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

Fully decentralized, multiagent trajectory planners enable complex tasks likesearch and rescue or package delivery by ensuring safe navigation in unknownenvironments. However, deconflicting trajectories with other agents andensuring collision-free paths in a fully decentralized setting is complicatedby dynamic elements and localization uncertainty. To this end, this paperpresents (1) an uncertainty-aware multiagent trajectory planner and (2) animage segmentation-based frame alignment pipeline. The uncertainty-awareplanner propagates uncertainty associated with the future motion of detectedobstacles, and by incorporating this propagated uncertainty into optimizationconstraints, the planner effectively navigates around obstacles. Unlikeconventional methods that emphasize explicit obstacle tracking, our approachintegrates implicit tracking. Sharing trajectories between agents can causepotential collisions due to frame misalignment. Addressing this, we introduce anovel frame alignment pipeline that rectifies inter-agent frame misalignment.This method leverages a zero-shot image segmentation model for detectingobjects in the environment and a data association framework based on geometricconsistency for map alignment. Our approach accurately aligns frames with only0.18 m and 2.7 deg of mean frame alignment error in our most challengingsimulation scenario. In addition, we conducted hardware experiments andsuccessfully achieved 0.29 m and 2.59 deg of frame alignment error. Togetherwith the alignment framework, our planner ensures safe navigation in unknownenvironments and collision avoidance in decentralized settings.

PUMA: Fully Decentralized Uncertainty-aware Multiagent Trajectory Planner with Real-time Image Segmentation-based Frame Alignment