Training Neural Network Controllers Using Control Barrier Functions in the Presence of Disturbances
This work addresses real-time safety control for resource-constrained systems like robotics, but it is incremental as it builds on existing CBF methods with a learning-based adaptation.
The paper tackles the computational expense of solving Quadratic Programs in real-time for safe control using Control Barrier Functions by proposing imitation learning to train Neural Network controllers that satisfy CBF constraints, achieving results demonstrated on a unicycle model with disturbances.
Control Barrier Functions (CBF) have been recently utilized in the design of provably safe feedback control laws for nonlinear systems. These feedback control methods typically compute the next control input by solving an online Quadratic Program (QP). Solving QP in real-time can be a computationally expensive process for resource constraint systems. In this work, we propose to use imitation learning to learn Neural Network-based feedback controllers which will satisfy the CBF constraints. In the process, we also develop a new class of High Order CBF for systems under external disturbances. We demonstrate the framework on a unicycle model subject to external disturbances, e.g., wind or currents.