Pointing the Way: Refining Radar-Lidar Localization Using Learned ICP Weights
This work addresses the challenge of achieving viable radar-lidar localization for autonomous driving, which is incremental by building on existing ICP-based methods with a learned component.
The paper tackles the problem of radar-lidar localization for autonomous driving by introducing a learned preprocessing step that weights radar points to filter out artefacts, noise, and vehicles, resulting in reduced localization errors and improved convergence in real-world data.
This paper presents a novel deep-learning-based approach to improve localizing radar measurements against lidar maps. This radar-lidar localization leverages the benefits of both sensors; radar is resilient against adverse weather, while lidar produces high-quality maps in clear conditions. However, owing in part to the unique artefacts present in radar measurements, radar-lidar localization has struggled to achieve comparable performance to lidar-lidar systems, preventing it from being viable for autonomous driving. This work builds on ICP-based radar-lidar localization by including a learned preprocessing step that weights radar points based on high-level scan information. To train the weight-generating network, we present a novel, stand-alone, open-source differentiable ICP library. The learned weights facilitate ICP by filtering out harmful radar points related to artefacts, noise, and even vehicles on the road. Combining an analytical approach with a learned weight reduces overall localization errors and improves convergence in radar-lidar ICP results run on real-world autonomous driving data. Our code base is publicly available to facilitate reproducibility and extensions.