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

Intelligent navigation among social crowds is an essential aspect of mobilerobotics for applications such as delivery, health care, or assistance. DeepReinforcement Learning emerged as an alternative planning method toconservative approaches and promises more efficient and flexible navigation.However, in highly dynamic environments employing different kinds of obstacleclasses, safe navigation still presents a grand challenge. In this paper, wepropose a semantic Deep-reinforcement-learning-based navigation approach thatteaches object-specific safety rules by considering high-level obstacleinformation. In particular, the agent learns object-specific behavior bycontemplating the specific danger zones to enhance safety around vulnerableobject classes. We tested the approach against a benchmark obstacle avoidanceapproach and found an increase in safety. Furthermore, we demonstrate that theagent could learn to navigate more safely by keeping an individual safetydistance dependent on the semantic information.

Enhancing Navigational Safety in Crowded Environments using Semantic-Deep-Reinforcement-Learning-based Navigation