Learning Performance-Oriented Control Barrier Functions Under Complex Safety Constraints and Limited Actuation (2401.05629v2)
Abstract: Control Barrier Functions (CBFs) provide an elegant framework for constraining nonlinear control system dynamics to remain within an invariant subset of a designated safe set. However, identifying a CBF that balances performance-by maximizing the control invariant set-and accommodates complex safety constraints, especially in systems with high relative degree and actuation limits, poses a significant challenge. In this work, we introduce a novel self-supervised learning framework to comprehensively address these challenges. Our method begins with a Boolean composition of multiple state constraints that define the safe set. We first construct a smooth function whose zero superlevel set forms an inner approximation of this safe set. This function is then combined with a smooth neural network to parameterize the CBF candidate. To train the CBF and maximize the volume of the resulting control invariant set, we design a physics-informed loss function based on a Hamilton-Jacobi Partial Differential Equation (PDE). We validate the efficacy of our approach on a 2D double integrator (DI) system and a 7D fixed-wing aircraft system (F16).
- Control barrier functions: Theory and applications. In 2019 18th European control conference (ECC), pages 3420–3431. IEEE.
- Hamilton-jacobi reachability: A brief overview and recent advances. In 2017 IEEE 56th Annual Conference on Decision and Control (CDC), pages 2242–2253. IEEE.
- Convex optimization. Cambridge university press.
- Compositions of multiple control barrier functions under input constraints. In 2023 American Control Conference (ACC), pages 3688–3695. IEEE.
- Robust control barrier–value functions for safety-critical control. In 2021 60th IEEE Conference on Decision and Control (CDC), pages 6814–6821. IEEE.
- Safe control with learned certificates: A survey of neural lyapunov, barrier, and contraction methods for robotics and control. IEEE Transactions on Robotics.
- Safe nonlinear control using robust neural lyapunov-barrier functions. In Conference on Robot Learning, pages 1724–1735. PMLR.
- Nonsmooth barrier functions with applications to multi-robot systems. IEEE control systems letters, 1(2):310–315.
- Constructing control lyapunov-value functions using hamilton-jacobi reachability analysis. IEEE Control Systems Letters, 7:925–930.
- Multi-layered safety for legged robots via control barrier functions and model predictive control. In 2021 IEEE International Conference on Robotics and Automation (ICRA), pages 8352–8358. IEEE.
- Multilayer feedforward networks are universal approximators. Neural networks, 2(5):359–366.
- Control barrier functions for signal temporal logic tasks. IEEE control systems letters, 3(1):96–101.
- Safe control under input limits with neural control barrier functions. In Conference on Robot Learning, pages 1970–1980. PMLR.
- Learning differentiable safety-critical control using control barrier functions for generalization to novel environments. In 2022 European Control Conference (ECC), pages 1301–1308. IEEE.
- Safe reinforcement learning: A control barrier function optimization approach. International Journal of Robust and Nonlinear Control, 31(6):1923–1940.
- A toolbox of hamilton-jacobi solvers for analysis of nondeterministic continuous and hybrid systems. In International workshop on hybrid systems: computation and control, pages 480–494. Springer.
- Composing control barrier functions for complex safety specifications. arXiv preprint arXiv:2309.06647.
- Nagumo, M. (1942). Über die lage der integralkurven gewöhnlicher differentialgleichungen. Proceedings of the Physico-Mathematical Society of Japan. 3rd Series, 24:551–559.
- Exponential control barrier functions for enforcing high relative-degree safety-critical constraints. In 2016 American Control Conference (ACC), pages 322–328. IEEE.
- Learning safe multi-agent control with decentralized neural barrier certificates. arXiv preprint arXiv:2101.05436.
- Searching for activation functions. arXiv preprint arXiv:1710.05941.
- Learning control barrier functions from expert demonstrations. In 2020 59th IEEE Conference on Decision and Control (CDC), pages 3717–3724. IEEE.
- Time-varying soft-maximum control barrier functions for safety in an a priori unknown environment. arXiv preprint arXiv:2310.05261.
- How to train your neural control barrier function: Learning safety filters for complex input-constrained systems. arXiv preprint arXiv:2310.15478.
- Refining control barrier functions through hamilton-jacobi reachability. In 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 13355–13362. IEEE.
- High-order control barrier functions. IEEE Transactions on Automatic Control, 67(7):3655–3662.
- Learning feasibility constraints for control barrier functions. arXiv preprint arXiv:2303.09403.
- Rule-based optimal control for autonomous driving. In Proceedings of the ACM/IEEE 12th International Conference on Cyber-Physical Systems, pages 143–154.
- Barriernet: Differentiable control barrier functions for learning of safe robot control. IEEE Transactions on Robotics.
- Safe teleoperation of dynamic uavs through control barrier functions. In 2018 IEEE International Conference on Robotics and Automation (ICRA), pages 7848–7855. IEEE.