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

Deep reinforcement learning (DRL) has been widely applied in autonomousexploration and mapping tasks, but often struggles with the challenges ofsampling efficiency, poor adaptability to unknown map sizes, and slowsimulation speed. To speed up convergence, we combine curriculum learning (CL)with DRL, and first propose a Cumulative Curriculum Reinforcement Learning(CCRL) training framework to alleviate the issue of catastrophic forgettingfaced by general CL. Besides, we present a novel state representation, whichconsiders a local egocentric map and a global exploration map resized to thefixed dimension, so as to flexibly adapt to environments with various sizes andshapes. Additionally, for facilitating the fast training of DRL models, wedevelop a lightweight grid-based simulator, which can substantially acceleratesimulation compared to popular robot simulation platforms such as Gazebo. Basedon the customized simulator, comprehensive experiments have been conducted, andthe results show that the CCRL framework not only mitigates the catastrophicforgetting problem, but also improves the sample efficiency and generalizationof DRL models, compared to general CL as well as without a curriculum. Our codeis available at https://github.com/BeamanLi/CCRL_Exploration.

Autonomous Exploration and Mapping for Mobile Robots via Cumulative Curriculum Reinforcement Learning