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

Target following in dynamic pedestrian environments is an important task formobile robots. However, it is challenging to keep tracking the target whileavoiding collisions in crowded environments, especially with only one robot. Inthis paper, we propose a multi-agent method for an arbitrary number of robotsto follow the target in a socially-aware manner using only 2D laser scans. Themulti-agent following problem is tackled by utilizing the complementarystrengths of both reinforcement learning and potential field, in which thereinforcement learning part handles local interactions while navigating to thegoals assigned by the potential field. Specifically, with the help of laserscans in obstacle map representation, the learning-based policy can help therobots avoid collisions with both static obstacles and dynamic obstacles likepedestrians in advance, namely socially aware. While the formation control andgoal assignment for each robot is obtained from a target-centered potentialfield constructed using aggregated state information from all the followingrobots. Experiments are conducted in multiple settings, including randomobstacle distributions and different numbers of robots. Results show that ourmethod works successfully in unseen dynamic environments. The robots can followthe target in a socially compliant manner with only 2D laser scans.

Socially-Aware Multi-Agent Following with 2D Laser Scans via Deep Reinforcement Learning and Potential Field