Formal Guarantees in Data-Driven Model Identification and Control Synthesis

Sadraddini, Sadra; Belta, Călin

doi:10.1145/3178126.3178145

Cited by 49 publications

(39 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although we are the first to explore hybrid program repair, several researchers have explored the problem of synthesizing hybrid systems from data [5,30]. This work is closely related to our Learn Linear Dynamics update.…”

Section: Related Workmentioning

confidence: 99%

“…This work is closely related to our Learn Linear Dynamics update. Sadraddini and Belta provide formal guarantees for data-driven model identification and controller synthesis [30]. Relative to this work, our Learn Linear Dynamics update is continuous-time, synthesizes a computer-checked correctness proof but does not consider the full class of linear ODEs.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Verifiably Safe Off-Model Reinforcement Learning

Fulton

Platzer

2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

The desire to use reinforcement learning in safety-critical settings has inspired a recent interest in formal methods for learning algorithms. Existing formal methods for learning and optimization primarily consider the problem of constrained learning or constrained optimization. Given a single correct model and associated safety constraint, these approaches guarantee efficient learning while provably avoiding behaviors outside the safety constraint. Acting well given an accurate environmental model is an important prerequisite for safe learning, but is ultimately insufficient for systems that operate in complex heterogeneous environments. This paper introduces verification-preserving model updates, the first approach toward obtaining formal safety guarantees for reinforcement learning in settings where multiple possible environmental models must be taken into account. Through a combination of inductive data and deductive proving with design-time model updates and runtime model falsification, we provide a first approach toward obtaining formal safety proofs for autonomous systems acting in heterogeneous environments. This research was sponsored by the Defense Advanced Research Projects Agency (DARPA) under grant number FA8750-18-C-0092. The views and conclusions contained in this document are those of the author and should not be interpreted as representing the official policies, either expressed or implied, of any sponsoring institution, the U.S. government or any other entity.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Verifiably Safe Off-Model Reinforcement Learning

Fulton

Platzer

2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Researchers have used methods inspired by reachability analysis in order to generate provably safe trajectories [2], [16], [11], [14]. Other data driven methods have also been proposed in [6], [20]. However, real-time computation of safe motion plans remains a challenge.…”

Section: Introductionmentioning

confidence: 99%

Risk-Bounded Control Using Stochastic Barrier Functions

Yaghoubi¹,

Majd

Fainekos

et al. 2021

IEEE Control Syst. Lett.

View full text Add to dashboard Cite

In this paper, we study Stochastic Control Barrier Functions (SCBFs) to enable the design of probabilistic safe real-time controllers in presence of uncertainties and based on noisy measurements. Our goal is to design controllers that bound the probability of a system failure in finite-time to a given desired value. To that end, we first estimate the system states from the noisy measurements using an Extended Kalman filter, and compute confidence intervals on the filtering errors. Then, we account for filtering errors and derive sufficient conditions on the control input based on the estimated states to bound the probability that the real states of the system enter an unsafe region within a finite time interval. We show that these sufficient conditions are linear constraints on the control input, and, hence, they can be used in tractable optimization problems to achieve safety, in addition to other properties like reachability, and stability. Our approach is evaluated using a simulation of a lane-changing scenario on a highway with dense traffic.

show abstract

“…Control approaches for LTL are mature and allow to use the full LTL fragment while STL control methods are still being investigated, currently only with results for fragments of STL [25], [31]. Existing methods for the full STL fragment [22], [28] discretize time (hence are, in some sense, equivalent to LTL) and are computationally demanding. We propose to use STL when timed tasks or tasks involving the coupling of agents are of interest while, otherwise, methods for LTL can be used.…”

Section: Introductionmentioning

confidence: 99%

Coupled Multi-Robot Systems Under Linear Temporal Logic and Signal Temporal Logic Tasks

Lindemann

Nowak

Schönbächler³

et al. 2021

IEEE Trans. Contr. Syst. Technol.

View full text Add to dashboard Cite

This paper presents the implementation and experimental results of two frameworks for multi-agent systems under temporal logic tasks, which we have recently proposed. Each agent is subject to either a local linear temporal logic or a local signal temporal logic task where each task may further be coupled, i.e., satisfaction of a task may depend on more than one agent. The agents are represented by mobile robots with different sensing and actuation capabilities. We propose to combine the two aforementioned frameworks to use the strengths of both linear temporal logic and signal temporal logic. For the implementation, we take into account practical issues such as collision avoidance and, in particular for the signal temporal logic framework, input saturations, the digital implementation of continuous-time feedback control laws, and a controllability assumption that was made in the original work. The experimental results contain three scenarios that show a wide variety of tasks. Index Terms-Autonomous mobile robots; decentralized robotic networks; formal methods-based control synthesis; linear temporal logic (LTL); signal temporal logic (STL).

show abstract

Formal Guarantees in Data-Driven Model Identification and Control Synthesis

Cited by 49 publications

References 28 publications

Verifiably Safe Off-Model Reinforcement Learning

Verifiably Safe Off-Model Reinforcement Learning

Risk-Bounded Control Using Stochastic Barrier Functions

Coupled Multi-Robot Systems Under Linear Temporal Logic and Signal Temporal Logic Tasks

Contact Info

Product

Resources

About