arXiv subjects

Nils Jansen

Publications and source records attributed to Nils Jansen.

At least 55 records · Page 3Linked to original sources

arXiv2023

Robust Control for Dynamical Systems With Non-Gaussian Noise via Formal Abstractions

Controllers for dynamical systems that operate in safety-critical settings must account for stochastic disturbances. Such disturbances are often modeled as process noise in a dynamical system, and common assumptions are that the underlying distributions are known and/or Gaussian. In practice, however, these assumptions may be unrealistic and can lead to poor approximations of the true noise distribution. We present a novel controller synthesis method that does not rely on any explicit representation of the noise distributions. In particular, we address the problem of computing a controller that provides probabilistic guarantees on safely reaching a target, while also avoiding unsafe regions of the state space. First, we abstract the continuous control system into a finite-state model that captures noise by probabilistic transitions between discrete states. As a key contribution, we adapt tools from the scenario approach to compute probably approximately correct (PAC) bounds on these transition probabilities, based on a finite number of samples of the noise. We capture these bounds in the transition probability intervals of a so-called interval Markov decision process (iMDP). This iMDP is, with a user-specified confidence probability, robust against uncertainty in the transition probabilities, and the tightness of the probability intervals can be controlled through the number of samples. We use state-of-the-art verification techniques to provide guarantees on the iMDP and compute a controller for which these guarantees carry over to the original control system. In addition, we develop a tailored computational scheme that reduces the complexity of the synthesis of these guarantees on the iMDP. Benchmarks on realistic control systems show the practical applicability of our method, even when the iMDP has hundreds of millions of transitions.

eess.SY↗

arXiv2022

Targeted Adversarial Attacks on Deep Reinforcement Learning Policies via Model Checking

Deep Reinforcement Learning (RL) agents are susceptible to adversarial noise in their observations that can mislead their policies and decrease their performance. However, an adversary may be interested not only in decreasing the reward, but also in modifying specific temporal logic properties of the policy. This paper presents a metric that measures the exact impact of adversarial attacks against such properties. We use this metric to craft optimal adversarial attacks. Furthermore, we introduce a model checking method that allows us to verify the robustness of RL policies against adversarial attacks. Our empirical analysis confirms (1) the quality of our metric to craft adversarial attacks against temporal logic properties, and (2) that we are able to concisely assess a system's robustness against attacks.

cs.LG↗

arXiv2022

Probabilities Are Not Enough: Formal Controller Synthesis for Stochastic Dynamical Models with Epistemic Uncertainty

Capturing uncertainty in models of complex dynamical systems is crucial to designing safe controllers. Stochastic noise causes aleatoric uncertainty, whereas imprecise knowledge of model parameters leads to epistemic uncertainty. Several approaches use formal abstractions to synthesize policies that satisfy temporal specifications related to safety and reachability. However, the underlying models exclusively capture aleatoric but not epistemic uncertainty, and thus require that model parameters are known precisely. Our contribution to overcoming this restriction is a novel abstraction-based controller synthesis method for continuous-state models with stochastic noise and uncertain parameters. By sampling techniques and robust analysis, we capture both aleatoric and epistemic uncertainty, with a user-specified confidence level, in the transition probability intervals of a so-called interval Markov decision process (iMDP). We synthesize an optimal policy on this iMDP, which translates (with the specified confidence level) to a feedback controller for the continuous model with the same performance guarantees. Our experimental benchmarks confirm that accounting for epistemic uncertainty leads to controllers that are more robust against variations in parameter values.

eess.SY↗

arXiv2022

Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation

We address the problem of safe reinforcement learning from pixel observations. Inherent challenges in such settings are (1) a trade-off between reward optimization and adhering to safety constraints, (2) partial observability, and (3) high-dimensional observations. We formalize the problem in a constrained, partially observable Markov decision process framework, where an agent obtains distinct reward and safety signals. To address the curse of dimensionality, we employ a novel safety critic using the stochastic latent actor-critic (SLAC) approach. The latent variable model predicts rewards and safety violations, and we use the safety critic to train safe policies. Using well-known benchmark environments, we demonstrate competitive performance over existing approaches with respects to computational requirements, final reward return, and satisfying the safety constraints.

cs.LG↗

arXiv2022

COOL-MC: A Comprehensive Tool for Reinforcement Learning and Model Checking

This paper presents COOL-MC, a tool that integrates state-of-the-art reinforcement learning (RL) and model checking. Specifically, the tool builds upon the OpenAI gym and the probabilistic model checker Storm. COOL-MC provides the following features: (1) a simulator to train RL policies in the OpenAI gym for Markov decision processes (MDPs) that are defined as input for Storm, (2) a new model builder for Storm, which uses callback functions to verify (neural network) RL policies, (3) formal abstractions that relate models and policies specified in OpenAI gym or Storm, and (4) algorithms to obtain bounds on the performance of so-called permissive policies. We describe the components and architecture of COOL-MC and demonstrate its features on multiple benchmark environments.

cs.LG↗

arXiv2022

Safe Reinforcement Learning via Shielding under Partial Observability

Safe exploration is a common problem in reinforcement learning (RL) that aims to prevent agents from making disastrous decisions while exploring their environment. A family of approaches to this problem assume domain knowledge in the form of a (partial) model of this environment to decide upon the safety of an action. A so-called shield forces the RL agent to select only safe actions. However, for adoption in various applications, one must look beyond enforcing safety and also ensure the applicability of RL with good performance. We extend the applicability of shields via tight integration with state-of-the-art deep RL, and provide an extensive, empirical study in challenging, sparse-reward environments under partial observability. We show that a carefully integrated shield ensures safety and can improve the convergence rate and final performance of RL agents. We furthermore show that a shield can be used to bootstrap state-of-the-art RL agents: they remain safe after initial learning in a shielded setting, allowing us to disable a potentially too conservative shield eventually.

cs.AI↗

arXiv2022

Parameter Synthesis in Markov Models: A Gentle Survey

This paper surveys the analysis of parametric Markov models whose transitions are labelled with functions over a finite set of parameters. These models are symbolic representations of uncountable many concrete probabilistic models, each obtained by instantiating the parameters. We consider various analysis problems for a given logical specification $φ$: do all parameter instantiations within a given region of parameter values satisfy $φ$?, which instantiations satisfy $φ$ and which ones do not?, and how can all such instantiations be characterised, either exactly or approximately? We address theoretical complexity results and describe the main ideas underlying state-of-the-art algorithms that established an impressive leap over the last decade enabling the fully automated analysis of models with millions of states and thousands of parameters.

cs.LO↗

arXiv2022

Sampling-Based Verification of CTMCs with Uncertain Rates

We employ uncertain parametric CTMCs with parametric transition rates and a prior on the parameter values. The prior encodes uncertainty about the actual transition rates, while the parameters allow dependencies between transition rates. Sampling the parameter values from the prior distribution then yields a standard CTMC, for which we may compute relevant reachability probabilities. We provide a principled solution, based on a technique called scenario-optimization, to the following problem: From a finite set of parameter samples and a user-specified confidence level, compute prediction regions on the reachability probabilities. The prediction regions should (with high probability) contain the reachability probabilities of a CTMC induced by any additional sample. To boost the scalability of the approach, we employ standard abstraction techniques and adapt our methodology to support approximate reachability probabilities. Experiments with various well-known benchmarks show the applicability of the approach.

cs.LO↗

arXiv2022

Scenario-Based Verification of Uncertain Parametric MDPs

We consider parametric Markov decision processes (pMDPs) that are augmented with unknown probability distributions over parameter values. The problem is to compute the probability to satisfy a temporal logic specification with any concrete MDP that corresponds to a sample from these distributions. As solving this problem precisely is infeasible, we resort to sampling techniques that exploit the so-called scenario approach. Based on a finite number of samples of the parameters, the proposed method yields high-confidence bounds on the probability of satisfying the specification. The number of samples required to obtain a high confidence on these bounds is independent of the number of states and the number of random parameters. Experiments on a large set of benchmarks show that several thousand samples suffice to obtain tight and high-confidence lower and upper bounds on the satisfaction probability.

cs.LO↗

arXiv2021

Sampling-Based Robust Control of Autonomous Systems with Non-Gaussian Noise

Controllers for autonomous systems that operate in safety-critical settings must account for stochastic disturbances. Such disturbances are often modelled as process noise, and common assumptions are that the underlying distributions are known and/or Gaussian. In practice, however, these assumptions may be unrealistic and can lead to poor approximations of the true noise distribution. We present a novel planning method that does not rely on any explicit representation of the noise distributions. In particular, we address the problem of computing a controller that provides probabilistic guarantees on safely reaching a target. First, we abstract the continuous system into a discrete-state model that captures noise by probabilistic transitions between states. As a key contribution, we adapt tools from the scenario approach to compute probably approximately correct (PAC) bounds on these transition probabilities, based on a finite number of samples of the noise. We capture these bounds in the transition probability intervals of a so-called interval Markov decision process (iMDP). This iMDP is robust against uncertainty in the transition probabilities, and the tightness of the probability intervals can be controlled through the number of samples. We use state-of-the-art verification techniques to provide guarantees on the iMDP, and compute a controller for which these guarantees carry over to the autonomous system. Realistic benchmarks show the practical applicability of our method, even when the iMDP has millions of states or transitions.

eess.SY↗

arXiv2021

Damage detection using in-domain and cross-domain transfer learning

We investigate the capabilities of transfer learning in the area of structural health monitoring. In particular, we are interested in damage detection for concrete structures. Typical image datasets for such problems are relatively small, calling for the transfer of learned representation from a related large-scale dataset. Past efforts of damage detection using images have mainly considered cross-domain transfer learning approaches using pre-trained IMAGENET models that are subsequently fine-tuned for the target task. However, there are rising concerns about the generalizability of IMAGENET representations for specific target domains, such as for visual inspection and medical imaging. We, therefore, evaluate a combination of in-domain and cross-domain transfer learning strategies for damage detection in bridges. We perform comprehensive comparisons to study the impact of cross-domain and in-domain transfer, with various initialization strategies, using six publicly available visual inspection datasets. The pre-trained models are also evaluated for their ability to cope with the extremely low-data regime. We show that the combination of cross-domain and in-domain transfer persistently shows superior performance specially with tiny datasets. Likewise, we also provide visual explanations of predictive models to enable algorithmic transparency and provide insights to experts about the intrinsic decision logic of typically black-box deep models.

cs.CV↗

arXiv2021

Convex Optimization for Parameter Synthesis in MDPs

Probabilistic model checking aims to prove whether a Markov decision process (MDP) satisfies a temporal logic specification. The underlying methods rely on an often unrealistic assumption that the MDP is precisely known. Consequently, parametric MDPs (pMDPs) extend MDPs with transition probabilities that are functions over unspecified parameters. The parameter synthesis problem is to compute an instantiation of these unspecified parameters such that the resulting MDP satisfies the temporal logic specification. We formulate the parameter synthesis problem as a quadratically constrained quadratic program (QCQP), which is nonconvex and is NP-hard to solve in general. We develop two approaches that iteratively obtain locally optimal solutions. The first approach exploits the so-called convex-concave procedure (CCP), and the second approach utilizes a sequential convex programming (SCP) method. The techniques improve the runtime and scalability by multiple orders of magnitude compared to black-box CCP and SCP by merging ideas from convex optimization and probabilistic model checking. We demonstrate the approaches on a satellite collision avoidance problem with hundreds of thousands of states and tens of thousands of parameters and their scalability on a wide range of commonly used benchmarks.

math.OC↗

arXiv2021

Model Repair Revamped: On the Automated Synthesis of Markov Chains

This paper outlines two approaches|based on counterexample-guided abstraction refinement (CEGAR) and counterexample-guided inductive synthesis (CEGIS), respectively to the automated synthesis of finite-state probabilistic models and programs. Our CEGAR approach iteratively partitions the design space starting from an abstraction of this space and refines this by a light-weight analysis of verification results. The CEGIS technique exploits critical subsystems as counterexamples to prune all programs behaving incorrectly on that input. We show the applicability of these synthesis techniques to sketching of probabilistic programs, controller synthesis of POMDPs, and software product lines.

cs.PL↗

arXiv2021

Enforcing Almost-Sure Reachability in POMDPs

Partially-Observable Markov Decision Processes (POMDPs) are a well-known stochastic model for sequential decision making under limited information. We consider the EXPTIME-hard problem of synthesising policies that almost-surely reach some goal state without ever visiting a bad state. In particular, we are interested in computing the winning region, that is, the set of system configurations from which a policy exists that satisfies the reachability specification. A direct application of such a winning region is the safe exploration of POMDPs by, for instance, restricting the behavior of a reinforcement learning agent to the region. We present two algorithms: A novel SAT-based iterative approach and a decision-diagram based alternative. The empirical evaluation demonstrates the feasibility and efficacy of the approaches.

cs.AI↗

arXiv2021

Robust Finite-State Controllers for Uncertain POMDPs

Uncertain partially observable Markov decision processes (uPOMDPs) allow the probabilistic transition and observation functions of standard POMDPs to belong to a so-called uncertainty set. Such uncertainty, referred to as epistemic uncertainty, captures uncountable sets of probability distributions caused by, for instance, a lack of data available. We develop an algorithm to compute finite-memory policies for uPOMDPs that robustly satisfy specifications against any admissible distribution. In general, computing such policies is theoretically and practically intractable. We provide an efficient solution to this problem in four steps. (1) We state the underlying problem as a nonconvex optimization problem with infinitely many constraints. (2) A dedicated dualization scheme yields a dual problem that is still nonconvex but has finitely many constraints. (3) We linearize this dual problem and (4) solve the resulting finite linear program to obtain locally optimal solutions to the original problem. The resulting problem formulation is exponentially smaller than those resulting from existing methods. We demonstrate the applicability of our algorithm using large instances of an aircraft collision-avoidance scenario and a novel spacecraft motion planning case study.

cs.AI↗

arXiv2021

Balancing Wind and Batteries: Towards Predictive Verification of Smart Grids

We study a smart grid with wind power and battery storage. Traditionally, day-ahead planning aims to balance demand and wind power, yet actual wind conditions often deviate from forecasts. Short-term flexibility in storage and generation fills potential gaps, planned on a minutes time scale for 30-60 minute horizons. Finding the optimal flexibility deployment requires solving a semi-infinite non-convex stochastic program, which is generally intractable to do exactly. Previous approaches rely on sampling, yet such critical problems call for rigorous approaches with stronger guarantees. Our method employs probabilistic model checking techniques. First, we cast the problem as a continuous-space Markov decision process with discretized control, for which an optimal deployment strategy minimizes the expected grid frequency deviation. To mitigate state space explosion, we exploit specific structural properties of the model to implement an iterative exploration method that reuses pre-computed values as wind data is updated. Our experiments show the method's feasibility and versatility across grid configurations and time scales.

eess.SY↗

arXiv2020

Adaptive Shielding under Uncertainty

This paper targets control problems that exhibit specific safety and performance requirements. In particular, the aim is to ensure that an agent, operating under uncertainty, will at runtime strictly adhere to such requirements. Previous works create so-called shields that correct an existing controller for the agent if it is about to take unbearable safety risks. However, so far, shields do not consider that an environment may not be fully known in advance and may evolve for complex control and learning tasks. We propose a new method for the efficient computation of a shield that is adaptive to a changing environment. In particular, we base our method on problems that are sufficiently captured by potentially infinite Markov decision processes (MDP) and quantitative specifications such as mean payoff objectives. The shield is independent of the controller, which may, for instance, take the form of a high-performing reinforcement learning agent. At runtime, our method builds an internal abstract representation of the MDP and constantly adapts this abstraction and the shield based on observations from the environment. We showcase the applicability of our method via an urban traffic control problem.

cs.LO↗

arXiv2020

Adversarial Patch Camouflage against Aerial Detection

Detection of military assets on the ground can be performed by applying deep learning-based object detectors on drone surveillance footage. The traditional way of hiding military assets from sight is camouflage, for example by using camouflage nets. However, large assets like planes or vessels are difficult to conceal by means of traditional camouflage nets. An alternative type of camouflage is the direct misleading of automatic object detectors. Recently, it has been observed that small adversarial changes applied to images of the object can produce erroneous output by deep learning-based detectors. In particular, adversarial attacks have been successfully demonstrated to prohibit person detections in images, requiring a patch with a specific pattern held up in front of the person, thereby essentially camouflaging the person for the detector. Research into this type of patch attacks is still limited and several questions related to the optimal patch configuration remain open. This work makes two contributions. First, we apply patch-based adversarial attacks for the use case of unmanned aerial surveillance, where the patch is laid on top of large military assets, camouflaging them from automatic detectors running over the imagery. The patch can prevent automatic detection of the whole object while only covering a small part of it. Second, we perform several experiments with different patch configurations, varying their size, position, number and saliency. Our results show that adversarial patch attacks form a realistic alternative to traditional camouflage activities, and should therefore be considered in the automated analysis of aerial surveillance imagery.

cs.CV↗