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/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Our paper proposes a direct sparse visual odometry method that combines eventand RGB-D data to estimate the pose of agile-legged robots during dynamiclocomotion and acrobatic behaviors. Event cameras offer high temporalresolution and dynamic range, which can eliminate the issue of blurred RGBimages during fast movements. This unique strength holds a potential foraccurate pose estimation of agile-legged robots, which has been a challengingproblem to tackle. Our framework leverages the benefits of both RGB-D and eventcameras to achieve robust and accurate pose estimation, even during dynamicmaneuvers such as jumping and landing a quadruped robot, the Mini-Cheetah. Ourmajor contributions are threefold: Firstly, we introduce an adaptive timesurface (ATS) method that addresses the whiteout and blackout issue inconventional time surfaces by formulating pixel-wise decay rates based on scenecomplexity and motion speed. Secondly, we develop an effective pixel selectionmethod that directly samples from event data and applies sample filteringthrough ATS, enabling us to pick pixels on distinct features. Lastly, wepropose a nonlinear pose optimization formula that simultaneously performs3D-2D alignment on both RGB-based and event-based maps and images, allowing thealgorithm to fully exploit the benefits of both data streams. We extensivelyevaluate the performance of our framework on both public datasets and our ownquadruped robot dataset, demonstrating its effectiveness in accuratelyestimating the pose of agile robots during dynamic movements.

Event Camera-based Visual Odometry for Dynamic Motion Tracking of a Legged Robot Using Adaptive Time Surface