Robots are increasingly introduced to work in concert with people in high-intensity domains, such as manufacturing, space exploration and hazardous environments. Although there are numerous studies on human teamwork and coordination in these settings, very little prior work exists on applying these models to human-robot interaction. This paper presents results from ongoing work aimed at translating qualitative methods from human factors engineering into computational models that can be applied to human-robot teaming. We describe a statistical approach to learning patterns of strong and weak agreements in human planning meetings that achieves up to 94% prediction accuracy. We also formulate a human-robot interactive planning method that emulates cross-training, a training strategy widely used in human teams. Results from human subject experiments show statistically significant improvements on team fluency metrics, compared to standard reinforcement learning techniques. Results from these two studies support the approach of modeling and applying common practices in human teaming to achieve more effective and fluent human-robot teaming.

Many interesting real-world tasks might be most efficiently, effectively and safely achieved with large teams of robots working together. For domains such as the military, rescue response and environmental monitoring, the ability for the team to be spread out in the environment collecting information and taking action is a key enabler. Over an extended period of time, we have developed an infrastructure that can be quickly implemented on a robot or software agent to allow that agent to become part of a team. That infrastructure, called Machinetta, works by implementing a theory of teamwork that knows how to execute Team Oriented Plans. The infrastructure understands how to allocate roles, share information, recover from failures and other routine coordination activities that do not need to be specified in the plan. In most applications of Machinetta, invocation of Team Oriented Plans is the mechanism by which the operator interacts with the team, letting them specify the team activities without worrying about low-level details. Recently we have extended the team oriented plan concept to include situational awareness and mixed initiative markup that tells the GUI what information and options to give to the operator at different points during plan execution. In recent experiments with teams of boats, we have begun including swarming behaviors as a part of the team plan, when useful. The innvocation of swarming behavior from within Team Oriented Plans, offers a new way of interacting with very large robotic teams.

Human control of vehicle swarms faces a dilemma: an operator must be able to exercise precise control over how a mission is executed, but controlling individual vehicles is not scalable. The Proto spatial computing lan- guage offers an intermediate representation, where the motion of a swarm is specified as a vector field, which is then approximated by the movement of individual members (Bachrach, Beal, and McLurkin 2010). I propose that this can be exploited to build a “tactical command” model of swarm control, whereby human “officers” dynamically decompose a swarm into units and task those units to carry out geometric and topological maneuvers under the constraints imposed by the platform. This abstraction may also allow situation awareness interfaces for individual agents to be extended to apply to swarm units.

Knowledge engineering from experimental design (KEfED) is a novel approach based on the dependency relationships that occur between the variables of a scientific study. We used this approach to curate the experimental designs of ten scientific papers from a well-established database of HIV vaccine trials in non-human primates. The KEfED models provide a characteristic, data-oriented signature for each measurement made in the study. We present preliminary analysis of these manually-curated, detailed representations using our own open-source curation tools and show the multi-variate statistical analyses on the resultant models of experimental design. The analyses produced a visualization of the similarities between studies and an account of the dependency relationships across studies. We describe our approach in the context of a knowledge engineering strategy based on creating large-scale domain-independent repositories of experimental observatio

We explore applicability of the situation calculus, the well-known logical framework developed in Artificial Intelligence for representation of dynamic systems, to the task of representing knowledge about processes, actions and events in the natural sciences. In this paper, we concentrate on a case study in the area of organic chemistry. More specifically, we adapt the situation calculus to the task of automating organic synthesis planning on a qualitative level, where the objective is to identify a chain of chemical reactions transforming the given initial molecules into the desired goal molecule. We present two approaches for reasoning about reactions in organic chemistry: a “micro” approach and a “macro” approach. The “micro” approach is a low level approach that explicitly represents the most elementary interactions between molecules during a single chemical reaction, namely the splitting and forming of bonds between atoms. In contrast, the“macro” approach is a higher level approach that treats each chemical reaction (a set of splits and formation of bonds) as an elementary action. Both approaches are implemented in PROLOG. Declarative heuristics are defined to reduce the search space and help the program to find the correct synthesis routes more quickly. We hope that the lessons learned from our successful case study can have discovery potential in other bio-medical sciences. We discuss briefly how the proposed approaches can contribute to solving other research problems and to communicating pathways.

In this paper, we describe an interactive environment for the representation, interpretation, and revision of explanatory biological models. We illustrate our approach on the systems biology of aging, a complex topic that involves many interacting components, and discuss our experiences using this environment to codify an informal model of aging. We close by discussing related efforts and directions for future research.

As biological data about genes and their interactions proliferates, scientists have the opportunity to identify sets of proteins whose interactions make them worthy of further investigation. This paper reports on a knowledge discovery technique to support that work. Foretell is an algorithm originally designed to support search for solutions to constraint satisfaction problems. Recent adaptations enable Foretell to detect sets of genes that interact heavily with one another. We provide empirical results, and describe ongoing work on biological meaning and knowledge infusion from the user.

When constructing visualization pipelines using toolkits, developers must understand what sequencing of operators will transform their data from its raw state to some requested visual representation. In some cases, the requested visual representation must be generated from hybrid pipelines, composed of both toolkit-based and custom operators. Traditionally, developers learn about how to construct these visualization pipelines by word of mouth, by reading documentation and by inspecting code examples, all of which can be costly in terms of time and effort expended. The Visualization Knowledge Project (VisKo) is built on a knowledge base of visualization toolkit operators including rules for how operators are chained together to form pipelines. VisKo helps scientists by automatically generating and suggesting fully functional visualization pipelines, alleviating scientists from having to write any pipeline code. This paper reports on the kinds of knowledge required to support automatic pipeline generation as well our successes when applying VisKo to a number of visualizations scenarios spanning geophysics, environmental and materials science.

Artificial Intelligence researchers have long sought to understand and replicate processes of scientific discovery. This article discusses Discovery Informatics as an emerging area of research that builds on that tradition and applies principles of intelligent computing and information systems to understand, automate, improve, and innovate processes of scientific discovery.

His informatics group built the reusable software platform for Stembook Despite the fact that we now have access to almost all peer reviewed (www.stembook.org), William Cohen exchanged and is orthogonal to any specific biomedical domain The growing size of the scientific literature has led to a number of ontology. We believe this approach will be extremely useful in attempts to automatically extract entities and relationships from drug discovery to break down information silos, increase information scientific papers, and then to populate databases with this extracted awareness and sharing, and integrate terminologies and information. In my group we have been exploring techniques data with documents and text, both public and private. We will for using this sort of extracted information for specific tasks, discuss applications we are currently developing in collaboration including "bootstrapping" to improve the coverage of an extraction with a major pharma.