Transfer from Imprecise and Abstract Models to Autonomous Technologies (TIAMAT)

Background
The Defense Advanced Research Projects Agency (DARPA) Information Innovation Office (I2O) is sponsoring a Proposers Day to provide information to potential proposers on the objectives of the anticipated Transfer from Imprecise and Abstract Models to Autonomous Technologies (TIAMAT) Program Solicitation (PS). The TIAMAT program seeks breakthrough innovation for rapid transfer learning techniques to enable same-day autonomy that is robust to the quick and inevitable changes in dynamic environments and adaptable to a variety of platforms and domains.

Work Details
The technical hypothesis for accomplishing the goal of the TIAMAT program is contrary to the conventional wisdom of high-fidelity simulation. Instead, it argues that learning and transferring autonomy across diverse low-fidelity simulations in reference to their shared semantics leads to rapid transfer from simulation to reality, robustness, and adaptability. The purpose of the Proposers Day is to outline TIAMAT’s technical goals and challenges and to promote an understanding of the Program Solicitation (PS) proposal requirements. In addition, the Proposers Day will familiarize participants with DARPA’s interest in the area of fast techniques to transfer autonomy from abstract or imprecise simulations to the real world such that said transfer is robust to the differences between what is modeled in simulation and what is encountered in reality.

Place of Performance
Arlington, Virginia, 22203