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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Simulation is a crucial tool for accelerating the development of autonomousvehicles. Making simulation realistic requires models of the human road userswho interact with such cars. Such models can be obtained by applying learningfrom demonstration (LfD) to trajectories observed by cars already on the road.However, existing LfD methods are typically insufficient, yielding policiesthat frequently collide or drive off the road. To address this problem, wepropose Symphony, which greatly improves realism by combining conventionalpolicies with a parallel beam search. The beam search refines these policies onthe fly by pruning branches that are unfavourably evaluated by a discriminator.However, it can also harm diversity, i.e., how well the agents cover the entiredistribution of realistic behaviour, as pruning can encourage mode collapse.Symphony addresses this issue with a hierarchical approach, factoring agentbehaviour into goal generation and goal conditioning. The use of such goalsensures that agent diversity neither disappears during adversarial training noris pruned away by the beam search. Experiments on both proprietary and openWaymo datasets confirm that Symphony agents learn more realistic and diversebehaviour than several baselines.

Symphony: Learning Realistic and Diverse Agents for Autonomous Driving Simulation