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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We present an end-to-end online motion planning framework that uses adata-driven approach to navigate a heterogeneous robot team towards a globalgoal while avoiding obstacles in uncertain environments. First, we usestochastic model predictive control (SMPC) to calculate control inputs thatsatisfy robot dynamics, and consider uncertainty during obstacle avoidance withchance constraints. Second, recurrent neural networks are used to provide aquick estimate of future state uncertainty considered in the SMPC finite-timehorizon solution, which are trained on uncertainty outputs of varioussimultaneous localization and mapping algorithms. When two or more robots arein communication range, these uncertainties are then updated using adistributed Kalman filtering approach. Lastly, a Deep Q-learning agent isemployed to serve as a high-level path planner, providing the SMPC with targetpositions that move the robots towards a desired global goal. Our completemethods are demonstrated on a ground and aerial robot simultaneously (codeavailable at: https://github.com/AlexS28/SABER).

SABER: Data-Driven Motion Planner for Autonomously Navigating Heterogeneous Robots