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

Domain-adaptive trajectory imitation is a skill that some predators learn forsurvival, by mapping dynamic information from one domain (their speed andsteering direction) to a different domain (current position of the movingprey). An intelligent agent with this skill could be exploited for a diversityof tasks, including the recognition of abnormal motion in traffic once it haslearned to imitate representative trajectories. Towards this direction, wepropose DATI, a deep reinforcement learning agent designed for domain-adaptivetrajectory imitation using a cycle-consistent generative adversarial method.Our experiments on a variety of synthetic families of reference trajectoriesshow that DATI outperforms baseline methods for imitation learning and optimalcontrol in this setting, keeping the same per-task hyperparameters. Itsgeneralization to a real-world scenario is shown through the discovery ofabnormal motion patterns in maritime traffic, opening the door for the use ofdeep reinforcement learning methods for spatially-unconstrained trajectory datamining.

Learning Representative Trajectories of Dynamical Systems via Domain-Adaptive Imitation