In Search of a Good Title » GVA algorithm

Ph.D. Thesis: Information Abstraction Visualization for Human-Robot Interaction

Curtis M. Humphrey — Fri, 05 Jun 2009 22:08:52 +0000

Vanderbilt School of Engineering

Future emergency incident responses, including Chemical, Biological, Radiological, Nuclear, and Explosive (CBRNE), will incorporate robots. The ability to interact with robots and understand the resulting volumes of information requires a system of human-robot interfaces employing directable visualizations that provide information immediacy, relevancy, and sharing appropriate for each human’s responsibilities.
This dissertation conducted two modified Cognitive Tasks Analyses (CTA) on the CBRNE incident response. The Cognitive Information Flow Analysis (CIFA) was developed to combine CTA results and to analyze the path of information as it passes through and is transformed by the system at different human-robot interaction (HRI) user levels. These analyses (i.e., modified CTAs and CIFA) collectively informed the HRI design and development.

The primary contributions of this dissertation are the development and evaluation of two novel visualization techniques that present immediate, relevant, and shared information provided by the robots to the human users in the system of human-robot interfaces. The General Visualization Abstraction (GVA) algorithm, the first technique, is designed to provide information immediacy and relevancy by displaying the most useful information at any given moment determined by rewarding information that is either historically and currently relevant or novel and emerging. The Decision Information Abstracted to a Relevant Encapsulation (DIARE) concept, the second technique, supports decision-making by representing prior event information as a defined volume in the visualization’s information space and encapsulates the volume into an explicit and visual object that can be shared across time and users.

User evaluations were conducted for both visualization techniques. The GVA algorithm’s evaluation results indicate that it can reduce cognitive workload, increase situational awareness, and improve performance for two different HRI user levels. The DIARE concept results indicate that participants were able to rapidly ascertain what had happened previously with great accuracy and good memory recall. Together, these two visualization techniques can assist decision-makers using directable visualizations, such as those used in HRI, by offering an effective method of sharing and providing real-time, relevant information.

Related Papers:

Curtis M. Humphrey. Information Abstraction Visualization for Human-Robot Interaction. PhD thesis,Vanderbilt University, August 2009

Designing a System of User Interfaces for Controlling Robots for Emergency Incident Response

Curtis M. Humphrey — Fri, 05 Jun 2009 21:52:23 +0000

System of User Interfaces

The emergency response incidents (e.g., Chemical, Biological, Radiological, Nuclear, and Explosive (CBRNE) incidents or weapons of mass destruction) are evolving from a response involving humans (e.g. first responders, government officials, civilians) with equipment (e.g. protective suits, vehicles, sensors) to a response system combining humans and thinking machines (e.g. robots, information technology). The difference between equipment (e.g. fire engines, radios, maps) and thinking machines (e.g. robots, computerized decision support systems) is that machines incorporate some cognitive abilities. If the emergency response system is to take effective advantage of emerging technology, the response activity needs to be understood in a way that facilitates the incorporation of these thinking machines and the development of effective human machine interactions. The incorporation of new thinking machines into the emergency response system is resulting in a shift, abet slowly, to a new paradigm.

The long-term objective is to design and develop a system of robots and associated human-robot interfaces (HRI) appropriate technology for all responders throughout the human response command hierarchy by first understanding the human activities, rather than starting with the technology design and then evaluating its effectiveness after development.

Remote Operator Interface an Operator/Supervisor Interaction Role

Operations Chief Interface an Abstract Supervisor

General Visualization Abstraction Algorithm for Geographic Map-Based Directable Interfaces

Curtis M. Humphrey — Fri, 05 Jun 2009 20:12:53 +0000

A screenshot of a directable interface visualization powered by the GVA algorithm in action.

Emergency incident response is evolving from a response involving humans with equipment to a response system combining humans and thinking machines (e.g. robots). The robots and other sensors will generate and capture volumes of information that will be presented in geographic map-based directable visualizations. This project involved presented a novel approach to performing information abstraction (i.e., selection and grouping) and determining how each information item should be presented (i.e., its shape) in direct-able visualizations for the emergency incident response. This new approach employs the General Visualization Abstraction (GVA) algorithm to make salient and direct attention to the most relevant information items by determining an importance value for each information item based on the item’s relationship with two classes of information: historically and currently relevant information, and novel and emerging information.

The evaluation results were statistically supportive, indicating that, in most cases, the GVA algorithm improved performance, lowered workload, and increased situational awareness. The implication to interface visualizations from these results is that the general approach behind the GVA algorithm (i.e., the grouping, filtering, and displaying of an information item based on an evaluation of its historical and currently relevant and novel and emerging properties) is not only possible but advantageous in directable visualizations.

Related Papers:

Humphrey, C. M., & Adams, J. A. (2009). General Visualization Abstraction Algorithm for Geographic Map-Based Human-Robot Interfaces. In Proceedings of the 4th ACM/IEEE international conference on Human robot interaction (pp. 289-290). La Jolla, California, USA: ACM. doi: 10.1145/1514095.1514180.

Humphrey, C. M., & Adams, J. A. (2009). General Visualization Abstraction Algorithm for Geographic Map-Based Directable Interfaces: Results. Manuscript in preparation.