Bounding Perception Neural Network Uncertainty for Safe Control of Autonomous Systems

Wang, Zhilu; Huang, Chao; Wang, Yixuan; Hobbs, Clara; Chakraborty, Samarjit; Zhu, Qi

doi:10.23919/date51398.2021.9474204

Cited by 7 publications

(1 citation statement)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Linear System with Linear Controller: For a linear time-invariant (LTI) system as ẋ = Ax + Bu, its reachable set under a linear controller within a finite time interval can be evaluated recursively [31]. Specifically, we consider the discretized LTI system as…”

Section: Verifier Reachable Set Computationmentioning

confidence: 99%

Verification in the Loop: Correct-by-Construction Control Learning with Reach-avoid Guarantees

Wang,

Huang,

Wang

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

In the current control design of safety-critical autonomous systems, formal verification techniques are typically applied after the controller is designed to evaluate whether the required properties (e.g., safety) are satisfied. However, due to the increasing system complexity and the fundamental hardness of designing a controller with formal guarantees, such an open-loop process of design-then-verify often results in many iterations and fails to provide the necessary guarantees. In this paper, we propose a correct-by-construction control learning framework that integrates the verification into the control design process in a closed-loop manner, i.e., design-while-verify. Specifically, we leverage the verification results (computed reachable set of the system state) to construct feedback metrics for control learning, which measure how likely the current design of control parameters can meet the required reach-avoid property for safety and goal-reaching. We formulate an optimization problem based on such metrics for tuning the controller parameters, and develop an approximated gradient descent algorithm with a difference method to solve the optimization problem and learn the controller. The learned controller is formally guaranteed to meet the required reach-avoid property. By treating verifiability as a first-class objective and effectively leveraging the verification results during the control learning process, our approach can significantly improve the chance of finding a control design with formal property guarantees. This is demonstrated via a set of experiments on both linear and non-linear systems that use model-based or neural network based controllers.Preprint. Under review.

show abstract

Section: Verifier Reachable Set Computationmentioning

confidence: 99%