用贝叶斯优化自动调参，让机械臂更精准地追踪轨迹。
Bayesian Optimization for Automatic Tuning of Torque-Level Nonlinear Model Predictive Control
- 通过高维贝叶斯优化自动调节非线性模型预测控制参数。
- 仿真中轨迹跟踪性能提升41.9%，求解时间减少2.5%。
- 基于数字孪生实现安全硬件迁移，适合机器人实时控制场景。
本文提出一种面向扭矩型非线性模型预测控制（nMPC）的自动调参框架，其中nMPC作为实时控制器生成最优关节扭矩指令。利用高维贝叶斯优化（特别是稀疏轴对齐子空间优化，SAASBO）结合数字孪生（DT），在UR10e机械臂上实现末端执行器轨迹的高精度实时跟踪。仿真模型可高效探索高维参数空间，并确保安全迁移到真实硬件。结果显示，相比人工调参，仿真阶段跟踪性能提升41.9%，求解时间减少2.5%。真实机器人实验验证了该趋势，性能提升达25.8%，凸显了数字孪生支持的自动化参数优化对机器人操作的重要性。
原文摘要 · Abstract (English)
This paper presents an auto-tuning framework for torque-based Nonlinear Model Predictive Control (nMPC), where the MPC serves as a real-time controller for optimal joint torque commands. The MPC parameters, including cost function weights and low-level controller gains, are optimized using high-dimensional Bayesian Optimization (BO) techniques, specifically Sparse Axis-Aligned Subspace (SAASBO) with a digital twin (DT) to achieve precise end-effector trajectory real-time tracking on an UR10e robot arm. The simulation model allows efficient exploration of the high-dimensional parameter space, and it ensures safe transfer to hardware. Our simulation results demonstrate significant improvements in tracking performance (+41.9%) and reduction in solve times (-2.5%) compared to manually-tuned parameters. Moreover, experimental validation on the real robot follows the trend (with a +25.8% improvement), emphasizing the importance of digital twin-enabled automated parameter optimization for robotic operations.
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。