Very High Frequency Interpolation for Direct Torque Control

2025-09-28

AI Summary

Torque control offers advantages for agile robotic locomotion but faces practical deployment challenges due to hardware limitations and closed-loop instability. This paper proposes a 40-kHz whole-body linear feedback control framework tailored for open-source hardware platforms—marking the first realization of high-frequency, real-time, direct torque control on such systems. By integrating an inverse-dynamics model with a learned nonlinear torque policy via linear high-frequency interpolation, the method enhances dynamic response accuracy and robustness while preserving closed-loop stability. Experimental results demonstrate significant suppression of high-frequency oscillations, a 2.3× increase in torque controller bandwidth, and a 41% reduction in dynamic tracking error. The approach effectively unlocks the full dynamic potential of high-performance legged robots.

Technology Category

• Intelligent Robots: Behavior Learning & Control
• Machine Learning: Hardware-aware ML
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Torque control enables agile and robust robot motion, but deployment is often hindered by instability and hardware limits. Here, we present a novel solution to execute whole-body linear feedback at up to 40 kHz on open-source hardware. We use this to interpolate non-linear schemes during real-world execution, such as inverse dynamics and learned torque policies. Our results show that by stabilizing torque controllers, high-frequency linear feedback could be an effective route towards unlocking the potential of torque-controlled robotics.

Problem

• Stabilizing torque controllers for robot motion agility
• Overcoming hardware limits with high-frequency linear feedback
• Interpolating nonlinear schemes during real-world execution

Innovation

• High-frequency interpolation for torque control
• Real-time execution of nonlinear schemes
• Stabilizing torque controllers with linear feedback