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

As robots across domains start collaborating with humans in sharedenvironments, algorithms that enable them to reason over human intent areimportant to achieve safe interplay. In our work, we study human intent throughthe problem of predicting trajectories in dynamic environments. We exploredomains where navigation guidelines are relatively strictly defined but notclearly marked in their physical environments. We hypothesize that within thesedomains, agents tend to exhibit short-term motion patterns that reveal contextinformation related to the agent's general direction, intermediate goals andrules of motion, e.g., social behavior. From this intuition, we proposeSocial-PatteRNN, an algorithm for recurrent, multi-modal trajectory predictionthat exploits motion patterns to encode the aforesaid contexts. Our approachguides long-term trajectory prediction by learning to predict short-term motionpatterns. It then extracts sub-goal information from the patterns andaggregates it as social context. We assess our approach across three domains:humans crowds, humans in sports and manned aircraft in terminal airspace,achieving state-of-the-art performance.

Social-PatteRNN: Socially-Aware Trajectory Prediction Guided by Motion Patterns