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

This paper presents a data-driven decentralized trajectory optimizationapproach for multi-robot motion planning in dynamic environments. Whennavigating in a shared space, each robot needs accurate motion predictions ofneighboring robots to achieve predictive collision avoidance. These motionpredictions can be obtained among robots by sharing their future plannedtrajectories with each other via communication. However, such communication maynot be available nor reliable in practice. In this paper, we introduce a noveltrajectory prediction model based on recurrent neural networks (RNN) that canlearn multi-robot motion behaviors from demonstrated trajectories generatedusing a centralized sequential planner. The learned model can run efficientlyonline for each robot and provide interaction-aware trajectory predictions ofits neighbors based on observations of their history states. We thenincorporate the trajectory prediction model into a decentralized modelpredictive control (MPC) framework for multi-robot collision avoidance.Simulation results show that our decentralized approach can achieve acomparable level of performance to a centralized planner while beingcommunication-free and scalable to a large number of robots. We also validateour approach with a team of quadrotors in real-world experiments.

Learning Interaction-Aware Trajectory Predictions for Decentralized Multi-Robot Motion Planning in Dynamic Environments