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

Developing autonomous vehicles (AVs) helps improve the road safety andtraffic efficiency of intelligent transportation systems (ITS). Accuratelypredicting the trajectories of traffic participants is essential to thedecision-making and motion planning of AVs in interactive scenarios. Recently,learning-based trajectory predictors have shown state-of-the-art performance inhighway or urban areas. However, most existing learning-based models trainedwith fixed datasets may perform poorly in continuously changing scenarios.Specifically, they may not perform well in learned scenarios after learning thenew one. This phenomenon is called "catastrophic forgetting". Few studiesinvestigate trajectory predictions in continuous scenarios, where catastrophicforgetting may happen. To handle this problem, first, a novel continuallearning (CL) approach for vehicle trajectory prediction is proposed in thispaper. Then, inspired by brain science, a dynamic memory mechanism is developedby utilizing the measurement of traffic divergence between scenarios, whichbalances the performance and training efficiency of the proposed CL approach.Finally, datasets collected from different locations are used to designcontinual training and testing methods in experiments. Experimental resultsshow that the proposed approach achieves consistently high prediction accuracyin continuous scenarios without re-training, which mitigates catastrophicforgetting compared to non-CL approaches. The implementation of the proposedapproach is publicly available at https://github.com/BIT-Jack/D-GSM

Continual Interactive Behavior Learning With Traffic Divergence Measurement: A Dynamic Gradient Scenario Memory Approach