# 安全过滤的分布式 Koopman-MPC

> 原文链接：https://robotics.hellobike.com/papers/2026-09-23-2609-27463
> 频道：papers | 更新日期：2026-09-23 | 标签：arxiv, cs.RO
> 核心摘要：针对DMPC丢包会同时丢失预测与避碰约束的问题，提出Koopman-MPC与局部感知QP安全投影分离的方法，并在仓储多机器人仿真等测试中验证。

# 安全过滤的分布式 Koopman-MPC

::: v-pre
> 原文链接：[Safety-Filtered Distributed Koopman-MPC](https://arxiv.org/abs/2609.27463)（arXiv 2609.27463 · 发布日期：2026-09-23）

**Safety-Filtered Distributed Koopman-MPC**

针对DMPC丢包会同时丢失预测与避碰约束的问题，提出Koopman-MPC与局部感知QP安全投影分离的方法，并在仓储多机器人仿真等测试中验证。

## 核心要点

- DMPC常由邻居轨迹构造预测和碰撞约束，丢包可能同时移除两者。
- 方法将两种角色分离：接收轨迹驱动Koopman-MPC，局部感知与货架几何定义硬约束QP投影输入。
- 给出采样间隔分离定理、同步局部可行性的精确max-min测试，以及切换交互图的感知半径条件。
- 八机器人仓储仿真中完整控制器20/20试验无碰并达到160/160目标，无最终投影的预测Koopman-MPC仅1/20无碰。

**验证范围与局限**：验证范围包括八机器人仓储仿真、五流车队扫描，以及有界感知和差速驱动压力测试。

## 英文摘要 (Abstract)

Distributed model predictive control (DMPC) often constructs both predictions and collision constraints from neighbor trajectories, so packet loss can remove both. We separate these roles: received trajectories drive Koopman-MPC, while local sensing and shelf geometry define a hard-constrained quadratic program (QP) that projects the applied input. Its radial demand is the least constant acceleration that keeps a supporting-plane clearance nonnegative throughout one zero-order-hold interval. Complementary pair rows recover the coupled demand without exchanging safety decisions. We give an intersample separation theorem under bounded snapshot and directional plant errors, an exact max-min test for simultaneous local feasibility, and a sensing-radius condition for switching interaction graphs. Anticipatory high-order rows may be relaxed for performance, but the finite-hold rows contain no safety slack. Matched eight-robot warehouse simulations use a frozen Koopman model, nonlinear drift, bounded inputs and speed, shelf constraints, a 120 ms control period, and packet dropout. The full controller is collision-free in 20/20 matched trials and reaches 160/160 robot goals; predictive Koopman-MPC without the final projection is collision-free in 1/20 trials. All 38,400 full-method hard-row sets pass the online feasibility test, and every local QP solves. Five-stream fleet sweeps are collision-free and hard-row feasible through 16 robots; the 20-robot boundary fails only after the online margin turns negative, while the reconstructed per-agent critical path remains below the sampling period. Bounded-sensing and differential-drive tests provide additional deployment stress.

作者：Shengjun Zhang, Wenhao Li, Zhenxin Lin, Zhenglong Sun
:::

## 原始参考来源 (Sources)

- [arXiv 2609.27463：Safety-Filtered Distributed Koopman-MPC](https://arxiv.org/abs/2609.27463)