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

Safe and efficient navigation in dynamic environments shared with humansremains an open and challenging task for mobile robots. Previous works haveshown the efficacy of using reinforcement learning frameworks to train policiesfor efficient navigation. However, their performance deteriorates when crowdconfigurations change, i.e. become larger or more complex. Thus, it is crucialto fully understand the complex, dynamic, and sophisticated interactions of thecrowd resulting in proactive and foresighted behaviors for robot navigation. Inthis paper, a novel deep graph learning architecture based on attentionmechanisms is proposed, which leverages the spatial-temporal graph to enhancerobot navigation. We employ spatial graphs to capture the current spatialinteractions, and through the integration with RNN, the temporal graphs utilizepast trajectory information to infer the future intentions of each agent. Thespatial-temporal graph reasoning ability allows the robot to better understandand interpret the relationships between agents over time and space, therebymaking more informed decisions. Compared to previous state-of-the-art methods,our method demonstrates superior robustness in terms of safety, efficiency, andgeneralization in various challenging scenarios.

Learning Crowd Behaviors in Navigation with Attention-based Spatial-Temporal Graphs