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

Mobile robotic systems are becoming increasingly popular. These systems areused in various indoor applications, raging from warehousing and manufacturingto test benches for assessment of advanced control strategies, such asartificial intelligence (AI)-based control solutions, just to name a few.Scaled robotic cars are commonly equipped with a hierarchical controlacthiecture that includes tasks dedicated to vehicle state estimation andcontrol. This paper covers both aspects by proposing (i) a federeted extendedKalman filter (FEKF), and (ii) a novel deep reinforcement learning (DRL) pathtracking controller trained via an expert demonstrator to expedite the learningphase and increase robustess to the simulation-to-reality gap. The paper alsopresents the formulation of a vehicle model along with an effective yet simpleprocedure for identifying tis paramters. The experimentally validated model isused for (i) supporting the design of the FEKF and (ii) serving as a digitaltwin for training the proposed DRL-based path tracking algorithm. Experimentalresults confirm the ability of the FEKF to improve the estimate of the mobilerobot's position. Furthermore, the effectiveness of the DRL path trackingstrateguy is experimentally tested along manoeuvres not considered duringtraining, showing also the ability of the AI-based solution to outpeformmodel-based control strategies and the demonstrator. The comparison withbenchmraking controllers is quantitavely evalueted through a set of keyperformance indicators.

Modelling, Positioning, and Deep Reinforcement Learning Path Tracking Control of Scaled Robotic Vehicles: Design and Experimental Validation