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

Well-established optimization-based methods can guarantee an optimaltrajectory for a short optimization horizon, typically no longer than a fewseconds. As a result, choosing the optimal trajectory for this short horizonmay still result in a sub-optimal long-term solution. At the same time, theresulting short-term trajectories allow for effective, comfortable and provablesafe maneuvers in a dynamic traffic environment. In this work, we address thequestion of how to ensure an optimal long-term driving strategy, while keepingthe benefits of classical trajectory planning. We introduce a ReinforcementLearning based approach that coupled with a trajectory planner, learns anoptimal long-term decision-making strategy for driving on highways. By onlinegenerating locally optimal maneuvers as actions, we balance between theinfinite low-level continuous action space, and the limited flexibility of afixed number of predefined standard lane-change actions. We evaluated ourmethod on realistic scenarios in the open-source traffic simulator SUMO andwere able to achieve better performance than the 4 benchmark approaches wecompared against, including a random action selecting agent, greedy agent,high-level, discrete actions agent and an IDM-based SUMO-controlled agent.

Amortized Q-learning with Model-based Action Proposals for Autonomous Driving on Highways