Remote Agent was born out of a high-priority request for technologies that would meet the goals of the New Millenium Program. The New Millenium program called for NASA to have a "virtual presence" in space. This would involve many small, robotic, inexpensive spacecraft and rovers exploring all parts of our solar system to gather information. To achieve this, NASA requested technologies that would enable spacecraft to control themselves automatically, yet were relatively easy and inexpensive to build.
Researchers at NASA's Ames Research Center and Cal Tech's Jet Propulsion Laboratory (JPL) combined forces and rose to this challenge with the development of Remote Agent. After only five months of work, a version of Remote Agent was ready to run on a simulated scenario known as NewMaap, the New Millennium Autonomous Architecture Rapid Prototype, which was based loosely on the Cassini Saturn Exploration Mission. In this simulation, a spacecraft, after years of relative inactivity, would have to pass through Saturn's potentially damaging rings, fire its rockets, and enter into orbit around Saturn. Remote Agent had to plan and execute the activities involved in this complex procedure and had to diagnose and fix spacecraft failures which were programmed into the simulation.
The efforts of the NASA Ames and JPL engineers were rewarded by Remote Agent's performance. Not only did Remote Agent meet the challenges of the test, but it also responded to an unplanned failure in the simulation, and adjusted its plan accordingly, successfully achieving the mission goals. This performance greatly exceeded expectations and earned Remote Agent a spot to be field tested on Deep Space One , the first mission of the New Millenium Program.