Bayesian Optimization for Automatic Tuning of Torque-Level Nonlinear Model Predictive Control
By: Gabriele Fadini , Deepak Ingole , Tong Duy Son and more
Potential Business Impact:
Robots move more smoothly and accurately.
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.
Similar Papers
Real-Time LPV-Based Non-Linear Model Predictive Control for Robust Trajectory Tracking in Autonomous Vehicles
Robotics
Helps self-driving cars steer perfectly.
Full-Dynamics Real-Time Nonlinear Model Predictive Control of Heavy-Duty Hydraulic Manipulator for Trajectory Tracking Tasks
Robotics
Keeps big robot arms safe and on track.
A Novel Robust Control Method Combining DNN-Based NMPC Approximation and PI Control: Application to Exoskeleton Squat Movements
Robotics
Makes robot suits help people move better.