error, particularly on low-cost platforms, where the linear current-to-joint-torque approximation τ = Kt I becomes unreliable because of friction, hysteresis, backlash, and thermal effects. Accurate actuator models can also support force perception and integrated force/position control. We present NeuralActuator, which jointly predicts (i) a torque surrogate for trajectory propagation on low-cost servo platforms, (ii) external forces with a contact-probability gate for sensorless force perception, and (iii) a motor-condition score for a supervised joint, distinguishing normal from mechanically restricted operation. A twin-arm teleoperation system records robot states and actuator telemetry alongside external-force labels, yielding the Neural Actuation Dataset (NAD). The torque-surrogate head is trained through differentiable simulation from pose trajectories without ground-truth joint-torque measurements. A Transformer captures temporal dependencies while enabling real-time inference. We validate NeuralActuator on a 5-DoF OpenManipulator-X, a 6-DoF SO-101 from LeRobot, and a 7-DoF Franka Emika Panda, spanning three actuator families and costs from approximately 500 to more than 30,000. The low-cost platforms support physically plausible dynamics and force evaluation, while the offline Franka experiment provides a payload-force-estimation benchmark. We also demonstrate motor-condition estimation and improved behavior-cloning performance using NeuralActuator as a pretrained module. We release the dataset, code, and hardware configurations on the project page: https://frank-zy-dou.github.io/projects/NeuralActuator/index.html.