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 densely populated environments, socially compliant navigation is criticalfor autonomous robots as driving close to people is unavoidable. This manner ofsocial navigation is challenging given the constraints of human comfort andsocial rules. Traditional methods based on hand-craft cost functions to achievethis task have difficulties to operate in the complex real world. Otherlearning-based approaches fail to address the naturalness aspect from theperspective of collective formation behaviors. We present an autonomousnavigation system capable of operating in dense crowds and utilizinginformation of social groups. The underlying system incorporates a deep neuralnetwork to track social groups and join the flow of a social group infacilitating the navigation. A collision avoidance layer in the system furtherensures navigation safety. In experiments, our method generates sociallycompliant behaviors as state-of-the-art methods. More importantly, the systemis capable of navigating safely in a densely populated area (10+ people in a10m x 20m area) following crowd flows to reach the goal.

Following Social Groups: Socially Compliant Autonomous Navigation in Dense Crowds