TARC: Time-Adaptive Robotic Control

TL;DR

This paper introduces TARC, a reinforcement learning method that enables robots to adaptively modulate their control frequency, improving efficiency and robustness in real-world tasks by jointly selecting control actions and durations.

Contribution

The paper presents a novel reinforcement learning approach allowing robots to autonomously adjust control frequency, addressing the fixed-frequency trade-off in robotic control systems.

Findings

Outperforms fixed-frequency baselines in reward metrics

Reduces control frequency significantly in real-world experiments

Demonstrates adaptive control frequency in diverse hardware platforms

Abstract

Fixed-frequency control in robotics imposes a trade-off between the efficiency of low-frequency control and the robustness of high-frequency control, a limitation not seen in adaptable biological systems. We address this with a reinforcement learning approach in which policies jointly select control actions and their application durations, enabling robots to autonomously modulate their control frequency in response to situational demands. We validate our method with zero-shot sim-to-real experiments on two distinct hardware platforms: a high-speed RC car and a quadrupedal robot. Our method matches or outperforms fixed-frequency baselines in terms of rewards while significantly reducing the control frequency and exhibiting adaptive frequency control under real-world conditions.