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 object-based Simultaneous Localization and Mapping (SLAM), 6D object posesoffer a compact representation of landmark geometry useful for downstreamplanning and manipulation tasks. However, measurement ambiguity then arises asobjects may possess complete or partial object shape symmetries (e.g., due toocclusion), making it difficult or impossible to generate a single consistentobject pose estimate. One idea is to generate multiple pose candidates tocounteract measurement ambiguity. In this paper, we develop a novel approachthat enables an object-based SLAM system to reason about multiple posehypotheses for an object, and synthesize this locally ambiguous informationinto a globally consistent robot and landmark pose estimation formulation. Inparticular, we (1) present a learned pose estimation network that providesmultiple hypotheses about the 6D pose of an object; (2) by treating the outputof our network as components of a mixture model, we incorporate posepredictions into a SLAM system, which, over successive observations, recovers aglobally consistent set of robot and object (landmark) pose estimates. Weevaluate our approach on the popular YCB-Video Dataset and a simulated videofeaturing YCB objects. Experiments demonstrate that our approach is effectivein improving the robustness of object-based SLAM in the face of object poseambiguity.

A Multi-Hypothesis Approach to Pose Ambiguity in Object-Based SLAM