With the advance of computer speech recognition programs, robotic operators have a new method of robot-operator communication. An experiment was conducted using a "Wizard of Oz" paradigm to investigate how different styles of communication affect robot navigation performance. Using manual inputs, verbal commands (restricted to directions only), and verbal commands with object referent labels, participants navigated a simulated robot through various simulated indoor environments. Results indicated that manual control was faster than free form verbal commands but not faster than simple directional commands. When provided the opportunity, participants did use object labels particularly objects related to the structure of the building (doors, rooms, and halls). Discussion focuses on improving robotic communication and object recognition in a robotic control system.
A multi-year effort was conducted to investigate the impact on human cognitive and physical performance capabilities, which the introduction of a new Army command and control vehicle with modernized digital communications systems would have. This was a joint effort by the Human Research and Engineering Directorate of the U.S. Army Research Laboratory in partnership with the Directorate of Force Developments at the U.S. Armor Center and School at Fort Knox, Kentucky, and the U.S. Army Operational Test and Evaluation Command at Alexandria, Virginia. Literature searches and background investigations were conducted, and a model architecture based on a taxonomy of human performance was developed. A computer simulation design and methodology was implemented with these taxonomic-based descriptors of human performance in the military command and control domain, using a commercially available simulation programming language. A series of computer models called Computer modeling of Human Operator System Tasks (CoHOST) was written and results were developed that suggest that automation alone does not necessarily improve human performance.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.