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 work, we present a novel Reinforcement Learning (RL) algorithm forthe off-road trajectory tracking problem. Off-road environments involve varyingterrain types and elevations, and it is difficult to model the interactiondynamics of specific off-road vehicles with such a diverse and complexenvironment. Standard RL policies trained on a simulator will fail to operatein such challenging real-world settings. Instead of using a naive domainrandomization approach, we propose an innovative supervised-learning basedapproach for overcoming the sim-to-real gap problem. Our approach efficientlyexploits the limited real-world data available to adapt the baseline RL policyobtained using a simple kinematics simulator. This avoids the need for modelingthe diverse and complex interaction of the vehicle with off-road environments.We evaluate the performance of the proposed algorithm using two differentoff-road vehicles, Warthog and Moose. Compared to the standard ILQR approach,our proposed approach achieves a 30% and 50% reduction in cross track error inWarthog and Moose, respectively, by utilizing only 30 minutes of real-worlddriving data.

OTTR: Off-Road Trajectory Tracking using Reinforcement Learning