Semantic Coherence: IHMC | Institute for Human & Machine Cognition – Signal Evidence & AI Readability

The Institute for Human & Machine Cognition (IHMC) pioneers technologies aimed at leveraging and extending human capabilities.
Explore our research areas to see what we’re doing.

[H5] Featured Research

IHMC researchers develop conceptual and computational models of expert knowledge and reasoning, and of complex cognitive work, as a core element to the paradigm of human-centered computing. IHMC research in this area is conducted by Associate Director and Senior Research Scientist Alberto J. Cañas and Senior Research Scientists William J. Clancey and ...
IHMC researchers develop conceptual and computational models of expert knowledge and reasoning, and of complex cognitive work, as a core element to the paradigm of human-centered computing. IHMC research in this area is conducted by Associate Director and Senior Research Scientist Alberto J. Cañas and Senior Research Scientists William J. Clancey and Robert R. Hoffman.
IHMC’s work on knowledge modeling involves representing a person’s understanding of a domain of knowledge in a form that others can easily comprehend. Such models are useful for learning, knowledge preservation, and organization of information. IHMC researchers have...

[H4] Knowledge Modeling, Work Analysis & Simulation, and Expertise Studies

Welcome to the robotics lab. We aim to change the future through innovation of robotics systems and the way they interact with humans. ...

Welcome to the robotics lab. We aim to change the future through innovation of robotics systems and the way they interact with humans. Visit our lab website here to learn more about our work, our team, our goals!

[H4] Robotics, Exoskeletons, & Human Robotic Interdependence

Advances in technology have made it ever easier to collect and store data.  While the amount of data has increased tremendously, data collection is often opportunistic: There is only limited control over what, when, and how much data is collected, leading to inconsistency and fragmentary and uneven coverage.  In addition, the connections one might...
Advances in technology have made it ever easier to collect and store data.  While the amount of data has increased tremendously, data collection is often opportunistic: There is only limited control over what, when, and how much data is collected, leading to inconsistency and fragmentary and uneven coverage.  In addition, the connections one might seek from the data are almost always non-deterministic and uncertain. Traditional statistical and logical analyses are inadequate in many of these situations.
IHMC researchers James Allen, Greg Dubbin, Clark Glymour and Choh Man Teng work on a...

[H4] Knowledge Discovery, Data Science, Learning from Big Data

[H2] See All Research Areas

[H4] UWF-IHMC Joint Ph.D. program in Intelligent Systems and Robotics
Learn More

[H3] Outreach

[H4] Upcoming Evening Lectures

No events scheduled at this time.

No events scheduled at this time.

[H4] Recent Episodes of STEM-Talk

Episode 195: Doug Cooke discusses NASA’s challenges in the space race to the Moon and Mars
[H6]
//
May 21, 2026

Episode 194: Tommy Wood discusses how to future-proof the adult brain
[H6]
//
Apr 16, 2026

[H4] View Our Latest Newsletters

View Archived Newsletters

[H4] Last Gallery from Pensacola

[H2] April 18, 2026

[H4] Dr. Marcas Bamman
What Genes are You Wearing?
View Gallery

[H4] Last Gallery from Ocala

[H2] April 11, 2026

[H4] Scott Weeks
Roller Coasters
View Gallery

[H4] Latest News

IHMC’s new humanoid Alex aces its first off-sit, off-tether demonstration A Letter From Our CEO IHMC project helps pioneer new tools for warfighters STEM-Talk: Doug Cooke talks about strengths and flaws of NASA’s Artemis mission IHMC hosts national workshop on collaborative autonomy Community turnout lifts IHMC clinical trial to a great start Two IHMC researchers named to top posts in worldwide organizations Public learns about robots, drones, virtual reality, Healthspan advances and more at open house STEM-Talk: Tommy Wood shares science-backed strategies to enhance your mental sharpness IHMC open house unveils the robotics team’s new advanced humanoid Alex

[H4] Participate
The IHMC Society welcomes your tax- deductible contribution to benefit the research and outreach programs of the Florida Institute for Human & Machine Cognition (IHMC).
The Board of Directors of the Florida Institute for Human & Machine Cognition appreciate your generosity and look forward to your further participation in the activities of the IHMC Public Lecture Series.

For more information on how to directly link yourself or your company to the work of IHMC, Please call 850-202-4400.

[H4] Donation Levels

Benefactors' Circle: $1,000 or more (Special invitations to dinner with Speakers, autographed books, reserved seating and private receptions)
Speakers' Circle: $500-$999 (Reserved seating and private receptions)
Friend: $100-$499

[H3] IHMC Newsletter

[IMG: v20.2-2025-Newsletter-619×792]

The IHMC Newsletter is generally published two to four times a year. It contains general information about what is going on at IHMC, including research projects, new employees, and outreach programs.
View Current Issue
View Archived Newsletters

[H4] Subscribe to IHMC Newsletters

[H3] Donate to IHMC
IHMC is a 501(c)3 not-for-profit organization. We appreciate your generosity and look forward to your participation in future IHMC activities.
Click the area you would like to donate to
Pensacola Evening Lecture
Ocala Evening Lecture
Science Saturday
General Donation
PayPal Giving Fund Donation to IHMC

[H2] Newsletters

[IMG: v20.2-2025-Newsletter-619×792]

The IHMC Newsletter is generally published twice a year. It offers an overview about what is going on at IHMC, including research projects, new employees, and outreach programs.
View Current Issue

[H4] Sign-up to Receive IHMC Newsletters

[H3] Archived Newsletters

[IMG: v20.2-2025-Newsletter-619×792]

[IMG: v20.1-2025-Newsletter-619×792]

[IMG: v19.3-2024-Newsletter]

[IMG: v19.2-2024-Newsletter-619×792]

[IMG: v19.1-2024-Newsletter-619×792]

[IMG: v18.1-2023-Newsletter-619×792]

[IMG: v17.2-2022-Newsletter-619×792]

[IMG: v17.1-2022-Newsletter-619×792]

[IMG: NewsLetter-v16.1-300]

[IMG: NewsLetter-v15.1]

[IMG: IHMCnewsletter_14.1]

[IMG: IHMCnewslettervol13iss1]

[IMG: IHMCnewslettervol12iss1]

[IMG: IHMCNewslettervol11iss2]

[IMG: IHMCnewslettervol11iss1]

[IMG: IHMCNewslettervol10iss3]

[IMG: IHMCNewslettervol10iss2]

[IMG: IHMCNewslettervol10iss1]

[IMG: IHMCNewslettervol9iss2]

[IMG: IHMCNewslettervol9iss1]

[IMG: IHMCNewslettervol8iss1]

[IMG: IHMCNewslettervol7iss1]

[IMG: IHMCNewslettervol6iss2]

[IMG: IHMCNewslettervol6iss1]

[IMG: IHMCNewslettervol5iss1]

[IMG: IHMCNewslettervol4iss2]

[IMG: IHMCNewslettervol4iss1]

[IMG: IHMCNewslettervol3iss3]

[IMG: IHMCNewslettervol3iss2]

[IMG: IHMCNewslettervol3iss1]

[IMG: IHMCNewslettervol2iss3]

[IMG: IHMCNewslettervol2iss2]

[IMG: IHMCNewslettervol2iss1]

[IMG: IHMCNewslettervol1iss3]

[IMG: IHMCNewslettervol1iss2]

[IMG: IHMCNewslettervol1iss1]

[H2] Knowledge Discovery, Data Science, Learning from Big Data

Advances in technology have made it ever easier to collect and store data.  While the amount of data has increased tremendously, data collection is often opportunistic: There is only limited control over what, when, and how much data is collected, leading to inconsistency and fragmentary and uneven coverage.  In addition, the connections one might seek from the data are almost always non-deterministic and uncertain. Traditional statistical and logical analyses are inadequate in many of these situations.
IHMC researchers James Allen, Greg Dubbin, Clark Glymour and Choh Man Teng work on a broad range of topics in Data Science, focusing on the development of methods to automatically analyze volumes of imperfect data to identify underlying connections. Although these researchers come from diverse backgrounds—linguistics, philosophy and computer science—the theme that unifies their research is the development of mechanisms that can learn from vast amounts of data and reason and understand the underlying structures that give rise to such data. Past and current projects include coastal zone mapping and target detection from LIDAR and sonar data, evidence-based paraconsistent reasoning, detecting and correcting data imperfections in satellite data, causal inference in climate teleconnections, forest fire predictions, and longitudinal modeling of glaucoma.
At the center of IHMC’s work on data science is a knowledge base consisting of general knowledge about the world, instantial knowledge about the specific instances of interest, and statistical knowledge reflecting objective relative frequencies observed in the world.  The statistical statements are by nature approximate, and they can be represented by intervals (at a certain level of confidence) whose values and widths are indicative of the relative frequency and amount of supporting evidence.
Reference sets relevant to a particular event are constructed dynamically from the knowledge base, and principles to adjudicate between inconsistent statements are being developed to take into account such information as the taxonomy of the reference sets, the set inclusion relationship between the intervals, and background knowledge.  Similar principles are also used to identify and correct erroneous data, in a method developed at IHMC called polishing.
IHMC researchers have designed paradigms that transcend predictions and work on identifying the causal temporal connections between elements in the data.  This is important for generating an explanation of the constructed models and their predictions, in particular when the goal is to influence the outcome of an event of interest by influencing selected elements under (partial) control.  Even though both the causes and effects of a variable are correlated with the variable itself, one can only expect to influence the state of the variable by changing its causes but not its effects.
Algorithms are being developed that construct graphical causal models based on the conditional and unconditional probabilistic relations obtained in the data.  In the context of the DRUM: Deep Reader for Understanding Mechanisms project (funded by DARPA’s “Big Mechanism” program), temporal and causal reasoning capabilities are being developed that can connect model fragments derived from both background knowledge and from reading scientific papers in English. Also in the area of Natural Language Processing, machine-learning methods are being developed to understand low resource languages, where syntactic and semantic information is scarce.

[H4] Researchers

Choh Man Teng
James Allen
Clark Glymour

[H2] Knowledge Modeling, Work Analysis & Simulation, and Expertise Studies

IHMC researchers develop conceptual and computational models of expert knowledge and reasoning, and of complex cognitive work, as a core element to the paradigm of human-centered computing. IHMC research in this area is conducted by Associate Director and Senior Research Scientist Alberto J. Cañas and Senior Research Scientists William J. Clancey and Robert R. Hoffman.
IHMC’s work on knowledge modeling involves representing a person’s understanding of a domain of knowledge in a form that others can easily comprehend. Such models are useful for learning, knowledge preservation, and organization of information. IHMC researchers have developed and continue to enhance CmapTools, a software toolkit that allows people to express and share their understanding about a topic in the form of concept maps. CmapTools is useful for organizing information to provide more effective browsing and searching; for eliciting and preserving knowledge in organizations; and for facilitating meaningful learning for students of all ages.
The interactions between people and their work environment continue to grow in complexity as work is increasingly mediated and automated by networks of web-based tools. IHMC scientists have devised new methodologies for understanding and modeling work through observation and simulation of work practices. Collaborating with managers and workers, researchers analyze problematic situations and propose new work system designs that account for the interactions of roles, computer tools, schedules and facilities in the work setting. Relevant applications include air transportation systems, self-driving vehicles, and office workflow automation.
To understand better the nature of work systems, IHMC researchers use the Brahms tool to model and simulate what people actually do in a work environment. Using data from time-lapse videos, first-hand observations, interviews, and documents, work practice modelers create detailed storyboards of activities, interactions affected by people’s beliefs, perceptions, and inferences. Brahms simulations depict how people communicate, use tools (including devices and computational systems), and how they move in a physical environment, modeled as a geographic layout of areas and objects with their own behaviors (e.g., automated systems). Brahms simulations can generate statistics that capture the effect of circumstantial, emergent interactions in time and space among distributed processes.  These simulations then can be altered to visualize new operational concepts, including the potential for automation, more appropriate roles, better physical design or improved scheduling.
IHMC researchers are also examining the difficult, challenging, and often risky tasks of modern workplaces where conditions of data overload and uncertainty are commonplace. A critical and necessary role is played by knowledge and reasoning of individuals and teams interacting with computers and with each other via networks of computers. Through cognitive work analysis and expertise studies IHMC scientists are advancing knowledge of how teams of humans and intelligent technologies coordinate to perform complex tasks. This research requires observing experts in their work environment. Researchers explore the nature of tasks and modes of reasoning and learning that can impede the development of expertise and skill or can lead to cognitive difficulty and error by novices and experts alike.
Expert practitioners in a given field possess knowledge and skills that cannot possibly be captured in anything like a simple check list. Methods of Cognitive Task Analysis (CTA)—pioneered by IHMC—help researchers envision and design work systems by revealing expert knowledge and reasoning, a feature that sets CTA in contrast to traditional task analysis. Workers engage in knowledge-driven, context-sensitive choice among activities. Similarly, IHMC research fits CTA methods to particular domains of practice and the goals of research. IHMC researchers are “expert apprentices”—that is, they can enter into a domain or organization and arrive at a rich empirical understanding of what work has to be accomplished and how it is done in practice. This supports the process of revolutionary work systems design.
In particular, cognitive work is governed by the principles of Human-Centered Computing that describe how work is conducted in sociotechnical contexts and provide a roadmap for evaluating systems in terms of learnability, usefulness and usability. The goal of HCC is to create technologies that amplify and extend human abilities to perceive, reason, know, collaborate, and achieve expert levels of proficiency.
CTA methods include Concept Mapping, the Critical Decision Method, and the Macrocognitive Modeling Procedure. IHMC researchers have used these methods in a wide variety of domains, including weather forecasting, terrain analysis, social network analysis, military command and control, electric utilities engineering and power generation, military command and control, intelligence analysis, and cybersecurity.

[H4] Researchers

Alberto J. Cañas
Bill Clancey
Robert Hoffman
In Memoriam: Joseph D. Novak
Roger Carff