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 Kimera-Multi, the first multi-robot system that (i) isrobust and capable of identifying and rejecting incorrect inter and intra-robotloop closures resulting from perceptual aliasing, (ii) is fully distributed andonly relies on local (peer-to-peer) communication to achieve distributedlocalization and mapping, and (iii) builds a globally consistentmetric-semantic 3D mesh model of the environment in real-time, where faces ofthe mesh are annotated with semantic labels. Kimera-Multi is implemented by ateam of robots equipped with visual-inertial sensors. Each robot builds a localtrajectory estimate and a local mesh using Kimera. When communication isavailable, robots initiate a distributed place recognition and robust posegraph optimization protocol based on a novel distributed graduatednon-convexity algorithm. The proposed protocol allows the robots to improvetheir local trajectory estimates by leveraging inter-robot loop closures whilebeing robust to outliers. Finally, each robot uses its improved trajectoryestimate to correct the local mesh using mesh deformation techniques.  We demonstrate Kimera-Multi in photo-realistic simulations, SLAM benchmarkingdatasets, and challenging outdoor datasets collected using ground robots. Bothreal and simulated experiments involve long trajectories (e.g., up to 800meters per robot). The experiments show that Kimera-Multi (i) outperforms thestate of the art in terms of robustness and accuracy, (ii) achieves estimationerrors comparable to a centralized SLAM system while being fully distributed,(iii) is parsimonious in terms of communication bandwidth, (iv) producesaccurate metric-semantic 3D meshes, and (v) is modular and can be also used forstandard 3D reconstruction (i.e., without semantic labels) or for trajectoryestimation (i.e., without reconstructing a 3D mesh).

Kimera-Multi: Robust, Distributed, Dense Metric-Semantic SLAM for Multi-Robot Systems