用图神经网络+模型预测控制，实现千节点软体机器人的实时精准控制。
Graph Neural Model Predictive Control for High-Dimensional Systems
- 用图结构建模系统动态，结合专用压缩算法降低计算复杂度。
- 支持1000个节点在100Hz下闭环运行，硬件实测误差小于1厘米。
- 适合高维系统如软体机器人，尤其需要快速避障的场景。
高维系统（如软体机器人）的控制需要既能准确捕捉复杂动态又具备计算可行性的模型。本文提出一种将图神经网络（GNN）动力学模型与结构利用型模型预测控制（MPC）结合的框架，实现高维系统的实时控制。通过将系统表示为具有局部交互的图结构，GNN保持了稀疏性，而定制的压缩算法消除了控制问题中的状态变量，确保高效计算。该压缩算法的复杂度随系统节点数呈线性增长，并利用图形处理器（GPU）并行化实现实时性能。方法在仿真和物理软体机械臂实验中得到验证，结果表明其可在闭环下扩展至最多1000个节点、100Hz频率运行，硬件实测实现亚厘米级参考轨迹跟踪，优于基线方法63.6%。最后，还展示了该方法在全身体避障方面的有效能力。
原文摘要 · Abstract (English)
The control of high-dimensional systems, such as soft robots, requires models that faithfully capture complex dynamics while remaining computationally tractable. This work presents a framework that integrates Graph Neural Network (GNN)-based dynamics models with structure-exploiting Model Predictive Control to enable real-time control of high-dimensional systems. By representing the system as a graph with localized interactions, the GNN preserves sparsity, while a tailored condensing algorithm eliminates state variables from the control problem, ensuring efficient computation. The complexity of our condensing algorithm scales linearly with the number of system nodes, and leverages Graphics Processing Unit (GPU) parallelization to achieve real-time performance. The proposed approach is validated in simulation and experimentally on a physical soft robotic trunk. Results show that our method scales to systems with up to 1,000 nodes at 100 Hz in closed-loop, and demonstrates real-time reference tracking on hardware with sub-centimeter accuracy, outperforming baselines by 63.6%. Finally, we show the capability of our method to achieve effective full-body obstacle avoidance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。