Control barrier functions (CBFs) have become a popular tool to enforce safety of a control system. CBFs are commonly utilized in a quadratic program formulation (CBF-QP) as safety-critical constraints. A class $\mathcal{K}$ function in CBFs usually needs to be tuned manually in order to balance the trade-off between performance and safety for each environment. However, this process is often heuristic and can become intractable for high relative-degree systems. Moreover, it prevents the CBF-QP from generalizing to different environments in the real world. By embedding the optimization procedure of the CBF-QP as a differentiable layer within a deep learning architecture, we propose a differentiable optimization-based safety-critical control framework that enables generalization to new environments with forward invariance guarantees. Finally, we validate the proposed control design with 2D double and quadruple integrator systems in various environments.
翻译:控制屏障功能(CBFs)已成为执行控制系统安全的流行工具。 CBFs通常作为安全关键因素在二次程序拟订中使用,CBFs的等级 $\ mathcal{K}$功能通常需要手工调整,以平衡每个环境的性能与安全之间的权衡。然而,这一过程往往过于繁琐,并且可能变得对高相对度系统十分棘手。此外,它阻止CBF-QP将CF-QP的优化程序推广到现实世界的不同环境。通过将CBF-QP的优化程序作为不同的层次嵌入深层学习结构,我们提出了一个不同的基于优化的安全临界控制框架,使基于安全临界值的优化能够向新的环境概括化,并具有前瞻性的保证。最后,我们用2D的双倍和四倍混合系统验证了拟议的控制设计。