论文标题
学习更好的控制障碍功能
Learning a Better Control Barrier Function
论文作者
论文摘要
控制屏障功能（CBF）广泛用于安全 - 关键控制器中。但是，构建有效的CBF是具有挑战性的，尤其是在非线性或非凸约限制下以及对于高度相对程度系统的情况下。同时，找到只能恢复真正安全集的一部分的保守的CBF通常是可能的。在这项工作中，从“保守”手工CBF（HCBF）开始，我们开发了一种方法来找到一种CBF，该CBF恢复了相当大的安全集合。由于在训练迭代期间不能保证学习的CBF控制器是安全的，因此我们使用模型预测控制器（MPC）来确保培训期间的安全性。使用包含安全和不安全相互作用的收集的轨迹数据，我们训练神经网络，以估算HCBF和CBF之间的差异，从而恢复了对真正安全集的更接近解决方案。通过我们提出的方法，我们可以生成更不保守和计算更有效的安全控制器。我们在两个系统上验证了我们的方法：二阶积分器和一个球梁。
Control barrier functions (CBFs) are widely used in safety-critical controllers. However, constructing a valid CBF is challenging, especially under nonlinear or non-convex constraints and for high relative degree systems. Meanwhile, finding a conservative CBF that only recovers a portion of the true safe set is usually possible. In this work, starting from a "conservative" handcrafted CBF (HCBF), we develop a method to find a CBF that recovers a reasonably larger portion of the safe set. Since the learned CBF controller is not guaranteed to be safe during training iterations, we use a model predictive controller (MPC) to ensure safety during training. Using the collected trajectory data containing safe and unsafe interactions, we train a neural network to estimate the difference between the HCBF and a CBF that recovers a closer solution to the true safe set. With our proposed approach, we can generate safe controllers that are less conservative and computationally more efficient. We validate our approach on two systems: a second-order integrator and a ball-on-beam.
