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

Finding feasible, collision-free paths for multiagent systems can bechallenging, particularly in non-communicating scenarios where each agent'sintent (e.g. goal) is unobservable to the others. In particular, finding timeefficient paths often requires anticipating interaction with neighboringagents, the process of which can be computationally prohibitive. This workpresents a decentralized multiagent collision avoidance algorithm based on anovel application of deep reinforcement learning, which effectively offloadsthe online computation (for predicting interaction patterns) to an offlinelearning procedure. Specifically, the proposed approach develops a valuenetwork that encodes the estimated time to the goal given an agent's jointconfiguration (positions and velocities) with its neighbors. Use of the valuenetwork not only admits efficient (i.e., real-time implementable) queries forfinding a collision-free velocity vector, but also considers the uncertainty inthe other agents' motion. Simulation results show more than 26 percentimprovement in paths quality (i.e., time to reach the goal) when compared withoptimal reciprocal collision avoidance (ORCA), a state-of-the-art collisionavoidance strategy.

Decentralized Non-communicating Multiagent Collision Avoidance with Deep Reinforcement Learning