Synthesis-guided Adversarial Scenario Generation for Gray-box Feedback Control Systems with Sensing Imperfections

Yang, Liren; Özay, Necmiye

doi:10.1145/3477033

Cited by 6 publications

(7 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unfortunately, Lemma 3 gives bilinear constraints when applied to Eqs. ( 6), (7) or to Eqs. ( 6), (8).…”

Section: B Naïve Approach With Bilinear Constraintsmentioning

confidence: 99%

“…1) Backward Reachability Analysis: Backward reachability analysis is concerned with finding a set of states (called the backward reachable set, BRS for short), from where a proper control strategy can steer the system's trajectories into a prescribed target region in finite time. The computation of BRSs is central to many control synthesis problems with reachability [1], [2], safety [3], [4] or even more complex temporal logic requirements [5], and can be used to search critical test cases for closed-loop systems with complex controllers in the loop [6], [7]. Whenever the exact computation is hard, an under-approximation can still be used to define a conservative strategy that accomplishes the reachability task.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Efficient Backward Reachability Using the Minkowski Difference of Constrained Zonotopes

Yang

Zhang

Jeannin

et al. 2022

IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst.

Self Cite

View full text Add to dashboard Cite

Backward reachability analysis is essential to synthesizing controllers that ensure the correctness of closedloop systems. This paper is concerned with developing scalable algorithms that under-approximate the backward reachable sets, for discrete-time uncertain linear and nonlinear systems. Our algorithm sequentially linearizes the dynamics, and uses constrained zonotopes for set representation and computation. The main technical ingredient of our algorithm is an efficient way to under-approximate the Minkowski difference between a constrained zonotopic minuend and a zonotopic subtrahend, which consists of all possible values of the uncertainties and the linearization error. This Minkowski difference needs to be represented as a constrained zonotope to enable subsequent computation, but, as we show, it is impossible to find a polynomial-sized representation for it in polynomial time. Our algorithm finds a polynomial-sized under-approximation in polynomial time. We further analyze the conservatism of this under-approximation technique, and show that it is exact under some conditions. Based on the developed Minkowski difference technique, we detail two backward reachable set computation algorithms to control the linearization error and incorporate nonconvex state constraints. Several examples illustrate the effectiveness of our algorithms.

show abstract

“…Unfortunately, Lemma 3 gives bilinear constraints when applied to Eqs. ( 6), (7) or to Eqs. ( 6), (8).…”

Section: B Naïve Approach With Bilinear Constraintsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Efficient Backward Reachability Using the Minkowski Difference of Constrained Zonotopes

Yang

Zhang

Jeannin

et al. 2022

IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In [34] the authors developed a synthesis guided approach to find adversarial examples that falsify a dynamical system with respect to reach-avoid type specifications. An example from that paper (Example 2) finds a series of measurement noises that causes the…”

Section: Adversarial Scenarios -Full Stlmentioning

confidence: 99%

“…In addition to finding the probability, our approach can find adversarial examples, as done in [34]. In Fig.…”

Section: Adversarial Scenarios -Full Stlmentioning

confidence: 99%

Elliptical Slice Sampling for Probabilistic Verification of Stochastic Systems with Signal Temporal Logic Specifications

Scher¹,

Sadraddini²,

Tedrake³

et al. 2022

Preprint

View full text Add to dashboard Cite

Autonomous robots typically incorporate complex sensors in their decision-making and control loops. These sensors, such as cameras and Lidars, have imperfections in their sensing and are influenced by environmental conditions. In this paper, we present a method for probabilistic verification of linearizable systems with Gaussian and Gaussian mixture noise models (e.g. from perception modules, machine learning components). We compute the probabilities of task satisfaction under Signal Temporal Logic (STL) specifications, using its robustness semantics, with a Markov Chain Monte-Carlo slice sampler. As opposed to other techniques, our method avoids over-approximations and double-counting of failure events. Central to our approach is a method for efficient and rejection-free sampling of signals from a Gaussian distribution such that satisfy or violate a given STL formula. We show illustrative examples from applications in robot motion planning. CCS CONCEPTS• Computer systems organization → Robotics; • Theory of computation → Modal and temporal logics.

show abstract

“…In addition, forward simulation approaches can be computationally prohibitive for finding rare, long-tail failure cases. To overcome this challenge, [22] leverages linear system dynamics along with a simulator to efficiently search for closed-loop failures. Our work builds upon this line of work to integrate sampling-based falsification approaches with HJ reachability analysis for exposing closed-loop failures of vision-based controllers for general non-linear systems.…”

Section: Related Workmentioning

confidence: 99%

Discovering Closed-Loop Failures of Vision-Based Controllers via Reachability Analysis

Chakraborty¹,

Bansal²

2022

Preprint

View full text Add to dashboard Cite

Machine learning driven image-based controllers allow robotic systems to take intelligent actions based on the visual feedback from their environment. Understanding when these controllers might lead to system safety violations is important for their integration in safety-critical applications and engineering corrective safety measures for the system. Existing methods leverage simulation-based testing (or falsification) to find the failures of vision-based controllers, i.e., the visual inputs that lead to closed-loop safety violations. However, these techniques do not scale well to the scenarios involving high-dimensional and complex visual inputs, such as RGB images. In this work, we cast the problem of finding closedloop vision failures as a Hamilton-Jacobi (HJ) reachability problem. Our approach blends simulation-based analysis with HJ reachability methods to compute an approximation of the backward reachable tube (BRT) of the system, i.e., the set of unsafe states for the system under vision-based controllers. Utilizing the BRT, we can tractably and systematically find the system states and corresponding visual inputs that lead to closed-loop failures. These visual inputs can be subsequently analyzed to find the input characteristics that might have caused the failure. Besides its scalability to high-dimensional visual inputs, an explicit computation of BRT allows the proposed approach to capture non-trivial system failures that are difficult to expose via random simulations. We demonstrate our framework on two case studies involving an RGB imagebased neural network controller for (a) autonomous indoor navigation, and (b) autonomous aircraft taxiing.

show abstract

Synthesis-guided Adversarial Scenario Generation for Gray-box Feedback Control Systems with Sensing Imperfections

Cited by 6 publications

References 42 publications

Efficient Backward Reachability Using the Minkowski Difference of Constrained Zonotopes

Efficient Backward Reachability Using the Minkowski Difference of Constrained Zonotopes

Elliptical Slice Sampling for Probabilistic Verification of Stochastic Systems with Signal Temporal Logic Specifications

Discovering Closed-Loop Failures of Vision-Based Controllers via Reachability Analysis

Contact Info

Product

Resources

About