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

Predicting pedestrians' trajectories is a crucial capability for autonomousvehicles' safe navigation, especially in spaces shared with pedestrians.Pedestrian motion in shared spaces is influenced by both the presence ofvehicles and other pedestrians. Therefore, effectively modelling bothpedestrian-pedestrian and pedestrian-vehicle interactions can increase theaccuracy of the pedestrian trajectory prediction models. Despite the hugeliterature on ways to encode the effect of interacting agents on a pedestrian'spredicted trajectory using deep-learning models, limited effort has been putinto the effective selection of interacting agents. In the majority of cases,the interaction features used are mainly based on relative distances whilepaying less attention to the effect of the velocity and approaching directionin the interaction formulation. In this paper, we propose a heuristic-basedprocess of selecting the interacting agents based on collision riskcalculation. Focusing on interactions of potentially colliding agents with atarget pedestrian, we propose the use of time-to-collision and the approachdirection angle of two agents for encoding the interaction effect. This is doneby introducing a novel polar collision grid map. Our results have shownpredicted trajectories closer to the ground truth compared to existing methods(used as a baseline) on the HBS dataset.

Polar Collision Grids: Effective Interaction Modelling for Pedestrian Trajectory Prediction in Shared Space Using Collision Checks