LiDAR Teach, Radar Repeat: Robust Cross-Modal Navigation in Degenerate and Varying Environments

Long-term autonomy requires robust navigation in environments subject to dynamic and static changes, as well as adverse weather conditions. Teach-and-repeat (T&R) navigation offers a reliable and cost-effective solution by avoiding the need for consistent global mapping; however, existing T&R systems lack a systematic solution to tackle various environmental variations, such as weather degradation, ephemeral dynamics, and structural changes. This work proposes LiDAR teach radar repeat (LTR${2}$), the first cross-modal, cross-platform LiDAR-teach-and-radar-repeat system that systematically addresses these challenges. LTR${2}$ leverages LiDAR during the teaching phase to capture precise structural information under normal conditions and utilizes 4-D millimeter-wave radar during the repeating phase for robust operation under environmental degradations. To align sparse and noisy forward-looking 4-D radar with dense and accurate omnidirectional 3-D LiDAR data, we introduce a cross-modal registration (CMR) network that jointly exploits Doppler-based motion priors and the physical laws governing LiDAR intensity and radar power density. Furthermore, we propose an adaptive fine-tuning strategy that incrementally updates the CMR network based on localization errors, enabling long-term adaptability to static environmental changes without ground-truth labels. We demonstrate that the proposed CMR network achieves state-of-the-art CMR performance on the open-access dataset. Then, we validate LTR${2}$ across three robot platforms over a large-scale, long-term deployment (40+ km over 6 months), including challenging conditions, such as nighttime smoke. Experimental results and ablation studies demonstrate centimeter-level accuracy and strong robustness against diverse environmental disturbances, significantly outperforming existing approaches.