Planning with action concurrency under time and resources constraints and uncertainty is a challenging problem. Current approaches which rely on Markov Decision Processes and a discrete model for time and resources are limited by a blow-up of the search state-space. This paper presents a planner which is based on a classical forward search for solving this kind a problems. A continuous model is used for time and resources. The uncertainty on time is represented by continuous random variables which are organized in a dynamically generated Bayesian network. Two versions of the ActuPlan planner are presented. As a first step, ActuPlan_nc performs a forward-search in an augmented state-space to generate epsilon-optimal nonconditional plans which are robust to uncertainty (threshold on the probability of success). ActuPlan_nc is then adapted to generate a set of nonconditional plans which are characterized by different trade-offs between their probability of success and their expected cost. ActuPlan, the second version, builds a conditional plan with a lower expected cost by merging previously generated nonconditional plans. The branches are built by conditioning on the time. Empirical experimentation on standard benchmarks demonstrates the effectiveness of the approach.

Cooperative multi-agent path planning around a common location has many applications, and has received significant at- tention from the research community. Our research is motivated by the need for groups of autonomous vehicles or mobile robots to collaboratively plan efficient paths around shared navigational coordinates (waypoints) in a distributed and decentralized manner. Our ongoing research is focused on creating a distributed solution to Dresner and Stone’s Autonomous Intersection Management problem. In the future we plan to relax the constraints of this problem, and allow more flexibility in the angles of approach and departure from a single waypoint, and also plan to consider efficient group plans for multi-waypoint routes. In this paper we briefly introduce intersection management, present preliminary results for an unstructured peer-to-peer approach to the problem, and discuss future research directions.

Interest in online education is surging, as dramatized bythe success of Khan Academy and recent Stanford online courses, but the technology for online education isin its infancy. Crowdsourcing mechanisms will likelybe essential in order to reach the full potential of thismedium. This paper sketches some of the challengesand directions we hope HCOMP researchers will address.

Underlying symbolic representations are opaque within neural networks that perform pattern recognition. Neural network weights are sub-symbolic, they commonly do not have a direct symbolic correlates. This work shows that by implementing network dynamics differently, during the testing phase instead of the training phase, pattern recognition can be performed using symbolically relevant weights. This advancement is an important step towards the merging of neural-symbolic representation, memory, and reasoning with pattern recognition.

Electronic health records (EHRs) are an emerging relational domain with large potential to improve clinical outcomes. We apply two statistical relational learning (SRL) algorithms to the task of predicting primary myocardial infarction. We show that one SRL algorithm, relational functional gradient boosting, outperforms propositional learners particularly in the medically-relevant high recall region. We observe that both SRL algorithms predict outcomes better than their propositional analogs and suggest how our methods can augment current epidemiological practices.

We present a novel approach to bidirectional breadth-first IDA* (BFIDA*) and demonstrate its effectiveness in the domain of peg solitaire, a simple puzzle. Our approach improves upon unidirectional BFIDA* by usually avoiding the last iteration of search entirely, greatly speeding up search. In addition, we provide a number of improvements specific to peg solitaire. We have improved duplicate-detection in the context of BFIDA*. We have strengthened the heuristic used in the previous state-of-the-art solver. Finally, we use bidirectional search frontiers to provide a stronger technique for pruning unsolvable states. The combination of these approaches allows us to improve over the previous state-of-the-art, often by a two-orders-of-magnitude reduction in search time.

In proof-of-payment transit systems, passengers are legally required to purchase tickets before entering but are not physically forced to do so. Instead, patrol units move about the transit system, inspecting the tickets of passengers, who face fines if caught fare evading. The deterrence of such fines depends on the unpredictability and effectiveness of the patrols. In this paper, we present TRUSTS, an application for scheduling randomized patrols for fare inspection in transit systems. TRUSTS models the problem of computing patrol strategies as a leader-follower Stackelberg game where the objective is to deter fare evasion and hence maximize revenue. This problem differs from previously studied Stackelberg settings in that the leader strategies must satisfy massive temporal and spatial constraints; moreover, unlike in these counterterrorism-motivated Stackelberg applications, a large fraction of the ridership might realistically consider fare evasion, and so the number of followers is potentially huge. A third key novelty in our work is deliberate simplification of leader strategies to make patrols easier to be executed. We present an efficient algorithm for computing such patrol strategies and present experimental results using real-world ridership data from the Los Angeles Metro Rail system. The Los Angeles County Sheriff’s department has begun trials of TRUSTS.

We investigate machine learning methods for diagnostic screening of heart disease. Coronary heart disease is the leading cause of death in the US, causing more deaths than all types of cancers combined. Early diagnosis of heart disease in women is harder than it is in men and typically requires the administration of several clinical tests on the patient. Most risk stratification methods aggregate the results of such tests, including the risky, invasive procedures that cannot be administered on all patients. In this paper, our goal is to identify patients who are under high-risk of having heart disease and related adverse events, using a minimal number of diagnostic tests, especially less invasive ones. The low frequency of patients with severe heart disease in the dataset is challenging for most conventional machine learning methods. To overcome this problem, we develop and apply a cost-sensitive k nearest neighbor algorithm. Our contributions are two fold: First, we compare the predictive value of several diagnostic procedures for heart disease, including electrocardiography, angiography, radionuclide perfusion and conclude that in womens heart disease, certain combinations of non-invasive techniques are more predictive than some of the widely used invasive procedures. Then, we evaluate held out data and achieve an AUROC over 0.70, signifying valuable clinical utility, using only the least costly and least invasive tests.

The Partner Units Problem (PUP) constitutes a challenging real-world configuration problem with diverse application domains such as railway safety, security monitoring, electrical engineering, or distributed systems.Although using the latest problem-solving methods including Constraint Programming, SAT Solving,Integer Programming, and Answer Set Programming, current methods fail to generate solutions for mid-sized real-world problems in acceptable time. This paper presents the QuickPup algorithm based on backtrack search combined with smart variable orderings and restarts. QuickPup outperforms the available methods by orders of magnitude and thus makes it possible toautomatically solve problems which couldn’t be solved without human expertise before. Furthermore, the runtimes of QuickPup are typically below one second for real-world problem instances.

The Next-Generation Transportation program coordinates the evolution and transformation of the current air-traffic management (ATM) system for the National Airspace System (NAS). Currently the NAS has a limited capacity and cannot handle the increasing future air traffic demands. However, before newly proposed ATM concepts are deployed they must be rigorously evaluated under realistic conditions. This paper presents AGENTFLY, an emerging NAS-wide highfidelity multi-agent ATM simulator with precise emulation of the human controller operation workload model and human-system interaction. The simulator is validated using a flight scenario developed by the U.S. Federal Aviation Administration that is based on real data. We present preliminary results focusing on the accuracy of the simulated controllers within AGENTFLY.