# Training Neural Network Controllers Using Control Barrier Functions in the Presence of Disturbances

arXiv: https://arxiv.org/abs/2001.08088 · HTML: https://mlsanity.com/paper/2001.08088/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jan 2020.

## Built on by (most cited first, 9 of 9)

- [Learning Robust Output Control Barrier Functions from Safe Expert Demonstrations](https://mlsanity.com/paper/2111.09971/) (2021)
- [Learning Robust Hybrid Control Barrier Functions for Uncertain Systems](https://mlsanity.com/paper/2101.06492/) (2021)
- [BarrierNet: A Safety-Guaranteed Layer for Neural Networks](https://mlsanity.com/paper/2111.11277/) (2021)
- [Differentiable Control Barrier Functions for Vision-based End-to-End Autonomous Driving](https://mlsanity.com/paper/2203.02401/) (2022)
- [End-to-End Imitation Learning with Safety Guarantees using Control Barrier Functions](https://mlsanity.com/paper/2212.11365/) (2022)
- [Bridging Model-based Safety and Model-free Reinforcement Learning through System Identification of Low Dimensional Linear Models](https://mlsanity.com/paper/2205.05787/) (2022)
- [Local Repair of Neural Networks Using Optimization](https://mlsanity.com/paper/2109.14041/) (2021)
- [Neural Network-based Control for Multi-Agent Systems from Spatio-Temporal Specifications](https://mlsanity.com/paper/2104.02737/) (2021)
- [Response-Aware Risk-Constrained Control Barrier Function With Application to Vehicles](https://mlsanity.com/paper/2603.24598/) (2026)

## Abstract (arXiv)

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.