为微型无人机设计高效学习型模型预测控制，实现在低算力下100Hz实时控制。
Tiny Learning-Based MPC for Multirotors: Solver-Aware Learning for Efficient Embedded Predictive Control
- 协同设计控制框架与优化求解器，适配资源受限的微型飞行器
- 在53克无人机上实现100Hz控制，轨迹跟踪性能提升43%（模型不确定下）
- 首次在53克微型多旋翼上完成学习型MPC的机载部署
微型空中机器人在环境监测和搜救等任务中前景广阔，但受限于机载计算能力与非线性动力学，控制难度大。模型预测控制（MPC）可实现敏捷轨迹跟踪与约束处理，但依赖精确的动力学模型。现有基于学习的（LB）MPC方法（如高斯过程MPC）通过学习残差动力学提升性能，但计算开销大，难以部署于微型机器人。本文提出Tiny LB MPC，一种为资源受限的微小型多旋翼平台量身定制的协同设计控制框架与优化求解器。该方法在配备Teensy 4.0微控制器的Crazyflie 2.1上实现了100 Hz控制，在模型不确定条件下相比现有嵌入式MPC方法平均提升43%的跟踪性能，并首次在53克多旋翼上实现学习型MPC的机载运行。
原文摘要 · Abstract (English)
Tiny aerial robots hold great promise for applications such as environmental monitoring and search-and-rescue, yet face significant control challenges due to limited onboard computing power and nonlinear dynamics. Model Predictive Control (MPC) enables agile trajectory tracking and constraint handling but depends on an accurate dynamics model. While existing Learning-Based (LB) MPC methods, such as Gaussian Process (GP) MPC, enhance performance by learning residual dynamics, their high computational cost restricts onboard deployment on tiny robots. This paper introduces Tiny LB MPC, a co-designed MPC framework and optimization solver for resource-constrained micro multirotor platforms. The proposed approach achieves 100 Hz control on a Crazyflie 2.1 equipped with a Teensy 4.0 microcontroller, demonstrating a 43% average improvement in tracking performance over existing embedded MPC methods under model uncertainty, and achieving the first onboard implementation of LB MPC on a 53 g multirotor.
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。