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

In this paper, we focus on motion estimation dedicated for non-holonomicground robots, by probabilistically fusing measurements from the wheel odometerand exteroceptive sensors. For ground robots, the wheel odometer is widely usedin pose estimation tasks, especially in applications under planar-scene basedenvironments. However, since the wheel odometer only provides 2D motionestimates, it is extremely challenging to use that for performing accurate full6D pose (3D position and 3D orientation) estimation. Traditional methods on 6Dpose estimation either approximate sensor or motion models, at the cost ofaccuracy reduction, or rely on other sensors, e.g., inertial measurement unit(IMU), to provide complementary measurements. By contrast, in this paper, wepropose a novel method to utilize the wheel odometer for 6D pose estimation, bymodeling and utilizing motion manifold for ground robots. Our approach isprobabilistically formulated and only requires the wheel odometer and anexteroceptive sensor (e.g., a camera). Specifically, our method i) formulatesthe motion manifold of ground robots by parametric representation, ii) performsmanifold based 6D integration with the wheel odometer measurements only, andiii) re-parameterizes manifold equations periodically for error reduction. Todemonstrate the effectiveness and applicability of the proposed algorithmicmodules, we integrate that into a sliding-window pose estimator by usingmeasurements from the wheel odometer and a monocular camera. By conductingextensive simulated and real-world experiments, we show that the proposedalgorithm outperforms competing state-of-the-art algorithms by a significantmargin in pose estimation accuracy, especially when deployed in complexlarge-scale real-world environments.

Pose Estimation for Ground Robots: On Manifold Representation, Integration, Re-Parameterization, and Optimization