TARC: Time-Adaptive Robotic Control
This work addresses a key limitation in robotic control for applications requiring efficiency and robustness, offering an incremental improvement over existing methods.
The paper tackles the problem of fixed-frequency control in robotics by introducing a reinforcement learning approach that allows policies to jointly select control actions and their durations, enabling adaptive control frequency. The method was validated on two hardware platforms, matching or outperforming fixed-frequency baselines in rewards while significantly reducing control frequency and demonstrating adaptability in real-world conditions.
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.