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

Recent advancements in motion planning for Autonomous Vehicles (AVs) showgreat promise in using expert driver behaviors in non-stationary drivingenvironments. However, learning only through expert drivers needs moregeneralizability to recover from domain shifts and near-failure scenarios dueto the dynamic behavior of traffic participants and weather conditions. A deepGraph-based Prediction and Planning Policy Network (GP3Net) framework isproposed for non-stationary environments that encodes the interactions betweentraffic participants with contextual information and provides a decision forsafe maneuver for AV. A spatio-temporal graph models the interactions betweentraffic participants for predicting the future trajectories of thoseparticipants. The predicted trajectories are utilized to generate a futureoccupancy map around the AV with uncertainties embedded to anticipate theevolving non-stationary driving environments. Then the contextual informationand future occupancy maps are input to the policy network of the GP3Netframework and trained using Proximal Policy Optimization (PPO) algorithm. Theproposed GP3Net performance is evaluated on standard CARLA benchmarkingscenarios with domain shifts of traffic patterns (urban, highway, and mixed).The results show that the GP3Net outperforms previous state-of-the-artimitation learning-based planning models for different towns. Further, inunseen new weather conditions, GP3Net completes the desired route with fewertraffic infractions. Finally, the results emphasize the advantage of includingthe prediction module to enhance safety measures in non-stationaryenvironments.

Graph-based Prediction and Planning Policy Network (GP3Net) for scalable self-driving in dynamic environments using Deep Reinforcement Learning