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/

Zendy Plus

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

Zendy Tools

Zendy Open

Precise trajectory prediction of surrounding vehicles is critical fordecision-making of autonomous vehicles and learning-based approaches are wellrecognized for the robustness. However, state-of-the-art learning-based methodsignore 1) the feasibility of the vehicle's multi-modal state information forprediction and 2) the mutual exclusive relationship between the global trafficscene receptive fields and the local position resolution when modelingvehicles' interactions, which may influence prediction accuracy. Therefore, wepropose a vehicle-descriptor based LSTM model with the dilated convolutionalsocial pooling (VD+DCS-LSTM) to cope with the above issues. First, eachvehicle's multi-modal state information is employed as our model's input and anew vehicle descriptor encoded by stacked sparse auto-encoders is proposed toreflect the deep interactive relationships between various states, achievingthe optimal feature extraction and effective use of multi-modal inputs.Secondly, the LSTM encoder is used to encode the historical sequences composedof the vehicle descriptor and a novel dilated convolutional social pooling isproposed to improve modeling vehicles' spatial interactions. Thirdly, the LSTMdecoder is used to predict the probability distribution of future trajectoriesbased on maneuvers. The validity of the overall model was verified over theNGSIM US-101 and I-80 datasets and our method outperforms the latest benchmark.

A Multi-Modal States based Vehicle Descriptor and Dilated Convolutional Social Pooling for Vehicle Trajectory Prediction