Differentiable Safe Controller Design Through Control Barrier Functions

Learning-based controllers, such as neural network (NN) controllers, can show high empirical performance but lack formal safety guarantees. To address this issue, control barrier functions (CBFs) have been applied as a safety filter to monitor and modify the outputs of learning-based controllers in order to guarantee the safety of the closed-loop system. However, such modification can be myopic with unpredictable long-term effects. In this letter, we propose a safe-by-construction NN controller which employs differentiable CBF-based safety layers and relies on a set-theoretic parameterization. We compare the performance and computational complexity of the proposed controller and an alternative projection-based safe NN controller in learning-based control. Both methods demonstrate improved closed-loop performance over using CBF as a separate safety filter in numerical experiments.