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 future trajectories of surrounding obstacles is a crucial task forautonomous driving cars to achieve a high degree of road safety. There areseveral challenges in trajectory prediction in real-world traffic scenarios,including obeying traffic rules, dealing with social interactions, handlingtraffic of multi-class movement, and predicting multi-modal trajectories withprobability. Inspired by people's natural habit of navigating traffic withattention to their goals and surroundings, this paper presents a unique dynamicgraph attention network to solve all those challenges. The network is designedto model the dynamic social interactions among agents and conform to trafficrules with a semantic map. By extending the anchor-based method to multipletypes of agents, the proposed method can predict multi-modal trajectories withprobabilities for multi-class movements using a single model. We validate ourapproach on the proprietary autonomous driving dataset for the logisticdelivery scenario and two publicly available datasets. The results show thatour method outperforms state-of-the-art techniques and demonstrates thepotential for trajectory prediction in real-world traffic.

Multi-modal Trajectory Prediction for Autonomous Driving with Semantic Map and Dynamic Graph Attention Network