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

We consider the problem of designing distributed collision-avoidancemulti-agent control in large-scale environments with potentially movingobstacles, where a large number of agents are required to maintain safety usingonly local information and reach their goals. This paper addresses the problemof collision avoidance, scalability, and generalizability by introducing graphcontrol barrier functions (GCBFs) for distributed control. The newly introducedGCBF is based on the well-established CBF theory for safety guarantees bututilizes a graph structure for scalable and generalizable decentralizedcontrol. We use graph neural networks to learn both neural a GCBF certificateand distributed control. We also extend the framework from handling state-basedmodels to directly taking point clouds from LiDAR for more practical roboticssettings. We demonstrated the efficacy of GCBF in a variety of numericalexperiments, where the number, density, and traveling distance of agents, aswell as the number of unseen and uncontrolled obstacles increase. Empiricalresults show that GCBF outperforms leading methods such as MAPPO andmulti-agent distributed CBF (MDCBF). Trained with only 16 agents, GCBF canachieve up to 3 times improvement of success rate (agents reach goals and neverencountered in any collisions) on <500 agents, and still maintain more than 50%success rates for >1000 agents when other methods completely fail.

Neural Graph Control Barrier Functions Guided Distributed Collision-avoidance Multi-agent Control