Learning to Coordinate: Distributed Meta-Trajectory Optimization Via Differentiable ADMM-DDP
This addresses the challenge of coordinating multi-agent systems in dynamic tasks, but it is incremental as it builds on existing ADMM-DDP methods.
The paper tackles the problem of tuning hyperparameters in distributed trajectory optimization for multi-agent systems by proposing Learning to Coordinate (L2C), a framework that meta-learns these hyperparameters using neural networks, resulting in up to 88% faster gradient computation than state-of-the-art methods.
Distributed trajectory optimization via ADMM-DDP is a powerful approach for coordinating multi-agent systems, but it requires extensive tuning of tightly coupled hyperparameters that jointly govern local task performance and global coordination. In this paper, we propose Learning to Coordinate (L2C), a general framework that meta-learns these hyperparameters, modeled by lightweight agent-wise neural networks, to adapt across diverse tasks and agent configurations. L2C differentiates end-to-end through the ADMM-DDP pipeline in a distributed manner. It also enables efficient meta-gradient computation by reusing DDP components such as Riccati recursions and feedback gains. These gradients correspond to the optimal solutions of distributed matrix-valued LQR problems, coordinated across agents via an auxiliary ADMM framework that becomes convex under mild assumptions. Training is further accelerated by truncating iterations and meta-learning ADMM penalty parameters optimized for rapid residual reduction, with provable Lipschitz-bounded gradient errors. On a challenging cooperative aerial transport task, L2C generates dynamically feasible trajectories in high-fidelity simulation using IsaacSIM, reconfigures quadrotor formations for safe 6-DoF load manipulation in tight spaces, and adapts robustly to varying team sizes and task conditions, while achieving up to $88\%$ faster gradient computation than state-of-the-art methods.