Abstract Puzzle‐based storage (PBS) systems provide a space efficient solution for storage and retrieval of unit loads (e.g., cars, boxes) in the very land‐expensive urban environment. In this work, we formulate a highly generic optimal retrieval problem, consisting of any number of loads to be retrieved, and an arbitrary number of I/O points and empty locations (escorts) on a two‐dimensional lattice graph. We theoretically analyze the characteristics of the problem and propose a set of graph search algorithms to tackle the inherent complexities thereof. In contrast to existing work in the field, we investigate the runtime‐memory tradeoff pertaining to our problem, highlighting the possible benefits and limitations of our heuristic search and tabulation techniques. Our results demonstrate that our algorithms are capable of optimally solving moderate‐sized PBS problems using a limited amount of memory and in a reasonable amount of time.

Predicting human strategic decisions is fundamental to the design of intelligent human-interacting systems. While the connection between emotion and strategic action has been well-established in the past, in this work, we introduce the following question: Can emotional signals, automatically captured and interpreted from short video and audio recordings of a user, serve as good predictors of strategic action selection in an economic context, modeled as a game? In order to initiate the research on this question, we perform a user study where emotional signals are elicited from users using short video clips of emotional content. These signals are automatically analyzed by standard off-the-shelf computational means and are in turn used as potential predictors of strategic decisions in two classic, well-studied one-shot economical games: the ultimatum game and the trust game. By employing supervised machine learning techniques, we demonstrate the potential predictive power of these emotional signals and show that relying on the interpreted emotions can bring about more accurate predictions than standard baseline approaches.

Artificial intelligence (AI) techniques, including, e.g., machine learning, multi-agent collaboration, planning, and heuristic search, are emerging as ever-stronger tools for solving hard problems in real-world applications. Executable specification techniques (ES), including, e.g., Statecharts and scenario-based programming, is a promising development approach, offering intuitiveness, ease of enhancement, compositionality, and amenability to formal analysis. We propose an approach for integrating AI and ES techniques in developing complex intelligent systems, which can greatly simplify agile/spiral development and maintenance processes. The approach calls for automated detection of whether certain goals and sub-goals are met; a clear division between sub-goals solved with AI and those solved with ES; compositional and incremental addition of AI-based or ES-based components, each focusing on a particular gap between a current capability and a well-stated goal; and, iterative refinement of sub-goals solved with AI into smaller sub-sub-goals where some are solved with ES, and some with AI. We describe the principles of the approach and its advantages, as well as key challenges and suggestions for how to tackle them.

Emergency Departments (EDs) provide an imperative source of medical care. Central to the ED workflow is the patientcaregiver scheduling, directed at getting the right patient to the right caregiver at the right time. Unfortunately, common ED scheduling practices are based on ad-hoc heuristics which may not be aligned with the complex and partially conflicting ED's objectives. In this paper, we propose a novel online deep-learning scheduling approach for the automatic assignment and scheduling of medical personnel to arriving patients. Our approach allows for the optimization of explicit, hospital-specific multi-variate objectives and takes advantage of available data, without altering the existing workflow of the ED. In an extensive empirical evaluation, using real-world data, we show that our approach can significantly improve an ED's performance metrics.

Emergency Departments (EDs) provide an imperative source of medical care. Central to the ED workflow is the patientcaregiver scheduling, directed at getting the right patient to the right caregiver at the right time. Unfortunately, common ED scheduling practices are based on ad-hoc heuristics which may not be aligned with the complex and partially conflicting ED’s objectives. In this paper, we propose a novel online deep-learning scheduling approach for the automatic assignment and scheduling of medical personnel to arriving patients. Our approach allows for the optimization of explicit, hospitalspecific multi-variate objectives and takes advantage of available data, without altering the existing workflow of the ED. In an extensive empirical evaluation, using real-world data, we show that our approach can significantly improve an ED’s performance metrics.

Human chess players prefer training with human opponents over chess agents as the latter are distinctively different in level and style than humans. Chess agents designed for human-agent play are capable of adjusting their level, however their style is not aligned with that of human players. In this paper, we propose a novel approach for designing such agents by integrating the theory of chess players' decision-making with a state-of-the-art Monte Carlo Tree Search (MCTS) algorithm. We demonstrate the benefits of our approach using two sets of analyses. Quantitatively, we establish that the agents attain their desired Elo ratings. Qualitatively, through a Turing-inspired test with a human chess expert, we show that our agents are indistinguishable from human players.

Drones can assist in mitigating traffic accidents by deterring reckless drivers, leveraging their flexible mobility. In the real world, drones are fundamentally limited by their battery/fuel capacity and have to be replenished during long operations. In this paper, we propose a novel approach where police cruisers act as mobile replenishment providers in addition to their traffic enforcement duties. We propose a binary integer linear program for determining the optimal rendezvous cruiser-drone enforcement policy which guarantees that all drones are replenished on time and minimizes the likelihood of accidents. In an extensive empirical evaluation, we first show that human drivers are expected to react to traffic enforcement drones in a similar fashion to how they react to police cruisers using a first-of-its-kind human study in realistic simulated driving. Then, we show that our proposed approach significantly outperforms the common practice of constructing stationary replenishment installations using both synthetic and real world road networks.

Online platforms which assist people in finding a suitable partner or match, such as online dating and job recruiting environments, have become increasingly popular in the last decade. Many of these platforms include recommender systems which aim at helping users discover other people who will also be interested in them. These recommender systems benefit from contemplating the interest of both sides of the recommended match, however the question of how to optimally balance the interest and the response of both sides remains open. In this study we present a novel recommendation method for recommending people to people. For each user receiving a recommendation, our method finds the optimal balance of two criteria: a) the likelihood of the user accepting the recommendation; and b) the likelihood of the recommended user positively responding. We extensively evaluate our recommendation method in a group of active users of an operational online dating site. We find that our method is significantly more effective in increasing the number of successful interactions compared to a state-of-the-art recommendation method.

Automated platforms which support users in finding a mutually beneficial match, such as online dating and job recruitment sites, are becoming increasingly popular. These platforms often include recommender systems that assist users in finding a suitable match. While recommender systems which provide explanations for their recommendations have shown many benefits, explanation methods have yet to be adapted and tested in recommending suitable matches. In this paper, we introduce and extensively evaluate the use of "reciprocal explanations" - explanations which provide reasoning as to why both parties are expected to benefit from the match. Through an extensive empirical evaluation, in both simulated and real-world dating platforms with 287 human participants, we find that when the acceptance of a recommendation involves a significant cost (e.g., monetary or emotional), reciprocal explanations outperform standard explanation methods, which consider the recommendation receiver alone. However, contrary to what one may expect, when the cost of accepting a recommendation is negligible, reciprocal explanations are shown to be less effective than the traditional explanation methods.

Efficient traffic enforcement is an essential, yet complex, component in preventing road accidents. In this paper, we present a novel model and an optimizing algorithm for mitigating some of the computational challenges of real-world traffic enforcement allocation in large road networks. Our approach allows for scalable, coupled and non-Markovian optimization of multiple police units and guarantees optimality. In an extensive empirical evaluation we show that our approach favorably compares to several baseline solutions achieving a significant speed-up, using both synthetic and real-world road networks.

Automated agents should be able to persuade people in the same way people persuade each other - via dialogs. Today, automated persuasion modeling and research use unnatural assumptions regarding persuasive interaction, which creates doubt regarding their applicability for real-world deployment with people. In this work we present a novel methodology for persuading people through argumentative dialogs. Our methodology combines theoretical argumentation modeling, machine learning and Markovian optimization techniques that together result in an innovative agent named SPA. Two extensive field experiments, with more than 100 human subjects, show that SPA is able to persuade people significantly more often than a baseline agent and no worse than people are able to persuade each other.

Exponential decay time series are prominent in many fields. In some applications, the time series behavior can change over time due to a change in the user's preferences or a change of environment. In this paper we present an innovative online learning algorithm, which we name Exponentron, for the prediction of exponential decay time series. We state a regret bound for our setting, which theoretically compares the performance of our online algorithm relative to the performance of the best batch prediction mechanism, which can be chosen in hindsight from a class of hypotheses after observing the entire time series. In experiments with synthetic and real-world data sets, we found that the proposed algorithm compares favorably with the classic time series prediction methods by providing up to 41% improvement in prediction accuracy. Furthermore, we used the proposed algorithm for the design of a novel automated agent for the improvement of the communication process between a driver and its automotive climate control system. Throughout extensive human study with 24 drivers we show that our agent improves the communication process and increases drivers' satisfaction, exemplifying the Exponentron's applicative benefit.

Argumentative discussion is a highly demanding task. In order to help people in such discussions, this article provides an innovative methodology for developing agents that can support people in argumentative discussions by proposing possible arguments. By gathering and analyzing human argumentative behavior from more than 1000 human study participants, we show that the prediction of human argumentative behavior using Machine Learning (ML) is possible and useful in designing argument provision agents. This paper first demonstrates that ML techniques can achieve up to 76% accuracy when predicting people’s top three argument choices given a partial discussion. We further show that well-established Argumentation Theory is not a good predictor of people’s choice of arguments. Then, we present 9 argument provision agents, which we empirically evaluate using hundreds of human study participants. We show that the Predictive and Relevance-Based Heuristic agent (PRH), which uses ML prediction with a heuristic that estimates the relevance of possible arguments to the current state of the discussion, results in significantly higher levels of satisfaction among study participants compared with the other evaluated agents. These other agents propose arguments based on Argumentation Theory; propose predicted arguments without the heuristics or with only the heuristics; or use Transfer Learning methods. Our findings also show that people use the PRH agents proposed arguments significantly more often than those proposed by the other agents.

Argumentative discussion is a highly demanding task. In order to help people in such situations, this paper provides an innovative methodology for developing an agent that can support people in argumentative discussions by proposing possible arguments to them. By analyzing more than 130 human discussions and 140 questionnaires, answered by people, we show that the well-established Argumentation Theory is not a good predictor of people's choice of arguments. Then, we present a model that has 76% accuracy when predicting people’s top three argument choices given a partial deliberation. We present the Predictive and Relevance based Heuristic agent (PRH), which uses this model with a heuristic that estimates the relevance of possible arguments to the last argument given in order to propose possible arguments. Through extensive human studies with over 200 human subjects, we show that people’s satisfaction from the PRH agent is significantly higher than from other agents that propose arguments based on Argumentation Theory, predict arguments without the heuristics or only the heuristics. People also use the PRH agent's proposed arguments significantly more often than those proposed by the other agents.