Conflict-Based Search (CBS) is a powerful algorithmic framework for optimally solving classical multi-agent path finding (MAPF) problems, where time is discretized into the time steps. Continuous-time CBS (CCBS) is a recently proposed version of CBS that guarantees optimal solutions without the need to discretize time. However, the scalability of CCBS is limited because it does not include any known improvements of CBS. In this paper, we begin to close this gap and explore how to adapt successful CBS improvements, namely, prioritizing conflicts (PC), disjoint splitting (DS), and high-level heuristics, to the continuous time setting of CCBS. These adaptions are not trivial, and require careful handling of different types of constraints, applying a generalized version of the Safe interval path planning (SIPP) algorithm, and extending the notion of cardinal conflicts. We evaluate the effect of the suggested enhancements by running experiments both on general graphs and $2^k$-neighborhood grids. CCBS with these improvements significantly outperforms vanilla CCBS, solving problems with almost twice as many agents in some cases and pushing the limits of multiagent path finding in continuous-time domains.

While the quality of GAN image synthesis has improved tremendously in recent years, our ability to control and condition the output is still limited. Focusing on StyleGAN, we introduce a simple and effective method for making local, semantically-aware edits to a target output image. This is accomplished by borrowing elements from a source image, also a GAN output, via a novel manipulation of style vectors. Our method requires neither supervision from an external model, nor involves complex spatial morphing operations. Instead, it relies on the emergent disentanglement of semantic objects that is learned by StyleGAN during its training. Semantic editing is demonstrated on GANs producing human faces, indoor scenes, cats, and cars. We measure the locality and photorealism of the edits produced by our method, and find that it accomplishes both.

In fluid physics, data-driven models to enhance or accelerate solution methods are becoming increasingly popular for many application domains, such as alternatives to turbulence closures, system surrogates, or for new physics discovery. In the context of reduced order models of high-dimensional time-dependent fluid systems, machine learning methods grant the benefit of automated learning from data, but the burden of a model lies on its reduced-order representation of both the fluid state and physical dynamics. In this work, we build a physics-constrained, data-driven reduced order model for the Navier-Stokes equations to approximate spatio-temporal turbulent fluid dynamics. The model design choices mimic numerical and physical constraints by, for example, implicitly enforcing the incompressibility constraint and utilizing continuous Neural Ordinary Differential Equations for tracking the evolution of the differential equation. We demonstrate this technique on three-dimensional, moderate Reynolds number turbulent fluid flow. In assessing the statistical quality and characteristics of the machine-learned model through rigorous diagnostic tests, we find that our model is capable of reconstructing the dynamics of the flow over large integral timescales, favoring accuracy at the larger length scales. More significantly, comprehensive diagnostics suggest that physically-interpretable model parameters, corresponding to the representations of the fluid state and dynamics, have attributable and quantifiable impact on the quality of the model predictions and computational complexity.

We propose replacing scene text in videos using deep style transfer and learned photometric transformations.Building on recent progress on still image text replacement,we present extensions that alter text while preserving the appearance and motion characteristics of the original video.Compared to the problem of still image text replacement,our method addresses additional challenges introduced by video, namely effects induced by changing lighting, motion blur, diverse variations in camera-object pose over time,and preservation of temporal consistency. We parse the problem into three steps. First, the text in all frames is normalized to a frontal pose using a spatio-temporal trans-former network. Second, the text is replaced in a single reference frame using a state-of-art still-image text replacement method. Finally, the new text is transferred from the reference to remaining frames using a novel learned image transformation network that captures lighting and blur effects in a temporally consistent manner. Results on synthetic and challenging real videos show realistic text trans-fer, competitive quantitative and qualitative performance,and superior inference speed relative to alternatives. We introduce new synthetic and real-world datasets with paired text objects. To the best of our knowledge this is the first attempt at deep video text replacement.

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.

The Winograd Schema Challenge - a set of twin sentences involving pronoun reference disambiguation that seem to require the use of commonsense knowledge - was proposed by Hector Levesque in 2011. By 2019, a number of AI systems, based on large pre-trained transformer-based language models and fine-tuned on these kinds of problems, achieved better than 90% accuracy. In this paper, we review the history of the Winograd Schema Challenge and discuss the lasting contributions of the flurry of research that has taken place on the WSC in the last decade. We discuss the significance of various datasets developed for WSC, and the research community's deeper understanding of the role of surrogate tasks in assessing the intelligence of an AI system.

We present a case study of artificial intelligence techniques applied to the control of production printing equipment. Like many other real-world applications, this complex domain requires high-speed autonomous decision-making and robust continual operation. To our knowledge, this work represents the first successful industrial application of embedded domain-independent temporal planning. Our system handles execution failures and multi-objective preferences. At its heart is an on-line algorithm that combines techniques from state-space planning and partial-order scheduling. We suggest that this general architecture may prove useful in other applications as more intelligent systems operate in continual, on-line settings. Our system has been used to drive several commercial prototypes and has enabled a new product architecture for our industrial partner. When compared with state-of-the-art off-line planners, our system is hundreds of times faster and often finds better plans. Our experience demonstrates that domain-independent AI planning based on heuristic search can flexibly handle time, resources, replanning, and multiple objectives in a high-speed practical application without requiring hand-coded control knowledge.

Graphlets are induced subgraphs of a large network and are important for understanding and modeling complex networks. Despite their practical importance, graphlets have been severely limited to applications and domains with relatively small graphs. Most previous work has focused on exact algorithms, however, it is often too expensive to compute graphlets exactly in massive networks with billions of edges, and finding an approximate count is usually sufficient for many applications. In this work, we propose an unbiased graphlet estimation framework that is (a) fast with significant speedups compared to the state-of-the-art, (b) parallel with nearly linear-speedups, (c) accurate with <1% relative error, (d) scalable and space-efficient for massive networks with billions of edges, and (e) flexible for a variety of real-world settings, as well as estimating macro and micro-level graphlet statistics (e.g., counts) of both connected and disconnected graphlets. In addition, an adaptive approach is introduced that finds the smallest sample size required to obtain estimates within a given user-defined error bound. On 300 networks from 20 domains, we obtain <1% relative error for all graphlets. This is significantly more accurate than existing methods while using less data. Moreover, it takes a few seconds on billion edge graphs (as opposed to days/weeks). These are by far the largest graphlet computations to date.

Low phase noise lasers based on the combination of III-V semiconductors and silicon photonics are well established in the near-infrared spectral regime. Recent advances in the development of low-loss silicon nitride-based photonic integrated resonators have allowed to outperform bulk external diode and fiber lasers in both phase noise and frequency agility in the 1550 nm-telecommunication window. Here, we demonstrate for the first time a hybrid integrated laser composed of a gallium nitride (GaN) based laser diode and a silicon nitride photonic chip-based microresonator operating at record low wavelengths as low as 410 nm in the near-ultraviolet wavelength region suitable for addressing atomic transitions of atoms and ions used in atomic clocks, quantum computing, or for underwater LiDAR. Using self-injection locking to a high Q (0.4 $\times$ 10$^6$) photonic integrated microresonator we observe a phase noise reduction of the Fabry-P\'erot laser at 461 nm by a factor greater than 100$\times$, limited by the device quality factor and back-reflection.

The underlying physics of quantum mechanics has been discussed for decades without an agreed resolution to many questions. The measurement problem, wave function collapse and entangled states are mired in complexity and the difficulty of even agreeing on a definition of a measurement. This paper explores a completely different aspect of quantum mechanics, the physical mechanism for phonon quantization, to gain insights into quantum mechanics that may help address the broader questions.

Our research aims at developing intelligent systems to reduce the transportation-related energy expenditure of a large city by influencing individual behavior. We introduce COPTER - an intelligent travel assistant that evaluates multi-modal travel alternatives to find a plan that is acceptable to a person given their context and preferences. We propose a formulation for acceptable planning that brings together ideas from AI, machine learning, and economics. This formulation has been incorporated in COPTER that produces acceptable plans in real-time. We adopt a novel empirical evaluation framework that combines human decision data with a high fidelity multi-modal transportation simulation to demonstrate a 4\% energy reduction and 20\% delay reduction in a realistic deployment scenario in Los Angeles, California, USA.

Our research aims to develop interactive, social agents that can coach people to learn new tasks, skills, and habits. In this paper, we focus on coaching sedentary, overweight individuals (i.e., trainees) to exercise regularly. We employ adaptive goal setting in which the intelligent health coach generates, tracks, and revises personalized exercise goals for a trainee. The goals become incrementally more difficult as the trainee progresses through the training program. Our approach is model-based - the coach maintains a parameterized model of the trainee's aerobic capability that drives its expectation of the trainee's performance. The model is continually revised based on trainee-coach interactions. The coach is embodied in a smartphone application, NutriWalking, which serves as a medium for coach-trainee interaction. We adopt a task-centric evaluation approach for studying the utility of the proposed algorithm in promoting regular aerobic exercise. We show that our approach can adapt the trainee program not only to several trainees with different capabilities, but also to how a trainee's capability improves as they begin to exercise more. Experts rate the goals selected by the coach better than other plausible goals, demonstrating that our approach is consistent with clinical recommendations. Further, in a 6-week observational study with sedentary participants, we show that the proposed approach helps increase exercise volume performed each week.

This paper presents a general graph representation learning framework called DeepGL for learning deep node and edge representations from large (attributed) graphs. In particular, DeepGL begins by deriving a set of base features (e.g., graphlet features) and automatically learns a multi-layered hierarchical graph representation where each successive layer leverages the output from the previous layer to learn features of a higher-order. Contrary to previous work, DeepGL learns relational functions (each representing a feature) that generalize across-networks and therefore useful for graph-based transfer learning tasks. Moreover, DeepGL naturally supports attributed graphs, learns interpretable features, and is space-efficient (by learning sparse feature vectors). In addition, DeepGL is expressive, flexible with many interchangeable components, efficient with a time complexity of $\mathcal{O}(|E|)$, and scalable for large networks via an efficient parallel implementation. Compared with the state-of-the-art method, DeepGL is (1) effective for across-network transfer learning tasks and attributed graph representation learning, (2) space-efficient requiring up to 6x less memory, (3) fast with up to 182x speedup in runtime performance, and (4) accurate with an average improvement of 20% or more on many learning tasks.

Turning is the most commonly available and least expensive machining operation, in terms of both machine-hour rates and tool insert prices. A practical CNC process planner has to maximize the utilization of turning, not only to attain precision requirements for turnable surfaces, but also to minimize the machining cost, while non-turnable features can be left for other processes such as milling. Most existing methods rely on separation of surface features and lack guarantees when analyzing complex parts with interacting features. In a previous study, we demonstrated successful implementation of a feature-free milling process planner based on configuration space methods used for spatial reasoning and AI search for planning. This paper extends the feature-free method to include turning process planning. It opens up the opportunity for seamless integration of turning actions into a mill-turn process planner that can handle arbitrarily complex shapes with or without a priori knowledge of feature semantics.

Represented as graphs, real networks are intricate combinations of order and disorder. Fixing some of the structural properties of network models to their values observed in real networks, many other properties appear as statistical consequences of these fixed observables, plus randomness in other respects. Here we employ the $dk$-series, a complete set of basic characteristics of the network structure, to study the statistical dependencies between different network properties. We consider six real networks---the Internet, US airport network, human protein interactions, technosocial web of trust, English word network, and an fMRI map of the human brain---and find that many important local and global structural properties of these networks are closely reproduced by $dk$-random graphs whose degree distributions, degree correlations, and clustering are as in the corresponding real network. We discuss important conceptual, methodological, and practical implications of this evaluation of network randomness, and release software to generate $dk$-random graphs.

Graph classification is a problem with practical applications in many different domains. Most of the existing methods take the entire graph into account when calculating graph features. In a graphlet-based approach, for instance, the entire graph is processed to get the total count of different graphlets or sub-graphs. In the real-world, however, graphs can be both large and noisy with discriminative patterns confined to certain regions in the graph only. In this work, we study the problem of attentional processing for graph classification. The use of attention allows us to focus on small but informative parts of the graph, avoiding noise in the rest of the graph. We present a novel RNN model, called the Graph Attention Model (GAM), that processes only a portion of the graph by adaptively selecting a sequence of "interesting" nodes. The model is equipped with an external memory component which allows it to integrate information gathered from different parts of the graph. We demonstrate the effectiveness of the model through various experiments.

There have been multiple attempts to demonstrate that quantum annealing and, in particular, quantum annealing on quantum annealing machines, has the potential to outperform current classical optimization algorithms implemented on CMOS technologies. The benchmarking of these devices has been controversial. Initially, random spin-glass problems were used, however, these were quickly shown to be not well suited to detect any quantum speedup. Subsequently, benchmarking shifted to carefully crafted synthetic problems designed to highlight the quantum nature of the hardware while (often) ensuring that classical optimization techniques do not perform well on them. Even worse, to date a true sign of improved scaling with the number of problem variables remains elusive when compared to classical optimization techniques. Here, we analyze the readiness of quantum annealing machines for real-world application problems. These are typically not random and have an underlying structure that is hard to capture in synthetic benchmarks, thus posing unexpected challenges for optimization techniques, both classical and quantum alike. We present a comprehensive computational scaling analysis of fault diagnosis in digital circuits, considering architectures beyond D-wave quantum annealers. We find that the instances generated from real data in multiplier circuits are harder than other representative random spin-glass benchmarks with a comparable number of variables. Although our results show that transverse-field quantum annealing is outperformed by state-of-the-art classical optimization algorithms, these benchmark instances are hard and small in the size of the input, therefore representing the first industrial application ideally suited for testing near-term quantum annealers and other quantum algorithmic strategies for optimization problems.

Architectures that implement the Common Model of Cognition - Soar, ACT-R, and Sigma - have a prominent place in research on cognitive modeling as well as on designing complex intelligent agents. In this paper, we explore how computational models of analogical processing can be brought into these architectures to enable concept acquisition from examples obtained interactively. We propose a new analogical concept memory for Soar that augments its current system of declarative long-term memories. We frame the problem of concept learning as embedded within the larger context of interactive task learning (ITL) and embodied language processing (ELP). We demonstrate that the analogical learning methods implemented in the proposed memory can quickly learn a diverse types of novel concepts that are useful not only in recognition of a concept in the environment but also in action selection. Our approach has been instantiated in an implemented cognitive system \textsc{Aileen} and evaluated on a simulated robotic domain.

In contrast to today's IP-based host-oriented Internet architecture, Information-Centric Networking (ICN) emphasizes content by making it directly addressable and routable. Named Data Networking (NDN) architecture is an instance of ICN that is being developed as a candidate next-generation Internet architecture. By opportunistically caching content within the network (in routers), NDN appears to be well-suited for large-scale content distribution and for meeting the needs of increasingly mobile and bandwidth-hungry applications that dominate today's Internet. One key feature of NDN is the requirement for each content object to be digitally signed by its producer. Thus, NDN should be, in principle, immune to distributing fake (aka "poisoned") content. However, in practice, this poses two challenges for detecting fake content in NDN routers: (1) overhead due to signature verification and certificate chain traversal, and (2) lack of trust context, i.e., determining which public keys are trusted to verify which content. Because of these issues, NDN does not force routers to verify content signatures, which makes the architecture susceptible to content poisoning attacks. This paper explores root causes of, and some cures for, content poisoning attacks in NDN. In the process, it becomes apparent that meaningful mitigation of content poisoning is contingent upon a network-layer trust management architecture, elements of which we construct while carefully justifying specific design choices. This work represents the initial effort towards comprehensive trust management for NDN.

In this paper, we propose PATO-a producibility-aware topology optimization (TO) framework to help efficiently explore the design space of components fabricated using metal additive manufacturing (AM), while ensuring manufacturability with respect to cracking. Specifically, parts fabricated through Laser Powder Bed Fusion are prone to defects such as warpage or cracking due to high residual stress values generated from the steep thermal gradients produced during the build process. Maturing the design for such parts and planning their fabrication can span months to years, often involving multiple handoffs between design and manufacturing engineers. PATO is based on the a priori discovery of crack-free designs, so that the optimized part can be built defect-free at the outset. To ensure that the design is crack free during optimization, producibility is explicitly encoded within the standard formulation of TO, using a crack index. Multiple crack indices are explored and using experimental validation, maximum shear strain index (MSSI) is shown to be an accurate crack index. Simulating the build process is a coupled, multi-physics computation and incorporating it in the TO loop can be computationally prohibitive. We leverage the current advances in deep convolutional neural networks and present a high-fidelity surrogate model based on an Attention-based U-Net architecture to predict the MSSI values as a spatially varying field over the part's domain. Further, we employ automatic differentiation to directly compute the gradient of maximum MSSI with respect to the input design variables and augment it with the performance-based sensitivity field to optimize the design while considering the trade-off between weight, manufacturability, and functionality. We demonstrate the effectiveness of the proposed method through benchmark studies in 3D as well as experimental validation.