English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Open

Presents the pdf analysis as premium feature

PDF Analysis

Insights

Presents the summarisation as premium feature

Summarisation

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Robust perception is an essential component to enable long-term operation ofmobile robots. It depends on failure resilience through reliable sensor dataand preprocessing, as well as failure awareness through introspection, forexample the ability to self-assess localization performance. This paperpresents CorAl: a principled, intuitive, and generalizable method to measurethe quality of alignment between pairs of point clouds, which learns to detectalignment errors in a self-supervised manner. CorAl compares the differentialentropy in the point clouds separately with the entropy in their union toaccount for entropy inherent to the scene. By making use of dual entropymeasurements, we obtain a quality metric that is highly sensitive to smallalignment errors and still generalizes well to unseen environments. In thiswork, we extend our previous work on lidar-only CorAl to radar data byproposing a two-stage filtering technique that produces high-quality pointclouds from noisy radar scans. Thus we target robust perception in two ways: byintroducing a method that introspectively assesses alignment quality, andapplying it to an inherently robust sensor modality. We show that our filteringtechnique combined with CorAl can be applied to the problem of alignmentclassification, and that it detects small alignment errors in urban settingswith up to 98% accuracy, and with up to 96% if trained only in a differentenvironment. Our lidar and radar experiments demonstrate that CorAl outperformsprevious methods both on the ETH lidar benchmark, which includes several indoorand outdoor environments, and the large-scale Oxford and MulRan radar data setsfor urban traffic scenarios The results also demonstrate that CorAl generalizesvery well across substantially different environments without the need ofretraining.

CorAl: Introspection for Robust Radar and Lidar Perception in Diverse Environments Using Differential Entropy