State constrained stochastic optimal control for continuous and hybrid dynamical systems using DFBSDE

Dai, Bolun; Krishnamurthy, P.; Papanicolaou, Andrew C.; Khorrami, Farshad

doi:10.1016/j.automatica.2023.111146

Cited by 3 publications

(1 citation statement)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the increasing capabilities of robotic systems, mobile robots have been deployed to navigate unstructured environments autonomously for various operations [1]- [10]. In all these applications of autonomous mobile robots, safety is of paramount importance [3]- [6]. Recently, control barrier functions (CBFs) [7] have been gaining popularity in synthesizing safe control actions.…”

Section: Introductionmentioning

confidence: 99%

Learning a Better Control Barrier Function

Dai

Krishnamurthy

Khorrami

2022

2022 IEEE 61st Conference on Decision and Control (CDC)

View full text Add to dashboard Cite

Control barrier functions (CBFs) have been widely used for synthesizing controllers in safety-critical applications. When used as a safety filter, it provides a simple and computationally efficient way to obtain safe controls from a possibly unsafe performance controller. Despite its conceptual simplicity, constructing a valid CBF is well known to be challenging, especially for high-relative degree systems under nonconvex constraints. Recently, work has been done to learn a valid CBF from data based on a handcrafted CBF (HCBF). Even though the HCBF gives a good initialization point, it still requires a large amount of data to train the CBF network. In this work, we propose a new method to learn more efficiently from the collected data through a novel prioritized data sampling strategy. A priority score is computed from the loss value of each data point. Then, a probability distribution based on the priority score of the data points is used to sample data and update the learned CBF. Using our proposed approach, we can learn a valid CBF that recovers a larger portion of the true safe set using a smaller amount of data. The effectiveness of our method is demonstrated in simulation on a unicycle and a two-link arm.

show abstract