To ensure quality results from unreliable crowdsourced workers, task designers often construct complex workflows and aggregate worker responses from redundant runs. Frequently, they create several alternative workflows to accomplish the task, and choose a single workflow to deploy (perhaps the one that achieves the best performance during early experiments). However, this seemingly natural design paradigm does not achieve the full potential of crowdsourcing. In particular, using a single workflow (even the best) to accomplish a task is suboptimal. We show that alternative workflows can compose synergistically to yield a much higher quality output. We formalize the insight with a novel probabilistic graphical model, design and implement AgentHunt, a POMDP-based controller that dynamically switches between these workflows to achieve higher returns on investment, and design offline and online methods for learning model parameters. Live experiments on Amazon Mechanical Turk demonstrate the superiority of AgentHunt for the practical task of generating NLP training data, yielding up to 50% error reduction and greater net utility compared to previous methods.

We are working to develop plan critiquing methods where a planner is used to identify flaws in an existing plan, in order to provide assistance to human planners. In this paper, we describe how to use any classical planning algorithm for verification and counterexample generation for plans already generated by some agent (human or an automated planning system). We show how to take an original classical planning domain, problem, and plan, and a set of uncontrollable (disturbance) actions and agents, and compile those inputs into a new "counter-planning'' problem. This counter-planning problem can be given to an arbitrary PDDL planner, in order to generate counterexample traces where uncontrollable actions can upset plan execution. Our experiments with a large set of planning problems in two multi-agent, dynamic planning domains demonstrated that our approach can verify a plan or generate a counterexample quickly and reliably. We have also compared our approach with a state-of-the-art model-checking system: the results suggest that using classical planners for generating counter plans is more promising than model-checking based verification.

Optimal solutions for multi-agent pathfinding problems are often too expensive to compute. For this reason, suboptimal approaches have been widely studied in the literature. Specifically, in recent years a number of efficient suboptimal algorithms that are complete for certain subclasses have been proposed at highly-rated robotics and AI conferences. However, it turns out that the problem of non-optimal multi-agent pathfinding has already been completely solved in another research community in the 1980s. In this paper, we would like to bring this earlier related work to the attention of the robotics and AI communities.

Much of the existing work on plan recognition assumes that actions of other agents can be observed directly. In continuous temporal domains such as traffic scenarios this assumption is typically not warranted. Instead, one is only able to observe facts about the world such as vehicle positions at different points in time, from which the agents' intentions need to be inferred. In this paper we show how this problem can be addressed in the situation calculus and a new variant of the action programming language Golog, which includes features such as continuous time and change, stochastic actions, nondeterminism, and concurrency. In our approach we match observations against a set of candidate plans in the form of Golog programs. We turn the observations into actions which are then executed concurrently with the given programs. Using decision-theoretic optimization techniques those programs are preferred which bring about the observations at the appropriate times. Besides defining this new variant of Golog we also discuss an implementation and experimental results using driving maneuvers as an example.

Several variants of A* have been recently proposed for find-ing optimal solutions for the multi-agent pathfinding (MAPF)problem. However, these variants have not been deeply com-pared either quantitatively or qualitatively. In this paper weaim to fill this gap. In addition to obtaining a deeper under-standing of the existing algorithms, we describe in detail theapplication of the new enhanced partial-expansion techniqueto MAPF and show how pattern databases can be applied ontop of this technique.

Linguistic communication relies on non-linguistic context toconvey meaning. That context might include, for instance, recent orlong-term experience, semantic knowledge of the world, or objects and events in the immediate environment. In this paper, we describe embodied agents instantiated in Soar cognitive architecture that use context derived from their linguistic, perceptual, procedural and semantic knowledge for comprehending imperative sentences.

Public sensing is a new research area in the fields of wireless sensor networks and mobile computing. It leverages the mobile sensors and system resources readily available in mobile phones to execute sensing tasks. In order to plan, execute and adapt large-scale sensing tasks, applications need to query for the available resources, e.g. the density of certain sensors. We investigate how such information can be provided, and we propose a resource manager for public sensing. Our primary goal is to minimize the energy consumed by the mobile devices to make public sensing feasible without disturbing users. We propose a cluster-based protocol for collecting local views of the resource state using local ad-hoc communication since this is much more energy-efficient than long-range (e.g. cellular) communication. We compare our solution to a standard approach where mobile devices communicate their resource states using the cellular phone network. We show that 65% of the energy is saved and the communication load on the infrastructure is reduced by 90% while an average delivery ratio of 93% is retained.

Recognizing social interests plays an important role of aiding human-computer interaction and human collaborative works. The recognition of social interest could be of great help to determine the smoothness of the interaction, which could be an indicator for group work performance and relationship. From socio-psychological theories, social engagement is the observable form of inner social interest, and represented as patterns of turn-taking and speech emotion during a face-to-face conversation. With these two kinds of features, a multi-layer learning structure is proposed to model the continuous trend of engagement. The level of engagement is classified into “high” and “low” two levels according to human-annotated score. In the result of assessing two-level engagemet, the highest accuracy of our model can reach 79.1%.

The core business of Mobile Network Operators (MNO) has moved from network management and phone services to service providing. In contrast to Information Communication Technology (ICT) service providers, MNOs handle large amounts of their customers’ context data and generated content, which can be used to bring value-added services to customers and therefore, generate solid revenues. Given this scenario, this paper describes how Telecom Italia (a major Italian MNO) has prototyped such type of services after a deep research performed in the context-awareness and context management field and using its user-generated content management facilities in federation with other platforms and systems.

For nearly 25 years my research group has investigated the use of domain knowledge, expressed in some version of mathematical logic, that is refined or exploited by numeric-based learning algorithms. These include what we called knowledge-based neural networks and knowledge-based support vector machines. I will cover the key ideas of these methods, as well as the behind-the-scenes motivations that lead to them. I will also describe why we switched from using the phrase 'prior knowledge' to using 'advice.' Finally, I will cover some of our recent work on fast learning and inference for Markov Logic Networks (which can be viewed as a knowledge-based graphical model).