Dejan Ničković

Axel Brunnbauer, Luigi Berducci, Peter Priller et al.

The automated generation of diverse and complex training scenarios has been an important ingredient in many complex learning tasks. Especially in real-world application domains, such as autonomous driving, auto-curriculum generation is considered vital for obtaining robust and general policies. However, crafting traffic scenarios with multiple, heterogeneous agents is typically considered as a tedious and time-consuming task, especially in more complex simulation environments. In our work, we introduce MATS-Gym, a Multi-Agent Traffic Scenario framework to train agents in CARLA, a high-fidelity driving simulator. MATS-Gym is a multi-agent training framework for autonomous driving that uses partial scenario specifications to generate traffic scenarios with variable numbers of agents. This paper unifies various existing approaches to traffic scenario description into a single training framework and demonstrates how it can be integrated with techniques from unsupervised environment design to automate the generation of adaptive auto-curricula. The code is available at https://github.com/AutonomousDrivingExaminer/mats-gym.

Anagha Athavale, Samuel Teuber, Matteo Maffei et al.

The robustness of deep neural networks (DNNs) is critical in security-sensitive applications, where small input perturbations should not alter model predictions. This property is commonly formalized as local or global robustness: the former considers perturbations around a single input, while the latter -- strictly stronger -- quantifies over all input pairs. While local robustness can be expressed as a safety property, global robustness is a 2-safety property, making it substantially more challenging to verify. We present a novel static analysis technique for verifying the global robustness of DNNs. Our approach is based on differential halo zonotopes, a new abstract domain that extends zonotopes to jointly propagate pairs of perturbed inputs in lock-step while tightly bounding their divergence. In addition, we introduce a symmetric variant of confidence-based global robustness that disregards perturbations leading to differing but low-confidence predictions. This relaxation yields a practically meaningful notion of robustness that applies to a broader class of networks. We implement our approach in a new tool, called TwoSafe, and evaluate it on standard DNN verification benchmarks, including widely deployed models. Our results show that TwoSafe significantly outperforms the state of the art in both precision and scalability, enabling the verification of networks an order of magnitude larger than those handled by prior techniques.

Jie He, Vincent Theo Willem Kenbeek, Zhantao Yang et al.

We introduce TD-Interpreter, a specialized ML tool that assists engineers in understanding complex timing diagrams (TDs), originating from a third party, during their design and verification process. TD-Interpreter is a visual question-answer environment which allows engineers to input a set of TDs and ask design and verification queries regarding these TDs. We implemented TD-Interpreter with multimodal learning by fine-tuning LLaVA, a lightweight 7B Multimodal Large Language Model (MLLM). To address limited training data availability, we developed a synthetic data generation workflow that aligns visual information with its textual interpretation. Our experimental evaluation demonstrates the usefulness of TD-Interpreter which outperformed untuned GPT-4o by a large margin on the evaluated benchmarks.

Anand Balakrishnan, Stefan Jakšić, Edgar A. Aguilar et al.

Reinforcement learning (RL) is a popular approach for robotic path planning in uncertain environments. However, the control policies trained for an RL agent crucially depend on user-defined, state-based reward functions. Poorly designed rewards can lead to policies that do get maximal rewards but fail to satisfy desired task objectives or are unsafe. There are several examples of the use of formal languages such as temporal logics and automata to specify high-level task specifications for robots (in lieu of Markovian rewards). Recent efforts have focused on inferring state-based rewards from formal specifications; here, the goal is to provide (probabilistic) guarantees that the policy learned using RL (with the inferred rewards) satisfies the high-level formal specification. A key drawback of several of these techniques is that the rewards that they infer are sparse: the agent receives positive rewards only upon completion of the task and no rewards otherwise. This naturally leads to poor convergence properties and high variance during RL. In this work, we propose using formal specifications in the form of symbolic automata: these serve as a generalization of both bounded-time temporal logic-based specifications as well as automata. Furthermore, our use of symbolic automata allows us to define non-sparse potential-based rewards which empirically shape the reward surface, leading to better convergence during RL. We also show that our potential-based rewarding strategy still allows us to obtain the policy that maximizes the satisfaction of the given specification.

Luigi Berducci, Edgar A. Aguilar, Dejan Ničković et al.

The automatic synthesis of policies for robotic-control tasks through reinforcement learning relies on a reward signal that simultaneously captures many possibly conflicting requirements. In this paper, we in\-tro\-duce a novel, hierarchical, potential-based reward-shaping approach (HPRS) for defining effective, multivariate rewards for a large family of such control tasks. We formalize a task as a partially-ordered set of safety, target, and comfort requirements, and define an automated methodology to enforce a natural order among requirements and shape the associated reward. Building upon potential-based reward shaping, we show that HPRS preserves policy optimality. Our experimental evaluation demonstrates HPRS's superior ability in capturing the intended behavior, resulting in task-satisfying policies with improved comfort, and converging to optimal behavior faster than other state-of-the-art approaches. We demonstrate the practical usability of HPRS on several robotics applications and the smooth sim2real transition on two autonomous-driving scenarios for F1TENTH race cars.

Ezio Bartocci, Jyotirmoy Deshmukh, Cristinel Mateis et al.

We present ShapeIt, a tool for mining specifications of cyber-physical systems (CPS) from their real-valued behaviors. The learned specifications are in the form of linear shape expressions, a declarative formal specification language suitable to express behavioral properties over real-valued signals. A linear shape expression is a regular expression composed of parameterized lines as atomic symbols with symbolic constraints on the line parameters. We present here the architecture of our tool along with the different steps of the specification mining algorithm. We also describe the usage of the tool demonstrating its applicability on several case studies from different application domains.

Jie He, Ezio Bartocci, Dejan Ničković et al.

Formal methods provide very powerful tools and techniques for the design and analysis of complex systems. Their practical application remains however limited, due to the widely accepted belief that formal methods require extensive expertise and a steep learning curve. Writing correct formal specifications in form of logical formulas is still considered to be a difficult and error prone task. In this paper we propose DeepSTL, a tool and technique for the translation of informal requirements, given as free English sentences, into Signal Temporal Logic (STL), a formal specification language for cyber-physical systems, used both by academia and advanced research labs in industry. A major challenge to devise such a translator is the lack of publicly available informal requirements and formal specifications. We propose a two-step workflow to address this challenge. We first design a grammar-based generation technique of synthetic data, where each output is a random STL formula and its associated set of possible English translations. In the second step, we use a state-of-the-art transformer-based neural translation technique, to train an accurate attentional translator of English to STL. The experimental results show high translation quality for patterns of English requirements that have been well trained, making this workflow promising to be extended for processing more complex translation tasks.

Nadja Marko, Eike Möhlmann, Dejan Ničković et al.

After more than a decade of intense focus on automated vehicles, we are still facing huge challenges for the vision of fully autonomous driving to become a reality. The same "disillusionment" is true in many other domains, in which autonomous Cyber-Physical Systems (CPS) could considerably help to overcome societal challenges and be highly beneficial to society and individuals. Taking the automotive domain, i.e. highly automated vehicles (HAV), as an example, this paper sets out to summarize the major challenges that are still to overcome for achieving safe, secure, reliable and trustworthy highly automated resp. autonomous CPS. We constrain ourselves to technical challenges, acknowledging the importance of (legal) regulations, certification, standardization, ethics, and societal acceptance, to name but a few, without delving deeper into them as this is beyond the scope of this paper. Four challenges have been identified as being the main obstacles to realizing HAV: Realization of continuous, post-deployment systems improvement, handling of uncertainties and incomplete information, verification of HAV with machine learning components, and prediction. Each of these challenges is described in detail, including sub-challenges and, where appropriate, possible approaches to overcome them. By working together in a common effort between industry and academy and focusing on these challenges, the authors hope to contribute to overcome the "disillusionment" for realizing HAV.

Ezio Bartocci, Roderick Bloem, Benedikt Maderbacher et al.

Ensuring correctness of cyber-physical systems (CPS) is an extremely challenging task that is in practice often addressed with simulation based testing. Formal specification languages, such as Signal Temporal Logic (STL), are used to mathematically express CPS requirements and thus render the simulation activity more systematic and principled. We propose a novel method for adaptive generation of tests with specification coverage for STL. To achieve this goal, we devise cooperative reachability games that we combine with numerical optimization to create tests that explore the system in a way that exercise various parts of the specification. To the best of our knowledge our approach is the first adaptive testing approach that can be applied directly to MATLAB\texttrademark\; Simulink/Stateflow models. We implemented our approach in a prototype tool and evaluated it on several illustrating examples and a case study from the avionics domain, demonstrating the effectiveness of adaptive testing to (1) incrementally build a test case that reaches a test objective, (2) generate a test suite that increases the specification coverage, and (3) infer what part of the specification is actually implemented.

Przemyslaw Daca, Thomas A. Henzinger, Willibald Krenn et al.

Model-based testing is a promising technology for black-box software and hardware testing, in which test cases are generated automatically from high-level specifications. Nowadays, systems typically consist of multiple interacting components and, due to their complexity, testing presents a considerable portion of the effort and cost in the design process. Exploiting the compositional structure of system specifications can considerably reduce the effort in model-based testing. Moreover, inferring properties about the system from testing its individual components allows the designer to reduce the amount of integration testing. In this paper, we study compositional properties of the IOCO-testing theory. We propose a new approach to composition and hiding operations, inspired by contract-based design and interface theories. These operations preserve behaviors that are compatible under composition and hiding, and prune away incompatible ones. The resulting specification characterizes the input sequences for which the unit testing of components is sufficient to infer the correctness of component integration without the need for further tests. We provide a methodology that uses these results to minimize integration testing effort, but also to detect potential weaknesses in specifications. While we focus on asynchronous models and the IOCO conformance relation, the resulting methodology can be applied to a broader class of systems.

Ezio Bartocci, Niveditha Manjunath, Leonardo Mariani et al.

Debugging Cyber-Physical System (CPS) models can be extremely complex. Indeed, only the detection of a failure is insuffcient to know how to correct a faulty model. Faults can propagate in time and in space producing observable misbehaviours in locations completely different from the location of the fault. Understanding the reason of an observed failure is typically a challenging and laborious task left to the experience and domain knowledge of the designer. \n In this paper, we propose CPSDebug, a novel approach that by combining testing, specification mining, and failure analysis, can automatically explain failures in Simulink/Stateflow models. We evaluate CPSDebug on two case studies, involving two use scenarios and several classes of faults, demonstrating the potential value of our approach.

César Sánchez, Gerardo Schneider, Wolfgang Ahrendt et al.

Runtime verification is an area of formal methods that studies the dynamic analysis of execution traces against formal specifications. Typically, the two main activities in runtime verification efforts are the process of creating monitors from specifications, and the algorithms for the evaluation of traces against the generated monitors. Other activities involve the instrumentation of the system to generate the trace and the communication between the system under analysis and the monitor. Most of the applications in runtime verification have been focused on the dynamic analysis of software, even though there are many more potential applications to other computational devices and target systems. In this paper we present a collection of challenges for runtime verification extracted from concrete application domains, focusing on the difficulties that must be overcome to tackle these specific challenges. The computational models that characterize these domains require to devise new techniques beyond the current state of the art in runtime verification.