cs.RONov 16, 2026

Hybrid Optimization-Generative Motion Planning for Multiagent Affine Formations

Authors: Zhonggang Li, Hongyu Zhou, Raj Thilak Rajan

Organizations: Signal Processing Systems group, Department of Microelectronics, Faculty of EEMCS of Delft University of Technology, The Netherlands

Abstract

Formation maneuver control enables a multiagent system to cooperatively navigate through constrained environments in collective motion. While various formation controllers exist, they rely heavily on high-quality and dynamically feasible reference trajectories provided a priori, making formation motion planning (FMP) essential. To address the computational challenges for high-dimensional joint trajectories faced by conventional constrained optimization-based solutions, this paper introduces a hybrid optimization-generative framework with a focus on affine formations, which provide the necessary spatial flexibility. By formulating the planning task as a constrained Maximum-a-Posteriori estimation, we decouple multiagent objectives to leverage pre-trained single-agent diffusion priors for dynamic feasibility, obstacle avoidance, and smoothness. We then interleave the generative process with projected gradient descent (PGD) to strictly enforce affine geometric constraints with safety guarantees. Simulations demonstrate that our framework generates highly smooth, collision-free plans that are readily trackable by common distributed controllers and outperforms state-of-the-art planners in various metrics.

Figures & tables

Explore similar work

CardsList
  1. Optimized and kinematically feasible multi-agent motion planning

    May 3, 2026Anja Hellander, Kristoffer Bergman, Daniel AxehillConstrained Motion PlanningTrajectory Optimization

  2. Training-Free Diffusion Planning with Analytical Local Scores

    Oct 1, 2026Michael Y. Fatemi, Jinhao Liang, Ferdinando FiorettoMulti-Robot Motion PlanningConstrained Motion Planning

  3. Leaderless Collective Motion in Affine Formation Control over the Complex Plane

    Apr 7, 2026Jesus Bautista, Enric Morella, Lili Wang +1Multi-Robot Formation ControlMulti-Agent Collaboration