安全过滤的分布式Koopman-MPC
Safety-Filtered Distributed Koopman-MPC
- Hubei University（湖北大学）
- Shenzhen Institute of Artificial Intelligence and Robotics for Society (AIRS)（深圳市人工智能与机器人研究院）
- The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen)（香港中文大学（深圳））
- Manchester Metropolitan Joint Institute, Hubei University（湖北大学曼城联合学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出一种安全过滤的分布式Koopman-MPC方法，通过分离预测与安全约束，利用局部感知和硬约束QP投影保证碰撞安全，在仓库模拟中实现20/20无碰撞并达到全部目标。
AI中文摘要：
分布式模型预测控制（DMPC）通常从邻居轨迹中同时构建预测和碰撞约束，因此数据包丢失可能会同时移除两者。我们将这些角色分离：接收到的轨迹驱动Koopman-MPC，而局部感知和货架几何定义了一个硬约束二次规划（QP），用于投影施加的输入。其径向需求是保持支撑平面间隙在一个零阶保持间隔内非负所需的最小恒定加速度。互补的行对在不交换安全决策的情况下恢复耦合需求。我们在有界快照和方向性植物误差下给出了一个采样间分离定理，一个用于同时局部可行性的精确最大-最小测试，以及一个用于切换交互图的感知半径条件。预期的高阶行可以为了性能而放宽，但有限保持行不包含安全余量。匹配的八机器人仓库模拟使用冻结的Koopman模型、非线性漂移、有界输入和速度、货架约束、120毫秒控制周期和数据包丢失。完整控制器在20/20次匹配试验中无碰撞，并达到160/160个机器人目标；没有最终投影的预测性Koopman-MPC在1/20次试验中无碰撞。所有38,400个完整方法硬行集都通过了在线可行性测试，并且每个局部QP都得到求解。五流车队扫描在16个机器人内无碰撞且硬行可行；20机器人边界仅在在线余量变为负值后失败，而重建的每代理关键路径保持在采样周期以下。有界感知和差速驱动测试提供了额外的部署压力。
英文摘要：
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.
