🚀 Excited to share that our work on multi-robot planning will appear at #IROS2025! 🎉 D4orm: Multi-Robot Trajectories with Dynamics-aware Diffusion Denoised Deformations Yuhao Zhang, Keisuke Okumura, Peter Woo, Ajay Shankar, Amanda Prorok
📄 Paper: arxiv.org/abs/2503.12204 💻 Code: github.com/proroklab/d4orm 🎬 Video: https://lnkd.in/ep7jK_yN
📅 When: Oct. 22, 16:40–18:00 📍 Session: WeDT23 102B — “Path Planning for Multiple Mobile Robots or Agents 4” D4orm introduces a novel optimization framework for multi-robot trajectory generation. Inspired by diffusion generative models, it iteratively denoises noisy trajectories into smooth, collision-free, and dynamically feasible ones — ready for real-world deployment on multi-robot systems such as our indoor multirotor platform 🚁
This work was brilliantly led by Yuhao Zhang as part of his MPhil project at the University of Cambridge’s #ProrokLab.