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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Multi-pedestrian trajectory prediction is an indispensable element ofautonomous systems that safely interact with crowds in unstructuredenvironments. Many recent efforts in trajectory prediction algorithms havefocused on understanding social norms behind pedestrian motions. Yet we observethese works usually hold two assumptions, which prevent them from beingsmoothly applied to robot applications: (1) positions of all pedestrians areconsistently tracked, and (2) the target agent pays attention to allpedestrians in the scene. The first assumption leads to biased interactionmodeling with incomplete pedestrian data. The second assumption introducesaggregation of redundant surrounding information, and the target agent may beaffected by unimportant neighbors or present overly conservative motion. Thus,we propose Gumbel Social Transformer, in which an Edge Gumbel Selector samplesa sparse interaction graph of partially detected pedestrians at each time step.A Node Transformer Encoder and a Masked LSTM encode pedestrian features withsampled sparse graphs to predict trajectories. We demonstrate that our modelovercomes potential problems caused by the aforementioned assumptions, and ourapproach outperforms related works in trajectory prediction benchmarks. Code isavailable at \url{https://github.com/tedhuang96/gst}.

Learning Sparse Interaction Graphs of Partially Detected Pedestrians for Trajectory Prediction