How to Train Your Neural Control Barrier Function: Learning Safety Filters for Complex Input-Constrained Systems
Authors:
- 13 May 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 11532-11539
Abstract
Control barrier functions (CBFs) have become popular as a safety filter to guarantee the safety of nonlinear dynamical systems for arbitrary inputs. However, it is difficult to construct functions that satisfy the CBF constraints for high relative degree systems with input constraints. To address these challenges, recent work has explored learning CBFs using neural networks via neural CBFs (NCBFs). However, such methods face difficulties when scaling to higher dimensional systems under input constraints. In this work, we first identify challenges that NCBFs face during training. Next, to address these challenges, we propose policy neural CBFs (PNCBFs), a method of constructing CBFs by learning the value function of a nominal policy, and show that the value function of the maximum-over-time cost is a CBF. We demonstrate the effectiveness of our method in simulation on a variety of systems ranging from toy linear systems to a jet aircraft with a 16-dimensional state space. Finally, we validate our approach on a two-agent quadcopter system on hardware under tight input constraints.Keywords
All Related Versions
This publication has 46 references indexed in Scilit:
- Learning safe control for multi-robot systems: Methods, verification, and open challengesAnnual Reviews in Control, 2024
- An Iterative Scheme of Safe Reinforcement Learning for Nonlinear Systems via Barrier Certificate Generation2021
- A predictive safety filter for learning-based control of constrained nonlinear dynamical systemsAutomatica, 2021
- Learning safe neural network controllers with barrier certificatesFormal Aspects of Computing, 2021
- Automated and Formal Synthesis of Neural Barrier Certificates for Dynamical Models2021
- Robustness of Control Barrier Functions for Safety Critical Control**This work is partially supported by the National Science Foundation Grants 1239055, 1239037 and 1239085.IFAC-PapersOnLine, 2015
- A general Hamilton-Jacobi framework for non-linear state-constrained control problemsESAIM: Control, Optimisation and Calculus of Variations, 2012
- The Flexible, Extensible and Efficient Toolbox of Level Set MethodsJournal of Scientific Computing, 2007
- Safety Verification of Hybrid Systems Using Barrier Certificates2004
- Contraction mappings underlying undiscounted Markov decision problemsJournal of Mathematical Analysis and Applications, 1978