# CALM：基于多智能体强化学习的协同空中操作去中心化控制

> 原文链接：https://robotics.hellobike.com/papers/2026-10-13-2610-18425
> 频道：papers | 更新日期：2026-10-13 | 标签：arxiv, cs.RO
> 核心摘要：CALM以去中心化MARL结合估计与观测器，控制多UAV提篮跟踪移动地面机器人，并在留出轨迹上验证。

# CALM：基于多智能体强化学习的协同空中操作去中心化控制

::: v-pre
> 原文链接：[CALM: Decentralized Control of Cooperative Aerial Manipulation with Multi-Agent Reinforcement Learning](https://arxiv.org/abs/2610.18425)（arXiv 2610.18425 · 发布日期：2026-10-13）

**CALM: Decentralized Control of Cooperative Aerial Manipulation with Multi-Agent Reinforcement Learning**

CALM以去中心化MARL结合估计与观测器，控制多UAV提篮跟踪移动地面机器人，并在留出轨迹上验证。

## 核心要点

- 问题源于多UAV经共享载荷耦合，风、载荷运动和含噪目标广播会增加协同空中操作难度。
- 方法结合参数共享MARL策略、MAPPO训练、目标估计、每机ESO、篮筐质量估计和编队偏航前馈。
- 前馈利用估计目标运动提前旋转编队，集中训练采用扰动条件化critic，执行保持去中心化。
- 在留出轨迹上，CALM位置和姿态平均误差低于所有评估基线；视频已提供网页链接。

**验证范围与局限**：验证任务为多UAV携带篮子跟踪移动地面机器人；摘要未说明仿真或真机设置及UAV数量。

## 英文摘要 (Abstract)

Cooperative aerial manipulation is difficult under wind, payload motion, and noisy goal broadcasts because multiple Unmanned Aerial Vehicles (UAVs) are coupled through a shared payload. We present CALM (Cooperative Aerial Learned Manipulation), a decentralized controller for aerial manipulators carrying a basket while tracking a moving ground robot. CALM combines a parameter-shared Multi-Agent Reinforcement Learning (MARL) policy, trained using Multi-Agent Proximal Policy Optimization (MAPPO), with goal estimation, per-UAV Extended State Observers (ESOs), basket-mass estimation, and anticipatory formation-yaw feedforward. The anticipatory formation-yaw feedforward uses estimated goal motion to rotate the formation before position error develops, reducing basket-yaw lag without adding net commanded force. A disturbance-conditioned critic supports centralized training while execution remains decentralized. Across held-out trajectories, CALM achieves lower mean position and orientation errors than all evaluated baselines, including the matched arm baseline (7.68 versus 10.95 cm and 3.3 versus 4.7$^\circ$), the cable-suspended realization, and two model-based controllers. Under unseen full-information-path degradation, CALM remains statistically comparable or superior to the arm baseline. Videos are available at https://petreric.github.io/CALM/.

作者：Jiaxi Huo, Petre Ricioppo, Fausto Francesco Lizzio
:::

## 原始参考来源 (Sources)

- [arXiv 2610.18425：CALM: Decentralized Control of Cooperative Aerial Manipulation with Multi-Agent Reinforcement Learning](https://arxiv.org/abs/2610.18425)