Intelligence, Surveillance and Reconnaissance Exploitation

Military operations depend upon the unimpeded flow of accurate and relevant information to support timely decisions related to battle planning and execution. To address these needs, numerous intelligence systems and technologies have been developed over the past 20 years, but each of these typically provides only a partial picture of the battlefield, and integrating the information has proven to be burdensome and inefficient.

Military intelligence analysts face the monumental and escalating task of analyzing massive volumes of complex data from multiple, diverse sources such as physical sensors, human contacts and contextual databases. These analysts consume and process information from all available sources to provide mission-relevant, timely insights to commanders. To enhance this largely manual process, analysts require more effective and efficient means to receive, correlate, analyze, report and share intelligence.

Existing speech signal processing technologies are inadequate for most noisy or degraded speech signals that are important to military intelligence.

Dr. David Doermann joined DARPA in April 2014. His areas of technical interest span language and media processing and exploitation, vision and mobile technologies. He comes to DARPA with a vision of increasing capabilities through joint vision/language interaction for triage and forensics applications.

Mr. Steve Jameson joined DARPA in August 2014. His current research focuses on technologies to enable situation understanding, improve effectiveness and timeliness of decision-making, and build trust between humans and autonomous reasoning systems. Specific interests include knowledge representation, techniques for causal modeling, reasoning, and inference, as well as technologies to support mixed initiative reasoning, with a focus on enabling non-expert users to effectively interact with automated reasoning systems.