The visual fog paradigm envisions tens of thousands of heterogeneous, camera-enabled edge devices distributed across the Internet, providing live sensing for a myriad of different visual processing applications. The scale, computational demands, and bandwidth needed for visual computing pipelines necessitates offloading intelligently to distributed computing infrastructure, including the cloud, Internet gateway devices, and the edge devices themselves. This paper focuses on the visual fog scheduling problem of assigning the visual computing tasks to various devices to optimize network utilization. We first prove this problem is NP-complete, and then formulate a practical, efficient solution. We demonstrate sub-minute computation time to optimally schedule 20,000 tasks across over 7,000 devices, and just 7-minute execution time to place 60,000 tasks across 20,000 devices, showing our approach is ready to meet the scale challenges introduced by visual fog.

Shortest path planning is a fundamental building block in many applications. Hence developing efficient methods for computing shortest paths in e.g. road or grid networks is an important challenge. The most successful techniques for fast query answering rely on preprocessing. But for many of these techniques it is not fully understood why they perform so remarkably well and theoretical justification for the empirical results is missing. An attempt to explain the excellent practical performance of preprocessing based techniques on road networks (as transit nodes, hub labels, or contraction hierarchies) in a sound theoretical way are parametrized analyses, e.g., considering the highway dimension or skeleton dimension of a graph. But these parameters tend to be large (order of Θ(√ n )) when the network contains grid-like substructures — which inarguably is the case for real-world road networks around the globe. In this paper, we use the very intuitive notion of bounded growth graphs to describe road networks and also grid graphs. We show that this model suffices to prove sublinear search spaces for the three above mentioned state-of-the-art shortest path planning techniques. For graphs with a large highway or skeleton dimension, our results turn out to be superior. Furthermore, our preprocessing methods are close to the ones used in practice and only require randomized polynomial time.

In this paper, we propose a novel SAT-based planning approach for hierarchical planning by introducing the SAT-based planner totSAT for the class of totally-ordered HTN planning problems. We use the same general approach as SAT planning for classical planning does: bound the problem, translate the problem into a formula, and if the formula is not satisfiable, increase the bound. In HTN planning, a suitable bound is the maximum depth of decomposition. We show how totally-ordered HTN planning problems can be translated into a SAT formula, given this bound. Furthermore, we have conducted an extensive empirical evaluation to compare our new planner against state-of-the-art HTN planners. It shows that our technique outperforms any of these systems.

We address the problem of mitigating congestion and preventing hotspots in busy water areas such as Singapore Straits and port waters. Increasing maritime traffic coupled with narrow waterways makes vessel schedule coordination for just-in-time arrival critical for navigational safety. Our contributions are: 1) We formulate the maritime traffic management problem based on the real case study of Singapore waters; 2) We model the problem as a variant of the resource-constrained project scheduling problem (RCPSP), and formulate mixed-integer and constraint programming (MIP/CP) formulations; 3) To improve the scalability, we develop a combinatorial Benders (CB) approach that is significantly more effective than standard MIP and CP formulations. We also develop symmetry breaking constraints and optimality cuts that further enhance the CB approach's effectiveness; 4) We develop a realistic maritime traffic simulator using electronic navigation charts of Singapore Straits. Our scheduling approach on synthetic problems and a real 55-day AIS dataset results in significant reduction of the traffic density while incurring minimal delays.

This paper defines a learning algorithm for plan grammars used for plan recognition. The algorithm learns Combinatory Categorial Grammars (CCGs) that capture the structure of plans from a set of successful plan execution traces paired with the goal of the actions. This work is motivated by past work on CCG learning algorithms for natural language processing, and is evaluated on five well know planning domains.

This paper proposes and evaluates Memory-Augmented Monte Carlo Tree Search (M-MCTS), which provides a new approach to exploit generalization in online real-time search. The key idea of M-MCTS is to incorporate MCTS with a memory structure, where each entry contains information of a particular state. This memory is used to generate an approximate value estimation by combining the estimations of similar states. We show that the memory based value approximation is better than the vanilla Monte Carlo estimation with high probability under mild conditions. We evaluate M-MCTS in the game of Go. Experimental results show that M-MCTS outperforms the original MCTS with the same number of simulations.

Scenario planning is a commonly used method by companies to develop their long-term plans. Scenario planning for risk management puts an added emphasis on identifying and managing emerging risk. While a variety of methods have been proposed for this purpose, we show that applying AI planning techniques to devise possible scenarios provides a unique advantage for scenario planning. Our system, the Scenario Planning Advisor (SPA), takes as input the relevant information from news and social media, representing key risk drivers, as well as the domain knowledge and generates scenarios that explain the key risk drivers and describe the alternative futures. To this end, we provide a characterization of the problem, knowledge engineering methodology, and transformation to planning. Furthermore, we describe the computation of the scenarios, lessons learned, and the feedback received from the pilot deployment of the SPA system in IBM.

We consider the problem of constructing abstract representations for planning in high-dimensional, continuous environments. We assume an agent equipped with a collection of high-level actions, and construct representations provably capable of evaluating plans composed of sequences of those actions. We first consider the deterministic planning case, and show that the relevant computation involves set operations performed over sets of states. We define the specific collection of sets that is necessary and sufficient for planning, and use them to construct a grounded abstract symbolic representation that is provably suitable for deterministic planning. The resulting representation can be expressed in PDDL, a canonical high-level planning domain language; we construct such a representation for the Playroom domain and solve it in milliseconds using an off-the-shelf planner. We then consider probabilistic planning, which we show requires generalizing from sets of states to distributions over states. We identify the specific distributions required for planning, and use them to construct a grounded abstract symbolic representation that correctly estimates the expected reward and probability of success of any plan. In addition, we show that learning the relevant probability distributions corresponds to specific instances of probabilistic density estimation and probabilistic classification. We construct an agent that autonomously learns the correct abstract representation of a computer game domain, and rapidly solves it. Finally, we apply these techniques to create a physical robot system that autonomously learns its own symbolic representation of a mobile manipulation task directly from sensorimotor data---point clouds, map locations, and joint angles---and then plans using that representation. Together, these results establish a principled link between high-level actions and abstract representations, a concrete theoretical foundation for constructing abstract representations with provable properties, and a practical mechanism for autonomously learning abstract high-level representations.

A recent press release states, "ClickSoftware, the leading provider of field service management software, today announced significant new capabilities for Field Service Edge, its cloud-based, mobile workforce management platform designed to meet the needs of the most demanding field service organizations. This latest offering introduces new strategic capabilities that will greatly improve field service efficiency and effectiveness. Major features are: (1) Predictive field service powered by ClickSoftware's Machine Learning Cloud, which identifies data patterns to make predictions and automatically improve valuable KPIs, (2) New demand forecasting capabilities to support more accurate resource planning and schedule optimization and provide richer insights to support proper staffing.

Addressing human needs must be top priorities to design, develop and implement successful AI technology. With a rising amount of media attention and a sevenfold increase of investment, artificial intelligence (AI) is on the agenda of businesses in all industries, who are identifying the massive potential with this kind of technology. Design sits at the forefront of the drive to develop innovative everyday AI solutions that people find intuitive and easy to use. To pave the way for successful AI implementation, companies must consider creating experiences with AI that are less artificial and more intelligent, and most importantly, those that make AI more human-shaped. This is where design comes in. Designers possess the skills to create a world where everything is designed around real human needs.