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 recent years Landmark Complexes have been successfully employed forlocalization-free and metric-free autonomous exploration using a group ofsensing-limited and communication-limited robots in a GPS-denied environment.To ensure rapid and complete exploration, existing works make assumptions onthe density and distribution of landmarks in the environment. These assumptionsmay be overly restrictive, especially in hazardous environments where landmarksmay be destroyed or completely missing. In this paper, we first propose a deepreinforcement learning framework for multi-agent cooperative exploration inenvironments with sparse landmarks while reducing client-server communication.By leveraging recent development on partial observability and creditassignment, our framework can train the exploration policy efficiently formulti-robot systems. The policy receives individual rewards from actions basedon a proximity sensor with limited range and resolution, which is combined withgroup rewards to encourage collaborative exploration and construction of theLandmark Complex through observation of 0-, 1- and 2-dimensional simplices. Inaddition, we employ a three-stage curriculum learning strategy to mitigate thereward sparsity by gradually adding random obstacles and destroying randomlandmarks. Experiments in simulation demonstrate that our method outperformsthe state-of-the-art landmark complex exploration method in efficiency amongdifferent environments with sparse landmarks.

Multi-Agent Exploration of an Unknown Sparse Landmark Complex via Deep Reinforcement Learning