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

Considering visual localization accuracy at the planning time givespreference to robot motion that can be better localized and thus has thepotential of improving vision-based navigation, especially in visually degradedenvironments. To integrate the knowledge about localization accuracy in motionplanning algorithms, a central task is to quantify the amount of informationthat an image taken at a 6 degree-of-freedom pose brings for localization,which is often represented by the Fisher information. However, computing theFisher information from a set of sparse landmarks (i.e., a point cloud), whichis the most common map for visual localization, is inefficient. This approachscales linearly with the number of landmarks in the environment and does notallow the reuse of the computed Fisher information. To overcome thesedrawbacks, we propose the first dedicated map representation for evaluating theFisher information of 6 degree-of-freedom visual localization forperception-aware motion planning. By formulating the Fisher information andsensor visibility carefully, we are able to separate the rotational invariantcomponent from the Fisher information and store it in a voxel grid, namely theFisher information field. This step only needs to be performed once for a knownenvironment. The Fisher information for arbitrary poses can then be computedfrom the field in constant time, eliminating the need of costly iterating allthe 3D landmarks at the planning time. Experimental results show that theproposed Fisher information field can be applied to different motion planningalgorithms and is at least one order-of-magnitude faster than using the pointcloud directly. Moreover,the proposed map representation is differentiable,resulting in better performance than the point cloud when used in trajectoryoptimization algorithms.

Fisher Information Field: an Efficient and Differentiable Map for Perception-aware Planning