AccelMPC：面向微型无人机的高速、低功耗FPGA加速模型预测控制
AccelMPC: High-Rate, Low-Power FPGA-Accelerated Model Predictive Control for Tiny Drones
- Dartmouth College（达特茅斯学院）
- École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
AccelMPC通过端到端协同设计，利用FPGA加速ADMM求解器，在微型无人机上实现1 kHz约束MPC，求解速度提升15.6倍，能量延迟积改善195.4倍，并开源全部设计。
AI中文摘要：
释放微型空中机器人的潜力需要对嵌入式边缘控制的性能进行数量级的提升。特别是，尽管最近的缓存模型预测控制（MPC）求解器能够处理敏捷无人机飞行所需的快速系统动力学和复杂约束，但其计算需求对于资源受限的机器人而言仍然过高，迫使先前的实现以降低的控制速率运行。AccelMPC通过端到端的协同设计方法克服了这一挑战，该方法联合优化了求解器算法、数值表示、硬件映射和物理集成。AccelMPC将协同设计的基于FPGA加速的交替方向乘子法（ADMM）的MPC求解器与定制的6克印刷电路板（PCB）配对，为部署在35克Crazyflie上提供高带宽通信。硬件实验展示了在动态障碍物下1 kHz的机载约束MPC，与最先进的基于嵌入式微控制器的求解器相比，求解速度提升高达15.6倍，能量延迟积改善195.4倍，同时可扩展到具有超过20,000个优化变量和相当数量约束的优化问题。我们开源了PCB设计文件、固件和FPGA求解器代码。
英文摘要：
Unlocking the potential of tiny aerial robots requires order of magnitude improvements in the performance of embedded edge control. In particular, although recent cached model predictive control (MPC) solvers can handle the fast system dynamics and complex constraints required for agile drone flight, their computational demands remain prohibitive for resource-constrained robots, forcing prior implementations to operate at reduced control rates. AccelMPC overcomes this challenge through an end-to-end co-design approach that jointly optimizes the solver algorithm, numerical representation, hardware mapping, and physical integration. AccelMPC pairs a co-designed FPGA-accelerated alternating direction method of multipliers (ADMM)-based MPC solver with a custom 6g PCB, providing high-bandwidth communication for deployment on a 35g Crazyflie. Hardware experiments demonstrate 1 kHz onboard constrained MPC with dynamic obstacles, up to 15.6x faster solve times and 195.4x improvement in energy-delay product over state-of-the-art embedded microcontroller-based solvers, all while scaling to optimization problems with over 20,000 optimization variables and a comparable number of constraints. We release our PCB design files, firmware, and FPGA solver code open source.
