Learning to Coordinate: Distributed Meta-Trajectory Optimization Via Differentiable ADMM-DDP

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Bingheng, Gao, Yichao, Sun, Tianchen, Zhao, Lin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916935431618560
author Wang, Bingheng
Gao, Yichao
Sun, Tianchen
Zhao, Lin
author_facet Wang, Bingheng
Gao, Yichao
Sun, Tianchen
Zhao, Lin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_01630
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning to Coordinate: Distributed Meta-Trajectory Optimization Via Differentiable ADMM-DDP
Wang, Bingheng
Gao, Yichao
Sun, Tianchen
Zhao, Lin
Machine Learning
Multiagent Systems
Robotics
Systems and Control
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.
title Learning to Coordinate: Distributed Meta-Trajectory Optimization Via Differentiable ADMM-DDP
topic Machine Learning
Multiagent Systems
Robotics
Systems and Control
url https://arxiv.org/abs/2509.01630