Decentralized No-Regret Frequency-Time Scheduling for FMCW Radar Interference Avoidance

TL;DR

This paper proposes a decentralized, game-theoretic time-frequency scheduling algorithm for FMCW radars that adaptively avoids interference, improving radar performance metrics without relying on centralized control or side-channel communication.

Contribution

It introduces a unified time-frequency no-regret hopping framework that enables radars to autonomously adapt and avoid interference through regret minimization in a repeated anti-coordination game.

Findings

Achieves vanishing regret and convergence to equilibrium.

Improves SINR, collision rate, and range-Doppler quality.

Enhances robustness against asynchronous interference.

Abstract

Automotive FMCW radars are indispensable to modern ADAS and autonomous-driving systems, but their increasing density has intensified the risk of mutual interference. Existing mitigation techniques, including reactive receiver-side suppression, proactive waveform design, and cooperative scheduling, often face limitations in scalability, reliance on side-channel communication, or degradation of range-Doppler resolution. Building on our earlier work on decentralized Frequency-Domain No-Regret hopping, this paper introduces a unified time-frequency game-theoretic framework that enables radars to adapt across both spectral and temporal resources. We formulate the interference-avoidance problem as a repeated anti-coordination game, in which each radar autonomously updates a mixed strategy over frequency subbands and chirp-level time offsets using regret-minimization dynamics. We show that the proposed Time-Frequency No-Regret Hopping algorithm achieves vanishing external and swap regret, and that the induced empirical play converges to an $\varepsilon$-coarse correlated equilibrium or a correlated equilibrium. Theoretical analysis provides regret bounds in the joint domain, revealing how temporal adaptation implicitly regularizes frequency selection and enhances robustness against asynchronous interference. Numerical experiments with multi-radar scenarios demonstrate substantial improvements in SINR, collision rate, and range-Doppler quality compared with time-frequency random hopping and centralized Nash-based benchmarks.