U.S. flag

An official website of the United States government, Department of Justice.

Imaging, Speech Technology Boost Simulation Training

NCJ Number
Date Published
July 2008
2 pages
This article describes the features of the Use of Force Training Simulator (UFTS) under development, which uses computer-generated images (CGI) and speech technology that enable variability in characters and scenarios as well as character and scenario responses to user commands and conversation.

By using CGI instead of videotaping performances by actors, the simulator can incorporate an array of features such as character ethnicity, voice, gender, mood, and compliance, in addition to weather and time of day. Also, because the trainer’s visual system is built in a three-dimensional virtual space, the after-action review of an individual’s training performance allows the instructor to use the mouse to pan and scroll in replaying the scenario in three dimensions rather than be limited by the fixed field of view shot by the camera in filming a videotape. The speech recognition capability built into the system enables the trainee to have a conversation with the CGI characters and the nature and tone of the conversation initiated by the trainee influences character and scenario responses. An officer can talk the suspect into compliance without using a gun or less-lethal weapon or cause the suspect’s resistance to escalate. The UFTS is expected to reach the prototype stage by September 2008. Because of Federal subsidies, the ultimate cost to law enforcement agencies should involve only the cost of the materials needed to build the system, a reasonable profit by the chosen vendor, and the cost to develop any new scenarios. Technical assistance will be provided in order to help agencies create their own training exercises. Discussions are underway for the creation of a central repository for all scenarios created by system users. This repository would be accessible to all agencies that have the system.

Date Published: July 1, 2008