Safe Learning-based Gradient-free Model Predictive Control Based on Cross-entropy Method
This work addresses safety and adaptability in control for robotics under uncertainty, representing an incremental improvement by combining existing methods like CEM and Gaussian Processes with minimal intervention techniques.
The paper tackled the problem of controlling nonlinear systems with non-differentiable objectives under uncertain disturbances by proposing a safe learning-based MPC framework that integrates incremental Gaussian Processes and the cross-entropy method, achieving safe and adaptive performance in simulated quadrotor tasks like trajectory tracking and obstacle avoidance.
In this paper, a safe and learning-based control framework for model predictive control (MPC) is proposed to optimize nonlinear systems with a non-differentiable objective function under uncertain environmental disturbances. The control framework integrates a learning-based MPC with an auxiliary controller in a way of minimal intervention. The learning-based MPC augments the prior nominal model with incremental Gaussian Processes to learn the uncertain disturbances. The cross-entropy method (CEM) is utilized as the sampling-based optimizer for the MPC with a non-differentiable objective function. A minimal intervention controller is devised with a control Lyapunov function and a control barrier function to guide the sampling process and endow the system with high probabilistic safety. The proposed algorithm shows a safe and adaptive control performance on a simulated quadrotor in the tasks of trajectory tracking and obstacle avoidance under uncertain wind disturbances.