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 safe multi-agent motion planning for drones inuncertain, cluttered workspaces. For this problem, we present a tractablemotion planner that builds upon the strengths of reinforcement learning andconstrained-control-based trajectory planning. First, we use single-agentreinforcement learning to learn motion plans from data that reach the targetbut may not be collision-free. Next, we use a convex optimization, chanceconstraints, and set-based methods for constrained control to ensure safety,despite the uncertainty in the workspace, agent motion, and sensing. Theproposed approach can handle state and control constraints on the agents, andenforce collision avoidance among themselves and with static obstacles in theworkspace with high probability. The proposed approach yields a safe, real-timeimplementable, multi-agent motion planner that is simpler to train than methodsbased solely on learning. Numerical simulations and experiments show theefficacy of the approach.

Safe multi-agent motion planning under uncertainty for drones using filtered reinforcement learning