Skip to content

Enhancing Sim-to-Real Transfer for a High-Gear-Ratio Quadruped Robot via Extended Actuator Dynamics Identification

Sep 2026 · Machines · Vol 14, pp. 1031 · 0 citations · 16 references
Robotic Locomotion and Control

TL;DR

An augmented friction model that incorporates the Stribeck effect to capture the low-velocity nonlinearities characteristic of high-gear-ratio actuators and indicates that explicitly modeling low-velocity friction is beneficial for high-fidelity sim-to-real transfer in high-reduction systems.

Abstract

Reinforcement learning (RL) has become a powerful tool for quadrupedal locomotion, and a sim-to-real approach is widely adopted to avoid hardware damage during training. However, the “sim-to-real gap” remains a critical challenge, particularly for robots driven by high-gear-ratio actuators, in which nonlinear friction effects are strongly amplified. Conventional methods, such as actuator networks or heuristic domain randomization, often require specialized sensors or extensive trial-and-error to tune appropriate randomization ranges. Building on a recent system-identification framework for actuator dynamics, we extend it with an augmented friction model that incorporates the Stribeck effect to capture the low-velocity nonlinearities characteristic of high-gear-ratio actuators. The physical parameters are identified from real-robot trajectory data using an evolutionary algorithm, and the resulting simulation is used to train a locomotion policy that is transferred zero-shot to a 55 kg quadruped without additional fine-tuning or base- or controller-level dynamics randomization. On our platform, adding the Stribeck term lowers the actuator identification error by 16% relative to a Coulomb–Viscous model on the trajectory used for identification, and this advantage generalizes to an unseen trajectory not used for identification. It also lowers the simulation-to-reality mean-velocity degradation from 40.2% and 26.8% for the Coulomb–Viscous model to 27.2% and 21.6% for our method at the 0.3 and 1.0 m/s commands, respectively. The trained policy achieves stable locomotion on flat ground as well as rough terrain including steps and stairs. These results indicate that explicitly modeling low-velocity friction is beneficial for high-fidelity sim-to-real transfer in high-reduction systems.

Read PDF

Similar papers

Review Open access Sep 2026

Extending the Speed Limit of Quadrupedal Locomotion via Refined Actuator Modeling and Adaptive Command Scheduling

A refined actuator model explicitly captures high-speed voltage coupling and magnetic saturation, enabling a more accurate representation of the torque–speed envelope and a reinforcement learning framework incorporating a two-stage curriculum and adaptive command scheduling (ACS) ensures stable training.

Yu-Cheng Tao, Shao-Wen Cheng, Guo-Rong Lan et al. · 0 citations
Conference Open access Jul 2026

Enhancing Sim2Real Transfer for Torque-Controlled Robots through Real2Sim Dynamics Estimation and Reinforcement Learning

This work proposes a Real2Sim2Real pipeline that improves Sim2Real transfer for torque-controlled robotic arms by combining trajectory matching, parameter optimization via genetic algorithms, and domain randomization, and demonstrates a significant improvement in tracking accuracy and policy robustness after parameter...

Davide Bargellini, Alex Pasquali, Andrea Govoni et al. · 0 citations
Conference Aug 2026

A Real-Time Affordable Predictive Trajectory Tracking Controller for Differential Drive Robots via Imitation Learning

Nonlinear Model Predictive Control (NMPC) achieves high-accuracy trajectory tracking for mobile robots but is often too computationally demanding for resourceconstrained platforms. We present a learning-based predictive tracking controller that imitates an expert NMPC policy to achieve real-time performance on differen...

Suryaprakash Rajkumar, Walter Lucia · 0 citations

Neural-Augmented Torque Control for Robotic Manipulators: Modeling, Learning, and Real-Time Performance

This thesis investigates advanced modeling and control strategies for robotic manipulators, focusing on the DLR-HIT II robotic hand and the KUKA LBR iiwa. It presents three core contributions that integrate simulation, model-based control, and data-driven methods to improve torque and position control under uncertainti...

Ali Al-Shahrabi · 0 citations
Open access Sep 2026

Sensorless variable impedance control of robot joints with 3K gear reducers based on hybrid dynamics model and meta-policy optimization

The proposed physics-informed data-driven joint dynamics modeling method achieves a 40% improvement in joint torque prediction accuracy compared to the conventional momentum disturbance observer (MDOB) baseline, satisfying the dual requirements of high-precision tracking in free space and high compliance in contact spa...

Ji-Yu Sun, Xiao-Shan Gao, Liang Yan · 0 citations

Related blog posts

MIT News · Artificial Intelligence Nov 17, 2026

Learning the language of machine learning

By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.

Microsoft Research Blog Nov 16, 2026

TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient

AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.