Cognitive Assistant that Learns and Organizes
As part of DARPA’s Perceptive Agent that Learns (PAL) program, SRI and team members are working on developing a next-generation "Cognitive Agent that Learns and Organizes" (CALO).
 

Neptune
A user-centric, integrated planning and scheduling system that assists the user in exploring the rich space of plans and associated resource assignment options in complex, real-world domains. Each component of the system (user, planner, and scheduler) reacts to the actions of the other, resolving conflicts, and iteratively refining the solution until acceptable.
 

Distributed Continual Planning and Execution for Autonomous Air Vehicles
This goal of this project is to develop a new software capability for the reprogrammable, coordinated command and control of teams of autonomous unmanned combat air vehicles (UCAVs) and unmanned ground vehicles (UGVs).
 

ENDSTATE
The objectives of the ENDSTATE initiative aim to provide new and innovative tools to aid in understanding and exploiting the vulnerabilities created by increasingly interconnected and interdependent physical network infrastructures. The vision was to bring together different but consistent model structures and analysis technologies so as to provide an insight into the vulnerabilities of the infrastructure. The insight could be used to derive the appropriate course of action, given desired effect
 

Explaining and Recovering from Computer Break-Ins
A system for forensic analysis of computer break-ins.
 

Intelligent Workflow for Collection Management
The objective of this project was to develop a revolutionary approach to workflow management within the Intelligence Survaillance and Reconnaissance (ISR) domain. The SWIM system was developed and demonstrated advanced workflow management techniques and intelligent reactive control. Research was conducted in the following areas. Information flow control, reasoning about agent capabilities and delegation, and algorithms necessary for dynamic process creation, adaptation and load balancing.
 

Multiagent Planning Architecture
MPA is an open planning architecture that facilitates incorporation of new plan-related technologies, capitalizing on the benefits of distributed computing for efficiency and robustness. MPA provides protocols to support the sharing of knowledge and capabilities among agents involved in cooperative problem solving. MPA has been demonstrated in the air campaign planning domain, and was used as the infrastructure for the flagship demonstration of the DARPA Planning Initiative.
 

Task Management for Dynamic Tactical Targeting
Provide task refinement, management and reasoning capabilities to support the Dynamic Sensor Management system being developed by Alphatech
 

TEAMBOTICA: A Robotic framework for integrated teaming, tasking, networking and control
Teambotica is a research initiative to develop the computational framework necessary for intelligent, autonomous teams of robots to operate in hostile environments.
 

The Link Analysis Workbench
The goal of this project is to develop the Link Analysis Workbench (LAW), a Web-accessible tool where analysts and machines collaboratively perform link analysis by defining hierarchical and temporal patterns, that include uncertain and qualitative elements, and by defining search strategies for pattern application, through a graphical user interface that supports direct graphical browsing and editing of patterns, search strategies, and summaries and details of resulting matches.