LinkedIn · 18 March 2026

Concrete multi-agent path planning published in npj Robotics

We are thrilled to announce that our latest work on multi-robot planning and control has been published in #npjRobotics (Nature Portfolio). Enjoy our large-scale indoor robot deployment demonstrations!

“Concrete multi-agent path planning enabling kinodynamically aggressive maneuvers” Keisuke Okumura, Guang Y., Zhan Gao, Peter Woo & Amanda Prorok. 📄 Paper: https://lnkd.in/etKTshMt 🌐 Project Page: https://lnkd.in/egzyj99N 📽️ Full Video: https://lnkd.in/eYsWgnNT

This work bridges CONtinuous robot dynamics and scalable disCRETE search — what we call “concrete” planning. By combining the strengths of both paradigms, together with data-driven modeling, our approach enables robots to execute agile, safe, and efficient motions even in dense environments 🚀

We validate our framework through a range of large-scale experiments, including coordinated navigation with 40 robots (aerial and ground), as well as application-inspired scenarios such as last-mile delivery and warehouse automation. The work has already been featured in several media outlets: #BBCClick #Fantastico 📺

Excited to see how this direction will further advance capable multi-robot coordination!

read the full post on LinkedIn →