The DARPA PAL program (the Personalized Assistant that Learns) focused on improving the way that computers support humans through the use of cognitive systems—that is, systems that reason, learn from experience, and accept guidance in order to provide effective, personalized assistance.
SRI International has led the PAL Framework effort to make available many of the successful machine learning and reasoning technologies developed on the PAL program for use by the broader DARPA, research, and military communities. Technical capabilities within the framework have been hardened, modularized, packaged, and where appropriate, adapted to meet industry standards to facilitate their incorporation into potential target applications. The framework further includes various infrastructure components and APIs to simplify integration with the framework technologies.
The PAL Framework includes contributions from Carnegie Mellon University, the University of Massachusetts, the University of Rochester, the Institute for Human and Machine Cognition, Oregon State University, the University of Southern California, and Stanford University, as well as from SRI.
To download components and access detailed documentation you will be required to register. Just go to the Downloads page and add to your cart the requested downloads. Registering is free of charge. Most components are available to all registered users, but a few are restricted to US Government users. Availability and licensing terms are described with each component.