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

Motion planning has been an important research topic in achieving safe andflexible maneuvers for intelligent vehicles. However, it remains challenging torealize efficient and optimal planning in the presence of uncertain modeldynamics. In this paper, a sparse kernel-based reinforcement learning (RL)algorithm with Gaussian Process (GP) Regression (called GP-SKRL) is proposed toachieve online adaption and near-optimal motion planning performance. In thisalgorithm, we design an efficient sparse GP regression method to learn theuncertain dynamics. Based on the updated model, a sparse kernel-based policyiteration algorithm with an exponential barrier function is designed to learnthe near-optimal planning policies with the capability to avoid dynamicobstacles. Thereby, batch-mode GP-SKRL with online adaption capability canestimate the changing system dynamics. The converged RL policies are thendeployed on vehicles efficiently under a safety-aware module. As a result, theproduced driving actions are safe and less conservative, and the planningperformance has been noticeably improved. Extensive simulation results showthat GP-SKRL outperforms several advanced motion planning methods in terms ofaverage cumulative cost, trajectory length, and task completion time. Inparticular, experiments on a Hongqi E-HS3 vehicle demonstrate that superiorGP-SKRL provides a practical planning solution.

Learning-based Near-optimal Motion Planning for Intelligent Vehicles with Uncertain Dynamics