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

In this study, we present two distinct approaches within the realm of DeepReinforcement Learning (Deep-RL) aimed at enhancing mapless navigation for aground-based mobile robot. The research methodology primarily involves acomparative analysis between a Deep-RL strategy grounded in the foundationalDeep Q-Network (DQN) algorithm, and an alternative approach based on the DoubleDeep Q-Network (DDQN) algorithm. The agents in these approaches leverage 24measurements from laser range sampling, coupled with the agent's positionaldifferentials and orientation relative to the target. This amalgamation of datainfluences the agents' determinations regarding navigation, ultimatelydictating the robot's velocities. By embracing this parsimonious sensoryframework as proposed, we successfully showcase the training of an agent forproficiently executing navigation tasks and adeptly circumventing obstacles.Notably, this accomplishment is attained without a dependency on intricatesensory inputs like those inherent to image-centric methodologies. The proposedmethodology is evaluated in three different real environments, revealing thatDouble Deep structures significantly enhance the navigation capabilities ofmobile robots compared to simple Q structures.

Enhanced Low-Dimensional Sensing Mapless Navigation of Terrestrial Mobile Robots Using Double Deep Reinforcement Learning Techniques