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

This paper presents a learning-based approach to consider the effect ofunobservable world states in kinodynamic motion planning in order to enableaccurate high-speed off-road navigation on unstructured terrain. Existingkinodynamic motion planners either operate in structured and homogeneousenvironments and thus do not need to explicitly account for terrain-vehicleinteraction, or assume a set of discrete terrain classes. However, whenoperating on unstructured terrain, especially at high speeds, even smallvariations in the environment will be magnified and cause inaccurate planexecution. In this paper, to capture the complex kinodynamic model andmathematically unknown world state, we learn a kinodynamic planner in adata-driven manner with onboard inertial observations. Our approach is testedon a physical robot in different indoor and outdoor environments, enables fastand accurate off-road navigation, and outperforms environment-independentalternatives, demonstrating 52.4% to 86.9% improvement in terms of planexecution success rate while traveling at high speeds.

Learning Inverse Kinodynamics for Accurate High-Speed Off-Road Navigation on Unstructured Terrain