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

The multi-agent pathfinding (MAPF) problem seeks collision-free paths for ateam of agents from their current positions to their pre-set goals in a knownenvironment, and is an essential problem found at the core of many logistics,transportation, and general robotics applications. Existing learning-based MAPFapproaches typically only let each agent make decisions based on a limitedfield-of-view (FOV) around its position, as a natural means to fix the inputdimensions of its policy network. However, this often makes policiesshort-sighted, since agents lack the ability to perceive and plan forobstacles/agents beyond their FOV. To address this challenge, we propose ALPHA,a new framework combining the use of ground truth proximal (local) informationand fuzzy distal (global) information to let agents sequence local decisionsbased on the full current state of the system, and avoid such myopicity. Wefurther allow agents to make short-term predictions about each others' paths,as a means to reason about each others' path intentions, thereby enhancing thelevel of cooperation among agents at the whole system level. Our neuralstructure relies on a Graph Transformer architecture to allow agents toselectively combine these different sources of information and reason abouttheir inter-dependencies at different spatial scales. Our simulationexperiments demonstrate that ALPHA outperforms both globally-guided MAPFsolvers and communication-learning based ones, showcasing its potential towardsscalability in realistic deployments.

ALPHA: Attention-based Long-horizon Pathfinding in Highly-structured Areas