Arvind Easwaran

Subrat Prasad Panda, Blaise Genest, Arvind Easwaran et al.

Decision Trees (DTs) constitute one of the major highly non-linear AI models, valued, e.g., for their efficiency on tabular data. Learning accurate DTs is, however, complicated, especially for oblique DTs, and does take a significant training time. Further, DTs suffer from overfitting, e.g., they proverbially "do not generalize" in regression tasks. Recently, some works proposed ways to make (oblique) DTs differentiable. This enables highly efficient gradient-descent algorithms to be used to learn DTs. It also enables generalizing capabilities by learning regressors at the leaves simultaneously with the decisions in the tree. Prior approaches to making DTs differentiable rely either on probabilistic approximations at the tree's internal nodes (soft DTs) or on approximations in gradient computation at the internal node (quantized gradient descent). In this work, we propose DTSemNet, a novel semantically equivalent and invertible encoding for (hard, oblique) DTs as Neural Networks (NNs), that uses standard vanilla gradient descent. Experiments across various classification and regression benchmarks show that oblique DTs learned using DTSemNet are more accurate than oblique DTs of similar size learned using state-of-the-art techniques. Further, DT training time is significantly reduced. We also experimentally demonstrate that DTSemNet can learn DT policies as efficiently as NN policies in the Reinforcement Learning (RL) setup with physical inputs (dimensions $\leq32$). The code is available at https://github.com/CPS-research-group/dtsemnet.

Mohit Prashant, Arvind Easwaran

Guaranteeing safety is critical to the deployment of reinforcement learning (RL) agents in the real-world, especially as policies learned using deep RL may demonstrate susceptibility to transition perturbations that result in unknown or unsafe behaviour. A method of policy verification is to construct probabilistic barrier-certificates by sampling policy trajectories with respect to safety constraints, thereby demarcating known safe behaviour from unknown behaviour. Obtaining tight upper and lower bounds on the probability of violation of these constraints may be difficult if the policy is susceptible to transition uncertainty or perturbation that places the agent in insufficiently explored states. To address this, we approximate the distribution of the encountered state-space using a variational autoencoder (VAE) and construct upper and lower-bound barrier-certificates using latent characteristics of states to optimize for regions of known, safe behaviour with high confidence. We frame this in our work as a dual optimization problem where the lower-bound barrier-certificate presents a more conservative estimate of the safe region than the upper-bound barrier-certificate. Sampling states that lie within the set difference of the two during training, i.e. the non-robust region, allows us to tighten the upper and lower bounds to provide sharper probabilistic guarantees on safety. Within our study, we describe the guarantees placed and demonstrate the tightness of our bounds experimentally.

Mohit Prashant, Arvind Easwaran

Cyber-physical systems (CPS) like autonomous vehicles, that utilize learning components, are often sensitive to noise and out-of-distribution (OOD) instances encountered during runtime. As such, safety critical tasks depend upon OOD detection subsystems in order to restore the CPS to a known state or interrupt execution to prevent safety from being compromised. However, it is difficult to guarantee the performance of OOD detectors as it is difficult to characterize the OOD aspect of an instance, especially in high-dimensional unstructured data. To distinguish between OOD data and data known to the learning component through the training process, an emerging technique is to incorporate variational autoencoders (VAE) within systems and apply classification or anomaly detection techniques on their latent spaces. The rationale for doing so is the reduction of the data domain size through the encoding process, which benefits real-time systems through decreased processing requirements, facilitates feature analysis for unstructured data and allows more explainable techniques to be implemented. This study places probably approximately correct (PAC) based guarantees on OOD detection using the encoding process within VAEs to quantify image features and apply conformal constraints over them. This is used to bound the detection error on unfamiliar instances with user-defined confidence. The approach used in this study is to empirically establish these bounds by sampling the latent probability distribution and evaluating the error with respect to the constraint violations that are encountered. The guarantee is then verified using data generated from CARLA, an open-source driving simulator.

Taoran Wu, Yiling Xue, Jingduo Pan et al.

Identifying controlled safety invariant sets (CSISs) is essential for safety-critical systems. This paper addresses the problem of computing CSISs for black-box discrete-time systems, where the dynamics are unknown and only limited simulation data are available. Traditionally, a CSIS requires that for every state in the set, there exists a control input that keeps the system within the set at the next step. However, enforcing such universal invariance, i.e., requiring the set to remain controlled invariant for all states, is often overly restrictive or impractical for black-box systems. To address this, we introduce the notion of a Probably Approximately Correct (PAC) CSIS, in which, with prescribed confidence, there exists a suitable control input to keep the system within the set at the next step for at least a specified fraction of the states. Our approach leverages barrier functions and scenario optimization, yielding a tractable linear programming method for estimating PAC CSISs. Several illustrative examples demonstrate the effectiveness of the proposed framework.

Xiang Fang, Arvind Easwaran, Blaise Genest

Out-of-distribution (OOD) detection targets to detect and reject test samples with semantic shifts, to prevent models trained on in-distribution (ID) dataset from producing unreliable predictions. Existing works only extract the appearance features on image datasets, and cannot handle dynamic multimedia scenarios with much motion information. Therefore, we target a more realistic and challenging OOD detection task: OOD action detection (ODAD). Given an untrimmed video, ODAD first classifies the ID actions and recognizes the OOD actions, and then localizes ID and OOD actions. To this end, in this paper, we propose a novel Uncertainty-Guided Appearance-Motion Association Network (UAAN), which explores both appearance features and motion contexts to reason spatial-temporal inter-object interaction for ODAD.Firstly, we design separate appearance and motion branches to extract corresponding appearance-oriented and motion-aspect object representations. In each branch, we construct a spatial-temporal graph to reason appearance-guided and motion-driven inter-object interaction. Then, we design an appearance-motion attention module to fuse the appearance and motion features for final action detection. Experimental results on two challenging datasets show that UAAN beats state-of-the-art methods by a significant margin, illustrating its effectiveness.

Michael Yuhas, Daniel Jun Xian Ng, Arvind Easwaran

When machine learning (ML) models are supplied with data outside their training distribution, they are more likely to make inaccurate predictions; in a cyber-physical system (CPS), this could lead to catastrophic system failure. To mitigate this risk, an out-of-distribution (OOD) detector can run in parallel with an ML model and flag inputs that could lead to undesirable outcomes. Although OOD detectors have been well studied in terms of accuracy, there has been less focus on deployment to resource constrained CPSs. In this study, a design methodology is proposed to tune deep OOD detectors to meet the accuracy and response time requirements of embedded applications. The methodology uses genetic algorithms to optimize the detector's preprocessing pipeline and selects a quantization method that balances robustness and response time. It also identifies several candidate task graphs under the Robot Operating System (ROS) for deployment of the selected design. The methodology is demonstrated on two variational autoencoder based OOD detectors from the literature on two embedded platforms. Insights into the trade-offs that occur during the design process are provided, and it is shown that this design methodology can lead to a drastic reduction in response time in relation to an unoptimized OOD detector while maintaining comparable accuracy.

Michael Yuhas, Arvind Easwaran

In a cyber-physical system such as an autonomous vehicle (AV), machine learning (ML) models can be used to navigate and identify objects that may interfere with the vehicle's operation. However, ML models are unlikely to make accurate decisions when presented with data outside their training distribution. Out-of-distribution (OOD) detection can act as a safety monitor for ML models by identifying such samples at run time. However, in safety critical systems like AVs, OOD detection needs to satisfy real-time constraints in addition to functional requirements. In this demonstration, we use a mobile robot as a surrogate for an AV and use an OOD detector to identify potentially hazardous samples. The robot navigates a miniature town using image data and a YOLO object detection network. We show that our OOD detector is capable of identifying OOD images in real-time on an embedded platform concurrently performing object detection and lane following. We also show that it can be used to successfully stop the vehicle in the presence of unknown, novel samples.

Michael Yuhas, Arvind Easwaran

Learning enabled components (LECs), while critical for decision making in autonomous vehicles (AVs), are likely to make incorrect decisions when presented with samples outside of their training distributions. Out-of-distribution (OOD) detectors have been proposed to detect such samples, thereby acting as a safety monitor, however, both OOD detectors and LECs require heavy utilization of embedded hardware typically found in AVs. For both components, there is a tradeoff between non-functional and functional performance, and both impact a vehicle's safety. For instance, giving an OOD detector a longer response time can increase its accuracy at the expense of the LEC. We consider an LEC with binary output like an autonomous emergency braking system (AEBS) and use risk, the combination of severity and occurrence of a failure, to model the effect of both components' design parameters on each other's functional and non-functional performance, as well as their impact on system safety. We formulate a co-design methodology that uses this risk model to find the design parameters for an OOD detector and LEC that decrease risk below that of the baseline system and demonstrate it on a vision based AEBS. Using our methodology, we achieve a 42.3% risk reduction while maintaining equivalent resource utilization.

Zahra Rahiminasab, Michael Yuhas, Arvind Easwaran

Out-of-distribution (OOD) detection, i.e., finding test samples derived from a different distribution than the training set, as well as reasoning about such samples (OOD reasoning), are necessary to ensure the safety of results generated by machine learning models. Recently there have been promising results for OOD detection in the latent space of variational autoencoders (VAEs). However, without disentanglement, VAEs cannot perform OOD reasoning. Disentanglement ensures a one- to-many mapping between generative factors of OOD (e.g., rain in image data) and the latent variables to which they are encoded. Although previous literature has focused on weakly-supervised disentanglement on simple datasets with known and independent generative factors. In practice, achieving full disentanglement through weak supervision is impossible for complex datasets, such as Carla, with unknown and abstract generative factors. As a result, we propose an OOD reasoning framework that learns a partially disentangled VAE to reason about complex datasets. Our framework consists of three steps: partitioning data based on observed generative factors, training a VAE as a logic tensor network that satisfies disentanglement rules, and run-time OOD reasoning. We evaluate our approach on the Carla dataset and compare the results against three state-of-the-art methods. We found that our framework outperformed these methods in terms of disentanglement and end-to-end OOD reasoning.

Aditya Bansal, Michael Yuhas, Arvind Easwaran

Out-of-distribution (OOD) detectors can act as safety monitors in embedded cyber-physical systems by identifying samples outside a machine learning model's training distribution to prevent potentially unsafe actions. However, OOD detectors are often implemented using deep neural networks, which makes it difficult to meet real-time deadlines on embedded systems with memory and power constraints. We consider the class of variational autoencoder (VAE) based OOD detectors where OOD detection is performed in latent space, and apply quantization, pruning, and knowledge distillation. These techniques have been explored for other deep models, but no work has considered their combined effect on latent space OOD detection. While these techniques increase the VAE's test loss, this does not correspond to a proportional decrease in OOD detection performance and we leverage this to develop lean OOD detectors capable of real-time inference on embedded CPUs and GPUs. We propose a design methodology that combines all three compression techniques and yields a significant decrease in memory and execution time while maintaining AUROC for a given OOD detector. We demonstrate this methodology with two existing OOD detectors on a Jetson Nano and reduce GPU and CPU inference time by 20% and 28% respectively while keeping AUROC within 5% of the baseline.

Archit Gupta, Arvind Easwaran

Duckiebots are low-cost mobile robots that are widely used in the fields of research and education. Although there are existing self-driving algorithms for the Duckietown platform, they are either too complex or perform too poorly to navigate a multi-lane track. Moreover, it is essential to give memory and computational resources to a Duckiebot so it can perform additional tasks such as out-of-distribution input detection. In order to satisfy these constraints, we built a low-cost autonomous driving algorithm capable of driving on a two-lane track. The algorithm uses traditional computer vision techniques to identify the central lane on the track and obtain the relevant steering angle. The steering is then controlled by a PID controller that smoothens the movement of the Duckiebot. The performance of the algorithm was compared to that of the NeurIPS 2018 AI Driving Olympics (AIDO) finalists, and it outperformed all but one finalists. The two main contributions of our algorithm are its low computational requirements and very quick set-up, with ongoing efforts to make it more reliable.

Zahra Rahiminasab, Michael Yuhas, Arvind Easwaran

Recently, the disentangled latent space of a variational autoencoder (VAE) has been used to reason about multi-label out-of-distribution (OOD) test samples that are derived from different distributions than training samples. Disentangled latent space means having one-to-many maps between latent dimensions and generative factors or important characteristics of an image. This paper proposes a disentangled distilled encoder (DDE) framework to decrease the OOD reasoner size for deployment on resource-constrained devices while preserving disentanglement. DDE formalizes student-teacher distillation for model compression as a constrained optimization problem while preserving disentanglement with disentanglement constraints. Theoretical guarantees for disentanglement during distillation based on Rademacher complexity are established. The approach is evaluated empirically by deploying the compressed model on an NVIDIA

Eduardo de Conto, Blaise Genest, Arvind Easwaran et al.

Digital twins (DTs) are increasingly utilized to monitor, manage, and optimize complex systems across various domains, including civil engineering. A core requirement for an effective DT is to act as a fast, accurate, and maintainable surrogate of its physical counterpart, the physical twin (PT). To this end, machine learning (ML) is frequently employed to (i) construct real-time DT prototypes using efficient reduced-order models (ROMs) derived from high-fidelity simulations of the PT's nominal behavior, and (ii) specialize these prototypes into DT instances by leveraging historical sensor data from the target PT. Despite the broad applicability of ML, its use in DT engineering remains largely ad hoc. Indeed, while conventional ML pipelines often train a single model for a specific task, DTs typically require multiple, task- and domain-dependent models. Thus, a more structured approach is required to design DTs. In this paper, we introduce DesCartes Builder, an open-source tool to enable the systematic engineering of ML-based pipelines for real-time DT prototypes and DT instances. The tool leverages an open and flexible visual data flow paradigm to facilitate the specification, composition, and reuse of ML models. It also integrates a library of parameterizable core operations and ML algorithms tailored for DT design. We demonstrate the effectiveness and usability of DesCartes Builder through a civil engineering use case involving the design of a real-time DT prototype to predict the plastic strain of a structure.

Subrat Prasad Panda, Blaise Genest, Arvind Easwaran

Decision Trees (DTs) are widely used in safety-critical domains such as medical diagnosis, valued for their interpretability and effectiveness on tabular data. However, training accurate oblique DTs is challenging due to complex optimization landscapes and overfitting risks, particularly in regression. Recent advances have introduced differentiable formulations that enable gradient-based training and joint optimization of decision boundaries and leaf regressors. Yet, existing approaches typically rely on approximations, either through probabilistic softening of boundaries (soft DTs) or quantized gradients such as the Straight-Through Estimator (STE). To overcome these limitations, we propose DTSemNet, a novel, semantically equivalent, and invertible representation of hard oblique DTs as neural networks. DTSemNet enables end-to-end training with standard gradient descent, eliminating the need for approximations in both classification and regression. While classification aligns naturally with this formulation, regression remains challenging due to the joint optimization of internal nodes and leaf regressors. To address this, we analyze the limitations of STE and introduce an annealed Top-k method that provides accurate gradient signals without approximation. Extensive experiments on classification and regression benchmarks show that DTSemNet-trained oblique DTs outperform state-of-the-art differentiable DTs. Furthermore, we demonstrate that DTSemNet can serve as programmatic DT policies in reinforcement learning environments, thereby broadening their applicability.

Xiang Fang, Arvind Easwaran, Blaise Genest et al.

Previous OOD detection systems only focus on the semantic gap between ID and OOD samples. Besides the semantic gap, we are faced with two additional gaps: the domain gap between source and target domains, and the class-imbalance gap between different classes. In fact, similar objects from different domains should belong to the same class. In this paper, we introduce a realistic yet challenging setting: class-imbalanced cross-domain OOD detection (CCOD), which contains a well-labeled (but usually small) source set for training and conducts OOD detection on an unlabeled (but usually larger) target set for testing. We do not assume that the target domain contains only OOD classes or that it is class-balanced: the distribution among classes of the target dataset need not be the same as the source dataset. To tackle this challenging setting with an OOD detection system, we propose a novel uncertainty-aware adaptive semantic alignment (UASA) network based on a prototype-based alignment strategy. Specifically, we first build label-driven prototypes in the source domain and utilize these prototypes for target classification to close the domain gap. Rather than utilizing fixed thresholds for OOD detection, we generate adaptive sample-wise thresholds to handle the semantic gap. Finally, we conduct uncertainty-aware clustering to group semantically similar target samples to relieve the class-imbalance gap. Extensive experiments on three challenging benchmarks demonstrate that our proposed UASA outperforms state-of-the-art methods by a large margin.

Mohit Prashant, Arvind Easwaran, Suman Das et al.

An issue concerning the use of deep reinforcement learning (RL) agents is whether they can be trusted to perform reliably when deployed, as training environments may not reflect real-life environments. Anticipating instances outside their training scope, learning-enabled systems are often equipped with out-of-distribution (OOD) detectors that alert when a trained system encounters a state it does not recognize or in which it exhibits uncertainty. There exists limited work conducted on the problem of OOD detection within RL, with prior studies being unable to achieve a consensus on the definition of OOD execution within the context of RL. By framing our problem using a Markov Decision Process, we assume there is a transition distribution mapping each state-action pair to another state with some probability. Based on this, we consider the following definition of OOD execution within RL: A transition is OOD if its probability during real-life deployment differs from the transition distribution encountered during training. As such, we utilize conditional variational autoencoders (CVAE) to approximate the transition dynamics of the training environment and implement a conformity-based detector using reconstruction loss that is able to guarantee OOD detection with a pre-determined confidence level. We evaluate our detector by adapting existing benchmarks and compare it with existing OOD detection models for RL.

Xiang Fang, Arvind Easwaran, Blaise Genest et al.

This paper focuses on a significant yet challenging task: out-of-distribution detection (OOD detection), which aims to distinguish and reject test samples with semantic shifts, so as to prevent models trained on in-distribution (ID) data from producing unreliable predictions. Although previous works have made decent success, they are ineffective for real-world challenging applications since these methods simply regard all unlabeled data as OOD data and ignore the case that different datasets have different label granularity. For example, "cat" on CIFAR-10 and "tabby cat" on Tiny-ImageNet share the same semantics but have different labels due to various label granularity. To this end, in this paper, we propose a novel Adaptive Hierarchical Graph Cut network (AHGC) to deeply explore the semantic relationship between different images. Specifically, we construct a hierarchical KNN graph to evaluate the similarities between different images based on the cosine similarity. Based on the linkage and density information of the graph, we cut the graph into multiple subgraphs to integrate these semantics-similar samples. If the labeled percentage in a subgraph is larger than a threshold, we will assign the label with the highest percentage to unlabeled images. To further improve the model generalization, we augment each image into two augmentation versions, and maximize the similarity between the two versions. Finally, we leverage the similarity score for OOD detection. Extensive experiments on two challenging benchmarks (CIFAR- 10 and CIFAR-100) illustrate that in representative cases, AHGC outperforms state-of-the-art OOD detection methods by 81.24% on CIFAR-100 and by 40.47% on CIFAR-10 in terms of "FPR95", which shows the effectiveness of our AHGC.

Mohit Prashant, Arvind Easwaran

In this study, we derive Probably Approximately Correct (PAC) bounds on the asymptotic sample-complexity for RL within the infinite-horizon Markov Decision Process (MDP) setting that are sharper than those in existing literature. The premise of our study is twofold: firstly, the further two states are from each other, transition-wise, the less relevant the value of the first state is when learning the $ε$-optimal value of the second; secondly, the amount of 'effort', sample-complexity-wise, expended in learning the $ε$-optimal value of a state is independent of the number of samples required to learn the $ε$-optimal value of a second state that is a sufficient number of transitions away from the first. Inversely, states within each other's vicinity have values that are dependent on each other and will require a similar number of samples to learn. By approximating the original MDP using smaller MDPs constructed using subsets of the original's state-space, we are able to reduce the sample-complexity by a logarithmic factor to $O(SA \log A)$ timesteps, where $S$ and $A$ are the state and action space sizes. We are able to extend these results to an infinite-horizon, model-free setting by constructing a PAC-MDP algorithm with the aforementioned sample-complexity. We conclude with showing how significant the improvement is by comparing our algorithm against prior work in an experimental setting.

Xiang Fang, Arvind Easwaran, Blaise Genest

Out-of-distribution (OOD) detection attempts to distinguish outlier samples to prevent models trained on the in-distribution (ID) dataset from producing unavailable outputs. Most OOD detection methods require many IID samples for training, which seriously limits their real-world applications. To this end, we target a challenging setting: few-shot OOD detection, where {Only a few {\em labeled ID} samples are available.} Therefore, few-shot OOD detection is much more challenging than the traditional OOD detection setting. Previous few-shot OOD detection works ignore the distinct diversity between different classes. In this paper, we propose a novel network: Adaptive Multi-prompt Contrastive Network (AMCN), which adapts the ID-OOD separation boundary by learning inter- and intra-class distribution. To compensate for the absence of OOD and scarcity of ID {\em image samples}, we leverage CLIP, connecting text with images, engineering learnable ID and OOD {\em textual prompts}. Specifically, we first generate adaptive prompts (learnable ID prompts, label-fixed OOD prompts and label-adaptive OOD prompts). Then, we generate an adaptive class boundary for each class by introducing a class-wise threshold. Finally, we propose a prompt-guided ID-OOD separation module to control the margin between ID and OOD prompts. Experimental results show that AMCN outperforms other state-of-the-art works.

Xinwei Gao, Arambam James Singh, Gangadhar Royyuru et al.

Lane keeping in autonomous driving systems requires scenario-specific weight tuning for different objectives. We formulate lane-keeping as a constrained reinforcement learning problem, where weight coefficients are automatically learned along with the policy, eliminating the need for scenario-specific tuning. Empirically, our approach outperforms traditional RL in efficiency and reliability. Additionally, real-world demonstrations validate its practical value for real-world autonomous driving.

Eduardo de Conto, Blaise Genest, Arvind Easwaran

The development of digital twins (DTs) for physical systems increasingly leverages artificial intelligence (AI), particularly for combining data from different sources or for creating computationally efficient, reduced-dimension models. Indeed, even in very different application domains, twinning employs common techniques such as model order reduction and modelization with hybrid data (that is, data sourced from both physics-based models and sensors). Despite this apparent generality, current development practices are ad-hoc, making the design of AI pipelines for digital twinning complex and time-consuming. Here we propose Function+Data Flow (FDF), a domain-specific language (DSL) to describe AI pipelines within DTs. FDF aims to facilitate the design and validation of digital twins. Specifically, FDF treats functions as first-class citizens, enabling effective manipulation of models learned with AI. We illustrate the benefits of FDF on two concrete use cases from different domains: predicting the plastic strain of a structure and modeling the electromagnetic behavior of a bearing.

Shreyas Ramakrishna, Zahra Rahiminasab, Gabor Karsai et al.

Deep Neural Networks are actively being used in the design of autonomous Cyber-Physical Systems (CPSs). The advantage of these models is their ability to handle high-dimensional state-space and learn compact surrogate representations of the operational state spaces. However, the problem is that the sampled observations used for training the model may never cover the entire state space of the physical environment, and as a result, the system will likely operate in conditions that do not belong to the training distribution. These conditions that do not belong to training distribution are referred to as Out-of-Distribution (OOD). Detecting OOD conditions at runtime is critical for the safety of CPS. In addition, it is also desirable to identify the context or the feature(s) that are the source of OOD to select an appropriate control action to mitigate the consequences that may arise because of the OOD condition. In this paper, we study this problem as a multi-labeled time series OOD detection problem over images, where the OOD is defined both sequentially across short time windows (change points) as well as across the training data distribution. A common approach to solving this problem is the use of multi-chained one-class classifiers. However, this approach is expensive for CPSs that have limited computational resources and require short inference times. Our contribution is an approach to design and train a single $β$-Variational Autoencoder detector with a partially disentangled latent space sensitive to variations in image features. We use the feature sensitive latent variables in the latent space to detect OOD images and identify the most likely feature(s) responsible for the OOD. We demonstrate our approach using an Autonomous Vehicle in the CARLA simulator and a real-world automotive dataset called nuImages.

Yeli Feng, Daniel Jun Xian Ng, Arvind Easwaran

Uncertainties in machine learning are a significant roadblock for its application in safety-critical cyber-physical systems (CPS). One source of uncertainty arises from distribution shifts in the input data between training and test scenarios. Detecting such distribution shifts in real-time is an emerging approach to address the challenge. The high dimensional input space in CPS applications involving imaging adds extra difficulty to the task. Generative learning models are widely adopted for the task, namely out-of-distribution (OoD) detection. To improve the state-of-the-art, we studied existing proposals from both machine learning and CPS fields. In the latter, safety monitoring in real-time for autonomous driving agents has been a focus. Exploiting the spatiotemporal correlation of motion in videos, we can robustly detect hazardous motion around autonomous driving agents. Inspired by the latest advances in the Variational Autoencoder (VAE) theory and practice, we tapped into the prior knowledge in data to further boost OoD detection's robustness. Comparison studies over nuScenes and Synthia data sets show our methods significantly improve detection capabilities of OoD factors unique to driving scenarios, 42% better than state-of-the-art approaches. Our model also generalized near-perfectly, 97% better than the state-of-the-art across the real-world and simulation driving data sets experimented. Finally, we customized one proposed method into a twin-encoder model that can be deployed to resource limited embedded devices for real-time OoD detection. Its execution time was reduced over four times in low-precision 8-bit integer inference, while detection capability is comparable to its corresponding floating-point model.

Yeli Feng, Arvind Easwaran

Highly complex deep learning models are increasingly integrated into modern cyber-physical systems (CPS), many of which have strict safety requirements. One problem arising from this is that deep learning lacks interpretability, operating as a black box. The reliability of deep learning is heavily impacted by how well the model training data represents runtime test data, especially when the input space dimension is high as natural images. In response, we propose a robust out-of-distribution (OOD) detection framework. Our approach detects unusual movements from driving video in real-time by combining classical optic flow operation with representation learning via variational autoencoder (VAE). We also design a method to locate OOD factors in images. Evaluation on a driving simulation data set shows that our approach is statistically more robust than related works.

Michael Yuhas, Yeli Feng, Daniel Jun Xian Ng et al.

Machine learning (ML) is actively finding its way into modern cyber-physical systems (CPS), many of which are safety-critical real-time systems. It is well known that ML outputs are not reliable when testing data are novel with regards to model training and validation data, i.e., out-of-distribution (OOD) test data. We implement an unsupervised deep neural network-based OOD detector on a real-time embedded autonomous Duckiebot and evaluate detection performance. Our OOD detector produces a success rate of 87.5% for emergency stopping a Duckiebot on a braking test bed we designed. We also provide case analysis on computing resource challenges specific to the Robot Operating System (ROS) middleware on the Duckiebot.

Omar Al-Bataineh, Daniel Jun Xian Ng, Arvind Easwaran

This paper considers the problem of decentralized monitoring of a class of non-functional properties (NFPs) with quantitative operators, namely cumulative cost properties. The decentralized monitoring of NFPs can be a non-trivial task for several reasons: (i) they are typically expressed at a high abstraction level where inter-event dependencies are hidden, (ii) NFPs are difficult to be monitored in a decentralized way, and (iii) lack of effective decomposition techniques. We address these issues by providing a formal framework for decentralised monitoring of LTL formulas with quantitative operators. The presented framework employs the tableau construction and a formula unwinding technique (i.e., a transformation technique that preserves the semantics of the original formula) to split and distribute the input LTL formula and the corresponding quantitative constraint in a way such that monitoring can be performed in a decentralised manner. The employment of these techniques allows processes to detect early violations of monitored properties and perform some corrective or recovery actions. We demonstrate the effectiveness of the presented framework using a case study based on a Fischertechnik training model,a sorting line which sorts tokens based on their color into storage bins. The analysis of the case study shows the effectiveness of the presented framework not only in early detection of violations, but also in developing failure recovery plans that can help to avoid serious impact of failures on the performance of the system.

Heejong Park, Arvind Easwaran, Sidharta Andalam

The recent advancement of information and communication technology makes digitalisation of an entire manufacturing shop-floor possible where physical processes are tightly intertwined with their cyber counterparts. This led to an emergence of a concept of digital twin, which is a realistic virtual copy of a physical object. Digital twin will be the key technology in Cyber-Physical Production Systems (CPPS) and its market is expected to grow significantly in the coming years. Nevertheless, digital twin is still relatively a new concept that people have different perspectives on its requirements, capabilities, and limitations. To better understand an effect of digital twin's operations, mitigate complexity of capturing dynamics of physical phenomena, and improve analysis and predictability, it is important to have a development tool with a strong semantic foundation that can accurately model, simulate, and synthesise the digital twin. This paper reviews current state-of-art on tools and developments of digital twin in manufacturing and discusses potential design challenges.

Heejong Park, Arvind Easwaran, Etienne Borde

In the fields of co-simulation and component-based modelling, designers import models as building blocks to create a composite model that provides more complex functionalities. Modelling tools perform instantaneous cycle detection (ICD) on the composite models having feedback loops to reject the models if the loops are mathematically unsound and to improve simulation performance. In this case, the analysis relies heavily on the availability of dependency information from the imported models. However, the cycle detection problem becomes harder when the model's input to output dependencies are mode-dependent, i.e. changes for certain events generated internally or externally as inputs. The number of possible modes created by composing such models increases significantly and unknown factors such as environmental inputs make the offline (statical) ICD a difficult task. In this paper, an online ICD method is introduced to address this issue for the models used in cyber-physical systems. The method utilises an oracle as a central source of information that can answer whether the individual models can make mode transition without creating instantaneous cycles. The oracle utilises three types of data-structures created offline that are adaptively chosen during online (runtime) depending on the frequency as well as the number of models that make mode transitions. During the analysis, the models used online are stalled from running, resulting in the discrepancy with the physical system. The objective is to detect an absence of the instantaneous cycle while minimising the stall time of the model simulation that is induced from the analysis. The benchmark results show that our method is an adequate alternative to the offline analysis methods and significantly reduces the analysis time.

Nitin Shivaraman, Seima Saki, Zhiwei Liu et al.

With rapid advancements in the Internet of Things (IoT) paradigm, electrical devices in the near future is expected to have IoT capabilities. This enables fine-grained tracking of individual energy consumption data of such devices, offering location-independent per-device billing. Thus, it is more fine-grained than the location-based metering of state-of-the-art infrastructure, which traditionally aggregates on a building or household level, defining the entity to be billed. However, such in-device energy metering is susceptible to manipulation and fraud. As a remedy, we propose a decentralized metering architecture that enables devices with IoT capabilities to measure their own energy consumption. In this architecture, the device-level consumption is additionally reported to a system-level aggregator that verifies distributed information and provides secure data storage using Blockchain, preventing data manipulation by untrusted entities. Using evaluations on an experimental testbed, we show that the proposed architecture supports device mobility and enables location-independent monitoring of energy consumption.

Rutvij H. Jhaveri, Rui Tan, Arvind Easwaran et al.

Recent technological advances have fostered the development of complex industrial cyber-physical systems which demand real-time communication with delay guarantees. The consequences of delay requirement violation in such systems may become increasingly severe. In this paper, we propose a contract-based fault-resilient methodology which aims at managing the communication delays of real-time flows in industries. With this objective, we present a light-weight mechanism to estimate end-to-end delay in the network in which the clocks of the switches are not synchronized. The mechanism aims at providing high level of accuracy with lower communication overhead. We then propose a contract-based framework using software-defined networking where the components are associated with delay contracts and a resilience manager. The proposed resilience management framework contains: (1) contracts which state guarantees about components behaviors, (2) observers which are responsible to detect contract failure (fault), (3) monitors to detect events such as run-time changes in the delay requirements and link failure, (4) control logic to take suitable decisions based on the type of the fault, (5) resilience manager to decide response strategies containing the best course of action as per the control logic decision. Finally, we present a delay-aware path finding algorithm which is used to route/reroute the real-time flows to provide resiliency in the case of faults and, to adapt to the changes in the network state. Performance of the proposed framework is evaluated with the Ryu SDN controller and Mininet network emulator.

Zhiheng Xu, Daniel Jun Xian Ng, Arvind Easwaran

With the growing scale of Cyber-Physical Systems (CPSs), it is challenging to maintain their stability under all operating conditions. How to reduce the downtime and locate the failures becomes a core issue in system design. In this paper, we employ a hierarchical contract-based resilience framework to guarantee the stability of CPS. In this framework, we use Assume Guarantee (A-G) contracts to monitor the non-functional properties of individual components (e.g., power and latency), and hierarchically compose such contracts to deduce information about faults at the system level. The hierarchical contracts enable rapid fault detection in large-scale CPS. However, due to the vast number of components in CPS, manually designing numerous contracts and the hierarchy becomes challenging. To address this issue, we propose a technique to automatically decompose a root contract into multiple lower-level contracts depending on I/O dependencies between components. We then formulate a multi-objective optimization problem to search the optimal parameters of each lower-level contract. This enables automatic contract refinement taking into consideration the communication overhead between components. Finally, we use a case study from the manufacturing domain to experimentally demonstrate the benefits of the proposed framework.

Daniel Jun Xian Ng, Arvind Easwaran, Sidharta Andalam

This demonstration presents a framework for building a resilient Cyber-Physical Systems (CPS) cyber-infrastructure through the use of hierarchical parametric assume-guarantee contracts. A Fischertechnik Sorting Line with Color Detection training model is used to showcase our framework.

Sidharta Andalam, Daniel Jun Xian Ng, Arvind Easwaran et al.

Industrial cyber-infrastructure is normally a multilayered architecture. The purpose of the layered architecture is to hide complexity and allow independent evolution of the layers. In this paper, we argue that this traditional strict layering results in poor transparency across layers affecting the ability to significantly improve resiliency. We propose a contract-based methodology where components across and within the layers of the cyber-infrastructure are associated with contracts and a light-weight resilience manager. This allows the system to detect faults (contract violation monitored using observers) and react (change contracts dynamically) effectively. It results in (1) improving transparency across layers; helps resiliency, (2) decoupling fault-handling code from application code; helps code maintenance, (3) systematically generate error-free fault handling code; reduces development time. Using an industrial case study, we demonstrate the proposed methodology.

Sidharta Andalam, Daniel Jun Xian Ng, Arvind Easwaran et al.

As the industrial cyber-infrastructure become increasingly important to realise the objectives of Industry~4.0, the consequence of disruption due to internal or external faults become increasingly severe. Thus there is a need for a resilient infrastructure. In this paper, we propose a contract-based methodology where components across layers of the cyber-infrastructure are associated with contracts and a light-weight resilience manager. This allows the system to detect faults (contract violation monitored using observers) and react (change contracts dynamically) effectively.

Mohammad Shihabul Haque, Daniel Jun Xian Ng, Arvind Easwaran et al.

Orchestrated collaborative effort of physical and cyber components to satisfy given requirements is the central concept behind Cyber-Physical Systems (CPS). To duly ensure the performance of components, a software-based resilience manager is a flexible choice to detect and recover from faults quickly. However, a single resilience manager, placed at the centre of the system to deal with every fault, suffers from decision-making overburden; and therefore, is out of the question for distributed large-scale CPS. On the other hand, prompt detection of failures and efficient recovery from them are challenging for decentralised resilience managers. In this regard, we present a novel resilience management framework that utilises the concept of management hierarchy. System design contracts play a key role in this framework for prompt fault-detection and recovery. Besides the details of the framework, an Industry 4.0 related test case is presented in this article to provide further insights.

Vijaya Kumar Sundar, Shreyas Ramakrishna, Zahra Rahiminasab et al.

Learning Enabled Components (LECs) are widely being used in a variety of perception based autonomy tasks like image segmentation, object detection, end-to-end driving, etc. These components are trained with large image datasets with multimodal factors like weather conditions, time-of-day, traffic-density, etc. The LECs learn from these factors during training, and while testing if there is variation in any of these factors, the components get confused resulting in low confidence predictions. The images with factors not seen during training is commonly referred to as Out-of-Distribution (OOD). For safe autonomy it is important to identify the OOD images, so that a suitable mitigation strategy can be performed. Classical one-class classifiers like SVM and SVDD are used to perform OOD detection. However, the multiple labels attached to the images in these datasets, restricts the direct application of these techniques. We address this problem using the latent space of the $β$-Variational Autoencoder ($β$-VAE). We use the fact that compact latent space generated by an appropriately selected $β$-VAE will encode the information about these factors in a few latent variables, and that can be used for computationally inexpensive detection. We evaluate our approach on the nuScenes dataset, and our results shows the latent space of $β$-VAE is sensitive to encode changes in the values of the generative factor.

Xiaozhe Gu, Arvind Easwaran

Machine learning (ML) techniques are increasingly applied to decision-making and control problems in Cyber-Physical Systems among which many are safety-critical, e.g., chemical plants, robotics, autonomous vehicles. Despite the significant benefits brought by ML techniques, they also raise additional safety issues because 1) most expressive and powerful ML models are not transparent and behave as a black box and 2) the training data which plays a crucial role in ML safety is usually incomplete. An important technique to achieve safety for ML models is "Safe Fail", i.e., a model selects a reject option and applies the backup solution, a traditional controller or a human operator for example, when it has low confidence in a prediction. Data-driven models produced by ML algorithms learn from training data, and hence they are only as good as the examples they have learnt. As pointed in [17], ML models work well in the "training space" (i.e., feature space with sufficient training data), but they could not extrapolate beyond the training space. As observed in many previous studies, a feature space that lacks training data generally has a much higher error rate than the one that contains sufficient training samples [31]. Therefore, it is essential to identify the training space and avoid extrapolating beyond the training space. In this paper, we propose an efficient Feature Space Partitioning Tree (FSPT) to address this problem. Using experiments, we also show that, a strong relationship exists between model performance and FSPT score.