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

Real-time planning under uncertainty is critical for robots operating incomplex dynamic environments. Consider, for example, an autonomous robotvehicle driving in dense, unregulated urban traffic of cars, motorcycles,buses, etc. The robot vehicle has to plan in both short and long terms, inorder to interact with many traffic participants with uncertain intentions anddrive effectively. Planning explicitly over a long time horizon, however,incurs prohibitive computational costs and is impractical under real-timeconstraints. To achieve real-time performance for large-scale planning, thiswork introduces a new algorithm Learning from Tree Search for Driving(LeTS-Drive), which integrates planning and learning in a closed loop, andapplies it to autonomous driving in crowded urban traffic in simulation.Specifically, LeTS-Drive learns a policy and its value function from dataprovided by an online planner, which searches a sparsely-sampled belief tree;the online planner in turn uses the learned policy and value functions asheuristics to scale up its run-time performance for real-time robot control.These two steps are repeated to form a closed loop so that the planner and thelearner inform each other and improve in synchrony. The algorithm learns on itsown in a self-supervised manner, without human effort on explicit datalabeling. Experimental results demonstrate that LeTS-Drive outperforms eitherplanning or learning alone, as well as open-loop integration of planning andlearning.

Closing the Planning-Learning Loop with Application to Autonomous Driving