Model-based reasoning agents are ill-equipped to act in novel situations in which their model of the environment no longer sufficiently represents the world. We propose HYDRA, a framework for designing model-based agents operating in mixed discrete-continuous worlds that can autonomously detect when the environment has evolved from its canonical setup, understand how it has evolved, and adapt the agents' models to perform effectively. HYDRA is based upon PDDL+, a rich modeling language for planning in mixed, discrete-continuous environments. It augments the planning module with visual reasoning, task selection, and action execution modules for closed-loop interaction with complex environments. HYDRA implements a novel meta-reasoning process that enables the agent to monitor its own behavior from a variety of aspects. The process employs a diverse set of computational methods to maintain expectations about the agent's own behavior in an environment. Divergences from those expectations are useful in detecting when the environment has evolved and identifying opportunities to adapt the underlying models. HYDRA builds upon ideas from diagnosis and repair and uses a heuristics-guided search over model changes such that they become competent in novel conditions. The HYDRA framework has been used to implement novelty-aware agents for three diverse domains - CartPole++ (a higher dimension variant of a classic control problem), Science Birds (an IJCAI competition problem), and PogoStick (a specific problem domain in Minecraft). We report empirical observations from these domains to demonstrate the efficacy of various components in the novelty meta-reasoning process.

Fault diagnosis has been addressed in many research communities, leading to a variety of fault diagnosis techniques.For a user to decide which fault diagnosis methods are suitable for a specific application scenario is thus a non-trivial task.Benchmarks are used to provide the community with a holistic understanding of the landscape of available and newly developed fault diagnosis methods.After a long hiatus, the DX Competition is revived with three fault diagnosis benchmarks: SLIDe, LUMEN, and LiU-ICE.The purpose of the benchmarks is to inspire fault diagnosis research with challenging industrial problems.The benchmarks share a common code structure and similar performance metrics to simplify the adaptation of diagnosis system solutions to the different case studies.

Assessing and comparing diagnosis algorithms is a surprisingly complex challenge. We have to make decisions ranging from identifying the implications of the chosen baseline, via defining and ensuring a representative sampling strategy, to the choice of metric best suited to capture the computational, probing, or repair costs as well as the deviations from the baseline. We discuss several aspects of the overall challenge, identify related issues, and evaluate a special economic metric.

International audience

We demonstrate an end-to-end framework to improve the resilience of man-made systems to unforeseen events. The framework is based on a physics-based digital twin model and three modules tasked with real-time fault diagnosis, prognostics and reconfiguration. The fault diagnosis module uses model-based diagnosis algorithms to detect and isolate faults and generates interventions in the system to disambiguate uncertain diagnosis solutions. We scale up the fault diagnosis algorithm to the required real-time performance through the use of parallelization and surrogate models of the physics-based digital twin. The prognostics module tracks fault progression and trains the online degradation models to compute remaining useful life of system components. In addition, we use the degradation models to assess the impact of the fault progression on the operational requirements. The reconfiguration module uses PDDL-based planning endowed with semantic attachments to adjust the system controls to minimize the fault impact on the system operation. We define a resilience metric and use a fuel system example to demonstrate how the metric improves with our framework.

We introduce two block coordinate descent algorithms for solving optimization problems with ordinary differential equations (ODEs) as dynamical constraints. In contrast to prior algorithms, ours do not need to implement sensitivity analysis methods to evaluate loss function gradients. They result from the reformulation of the original problem as an equivalent optimization problem with equality constraints. In our first algorithm we avoid explicitly solving the ODE by integrating the ODE solver as a sequence of implicit constraints. In our second algorithm, we add an ODE solver to reset the estimate of the ODE solution, but no sensitivity analysis method is needed. We test the proposed algorithms on the problem of learning the parameters of the Cucker-Smale model. The algorithms are compared with gradient descent algorithms based on ODE solvers endowed with sensitivity analysis capabilities. We show that the proposed algorithms are at least 4x faster when implemented in Pytorch, and at least 16x faster when implemented in Jax. For large versions of the Cucker-Smale model, the Jax implementation is thousands of times faster. Our algorithms generate more accurate results both on training and test data. In addition, we show how the proposed algorithms scale with the number of optimization variables, and how they can be applied to learning black-box models of dynamical systems. Moreover, we demonstrate how our approach can be combined with approaches based on sensitivity analysis enabled ODE solvers to reduce the training time.

In Model-Based Diagnosis (MBD), we concern ourselves with the health and safety of physical and software systems. Although we often use different knowledge representations and algorithms, some tools like satisfiability (SAT) solvers and temporal logics, are used in both domains. In this paper we introduce Finite Trace Next Logic (FTNL) models of sequential circuits and propose an enhanced algorithm for computing minimal-cardinality diagnoses. Existing state-of-the-art satisfiability algorithms for minimal diagnosis use Sorting Networks (SNs) for constraining the cardinality of the diagnostic candidates. In our approach we exploit Multi-Operand Adders (MOAs). Based on extensive tests with ISCAS-89 circuits, we found that MOAs enable Conjunctive Normal Form (CNF) encodings that are significantly more compact. These encodings lead to 19.7 to 67.6 times fewer variables and 18.4 to 62 times fewer clauses. For converting an FTNL model to CNF, we could achieve a speed-up ranging from 6.2 to 22.2. Using SNs fosters 3.4 to 5.5 times faster on-line satisfiability checking though. This makes MOAs preferable for applications where RAM and off-line time are more limited than on-line CPU time.

This paper presents an approach to applying model-based diagnosis to the task of interpreting in- formation from a wide variety of sources: text, video, meta-data, audio, etc. Much of the information contained in the sources is contradictory, incomplete, purposely deceptive or biased. People make critical decisions based on such murky information. By automating the construction of alternatives, we can design systems that support intelligence analysts and ordinary citizens in understanding the world. We have developed a preliminary version of our HCDX tool (hypothesis construction through diagnosis). We plan to distribute this tool as open source.

Software diagnosis is a particularly challenging problem for modern systems, which may consist of dozens, if not hundreds, of components computing on concurrent and potentially distributed platforms, and using infrastructure and services built by many organizations. We propose a framework that generalizes state-of-the-art classical reasoning-based fault diagnosis which tolerates observation uncertainty and addresses degradation of quality of service. Empirical evaluation involving 27000 highly realistic synthetic scenarios demonstrates an average accuracy improvement of 20% (with 99% statistical significance) which is considerable in the domain of Software Fault Localization (SFL). We measure the improvement in accuracy on well-established SFL performance metrics.

Qualitative reasoning can play an important role in early stage design. Currently, engineers explore the design space using simulation models built in languages such as Modelica. To make qualitative reasoning useful to them, designs specified in their languages must be translated into a qualitative modeling language for analysis. The contribution of this paper is a sound and effective mapping between Modelica and qualitative reasoning. To achieve a sound mapping, we extend envisioning, the process of generating all relevant qualitative behaviors, to support Modelica's declarative events. For an effective mapping, we identify three classes of additional constraints that should be inferred from the Modelica representation thereby exponentially reducing the number of unrealizable trajectories. We support this contribution with examples and a case study.

In case of a plan failure, plan-repair is a more promising solution than replanning from scratch. The effectiveness of plan-repair depends on knowledge of which plan action failed and why. Therefore, in this paper, we propose an Extended Spectrum Based Diagnosis approach that efficiently pinpoints failed actions. Unlike Model Based Diagnosis (MBD), it does not require the fault models and behavioral descriptions of actions. Our approach first computes the likelihood of an action being faulty and subsequently proposes optimal probe locations to refine the diagnosis. We also exploit knowledge of plan steps that are instances of the same plan operator to optimize the selection of the most informative diagnostic probes. In this paper, we only focus on diagnostic aspect of plan-repair process.

Our goal is to enable military planners to rapidly critique alternative battle plans by simulating multiple outcomes of adversarial plans. We describe a novel simulator, SimPath, that combines qualitative reasoning, a geographic information system (GIS), and targeted probabilistic calculations to envision how adversarial battle plans can play out. We outline the problem and describe the overall operation of the simulator. We then explain how qualitative process theory is extended with actions to model military tasks, how envisioning is factored to reduce combinatorial explosions, and how probabilities are computed for transitions and used to filter possibilities. Empirical results, including an experiment conducted by an independent evaluator, are summarized. The results show that it is possible to identify dozens of possible outcomes on each of 9 combinations of adversarial plans (COAs) in under two minutes. We close with a discussion of future work.

In model-based production, a planner uses a system description to create plans that achieve production goals. The same description can be used by model-based diagnosis to infer the condition of components from sensor data. When production is realized by a sequence of plans, prior work has demonstrated that diagnosis can be used to adapt the plans to compensate for component degradation. However, the sources of diagnostic information are severely limited. Diagnosis must either make inferences from observations during production over which it has no control (passive diagnosis), or production must be halted to introduce diagnostic-specific plans (explicit diagnosis). We observe that the declarative nature of the model-based approach allows the planner to achieve production goals in multiple ways. This flexibility is exploited by a novel paradigm, i.e.,pervasive (active) diagnosis, which constructsinformative production plansthat simultaneously achieve production goals while uncovering additional diagnostic information about the condition of components. We present an efficient heuristic search for these informative production plans and show through experiments on a model of an industrial digital printing press that the theoretical increase in long-run productivity can be realized on practical real-time systems. We obtain higher long-run productivity than a decoupled combination of planning and diagnosis.

The six papers in this special issue cover different approaches and different applications to model-based diagnostics.