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 focus on improving the efficiency and generalisation oflearned navigation strategies when transferred from its training environment topreviously unseen ones. We present an extension of the residual reinforcementlearning framework from the robotic manipulation literature and adapt it to thevast and unstructured environments that mobile robots can operate in. Theconcept is based on learning a residual control effect to add to a typicalsub-optimal classical controller in order to close the performance gap, whilstguiding the exploration process during training for improved data efficiency.We exploit this tight coupling and propose a novel deployment strategy,switching Residual Reactive Navigation (sRRN), which yields efficienttrajectories whilst probabilistically switching to a classical controller incases of high policy uncertainty. Our approach achieves improved performanceover end-to-end alternatives and can be incorporated as part of a completenavigation stack for cluttered indoor navigation tasks in the real world. Thecode and training environment for this project is made publicly available athttps://sites.google.com/view/srrn/home.

Residual Reactive Navigation: Combining Classical and Learned Navigation Strategies For Deployment in Unknown Environments